relative_rank
int64 0
0
| win_prob
float64 0
0
| title
stringlengths 28
102
| abstract
stringclasses 1
value | full_text
stringlengths 97
102k
| review
stringlengths 97
102k
| source
stringclasses 1
value | review_src
stringlengths 18
25
| criteria_count
dict | dimension_scores
dict | overall_score
float64 0
3
| thinking_trace
stringclasses 1
value | prompt
stringclasses 1
value | prompt_length
int64 0
0
| conversations
listlengths 2
2
| year
int64 2.01k
2.02k
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0
| 0
|
ABHD4-dependent developmental anoikis safeguards the embryonic brain
|
Reviewers' Comments:
Reviewer #1:
Remarks to the Author:
Prof. Katona and colleagues proposed developmental anoikis and the molecular player that
controls this process. Developmental anoikis was triggered as a result of exposure to different
types of insults. One is forced delamination of neural progenitor cells by overexpression of Cdh2
mutant. Another is prenatal alcohol exposure. Concept of “developmental anoikis” that reduces
errors of development that is elicited by environmental insults is novel. Based on the known
function in cancer anoikis, and the specific expression in developmental stage, the authors picked
up Abhd4 as a candidate gene of a controller of this event. The knockout animal did not show
obvious phenotypes in normal condition. However, under exposure to insults, the aniokis is
significantly reduced in the knockout. The authors also provide good discussion of potential
mechanisms how Abhd4 controls developmental aniokis. This article provides very interesting
model, and I believe the model will be further strengthened by answering the questions below.
Abhd4 expression is remarkably specific to radial glial progenitor cells. Did authors observe
reduction of cell death only in that cell population (for example, no changes in cortical plate?) in
the knockout cortex of Abhd4 in cases of delta cdh2 overexpression and FASD model? A related
comment; is Abhd4 expression altered by prenatal alcohol exposure? For example, do cells other
than radial glial progenitor cells increase the expression of Abhd4, so that reduction of cell death is
not limited to radial glial progenitor cells in the knockout? Depending on answers to those
questions, proposed model may also require revision.
The effects on migration and cell death are obvious in embryonic stages in Adhd4 manipulation.
Are those effects kept until adulthood and make abnormal adult brain structure, or do cells catch
up migration? This information is important for discussion about significance of developmental
aniokis.
Other comments:
Most of TUNEL labelling did not overlap with GFP. Does cell death happen in cell non autonomous
manner?
Reviewer #2:
Remarks to the Author:
With this paper the Katona’s lab seeks to introduce a new concept in the field of developmental
neuroscience: the developmental anoikis as a safeguarding mechanism responsible for the
elimination of abnormally delaminated apical progenitors (RGPCs) during brain development. The
authors identified (i) ABDH4 as a crucial molecular player in developmental anoikis and (ii)
developmental anoikis as one of the possible mechanisms responsible for the elimination of
abnormally delaminated cells in a pathological condition, fetal alcohol syndrome.
The paper is a pleasant read and the ideas illustrated by the authors bring a fresh perspective in
the neurogenesis field. I acknowledge that the authors address an issue that is under-represented
in our field: how robustness is achieved in the context of cortical development and brain
morphogenesis.
Given the potential of their work, the authors must address the following points to make their
paper suitable for acceptance and publication in Nature Communication.
MINOR POINTS
- A general remark. Throughout the text, the authors refer to abnormal RGPC delamination and
AJs disassembly. Strictly speaking, delamination is always paralleled by the cell’s disengagement
from the AJs belt. What abnormal exactly means? What is different between a normal and an
abnormal AJ disassembly/delamination? What is then setting the difference?
The same apply to the use of the word “premature”, referred to delamination. Premature
compared to what exactly? Do the authors mean a delamination that is not paralleled by a fate
transition? Or a delamination that is not sync with cell cycle progression? The authors must clarify
and elaborate conceptually on that.
- Page 5: the authors write “spatially limited destruction…” upon nCadh20-GFP manipulation
referring to Figure1 a-d.
However, the panels show a deep and generalized modification of the AJs. The authors must clarify
this point and make clear if the image is representative of their conclusions. Is the manipulation
really causing a limited change in the AJ?
If so, then the authors should choose a picture reflecting this claim.
Otherwise, the authors should change the sentence to reflect what the picture showed: a
pronounced and general change in the AJs.
The same apply to the phalloidin staining shown in Supplementary Figure 1a-f. The phalloidin
staining at the apical surface is clearly less intense in the nCadh20-GFP -electroporated area
compared to control electroporation area. This is of course compatible with a junctional
perturbation, but it suggests that the perturbation is generalized, and not is “spatially limited”.
- Regarding the effect of the manipulation on the basal endfeet. I believe this data is crucial in the
clarification of the specificity of the cell biological effects of the experimental manipulation. The
authors must show the data now parked in Supplementary Figure 1j-k in the main figure, possibly
in Figure 1.
Furthermore, given previous literature on the dynamics of the basal endfeet (Yokota et al, 2010),
it would be important to define if any morphological change happens at the basal endfoot. I am
not asking the author to generate new data, but rather to show the data they already have in a
quantitative manner. For example, the authors should show a classification/quantification of the
structure of the basal end feet as in Yokota et al, 2010, Figure 2 (club like vs branched end feet).
In addition, the authors should add a quantification of the data shown in Supplementary Figure
1m-n.
- Page 5. The delaminated progenitors generated upon nCadh20-GFP retain the basal process,
Pax6 expression and show an increased apoptosis
(i) which is the % of delaminated cells that are also apoptotic?
(ii) For those cells that are not apoptotic: do these delaminated cells correspond to bRG/oRG cells?
The authors must address this point.
I would suggest doing 3D reconstruction of their STORM data (or other suitable data sets) to
highlight the complete morphology of the manipulated cells in the SVZ. Additionally, I recommend
a staining with p-Vim to understand if there are more cells in SVZ retaining the basal process in
mitosis, as hallmark of bRGs.
- As for scRNAseq public libraries: it would be informative for the readers to show the actual
data/plots for the ABHD4 expression in different cell types in the mentioned libraries. These data
can be added as or in a supplementary figure.
- Based on the data shown by the authors, the main role of ABDH4 seems to be associated with its
downregulation. Based in the author’s claim, ABDH4 downregulation takes place immediately after
delamination. This point is interesting and it is crucial in defining the mechanism of action of
ABDH4. However, I think the claim is not fully supported by the data. It would be very informative
to show an immnunostaining to define the localization of ABDH4. I am actually surprised that,
given their experience with high resolution microscopy, the authors limit their attention the
mRNAs, without investigating the protein localization. Please clarify if this is technical issue related
to the Ab availability. Is ABDH4 -both at the mRNa and protein level- associated with the AJs or to
the asymmetric partitioning of ABDH4 during RGPC mitosis? That could provide a cellular
mechanism for the fast downregulation of ABDH4 in delaminated cells. Investigating this point
would bring the entire paper to a higher level.
- Page 7-8: the observation of the inverse correlation of ABHD4 with Tbr2 mRNA is interesting.
However, I urge the authors to consider their data in light of previously published work. Of note, it
has been demonstrated that aRGs cells already express Tbr2 mRNA (see Florio et al, 2015). So,
Tbr2 mRNA is not a specific marker for delaminated IPs, as it is present also in not a delaminated
IPs, and more importantly also in aRG cells (see Wilsch-Brauninger et al, 2012 and Florio et al,
2015). In addition, the authors mentioned that they consider cells in the VZ. Again, the VZ
localization is not indicative of a certain fate, as VZ contain APs, and IPs, both non-delaminated
and delaminated. It is not clear if the cells analyzed by the authors are retaining or not the apical
contact. I think the authors should run an additional quantification in which they score separately
cells with and without the apical contact. That will help with the interpretation of the graphs shown
in Figure panel X, that in its present state is hard to interpret and not particularly convincing.
MINOR POINTS
- Page 65-66: the model should be added as last panel to the main figure.
- Page 3: the word INTRODUCTION is missing.
- the paper address the issue of how robustness is achieved in the context of cortical development
and brain morphogenesis. I would find extremely interesting if the authors could elaborate more
on that in the discussion part.
|
Reviewers' Comments:
Reviewer #1:
Remarks to the Author:
Prof. Katona and colleagues proposed developmental anoikis and the molecular player that
controls this process. Developmental anoikis was triggered as a result of exposure to different
types of insults. One is forced delamination of neural progenitor cells by overexpression of Cdh2
mutant. Another is prenatal alcohol exposure. Concept of “developmental anoikis” that reduces
errors of development that is elicited by environmental insults is novel. Based on the known
function in cancer anoikis, and the specific expression in developmental stage, the authors picked
up Abhd4 as a candidate gene of a controller of this event. The knockout animal did not show
obvious phenotypes in normal condition. However, under exposure to insults, the aniokis is
significantly reduced in the knockout. The authors also provide good discussion of potential
mechanisms how Abhd4 controls developmental aniokis. This article provides very interesting
model, and I believe the model will be further strengthened by answering the questions below.
Abhd4 expression is remarkably specific to radial glial progenitor cells. Did authors observe
reduction of cell death only in that cell population (for example, no changes in cortical plate?) in
the knockout cortex of Abhd4 in cases of delta cdh2 overexpression and FASD model? A related
comment; is Abhd4 expression altered by prenatal alcohol exposure? For example, do cells other
than radial glial progenitor cells increase the expression of Abhd4, so that reduction of cell death is
not limited to radial glial progenitor cells in the knockout? Depending on answers to those
questions, proposed model may also require revision.
The effects on migration and cell death are obvious in embryonic stages in Adhd4 manipulation.
Are those effects kept until adulthood and make abnormal adult brain structure, or do cells catch
up migration? This information is important for discussion about significance of developmental
aniokis.
Other comments:
Most of TUNEL labelling did not overlap with GFP. Does cell death happen in cell non autonomous
manner?
Reviewer #2:
Remarks to the Author:
With this paper the Katona’s lab seeks to introduce a new concept in the field of developmental
neuroscience: the developmental anoikis as a safeguarding mechanism responsible for the
elimination of abnormally delaminated apical progenitors (RGPCs) during brain development. The
authors identified (i) ABDH4 as a crucial molecular player in developmental anoikis and (ii)
developmental anoikis as one of the possible mechanisms responsible for the elimination of
abnormally delaminated cells in a pathological condition, fetal alcohol syndrome.
The paper is a pleasant read and the ideas illustrated by the authors bring a fresh perspective in
the neurogenesis field. I acknowledge that the authors address an issue that is under-represented
in our field: how robustness is achieved in the context of cortical development and brain
morphogenesis.
Given the potential of their work, the authors must address the following points to make their
paper suitable for acceptance and publication in Nature Communication.
MINOR POINTS
- A general remark. Throughout the text, the authors refer to abnormal RGPC delamination and
AJs disassembly. Strictly speaking, delamination is always paralleled by the cell’s disengagement
from the AJs belt. What abnormal exactly means? What is different between a normal and an
abnormal AJ disassembly/delamination? What is then setting the difference?
The same apply to the use of the word “premature”, referred to delamination. Premature
compared to what exactly? Do the authors mean a delamination that is not paralleled by a fate
transition? Or a delamination that is not sync with cell cycle progression? The authors must clarify
and elaborate conceptually on that.
- Page 5: the authors write “spatially limited destruction…” upon nCadh20-GFP manipulation
referring to Figure1 a-d.
However, the panels show a deep and generalized modification of the AJs. The authors must clarify
this point and make clear if the image is representative of their conclusions. Is the manipulation
really causing a limited change in the AJ?
If so, then the authors should choose a picture reflecting this claim.
Otherwise, the authors should change the sentence to reflect what the picture showed: a
pronounced and general change in the AJs.
The same apply to the phalloidin staining shown in Supplementary Figure 1a-f. The phalloidin
staining at the apical surface is clearly less intense in the nCadh20-GFP -electroporated area
compared to control electroporation area. This is of course compatible with a junctional
perturbation, but it suggests that the perturbation is generalized, and not is “spatially limited”.
- Regarding the effect of the manipulation on the basal endfeet. I believe this data is crucial in the
clarification of the specificity of the cell biological effects of the experimental manipulation. The
authors must show the data now parked in Supplementary Figure 1j-k in the main figure, possibly
in Figure 1.
Furthermore, given previous literature on the dynamics of the basal endfeet (Yokota et al, 2010),
it would be important to define if any morphological change happens at the basal endfoot. I am
not asking the author to generate new data, but rather to show the data they already have in a
quantitative manner. For example, the authors should show a classification/quantification of the
structure of the basal end feet as in Yokota et al, 2010, Figure 2 (club like vs branched end feet).
In addition, the authors should add a quantification of the data shown in Supplementary Figure
1m-n.
- Page 5. The delaminated progenitors generated upon nCadh20-GFP retain the basal process,
Pax6 expression and show an increased apoptosis
(i) which is the % of delaminated cells that are also apoptotic?
(ii) For those cells that are not apoptotic: do these delaminated cells correspond to bRG/oRG cells?
The authors must address this point.
I would suggest doing 3D reconstruction of their STORM data (or other suitable data sets) to
highlight the complete morphology of the manipulated cells in the SVZ. Additionally, I recommend
a staining with p-Vim to understand if there are more cells in SVZ retaining the basal process in
mitosis, as hallmark of bRGs.
- As for scRNAseq public libraries: it would be informative for the readers to show the actual
data/plots for the ABHD4 expression in different cell types in the mentioned libraries. These data
can be added as or in a supplementary figure.
- Based on the data shown by the authors, the main role of ABDH4 seems to be associated with its
downregulation. Based in the author’s claim, ABDH4 downregulation takes place immediately after
delamination. This point is interesting and it is crucial in defining the mechanism of action of
ABDH4. However, I think the claim is not fully supported by the data. It would be very informative
to show an immnunostaining to define the localization of ABDH4. I am actually surprised that,
given their experience with high resolution microscopy, the authors limit their attention the
mRNAs, without investigating the protein localization. Please clarify if this is technical issue related
to the Ab availability. Is ABDH4 -both at the mRNa and protein level- associated with the AJs or to
the asymmetric partitioning of ABDH4 during RGPC mitosis? That could provide a cellular
mechanism for the fast downregulation of ABDH4 in delaminated cells. Investigating this point
would bring the entire paper to a higher level.
- Page 7-8: the observation of the inverse correlation of ABHD4 with Tbr2 mRNA is interesting.
However, I urge the authors to consider their data in light of previously published work. Of note, it
has been demonstrated that aRGs cells already express Tbr2 mRNA (see Florio et al, 2015). So,
Tbr2 mRNA is not a specific marker for delaminated IPs, as it is present also in not a delaminated
IPs, and more importantly also in aRG cells (see Wilsch-Brauninger et al, 2012 and Florio et al,
2015). In addition, the authors mentioned that they consider cells in the VZ. Again, the VZ
localization is not indicative of a certain fate, as VZ contain APs, and IPs, both non-delaminated
and delaminated. It is not clear if the cells analyzed by the authors are retaining or not the apical
contact. I think the authors should run an additional quantification in which they score separately
cells with and without the apical contact. That will help with the interpretation of the graphs shown
in Figure panel X, that in its present state is hard to interpret and not particularly convincing.
MINOR POINTS
- Page 65-66: the model should be added as last panel to the main figure.
- Page 3: the word INTRODUCTION is missing.
- the paper address the issue of how robustness is achieved in the context of cortical development
and brain morphogenesis. I would find extremely interesting if the authors could elaborate more
on that in the discussion part.
|
TPR
|
NC_BS_BIOCH_001_RR1.txt
|
{
"criticism": 6,
"example": 9,
"importance_and_relevance": 8,
"materials_and_methods": 39,
"praise": 7,
"presentation_and_reporting": 18,
"results_and_discussion": 7,
"suggestion_and_solution": 24,
"total": 83
}
|
{
"criticism": 0.07228915662650602,
"example": 0.10843373493975904,
"importance_and_relevance": 0.0963855421686747,
"materials_and_methods": 0.46987951807228917,
"praise": 0.08433734939759036,
"presentation_and_reporting": 0.21686746987951808,
"results_and_discussion": 0.08433734939759036,
"suggestion_and_solution": 0.2891566265060241
}
| 1.421687
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "Reviewers' Comments: \n \nReviewer #1: \nRemarks to the Author: \nProf. Katona and colleagues proposed developmental anoikis and the molecular player that \ncontrols this process. Developmental anoikis was triggered as a result of exposure to different \ntypes of insults. One is forced delamination of neural progenitor cells by overexpression of Cdh2 \nmutant. Another is prenatal alcohol exposure. Concept of “developmental anoikis” that reduces \nerrors of development that is elicited by environmental insults is novel. Based on the known \nfunction in cancer anoikis, and the specific expression in developmental stage, the authors picked \nup Abhd4 as a candidate gene of a controller of this event. The knockout animal did not show \nobvious phenotypes in normal condition. However, under exposure to insults, the aniokis is \nsignificantly reduced in the knockout. The authors also provide good discussion of potential \nmechanisms how Abhd4 controls developmental aniokis. This article provides very interesting \nmodel, and I believe the model will be further strengthened by answering the questions below. \n \nAbhd4 expression is remarkably specific to radial glial progenitor cells. Did authors observe \nreduction of cell death only in that cell population (for example, no changes in cortical plate?) in \nthe knockout cortex of Abhd4 in cases of delta cdh2 overexpression and FASD model? A related \ncomment; is Abhd4 expression altered by prenatal alcohol exposure? For example, do cells other \nthan radial glial progenitor cells increase the expression of Abhd4, so that reduction of cell death is \nnot limited to radial glial progenitor cells in the knockout? Depending on answers to those \nquestions, proposed model may also require revision. \n \nThe effects on migration and cell death are obvious in embryonic stages in Adhd4 manipulation. \nAre those effects kept until adulthood and make abnormal adult brain structure, or do cells catch \nup migration? This information is important for discussion about significance of developmental \naniokis. \n \nOther comments: \nMost of TUNEL labelling did not overlap with GFP. Does cell death happen in cell non autonomous \nmanner? \n \n \n \nReviewer #2: \nRemarks to the Author: \nWith this paper the Katona’s lab seeks to introduce a new concept in the field of developmental \nneuroscience: the developmental anoikis as a safeguarding mechanism responsible for the \nelimination of abnormally delaminated apical progenitors (RGPCs) during brain development. The \nauthors identified (i) ABDH4 as a crucial molecular player in developmental anoikis and (ii) \ndevelopmental anoikis as one of the possible mechanisms responsible for the elimination of \nabnormally delaminated cells in a pathological condition, fetal alcohol syndrome. \n \nThe paper is a pleasant read and the ideas illustrated by the authors bring a fresh perspective in \nthe neurogenesis field. I acknowledge that the authors address an issue that is under-represented \nin our field: how robustness is achieved in the context of cortical development and brain \nmorphogenesis. \n \nGiven the potential of their work, the authors must address the following points to make their \npaper suitable for acceptance and publication in Nature Communication. \n \nMINOR POINTS \n \n- A general remark. Throughout the text, the authors refer to abnormal RGPC delamination and \n\n\fAJs disassembly. Strictly speaking, delamination is always paralleled by the cell’s disengagement \nfrom the AJs belt. What abnormal exactly means? What is different between a normal and an \nabnormal AJ disassembly/delamination? What is then setting the difference? \nThe same apply to the use of the word “premature”, referred to delamination. Premature \ncompared to what exactly? Do the authors mean a delamination that is not paralleled by a fate \ntransition? Or a delamination that is not sync with cell cycle progression? The authors must clarify \nand elaborate conceptually on that. \n \n- Page 5: the authors write “spatially limited destruction…” upon nCadh20-GFP manipulation \nreferring to Figure1 a-d. \nHowever, the panels show a deep and generalized modification of the AJs. The authors must clarify \nthis point and make clear if the image is representative of their conclusions. Is the manipulation \nreally causing a limited change in the AJ? \nIf so, then the authors should choose a picture reflecting this claim. \nOtherwise, the authors should change the sentence to reflect what the picture showed: a \npronounced and general change in the AJs. \nThe same apply to the phalloidin staining shown in Supplementary Figure 1a-f. The phalloidin \nstaining at the apical surface is clearly less intense in the nCadh20-GFP -electroporated area \ncompared to control electroporation area. This is of course compatible with a junctional \nperturbation, but it suggests that the perturbation is generalized, and not is “spatially limited”. \n \n- Regarding the effect of the manipulation on the basal endfeet. I believe this data is crucial in the \nclarification of the specificity of the cell biological effects of the experimental manipulation. The \nauthors must show the data now parked in Supplementary Figure 1j-k in the main figure, possibly \nin Figure 1. \nFurthermore, given previous literature on the dynamics of the basal endfeet (Yokota et al, 2010), \nit would be important to define if any morphological change happens at the basal endfoot. I am \nnot asking the author to generate new data, but rather to show the data they already have in a \nquantitative manner. For example, the authors should show a classification/quantification of the \nstructure of the basal end feet as in Yokota et al, 2010, Figure 2 (club like vs branched end feet). \nIn addition, the authors should add a quantification of the data shown in Supplementary Figure \n1m-n. \n \n- Page 5. The delaminated progenitors generated upon nCadh20-GFP retain the basal process, \nPax6 expression and show an increased apoptosis \n(i) which is the % of delaminated cells that are also apoptotic? \n(ii) For those cells that are not apoptotic: do these delaminated cells correspond to bRG/oRG cells? \nThe authors must address this point. \nI would suggest doing 3D reconstruction of their STORM data (or other suitable data sets) to \nhighlight the complete morphology of the manipulated cells in the SVZ. Additionally, I recommend \na staining with p-Vim to understand if there are more cells in SVZ retaining the basal process in \nmitosis, as hallmark of bRGs. \n \n- As for scRNAseq public libraries: it would be informative for the readers to show the actual \ndata/plots for the ABHD4 expression in different cell types in the mentioned libraries. These data \ncan be added as or in a supplementary figure. \n \n- Based on the data shown by the authors, the main role of ABDH4 seems to be associated with its \ndownregulation. Based in the author’s claim, ABDH4 downregulation takes place immediately after \ndelamination. This point is interesting and it is crucial in defining the mechanism of action of \nABDH4. However, I think the claim is not fully supported by the data. It would be very informative \nto show an immnunostaining to define the localization of ABDH4. I am actually surprised that, \ngiven their experience with high resolution microscopy, the authors limit their attention the \nmRNAs, without investigating the protein localization. Please clarify if this is technical issue related \nto the Ab availability. Is ABDH4 -both at the mRNa and protein level- associated with the AJs or to \n\n\fthe asymmetric partitioning of ABDH4 during RGPC mitosis? That could provide a cellular \nmechanism for the fast downregulation of ABDH4 in delaminated cells. Investigating this point \nwould bring the entire paper to a higher level. \n \n- Page 7-8: the observation of the inverse correlation of ABHD4 with Tbr2 mRNA is interesting. \nHowever, I urge the authors to consider their data in light of previously published work. Of note, it \nhas been demonstrated that aRGs cells already express Tbr2 mRNA (see Florio et al, 2015). So, \nTbr2 mRNA is not a specific marker for delaminated IPs, as it is present also in not a delaminated \nIPs, and more importantly also in aRG cells (see Wilsch-Brauninger et al, 2012 and Florio et al, \n2015). In addition, the authors mentioned that they consider cells in the VZ. Again, the VZ \nlocalization is not indicative of a certain fate, as VZ contain APs, and IPs, both non-delaminated \nand delaminated. It is not clear if the cells analyzed by the authors are retaining or not the apical \ncontact. I think the authors should run an additional quantification in which they score separately \ncells with and without the apical contact. That will help with the interpretation of the graphs shown \nin Figure panel X, that in its present state is hard to interpret and not particularly convincing. \n \n \nMINOR POINTS \n \n- Page 65-66: the model should be added as last panel to the main figure. \n \n- Page 3: the word INTRODUCTION is missing. \n \n- the paper address the issue of how robustness is achieved in the context of cortical development \nand brain morphogenesis. I would find extremely interesting if the authors could elaborate more \non that in the discussion part. \n \n \n \n\n\f\f\n",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
ABHD4-dependent developmental anoikis safeguards the embryonic brain
|
Reviewers' Comments:
Reviewer #1:
Remarks to the Author:
The authors addressed all of points and the manuscript reads well.
Reviewer #2:
Remarks to the Author:
The revised version of László et al. addresses the points raised during the previous round of
review.
I appreciate the fact that in the present version the authors provide additional data and
quantifications corroborating and strengthening their original claims.
It is my opinion that the paper in its present form should be accepted for publication.
Only one point should be addressed: there are here and there several typos, that must be
corrected and edited before publication.
|
Reviewers' Comments:
Reviewer #1:
Remarks to the Author:
The authors addressed all of points and the manuscript reads well.
Reviewer #2:
Remarks to the Author:
The revised version of László et al. addresses the points raised during the previous round of
review.
I appreciate the fact that in the present version the authors provide additional data and
quantifications corroborating and strengthening their original claims.
It is my opinion that the paper in its present form should be accepted for publication.
Only one point should be addressed: there are here and there several typos, that must be
corrected and edited before publication.
|
TPR
|
NC_BS_BIOCH_001_RR2.txt
|
{
"criticism": 0,
"example": 0,
"importance_and_relevance": 0,
"materials_and_methods": 1,
"praise": 3,
"presentation_and_reporting": 1,
"results_and_discussion": 0,
"suggestion_and_solution": 3,
"total": 6
}
|
{
"criticism": 0,
"example": 0,
"importance_and_relevance": 0,
"materials_and_methods": 0.16666666666666666,
"praise": 0.5,
"presentation_and_reporting": 0.16666666666666666,
"results_and_discussion": 0,
"suggestion_and_solution": 0.5
}
| 1.333333
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "\n \n\n\fReviewers' Comments: \n \nReviewer #1: \nRemarks to the Author: \nThe authors addressed all of points and the manuscript reads well. \n \n \n \nReviewer #2: \nRemarks to the Author: \nThe revised version of László et al. addresses the points raised during the previous round of \nreview. \nI appreciate the fact that in the present version the authors provide additional data and \nquantifications corroborating and strengthening their original claims. \n \nIt is my opinion that the paper in its present form should be accepted for publication. \n \nOnly one point should be addressed: there are here and there several typos, that must be \ncorrected and edited before publication. \n \n \n\n\n \n\n\f\n",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Dynamic remodelling of the human host cell proteome and phosphoproteome upon
|
Reviewers' comments:
Reviewer #1 (Remarks to the Author):
Giansanti et al. - Dynamic remodeling of the human host cell (phospho)proteome upon enterovirus
infection
GENERAL COMMENTS
This manuscript explores the altered proteome in cells infected with Coxsackievirus B3. The authors
use MS proteomics to assess the change in the proteome and phosphoproteome in infected cells.
They find phosphoproteomic changes early in infection, while proteomic changes are only detected
in later timepoints (after ~8 hrs). The authors use the patterns of phosphorylation to predict the
kinases involved and investigate their effects on the mTOR pathway specifically. Through
investigation of the downstream targets of mTOR, they show that eEF2 phosphorylation is decreased
over the course of infection. The authors also discuss the role of mTOR target TFEB, a regulator of
lysosomal and autophagy. They find that TFEB is activated by infection and that knockdown of this
factor inhibits virus production, but not replication, suggesting a role for lysosomal/autophagic
pathways in egress.
The work reported in the manuscript is well done and describes the phosphoproteomic flux
associated with infection, which is sure to be a useful reference and source for hyptheses for others
in the field. The paper itself focuses on mTOR and its downstream targets. These are known to be
involved in enterovirus biology, as the authors note, which makes their observation less novel, but
still provides more context for mTOR involvement. The authors suggest one downstream target
(TFEB) of mTOR that effects virus production, but again this observation lacks mechanistic insight
beyond the genetic experiment.
Because of its quality, I believe the paper does merit acceptance and publication after the authors
address some of the comments below.
Specific Comments:
ll. 152-5. “While a decrease in protein levels may be explained by the virus-induced shutdown of
protein translation, the observation that certain protein
154 levels increased suggests that a subset of cellular proteins escape the bulk translational
shutdown induced by viral cleavage of eIF4G.“ Can the author distinguish between altered turnover
vs. EIF4G independent translation? Any analysis that could be performed to confirm this hypothesis?
Supp. Table 4.3: Why do the authors include Apoptotic signaling in the translation and transcription?
Perhaps labeling the top enriched categories on the plots would be useful for transparency.
Have the authors considered a gene set enrichment approach based on fold-change of factors in
given pathways. e.g. Do genes in this pathway have a greater fold-change than expected by chance,
this might better reflect the phenotype of the infected cells.
Small Notes:
I recommend renaming the section called “Regulation of viral protein levels during CVB3 expression”
as the section does not discuss regulation perse.
Coxsackievirus is capitalized as it is named after a city “Coxsackie, NY, USA”
Figures: The Blue gradient background is distracting and unnecessary, makes the grey lines and blue
boxes hard to visualize.
I’d encourage the authors to include some of the more “systems level” figures in the main text to
give a general sense of the hits on the screen (S2C specifically).
Reviewer #2 (Remarks to the Author):
In the manuscript “Dynamic remodeling of the human host cell (phospho)proteome Upon
enterovirus infection” Giansanti et al present a comprehensive proteomic and phospoproteomic
dataset across a time course of enterovirus infection. The extensive datasets are analyzed to identify
changes on the protein and phosphorylation levels and described globally. To interpret findings in
the phosphoproteomic dataset further analysis was performed to predict kinases that are active
during enterovirus infection. The authors then pick the mTORC1 signaling pathways for more in
depth description of its possible regulation during infection and provide limited follow up studies,
which do not lead to conclusive biological insights in enterovirus infection.
My main concerns regarding the current version of the manuscript are as follows: While the
manuscript describes an extensive dataset that seems to be of high quality, the manuscript is mainly
focused on describing the dataset rather than deriving biological insights into enterovirus infection
and identifying novel host factors/signaling pathways relevant for infection. The majority of the
paragraphs are highly descriptive, but the observations are not really linked back to the biological
question. The authors derive some hypotheses from the dataset, but they either do not provide any
functional follow up study to validate the hypothesis and the follow up studies they performed do
not provide conclusive results.
Some concerns/questions that I have regarding the proteomic datasets:
Currently the authors analyze the proteome and phosphoproteome datasets separately. It would we
important to determine whether observed changes in phosphorylation are in fact changing because
of different levels of phosphorylation or because of protein abundance changes. This is especially
important at later stages of infection where more changes on the proteome level are observed.
Some of the earlier time points for the proteome analysis do not cluster at all with the replicates. Is
this a reason why there are little significant protein abundance changes observed at earlier
timepoints of infection? Were the proteome and phosphoproteome datasets generated from the
same samples?
In summary, the current version of the manuscript lacks novel biological insights into CVBB3
infection and revisions are necessary to (1) put results in a biological context rather than just
providing a detailed description, (2) provide additional functional follow up studies demonstrating
the validity of the datasets, and (3) address the specific concerns listed below.
Specific concerns:
Page 4, Introduction
The authors should provide a few sentence summary of the major findings of their study at the end
of the introduction. What was the specific goal/motivation of the study? What was the motivation to
use CVB3?
Page 5, Results, Analysis of the proteome of infected cells
• What is the biological motivation to use CVB3 in the study? Why was an MOI of 10 used and what
was the infection rate obtained with this MOI? How reproducible was the infection?
• Reproducibility of the infection seem concerning, since the clustering of the overall proteome data
is variable and shows that replicates of earlier timepoint of the infection do not cluster at all with
their respective biological replicates.
• How were the clusters defined in Figure 2a (no dendogram provided)?
• Sections of this paragraphs sound just like a description of the method and could be shortened.
• I would suggest to restructure the manuscript. The flow of the manuscript feels interrupted, since
the overall proteome dataset is descried in the first paragraph, but then not followed by the analysis
of the proteome changes in the course of infection.
Page 6, Results, Analysis of the phosphoproteome of infected cells
• See above, sections of this paragraphs sound just like a description of the method and could be
shortened.
• How were the clusters defined in Figure 2b (no dendogram provided)?
• It seems surprising to me that 85% of the phosphoproteome is changing in the course of infection.
How does this compare to other phosphoproteomic datasets generated in the course of viral
infection? How was the data normalized? Often in proteomic datasets normalization strategies are
employed which assume that the majority of the sites are not changing. How did the authors
address this in their data analysis? More details need to be provided in the method section?
• See above, the manuscript feels interrupted, since the description of the phosphoproteomic
dataset is not followed by the analysis of the phosphorylation changes.
Page 6, Results, Regulation of viral protein levels during CVB3 infection
• This paragraph is purely descriptive and out of the context in this part of the manuscript.
• I would suggest to link it ack to CVB3 biology, otherwise I would remove it completely.
Page 7, Results, Changes in host protein levels during CVB3 infection
• I think for a better reading of the manuscript the authors should consider to restructure the result
section and move this section after describing the proteome dataset.
• See above, it is concerning to me that replicates of some timepoints do not cluster at all and look
very different in the heatmap. What is the reason for this? Was there a quality control for the
reproducibility of infection?
• Paragraph misses more biology, what are these proteins that escape virus-induced translational
shutdown?
• It would also be highly interesting if the authors could perform an integrative analysis of their data
with the CVB3 host-pathogen interaction network that was recently published in Nature
Microbiology.
Page 8, Results, Regulation of protein phosphorylation levels during CVB3 infection
• I think for a better reading of the manuscript the authors should consider to restructure the result
section and move this section after describing the phosphoproteome dataset.
• At the end of the section, changes in phosphoproteome and total proteome are compared, I am
wondering what the fraction of the phosphoproteome changes can in fact be explained by protein
abundance changes. What is the fraction of phosphosites that change while there is no change
observed on the protein level?
Page 8, Results, Identification of kinases that are activated by CVB3 infection
It is stated in the text that three findings of this analysis are of particular interest, such as
overrepresentation of ATM/ATR motifs. Why are these findings of particular of particular interest?
What does this mean for the infection process? What is the role of ATM/ATR or c PKC and GRKs in
CVB3 infection?
Page 9, Results, Phosphorylation of host factors involved in formation of viral replication organelles
The authors describe in this section the phosphorylation of know proteins that might play a role in
replication organelle formation and suggest that the specific sites might be relevant for the organelle
formation, but again this is only descriptive and no biological follow up is provided. What is the
possible impact of knowing the phosphorylation sites of these specific factors? Does mutating these
sides lead to a reduction in viral replication?
Page 11, Results, Signaling pathways affected during CVB3 infection
More details need to be provided how the pathway analysis was performed. What are the
predefined pathways known to be affected by CVB3? Where are they taken from? Was the
proteome and phosphoproteome data just mapped onto pathways or was an enrichment analysis
performed? Which input data was provided in for the pathway analysis, quantitative data across all
time points?
Page 11, Results, Inactivation of mTORC1 signaling during CVB3 infection
Figure 3 associated with this section is very difficult to read:
I would suggest now to use the blue background, which reduces the contrast in the figure. +/-
symbols are so small that they are hard to see. Also it is not clear what the different colored arrows
and lines mean.
Why was a higher MOI of 50 used for validating the phosphoproteomic data by Western Blot, which
itself was generated at an MOI of 10.
Page 14, Results, Activation of the mTORC1-regulated protein transcription factor EB
How was the knockout of TFEB performed? There is no information provided in the method section.
Additionally, validation of the ko is missing.
What is the explanation that 8hpi a significant decrease in virus titers is observed upon ko of TFEB,
however there is no significant difference 10hpi? Does this makes sense?
Page 18, Experimental procedures
As mentioned in different comments above, a more detailed description of some of the methods is
missing and should be provided.
|
Reviewers' comments:
Reviewer #1 (Remarks to the Author):
Giansanti et al. - Dynamic remodeling of the human host cell (phospho)proteome upon enterovirus
infection
GENERAL COMMENTS
This manuscript explores the altered proteome in cells infected with Coxsackievirus B3. The authors
use MS proteomics to assess the change in the proteome and phosphoproteome in infected cells.
They find phosphoproteomic changes early in infection, while proteomic changes are only detected
in later timepoints (after ~8 hrs). The authors use the patterns of phosphorylation to predict the
kinases involved and investigate their effects on the mTOR pathway specifically. Through
investigation of the downstream targets of mTOR, they show that eEF2 phosphorylation is decreased
over the course of infection. The authors also discuss the role of mTOR target TFEB, a regulator of
lysosomal and autophagy. They find that TFEB is activated by infection and that knockdown of this
factor inhibits virus production, but not replication, suggesting a role for lysosomal/autophagic
pathways in egress.
The work reported in the manuscript is well done and describes the phosphoproteomic flux
associated with infection, which is sure to be a useful reference and source for hyptheses for others
in the field. The paper itself focuses on mTOR and its downstream targets. These are known to be
involved in enterovirus biology, as the authors note, which makes their observation less novel, but
still provides more context for mTOR involvement. The authors suggest one downstream target
(TFEB) of mTOR that effects virus production, but again this observation lacks mechanistic insight
beyond the genetic experiment.
Because of its quality, I believe the paper does merit acceptance and publication after the authors
address some of the comments below.
Specific Comments:
ll. 152-5. “While a decrease in protein levels may be explained by the virus-induced shutdown of
protein translation, the observation that certain protein
154 levels increased suggests that a subset of cellular proteins escape the bulk translational
shutdown induced by viral cleavage of eIF4G.“ Can the author distinguish between altered turnover
vs. EIF4G independent translation? Any analysis that could be performed to confirm this hypothesis?
Supp. Table 4.3: Why do the authors include Apoptotic signaling in the translation and transcription?
Perhaps labeling the top enriched categories on the plots would be useful for transparency.
Have the authors considered a gene set enrichment approach based on fold-change of factors in
given pathways. e.g. Do genes in this pathway have a greater fold-change than expected by chance,
this might better reflect the phenotype of the infected cells.
Small Notes:
I recommend renaming the section called “Regulation of viral protein levels during CVB3 expression”
as the section does not discuss regulation perse.
Coxsackievirus is capitalized as it is named after a city “Coxsackie, NY, USA”
Figures: The Blue gradient background is distracting and unnecessary, makes the grey lines and blue
boxes hard to visualize.
I’d encourage the authors to include some of the more “systems level” figures in the main text to
give a general sense of the hits on the screen (S2C specifically).
Reviewer #2 (Remarks to the Author):
In the manuscript “Dynamic remodeling of the human host cell (phospho)proteome Upon
enterovirus infection” Giansanti et al present a comprehensive proteomic and phospoproteomic
dataset across a time course of enterovirus infection. The extensive datasets are analyzed to identify
changes on the protein and phosphorylation levels and described globally. To interpret findings in
the phosphoproteomic dataset further analysis was performed to predict kinases that are active
during enterovirus infection. The authors then pick the mTORC1 signaling pathways for more in
depth description of its possible regulation during infection and provide limited follow up studies,
which do not lead to conclusive biological insights in enterovirus infection.
My main concerns regarding the current version of the manuscript are as follows: While the
manuscript describes an extensive dataset that seems to be of high quality, the manuscript is mainly
focused on describing the dataset rather than deriving biological insights into enterovirus infection
and identifying novel host factors/signaling pathways relevant for infection. The majority of the
paragraphs are highly descriptive, but the observations are not really linked back to the biological
question. The authors derive some hypotheses from the dataset, but they either do not provide any
functional follow up study to validate the hypothesis and the follow up studies they performed do
not provide conclusive results.
Some concerns/questions that I have regarding the proteomic datasets:
Currently the authors analyze the proteome and phosphoproteome datasets separately. It would we
important to determine whether observed changes in phosphorylation are in fact changing because
of different levels of phosphorylation or because of protein abundance changes. This is especially
important at later stages of infection where more changes on the proteome level are observed.
Some of the earlier time points for the proteome analysis do not cluster at all with the replicates. Is
this a reason why there are little significant protein abundance changes observed at earlier
timepoints of infection? Were the proteome and phosphoproteome datasets generated from the
same samples?
In summary, the current version of the manuscript lacks novel biological insights into CVBB3
infection and revisions are necessary to (1) put results in a biological context rather than just
providing a detailed description, (2) provide additional functional follow up studies demonstrating
the validity of the datasets, and (3) address the specific concerns listed below.
Specific concerns:
Page 4, Introduction
The authors should provide a few sentence summary of the major findings of their study at the end
of the introduction. What was the specific goal/motivation of the study? What was the motivation to
use CVB3?
Page 5, Results, Analysis of the proteome of infected cells
• What is the biological motivation to use CVB3 in the study? Why was an MOI of 10 used and what
was the infection rate obtained with this MOI? How reproducible was the infection?
• Reproducibility of the infection seem concerning, since the clustering of the overall proteome data
is variable and shows that replicates of earlier timepoint of the infection do not cluster at all with
their respective biological replicates.
• How were the clusters defined in Figure 2a (no dendogram provided)?
• Sections of this paragraphs sound just like a description of the method and could be shortened.
• I would suggest to restructure the manuscript. The flow of the manuscript feels interrupted, since
the overall proteome dataset is descried in the first paragraph, but then not followed by the analysis
of the proteome changes in the course of infection.
Page 6, Results, Analysis of the phosphoproteome of infected cells
• See above, sections of this paragraphs sound just like a description of the method and could be
shortened.
• How were the clusters defined in Figure 2b (no dendogram provided)?
• It seems surprising to me that 85% of the phosphoproteome is changing in the course of infection.
How does this compare to other phosphoproteomic datasets generated in the course of viral
infection? How was the data normalized? Often in proteomic datasets normalization strategies are
employed which assume that the majority of the sites are not changing. How did the authors
address this in their data analysis? More details need to be provided in the method section?
• See above, the manuscript feels interrupted, since the description of the phosphoproteomic
dataset is not followed by the analysis of the phosphorylation changes.
Page 6, Results, Regulation of viral protein levels during CVB3 infection
• This paragraph is purely descriptive and out of the context in this part of the manuscript.
• I would suggest to link it ack to CVB3 biology, otherwise I would remove it completely.
Page 7, Results, Changes in host protein levels during CVB3 infection
• I think for a better reading of the manuscript the authors should consider to restructure the result
section and move this section after describing the proteome dataset.
• See above, it is concerning to me that replicates of some timepoints do not cluster at all and look
very different in the heatmap. What is the reason for this? Was there a quality control for the
reproducibility of infection?
• Paragraph misses more biology, what are these proteins that escape virus-induced translational
shutdown?
• It would also be highly interesting if the authors could perform an integrative analysis of their data
with the CVB3 host-pathogen interaction network that was recently published in Nature
Microbiology.
Page 8, Results, Regulation of protein phosphorylation levels during CVB3 infection
• I think for a better reading of the manuscript the authors should consider to restructure the result
section and move this section after describing the phosphoproteome dataset.
• At the end of the section, changes in phosphoproteome and total proteome are compared, I am
wondering what the fraction of the phosphoproteome changes can in fact be explained by protein
abundance changes. What is the fraction of phosphosites that change while there is no change
observed on the protein level?
Page 8, Results, Identification of kinases that are activated by CVB3 infection
It is stated in the text that three findings of this analysis are of particular interest, such as
overrepresentation of ATM/ATR motifs. Why are these findings of particular of particular interest?
What does this mean for the infection process? What is the role of ATM/ATR or c PKC and GRKs in
CVB3 infection?
Page 9, Results, Phosphorylation of host factors involved in formation of viral replication organelles
The authors describe in this section the phosphorylation of know proteins that might play a role in
replication organelle formation and suggest that the specific sites might be relevant for the organelle
formation, but again this is only descriptive and no biological follow up is provided. What is the
possible impact of knowing the phosphorylation sites of these specific factors? Does mutating these
sides lead to a reduction in viral replication?
Page 11, Results, Signaling pathways affected during CVB3 infection
More details need to be provided how the pathway analysis was performed. What are the
predefined pathways known to be affected by CVB3? Where are they taken from? Was the
proteome and phosphoproteome data just mapped onto pathways or was an enrichment analysis
performed? Which input data was provided in for the pathway analysis, quantitative data across all
time points?
Page 11, Results, Inactivation of mTORC1 signaling during CVB3 infection
Figure 3 associated with this section is very difficult to read:
I would suggest now to use the blue background, which reduces the contrast in the figure. +/-
symbols are so small that they are hard to see. Also it is not clear what the different colored arrows
and lines mean.
Why was a higher MOI of 50 used for validating the phosphoproteomic data by Western Blot, which
itself was generated at an MOI of 10.
Page 14, Results, Activation of the mTORC1-regulated protein transcription factor EB
How was the knockout of TFEB performed? There is no information provided in the method section.
Additionally, validation of the ko is missing.
What is the explanation that 8hpi a significant decrease in virus titers is observed upon ko of TFEB,
however there is no significant difference 10hpi? Does this makes sense?
Page 18, Experimental procedures
As mentioned in different comments above, a more detailed description of some of the methods is
missing and should be provided.
|
TPR
|
NC_BS_BIOCH_002_RR1.txt
|
{
"criticism": 16,
"example": 14,
"importance_and_relevance": 5,
"materials_and_methods": 48,
"praise": 3,
"presentation_and_reporting": 19,
"results_and_discussion": 18,
"suggestion_and_solution": 19,
"total": 93
}
|
{
"criticism": 0.17204301075268819,
"example": 0.15053763440860216,
"importance_and_relevance": 0.053763440860215055,
"materials_and_methods": 0.5161290322580645,
"praise": 0.03225806451612903,
"presentation_and_reporting": 0.20430107526881722,
"results_and_discussion": 0.1935483870967742,
"suggestion_and_solution": 0.20430107526881722
}
| 1.526882
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "Reviewers' comments: \n\n \n\nReviewer #1 (Remarks to the Author): \n\n \n\nGiansanti et al. - Dynamic remodeling of the human host cell (phospho)proteome upon enterovirus \ninfection \n\n \n\nGENERAL COMMENTS \n\n \n\nThis manuscript explores the altered proteome in cells infected with Coxsackievirus B3. The authors \nuse MS proteomics to assess the change in the proteome and phosphoproteome in infected cells. \nThey find phosphoproteomic changes early in infection, while proteomic changes are only detected \nin later timepoints (after ~8 hrs). The authors use the patterns of phosphorylation to predict the \nkinases involved and investigate their effects on the mTOR pathway specifically. Through \ninvestigation of the downstream targets of mTOR, they show that eEF2 phosphorylation is decreased \nover the course of infection. The authors also discuss the role of mTOR target TFEB, a regulator of \nlysosomal and autophagy. They find that TFEB is activated by infection and that knockdown of this \nfactor inhibits virus production, but not replication, suggesting a role for lysosomal/autophagic \npathways in egress. \n\n \n\nThe work reported in the manuscript is well done and describes the phosphoproteomic flux \nassociated with infection, which is sure to be a useful reference and source for hyptheses for others \nin the field. The paper itself focuses on mTOR and its downstream targets. These are known to be \ninvolved in enterovirus biology, as the authors note, which makes their observation less novel, but \nstill provides more context for mTOR involvement. The authors suggest one downstream target \n(TFEB) of mTOR that effects virus production, but again this observation lacks mechanistic insight \nbeyond the genetic experiment. \n\n \n\nBecause of its quality, I believe the paper does merit acceptance and publication after the authors \naddress some of the comments below. \n\n \n\nSpecific Comments: \n\n \n\n\fll. 152-5. “While a decrease in protein levels may be explained by the virus-induced shutdown of \nprotein translation, the observation that certain protein \n\n154 levels increased suggests that a subset of cellular proteins escape the bulk translational \nshutdown induced by viral cleavage of eIF4G.“ Can the author distinguish between altered turnover \nvs. EIF4G independent translation? Any analysis that could be performed to confirm this hypothesis? \n\n \n\nSupp. Table 4.3: Why do the authors include Apoptotic signaling in the translation and transcription? \nPerhaps labeling the top enriched categories on the plots would be useful for transparency. \n\n \n\nHave the authors considered a gene set enrichment approach based on fold-change of factors in \ngiven pathways. e.g. Do genes in this pathway have a greater fold-change than expected by chance, \nthis might better reflect the phenotype of the infected cells. \n\n \n\nSmall Notes: \n\n \n\nI recommend renaming the section called “Regulation of viral protein levels during CVB3 expression” \nas the section does not discuss regulation perse. \n\n \n\nCoxsackievirus is capitalized as it is named after a city “Coxsackie, NY, USA” \n\n \n\nFigures: The Blue gradient background is distracting and unnecessary, makes the grey lines and blue \nboxes hard to visualize. \n\n \n\nI’d encourage the authors to include some of the more “systems level” figures in the main text to \ngive a general sense of the hits on the screen (S2C specifically). \n\n \n\n \n\nReviewer #2 (Remarks to the Author): \n\n \n\nIn the manuscript “Dynamic remodeling of the human host cell (phospho)proteome Upon \nenterovirus infection” Giansanti et al present a comprehensive proteomic and phospoproteomic \ndataset across a time course of enterovirus infection. The extensive datasets are analyzed to identify \n\n\fchanges on the protein and phosphorylation levels and described globally. To interpret findings in \nthe phosphoproteomic dataset further analysis was performed to predict kinases that are active \nduring enterovirus infection. The authors then pick the mTORC1 signaling pathways for more in \ndepth description of its possible regulation during infection and provide limited follow up studies, \nwhich do not lead to conclusive biological insights in enterovirus infection. \n\n \n\nMy main concerns regarding the current version of the manuscript are as follows: While the \nmanuscript describes an extensive dataset that seems to be of high quality, the manuscript is mainly \nfocused on describing the dataset rather than deriving biological insights into enterovirus infection \nand identifying novel host factors/signaling pathways relevant for infection. The majority of the \nparagraphs are highly descriptive, but the observations are not really linked back to the biological \nquestion. The authors derive some hypotheses from the dataset, but they either do not provide any \nfunctional follow up study to validate the hypothesis and the follow up studies they performed do \nnot provide conclusive results. \n\n \n\nSome concerns/questions that I have regarding the proteomic datasets: \n\nCurrently the authors analyze the proteome and phosphoproteome datasets separately. It would we \nimportant to determine whether observed changes in phosphorylation are in fact changing because \nof different levels of phosphorylation or because of protein abundance changes. This is especially \nimportant at later stages of infection where more changes on the proteome level are observed. \n\nSome of the earlier time points for the proteome analysis do not cluster at all with the replicates. Is \nthis a reason why there are little significant protein abundance changes observed at earlier \ntimepoints of infection? Were the proteome and phosphoproteome datasets generated from the \nsame samples? \n\n \n\nIn summary, the current version of the manuscript lacks novel biological insights into CVBB3 \ninfection and revisions are necessary to (1) put results in a biological context rather than just \nproviding a detailed description, (2) provide additional functional follow up studies demonstrating \nthe validity of the datasets, and (3) address the specific concerns listed below. \n\n \n\nSpecific concerns: \n\n \n\nPage 4, Introduction \n\nThe authors should provide a few sentence summary of the major findings of their study at the end \nof the introduction. What was the specific goal/motivation of the study? What was the motivation to \nuse CVB3? \n\n\f \n\nPage 5, Results, Analysis of the proteome of infected cells \n\n• What is the biological motivation to use CVB3 in the study? Why was an MOI of 10 used and what \nwas the infection rate obtained with this MOI? How reproducible was the infection? \n\n• Reproducibility of the infection seem concerning, since the clustering of the overall proteome data \nis variable and shows that replicates of earlier timepoint of the infection do not cluster at all with \ntheir respective biological replicates. \n\n• How were the clusters defined in Figure 2a (no dendogram provided)? \n\n• Sections of this paragraphs sound just like a description of the method and could be shortened. \n\n• I would suggest to restructure the manuscript. The flow of the manuscript feels interrupted, since \nthe overall proteome dataset is descried in the first paragraph, but then not followed by the analysis \nof the proteome changes in the course of infection. \n\n \n\nPage 6, Results, Analysis of the phosphoproteome of infected cells \n\n• See above, sections of this paragraphs sound just like a description of the method and could be \nshortened. \n\n• How were the clusters defined in Figure 2b (no dendogram provided)? \n\n• It seems surprising to me that 85% of the phosphoproteome is changing in the course of infection. \nHow does this compare to other phosphoproteomic datasets generated in the course of viral \ninfection? How was the data normalized? Often in proteomic datasets normalization strategies are \nemployed which assume that the majority of the sites are not changing. How did the authors \naddress this in their data analysis? More details need to be provided in the method section? \n\n• See above, the manuscript feels interrupted, since the description of the phosphoproteomic \ndataset is not followed by the analysis of the phosphorylation changes. \n\n \n\nPage 6, Results, Regulation of viral protein levels during CVB3 infection \n\n• This paragraph is purely descriptive and out of the context in this part of the manuscript. \n\n• I would suggest to link it ack to CVB3 biology, otherwise I would remove it completely. \n\n \n\nPage 7, Results, Changes in host protein levels during CVB3 infection \n\n• I think for a better reading of the manuscript the authors should consider to restructure the result \nsection and move this section after describing the proteome dataset. \n\n\f• See above, it is concerning to me that replicates of some timepoints do not cluster at all and look \nvery different in the heatmap. What is the reason for this? Was there a quality control for the \nreproducibility of infection? \n\n• Paragraph misses more biology, what are these proteins that escape virus-induced translational \nshutdown? \n\n• It would also be highly interesting if the authors could perform an integrative analysis of their data \nwith the CVB3 host-pathogen interaction network that was recently published in Nature \nMicrobiology. \n\n \n\nPage 8, Results, Regulation of protein phosphorylation levels during CVB3 infection \n\n• I think for a better reading of the manuscript the authors should consider to restructure the result \nsection and move this section after describing the phosphoproteome dataset. \n\n• At the end of the section, changes in phosphoproteome and total proteome are compared, I am \nwondering what the fraction of the phosphoproteome changes can in fact be explained by protein \nabundance changes. What is the fraction of phosphosites that change while there is no change \nobserved on the protein level? \n\n \n\nPage 8, Results, Identification of kinases that are activated by CVB3 infection \n\nIt is stated in the text that three findings of this analysis are of particular interest, such as \noverrepresentation of ATM/ATR motifs. Why are these findings of particular of particular interest? \nWhat does this mean for the infection process? What is the role of ATM/ATR or c PKC and GRKs in \nCVB3 infection? \n\n \n\n \n\nPage 9, Results, Phosphorylation of host factors involved in formation of viral replication organelles \n\nThe authors describe in this section the phosphorylation of know proteins that might play a role in \nreplication organelle formation and suggest that the specific sites might be relevant for the organelle \nformation, but again this is only descriptive and no biological follow up is provided. What is the \npossible impact of knowing the phosphorylation sites of these specific factors? Does mutating these \nsides lead to a reduction in viral replication? \n\n \n\nPage 11, Results, Signaling pathways affected during CVB3 infection \n\nMore details need to be provided how the pathway analysis was performed. What are the \npredefined pathways known to be affected by CVB3? Where are they taken from? Was the \n\n\fproteome and phosphoproteome data just mapped onto pathways or was an enrichment analysis \nperformed? Which input data was provided in for the pathway analysis, quantitative data across all \ntime points? \n\n \n\nPage 11, Results, Inactivation of mTORC1 signaling during CVB3 infection \n\nFigure 3 associated with this section is very difficult to read: \n\nI would suggest now to use the blue background, which reduces the contrast in the figure. +/- \nsymbols are so small that they are hard to see. Also it is not clear what the different colored arrows \nand lines mean. \n\nWhy was a higher MOI of 50 used for validating the phosphoproteomic data by Western Blot, which \nitself was generated at an MOI of 10. \n\n \n\nPage 14, Results, Activation of the mTORC1-regulated protein transcription factor EB \n\nHow was the knockout of TFEB performed? There is no information provided in the method section. \nAdditionally, validation of the ko is missing. \n\nWhat is the explanation that 8hpi a significant decrease in virus titers is observed upon ko of TFEB, \nhowever there is no significant difference 10hpi? Does this makes sense? \n\n \n\nPage 18, Experimental procedures \n\nAs mentioned in different comments above, a more detailed description of some of the methods is \nmissing and should be provided. \n\n\f",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Dynamic remodelling of the human host cell proteome and phosphoproteome upon
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
The revised version of this manuscript address all the questions and suggestions by the authors and
in my opinion the majority of the concerns describe by the other reviewer. I believe that the
inclusion of of additional experimental validations on GBF1 and PI4KB phosphorylation in the
formation of the replication organelles and the connection of TFEB and secretory autophagy during
CVB3 infection is interesting finding. I believe the paper has significantly increased in quality and I
have not additional comments or concerns.
Reviewer #2 (Remarks to the Author):
For the revised version of the manuscript entitled “Dynamic remodeling of the host cell
(phospho)proteome upon enterovirus infection” the authors addressed the majority of my
comments. The main concerns that I raised included the focus on the previous version on the
description of the dataset rather than emphasizing what the data tells us about the biology of
enterovirus infection, the lack of functional follow up studies, and restructuring of the manuscript.
The authors restructured the manuscript substantially as well as shorten some of the descriptive
sections, so that it is more intuitive for the reader to follow the major findings of the study.
In order to address the lack of biological insights extracted from the large scale dataset the authors
added functional data characterizing the role of mTORC1 inactivation leading to increased TFEB
activity as well as investigating the role of phosphorylation of host factors involved in the formation
of viral replication organelles.
I have a few remaining concerns/questions regarding the functional follow up findings:
1. The authors hypothesize that TFEB activation downstream of mTORC1 affect non-lytic virus
release vis extracellular vesicles (EV). While the authors show a significantly reduced EV-enclosed
virus release, but at the same time TFEB ko also reduces the naked virus, even though it is not
significant reduced, which is likely due to variability in the measurements/experiment. Does this
result imply that TFEB does not only affect the non-lytic but also the lytic virus release? How do the
authors explain ths oberservation?
2. The last sentence of the Result section “These data lend further support to the idea that
(entero)viruses not only hijack cellular pathways to build their replication organelles but that they
also rewire them from their regulation in non-infected cells.” seems unclear to me. Please clarify the
meaning of “…rewire them from their regulation in non-infected cells.”
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
The revised version of this manuscript address all the questions and suggestions by the authors and
in my opinion the majority of the concerns describe by the other reviewer. I believe that the
inclusion of of additional experimental validations on GBF1 and PI4KB phosphorylation in the
formation of the replication organelles and the connection of TFEB and secretory autophagy during
CVB3 infection is interesting finding. I believe the paper has significantly increased in quality and I
have not additional comments or concerns.
Reviewer #2 (Remarks to the Author):
For the revised version of the manuscript entitled “Dynamic remodeling of the host cell
(phospho)proteome upon enterovirus infection” the authors addressed the majority of my
comments. The main concerns that I raised included the focus on the previous version on the
description of the dataset rather than emphasizing what the data tells us about the biology of
enterovirus infection, the lack of functional follow up studies, and restructuring of the manuscript.
The authors restructured the manuscript substantially as well as shorten some of the descriptive
sections, so that it is more intuitive for the reader to follow the major findings of the study.
In order to address the lack of biological insights extracted from the large scale dataset the authors
added functional data characterizing the role of mTORC1 inactivation leading to increased TFEB
activity as well as investigating the role of phosphorylation of host factors involved in the formation
of viral replication organelles.
I have a few remaining concerns/questions regarding the functional follow up findings:
1. The authors hypothesize that TFEB activation downstream of mTORC1 affect non-lytic virus
release vis extracellular vesicles (EV). While the authors show a significantly reduced EV-enclosed
virus release, but at the same time TFEB ko also reduces the naked virus, even though it is not
significant reduced, which is likely due to variability in the measurements/experiment. Does this
result imply that TFEB does not only affect the non-lytic but also the lytic virus release? How do the
authors explain ths oberservation?
2. The last sentence of the Result section “These data lend further support to the idea that
(entero)viruses not only hijack cellular pathways to build their replication organelles but that they
also rewire them from their regulation in non-infected cells.” seems unclear to me. Please clarify the
meaning of “…rewire them from their regulation in non-infected cells.”
|
TPR
|
NC_BS_BIOCH_002_RR2.txt
|
{
"criticism": 3,
"example": 0,
"importance_and_relevance": 0,
"materials_and_methods": 4,
"praise": 1,
"presentation_and_reporting": 3,
"results_and_discussion": 4,
"suggestion_and_solution": 2,
"total": 15
}
|
{
"criticism": 0.2,
"example": 0,
"importance_and_relevance": 0,
"materials_and_methods": 0.26666666666666666,
"praise": 0.06666666666666667,
"presentation_and_reporting": 0.2,
"results_and_discussion": 0.26666666666666666,
"suggestion_and_solution": 0.13333333333333333
}
| 1.133333
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "\n\n\n\fREVIEWERS' COMMENTS: \n\n \n\nReviewer #1 (Remarks to the Author): \n\n \n\nThe revised version of this manuscript address all the questions and suggestions by the authors and \nin my opinion the majority of the concerns describe by the other reviewer. I believe that the \ninclusion of of additional experimental validations on GBF1 and PI4KB phosphorylation in the \nformation of the replication organelles and the connection of TFEB and secretory autophagy during \nCVB3 infection is interesting finding. I believe the paper has significantly increased in quality and I \nhave not additional comments or concerns. \n\n \n\n \n\nReviewer #2 (Remarks to the Author): \n\n \n\nFor the revised version of the manuscript entitled “Dynamic remodeling of the host cell \n(phospho)proteome upon enterovirus infection” the authors addressed the majority of my \ncomments. The main concerns that I raised included the focus on the previous version on the \ndescription of the dataset rather than emphasizing what the data tells us about the biology of \nenterovirus infection, the lack of functional follow up studies, and restructuring of the manuscript. \n\nThe authors restructured the manuscript substantially as well as shorten some of the descriptive \nsections, so that it is more intuitive for the reader to follow the major findings of the study. \n\nIn order to address the lack of biological insights extracted from the large scale dataset the authors \nadded functional data characterizing the role of mTORC1 inactivation leading to increased TFEB \nactivity as well as investigating the role of phosphorylation of host factors involved in the formation \nof viral replication organelles. \n\n \n\nI have a few remaining concerns/questions regarding the functional follow up findings: \n\n1. The authors hypothesize that TFEB activation downstream of mTORC1 affect non-lytic virus \nrelease vis extracellular vesicles (EV). While the authors show a significantly reduced EV-enclosed \nvirus release, but at the same time TFEB ko also reduces the naked virus, even though it is not \nsignificant reduced, which is likely due to variability in the measurements/experiment. Does this \nresult imply that TFEB does not only affect the non-lytic but also the lytic virus release? How do the \nauthors explain ths oberservation? \n\n2. The last sentence of the Result section “These data lend further support to the idea that \n(entero)viruses not only hijack cellular pathways to build their replication organelles but that they \n\n\falso rewire them from their regulation in non-infected cells.” seems unclear to me. Please clarify the \nmeaning of “…rewire them from their regulation in non-infected cells.” \n\n\f",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Visualizing the enzyme mechanism of mevalonate diphosphate decarboxylase
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
I am totally satisfied with the revisions made by the authors, in which all my comments have been
addressed. Now the reaction mechanism of MDD proposed by the authors is updated appropriately
and agrees well with recent knowledges of the enzyme. The comparison of the structures of MDD
solved in the study with the previously known structures of the enzyme and its orthologs,
considering the effect of crystal packing, makes sense. I still hope the catalytic mechanism of this
interesting decarboxylase is elucidated by QM/MM study, but it is not necessary in this paper. The
elucidation will be made in future probably by the authors or other groups.
Reviewer #2 (Remarks to the Author):
In the manuscript entitled "Visualizing the Enzyme Mechanism of Mevalonate Diphosphate
Decarboxylase" by Chen et al. (Manuscript NCOMMS-19-27996A) the authors submitted a revised
version of their manuscript.
The revised version has substantially improved.
(1) The structural comparison of different MDD structures available in the PDB improves the
understanding of the differences of the structures for example different crystal packing effects and
hence restricted conformational flexibility of the elements. See also the novel Supplementary
Figure 7. Here, I just have a minor point: I personally find it useful if the PDB-ID for the displayed
structure (panel c to e) is provided and/or a reference to the primary citation. This suggestion
applies as well to Supplementary figures.
The functional implications are now much better to follow. In particular, the discussion of the
putative function of Asp282 is now better to understand. By the discussion of the other two recent
publications, as suggested by the other reviewer, the authors were able to discard the contested
hypothesis section on the mechanism. It is a very beautiful example how structural biology can
provide insightful structural information to elucidate an enzymatic mechanism.
I recommend to accept the current version of the manuscript.
Minor points:
- Page 12, line 11: Names of organism should be in italic
- Supplementary Figure 5: I suggest deleting the primer sequences. They are given in the
Materials and Methods section.
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
I am totally satisfied with the revisions made by the authors, in which all my comments have been
addressed. Now the reaction mechanism of MDD proposed by the authors is updated appropriately
and agrees well with recent knowledges of the enzyme. The comparison of the structures of MDD
solved in the study with the previously known structures of the enzyme and its orthologs,
considering the effect of crystal packing, makes sense. I still hope the catalytic mechanism of this
interesting decarboxylase is elucidated by QM/MM study, but it is not necessary in this paper. The
elucidation will be made in future probably by the authors or other groups.
Reviewer #2 (Remarks to the Author):
In the manuscript entitled "Visualizing the Enzyme Mechanism of Mevalonate Diphosphate
Decarboxylase" by Chen et al. (Manuscript NCOMMS-19-27996A) the authors submitted a revised
version of their manuscript.
The revised version has substantially improved.
(1) The structural comparison of different MDD structures available in the PDB improves the
understanding of the differences of the structures for example different crystal packing effects and
hence restricted conformational flexibility of the elements. See also the novel Supplementary
Figure 7. Here, I just have a minor point: I personally find it useful if the PDB-ID for the displayed
structure (panel c to e) is provided and/or a reference to the primary citation. This suggestion
applies as well to Supplementary figures.
The functional implications are now much better to follow. In particular, the discussion of the
putative function of Asp282 is now better to understand. By the discussion of the other two recent
publications, as suggested by the other reviewer, the authors were able to discard the contested
hypothesis section on the mechanism. It is a very beautiful example how structural biology can
provide insightful structural information to elucidate an enzymatic mechanism.
I recommend to accept the current version of the manuscript.
Minor points:
- Page 12, line 11: Names of organism should be in italic
- Supplementary Figure 5: I suggest deleting the primer sequences. They are given in the
Materials and Methods section.
|
TPR
|
NC_BS_BIOCH_003_RR2.txt
|
{
"criticism": 0,
"example": 3,
"importance_and_relevance": 1,
"materials_and_methods": 6,
"praise": 6,
"presentation_and_reporting": 6,
"results_and_discussion": 3,
"suggestion_and_solution": 4,
"total": 19
}
|
{
"criticism": 0,
"example": 0.15789473684210525,
"importance_and_relevance": 0.05263157894736842,
"materials_and_methods": 0.3157894736842105,
"praise": 0.3157894736842105,
"presentation_and_reporting": 0.3157894736842105,
"results_and_discussion": 0.15789473684210525,
"suggestion_and_solution": 0.21052631578947367
}
| 1.526316
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "\n\n\fREVIEWERS' COMMENTS: \n\nReviewer #1 (Remarks to the Author): \n\nI am totally satisfied with the revisions made by the authors, in which all my comments have been \naddressed. Now the reaction mechanism of MDD proposed by the authors is updated appropriately \nand agrees well with recent knowledges of the enzyme. The comparison of the structures of MDD \nsolved in the study with the previously known structures of the enzyme and its orthologs, \nconsidering the effect of crystal packing, makes sense. I still hope the catalytic mechanism of this \ninteresting decarboxylase is elucidated by QM/MM study, but it is not necessary in this paper. The \nelucidation will be made in future probably by the authors or other groups. \n\nReviewer #2 (Remarks to the Author): \n\nIn the manuscript entitled \"Visualizing the Enzyme Mechanism of Mevalonate Diphosphate \nDecarboxylase\" by Chen et al. (Manuscript NCOMMS-19-27996A) the authors submitted a revised \nversion of their manuscript. \n\nThe revised version has substantially improved. \n(1) The structural comparison of different MDD structures available in the PDB improves the \nunderstanding of the differences of the structures for example different crystal packing effects and \nhence restricted conformational flexibility of the elements. See also the novel Supplementary \nFigure 7. Here, I just have a minor point: I personally find it useful if the PDB-ID for the displayed \nstructure (panel c to e) is provided and/or a reference to the primary citation. This suggestion \napplies as well to Supplementary figures. \n\nThe functional implications are now much better to follow. In particular, the discussion of the \nputative function of Asp282 is now better to understand. By the discussion of the other two recent \npublications, as suggested by the other reviewer, the authors were able to discard the contested \nhypothesis section on the mechanism. It is a very beautiful example how structural biology can \nprovide insightful structural information to elucidate an enzymatic mechanism. \n\nI recommend to accept the current version of the manuscript. \n\nMinor points: \n- Page 12, line 11: Names of organism should be in italic \n- Supplementary Figure 5: I suggest deleting the primer sequences. They are given in the \nMaterials and Methods section. \n\n\f",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Visualizing the enzyme mechanism of mevalonate diphosphate decarboxylase
|
Reviewers' comments:
Reviewer #1 (Remarks to the Author):
The manuscript “Visualizing the enzyme mechanism of mevalonate diphosphate decarboxylase” by
C.-L. Chen et al. reports the structural studies on mevalonate decarboxylase from a vancomycin
resistant enterococcus, Enterococcus faecalis (MDDEF). The authors succeeded in solving not only
the apo-structure but also the structures with the substrate mevalonate diphosphate (MVAPP),
MVAPP and an ATP analog AMPPCP, MVAPP and ADP, or MVAPP and ADP/BeF3-. As observed with
the structures of other MDDs, the MDDEF structures took open or closed conformations, which
allowed the authors to suppose the reaction mechanisms of the enzyme through substrate binding
and phosphoryl-transfer, which is the first half of the MDD reaction. It is quite impressive that the
authors could verify the binding positions of magnesium ions in the catalytic center of the enzyme.
To my knowledge, this is the first discovery for this enzyme family and also the information
needed to reveal detailed catalytic mechanism of MDDEF and to develop inhibitor molecules
specific to the enzyme. Because human also possesses MDD, only such specific inhibitors can be
utilized as antibiotics for VREs. The metal binding sites are confirmed with anomalous dispersion
observed in the analysis of the crystals soaked with MVAPP and ADP in the presence of cobalt ion,
instead of magnesium ion. This study is basically an extension of their previous studies on the
structures and biochemical properties of MDDEF, but it clearly made a substantial progress. The
manuscript is readable, and all the data look sound and persuasive. The reviewer, however, still
has several concerns with the manuscript. First, the authors proposed the substrate binding
mechanism based on the open-close change observed in the enzyme structures through the
bindings of different substrates or their analogs. The proposed mechanism fits well the structural
changes observed with MDDEF, but not with other MDD structures previously reported. For
example, the alfa10-beta4-loop was in the closed position in the MDDEF structure with
MVAPP/ADP/BeF3-/Mg2+, but in the open position with MVAPP/AMPPCP/Mg2+, thus the authors
concluded that the former structure represents the pre-phosphoryl transfer state, while the latter
does an earlier state. In contrast, the loop, and also the Lys residue corresponding to Lys187,
were reported to be at the same positions in MDD from an archaeon Sulfolobus solfataricus
(MDDSS) not only in similar substrate-binding structures but also in its apo form (pdb: 5gmd,
5gme, 4z7c). The discrepancy casts question if the induced-fit mechanism proposed in this paper
is general for MDDs or not. Additional discussion based on the comparison with the previously
reported MDD structures is needed. Secondly, the mechanism of the ATP-dependent
decarboxylation of MVAPP described in the manuscript, in which Asp282 acts as a base that
deprotonate 3’-OH of MVAPP, has been controverted by recent finding of a MDD-homolog kinase
that lacks the corresponding Asp residue but can catalyze 3’-phosphorylation of mevalonate
(Vinokur J.M. et al., 2015, Protein Sci.), and also by a mutagenic study on MDDSS, which led the
proposal of a hypothesis that Asp residue is required in the decarboxylation step (Motoyama K. et
al., 2017, J. Biol. Chem.). If the authors want to refute the new hypothesis, they should perform
QM/MM calculation study based on the structure of MDDEF binding MVAPP/ADP/BeF3-/Mg2+ or
MVAPP/AMPPCP/Mg2+, which will clarify the protonation states of the substrates and catalytic
residues and might support the less-persuasive discussion in page 15-16.
Minor concerns:
1) Page 2, line 7: large conformational “change”?
2) Page 3, the 1st paragraph: The MEP pathway is found primarily in bacteria, not in prokaryotes.
Archaea, another prokaryotes lineage, have the MVA pathway.
3) Page 3, line 8: privarily > primarily
4) Page 17, lines 19-: The method utilized for site-directed mutagenesis is obviously based on the
QuickChange method. Appropriate references such as Zheng L. et al. (2004) Nucleic Acid Res. are
needed.
5) Page 19, line 10: Instead of 100 nM MDDEF, a higher amount of the mutant enzyme was
considered to be used. Please show the amount.
6) Page 21, lines 19-20: ligands “were” manually placed
7) Supplementary Table 4: The table seems not showing the angles of alfa-helices, but their 3D
positions. I am afraid that the title and legend are confused with those in Supplementary Table 3.
Reviewer #2 (Remarks to the Author):
In the manuscript entitled "Visualizing the Enzyme Mechanism of Mevalonate Diphosphate
Decarboxylase" by Chen et al. (Manuscript NCOMMS-19-27996-T) the authors describe that two
Mg2+ ions are bound to the enzyme preloaded with substrate and ATP. By this sequential binding,
the active site is shaped for catalysis.
The authors used X-ray crystallography to visualize the Mg2+ ions plus structures with transition
state analogues. The resolution of the diffraction data is very high and the quality of the refined
structures is very good. Surprised by the localization of the two Mg2+ ions, the authors generated
structure-based variants of the MDD protein.
To the reviewer’s point of view the current version of the manuscript is very well written and
comprehensive. Nevertheless, I have the impression that most of the techniques described were
already very well established in the lab and for instance described in earlier publications (Chen et
al. (2017) JBC. For instance, the crystallization system has been described in the JBC publication.
Probably in many instances, the described methods could be drastically shortened. Most of the
designed variants have already been shown, to have functional implications. It is not proven, that
the proposed mechanism is valid in other organisms than S. faecalis as well. In particular, the
beta10-alpha4 loops show very little conservation. What is the function of R192? It seems to be
conserved in bacteria, where as in higher organisms it seems to be a strict threonine residue. Is
the catalytic side in both monomers identical?
Minor points:
- Throughout the manuscript, there is a mixture of one-letter and three-letter code for amino
acids.
- Page 5, line 13: Space is missing 1.6 M
- Page 7, line 7: “extra density”. Please be more precise “extra electron density”
- Page 7, line 19: probably “…next section” is meant
- Page 19, line 8: Space is missing after 30
- Page 19, line 18: please remove dot after Mus
- Figure 1, panel a: I do not think that the topology diagram is necessary. The overall structure of
MDDs is very well known
- Figure 6, panel a: please carefully check the numbering of the alignment. I see some
inconsistencies between the numbers of amino acids mentioned in the body of the text the
provided numbering in the figure. Names of organism should be in italic.
|
Reviewers' comments:
Reviewer #1 (Remarks to the Author):
The manuscript “Visualizing the enzyme mechanism of mevalonate diphosphate decarboxylase” by
C.-L. Chen et al. reports the structural studies on mevalonate decarboxylase from a vancomycin
resistant enterococcus, Enterococcus faecalis (MDDEF). The authors succeeded in solving not only
the apo-structure but also the structures with the substrate mevalonate diphosphate (MVAPP),
MVAPP and an ATP analog AMPPCP, MVAPP and ADP, or MVAPP and ADP/BeF3-. As observed with
the structures of other MDDs, the MDDEF structures took open or closed conformations, which
allowed the authors to suppose the reaction mechanisms of the enzyme through substrate binding
and phosphoryl-transfer, which is the first half of the MDD reaction. It is quite impressive that the
authors could verify the binding positions of magnesium ions in the catalytic center of the enzyme.
To my knowledge, this is the first discovery for this enzyme family and also the information
needed to reveal detailed catalytic mechanism of MDDEF and to develop inhibitor molecules
specific to the enzyme. Because human also possesses MDD, only such specific inhibitors can be
utilized as antibiotics for VREs. The metal binding sites are confirmed with anomalous dispersion
observed in the analysis of the crystals soaked with MVAPP and ADP in the presence of cobalt ion,
instead of magnesium ion. This study is basically an extension of their previous studies on the
structures and biochemical properties of MDDEF, but it clearly made a substantial progress. The
manuscript is readable, and all the data look sound and persuasive. The reviewer, however, still
has several concerns with the manuscript. First, the authors proposed the substrate binding
mechanism based on the open-close change observed in the enzyme structures through the
bindings of different substrates or their analogs. The proposed mechanism fits well the structural
changes observed with MDDEF, but not with other MDD structures previously reported. For
example, the alfa10-beta4-loop was in the closed position in the MDDEF structure with
MVAPP/ADP/BeF3-/Mg2+, but in the open position with MVAPP/AMPPCP/Mg2+, thus the authors
concluded that the former structure represents the pre-phosphoryl transfer state, while the latter
does an earlier state. In contrast, the loop, and also the Lys residue corresponding to Lys187,
were reported to be at the same positions in MDD from an archaeon Sulfolobus solfataricus
(MDDSS) not only in similar substrate-binding structures but also in its apo form (pdb: 5gmd,
5gme, 4z7c). The discrepancy casts question if the induced-fit mechanism proposed in this paper
is general for MDDs or not. Additional discussion based on the comparison with the previously
reported MDD structures is needed. Secondly, the mechanism of the ATP-dependent
decarboxylation of MVAPP described in the manuscript, in which Asp282 acts as a base that
deprotonate 3’-OH of MVAPP, has been controverted by recent finding of a MDD-homolog kinase
that lacks the corresponding Asp residue but can catalyze 3’-phosphorylation of mevalonate
(Vinokur J.M. et al., 2015, Protein Sci.), and also by a mutagenic study on MDDSS, which led the
proposal of a hypothesis that Asp residue is required in the decarboxylation step (Motoyama K. et
al., 2017, J. Biol. Chem.). If the authors want to refute the new hypothesis, they should perform
QM/MM calculation study based on the structure of MDDEF binding MVAPP/ADP/BeF3-/Mg2+ or
MVAPP/AMPPCP/Mg2+, which will clarify the protonation states of the substrates and catalytic
residues and might support the less-persuasive discussion in page 15-16.
Minor concerns:
1) Page 2, line 7: large conformational “change”?
2) Page 3, the 1st paragraph: The MEP pathway is found primarily in bacteria, not in prokaryotes.
Archaea, another prokaryotes lineage, have the MVA pathway.
3) Page 3, line 8: privarily > primarily
4) Page 17, lines 19-: The method utilized for site-directed mutagenesis is obviously based on the
QuickChange method. Appropriate references such as Zheng L. et al. (2004) Nucleic Acid Res. are
needed.
5) Page 19, line 10: Instead of 100 nM MDDEF, a higher amount of the mutant enzyme was
considered to be used. Please show the amount.
6) Page 21, lines 19-20: ligands “were” manually placed
7) Supplementary Table 4: The table seems not showing the angles of alfa-helices, but their 3D
positions. I am afraid that the title and legend are confused with those in Supplementary Table 3.
Reviewer #2 (Remarks to the Author):
In the manuscript entitled "Visualizing the Enzyme Mechanism of Mevalonate Diphosphate
Decarboxylase" by Chen et al. (Manuscript NCOMMS-19-27996-T) the authors describe that two
Mg2+ ions are bound to the enzyme preloaded with substrate and ATP. By this sequential binding,
the active site is shaped for catalysis.
The authors used X-ray crystallography to visualize the Mg2+ ions plus structures with transition
state analogues. The resolution of the diffraction data is very high and the quality of the refined
structures is very good. Surprised by the localization of the two Mg2+ ions, the authors generated
structure-based variants of the MDD protein.
To the reviewer’s point of view the current version of the manuscript is very well written and
comprehensive. Nevertheless, I have the impression that most of the techniques described were
already very well established in the lab and for instance described in earlier publications (Chen et
al. (2017) JBC. For instance, the crystallization system has been described in the JBC publication.
Probably in many instances, the described methods could be drastically shortened. Most of the
designed variants have already been shown, to have functional implications. It is not proven, that
the proposed mechanism is valid in other organisms than S. faecalis as well. In particular, the
beta10-alpha4 loops show very little conservation. What is the function of R192? It seems to be
conserved in bacteria, where as in higher organisms it seems to be a strict threonine residue. Is
the catalytic side in both monomers identical?
Minor points:
- Throughout the manuscript, there is a mixture of one-letter and three-letter code for amino
acids.
- Page 5, line 13: Space is missing 1.6 M
- Page 7, line 7: “extra density”. Please be more precise “extra electron density”
- Page 7, line 19: probably “…next section” is meant
- Page 19, line 8: Space is missing after 30
- Page 19, line 18: please remove dot after Mus
- Figure 1, panel a: I do not think that the topology diagram is necessary. The overall structure of
MDDs is very well known
- Figure 6, panel a: please carefully check the numbering of the alignment. I see some
inconsistencies between the numbers of amino acids mentioned in the body of the text the
provided numbering in the figure. Names of organism should be in italic.
|
TPR
|
NC_BS_BIOCH_003_RR1.txt
|
{
"criticism": 6,
"example": 11,
"importance_and_relevance": 2,
"materials_and_methods": 27,
"praise": 6,
"presentation_and_reporting": 13,
"results_and_discussion": 3,
"suggestion_and_solution": 11,
"total": 56
}
|
{
"criticism": 0.10714285714285714,
"example": 0.19642857142857142,
"importance_and_relevance": 0.03571428571428571,
"materials_and_methods": 0.48214285714285715,
"praise": 0.10714285714285714,
"presentation_and_reporting": 0.23214285714285715,
"results_and_discussion": 0.05357142857142857,
"suggestion_and_solution": 0.19642857142857142
}
| 1.410714
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "Reviewers' comments: \n\nReviewer #1 (Remarks to the Author): \n\nThe manuscript “Visualizing the enzyme mechanism of mevalonate diphosphate decarboxylase” by \nC.-L. Chen et al. reports the structural studies on mevalonate decarboxylase from a vancomycin \nresistant enterococcus, Enterococcus faecalis (MDDEF). The authors succeeded in solving not only \nthe apo-structure but also the structures with the substrate mevalonate diphosphate (MVAPP), \nMVAPP and an ATP analog AMPPCP, MVAPP and ADP, or MVAPP and ADP/BeF3-. As observed with \nthe structures of other MDDs, the MDDEF structures took open or closed conformations, which \nallowed the authors to suppose the reaction mechanisms of the enzyme through substrate binding \nand phosphoryl-transfer, which is the first half of the MDD reaction. It is quite impressive that the \nauthors could verify the binding positions of magnesium ions in the catalytic center of the enzyme. \nTo my knowledge, this is the first discovery for this enzyme family and also the information \nneeded to reveal detailed catalytic mechanism of MDDEF and to develop inhibitor molecules \nspecific to the enzyme. Because human also possesses MDD, only such specific inhibitors can be \nutilized as antibiotics for VREs. The metal binding sites are confirmed with anomalous dispersion \nobserved in the analysis of the crystals soaked with MVAPP and ADP in the presence of cobalt ion, \ninstead of magnesium ion. This study is basically an extension of their previous studies on the \nstructures and biochemical properties of MDDEF, but it clearly made a substantial progress. The \nmanuscript is readable, and all the data look sound and persuasive. The reviewer, however, still \nhas several concerns with the manuscript. First, the authors proposed the substrate binding \nmechanism based on the open-close change observed in the enzyme structures through the \nbindings of different substrates or their analogs. The proposed mechanism fits well the structural \nchanges observed with MDDEF, but not with other MDD structures previously reported. For \nexample, the alfa10-beta4-loop was in the closed position in the MDDEF structure with \nMVAPP/ADP/BeF3-/Mg2+, but in the open position with MVAPP/AMPPCP/Mg2+, thus the authors \nconcluded that the former structure represents the pre-phosphoryl transfer state, while the latter \ndoes an earlier state. In contrast, the loop, and also the Lys residue corresponding to Lys187, \nwere reported to be at the same positions in MDD from an archaeon Sulfolobus solfataricus \n(MDDSS) not only in similar substrate-binding structures but also in its apo form (pdb: 5gmd, \n5gme, 4z7c). The discrepancy casts question if the induced-fit mechanism proposed in this paper \nis general for MDDs or not. Additional discussion based on the comparison with the previously \nreported MDD structures is needed. Secondly, the mechanism of the ATP-dependent \ndecarboxylation of MVAPP described in the manuscript, in which Asp282 acts as a base that \ndeprotonate 3’-OH of MVAPP, has been controverted by recent finding of a MDD-homolog kinase \nthat lacks the corresponding Asp residue but can catalyze 3’-phosphorylation of mevalonate \n(Vinokur J.M. et al., 2015, Protein Sci.), and also by a mutagenic study on MDDSS, which led the \nproposal of a hypothesis that Asp residue is required in the decarboxylation step (Motoyama K. et \nal., 2017, J. Biol. Chem.). If the authors want to refute the new hypothesis, they should perform \nQM/MM calculation study based on the structure of MDDEF binding MVAPP/ADP/BeF3-/Mg2+ or \nMVAPP/AMPPCP/Mg2+, which will clarify the protonation states of the substrates and catalytic \nresidues and might support the less-persuasive discussion in page 15-16. \n\nMinor concerns: \n1) Page 2, line 7: large conformational “change”? \n2) Page 3, the 1st paragraph: The MEP pathway is found primarily in bacteria, not in prokaryotes. \nArchaea, another prokaryotes lineage, have the MVA pathway. \n3) Page 3, line 8: privarily > primarily \n4) Page 17, lines 19-: The method utilized for site-directed mutagenesis is obviously based on the \nQuickChange method. Appropriate references such as Zheng L. et al. (2004) Nucleic Acid Res. are \nneeded. \n5) Page 19, line 10: Instead of 100 nM MDDEF, a higher amount of the mutant enzyme was \nconsidered to be used. Please show the amount. \n6) Page 21, lines 19-20: ligands “were” manually placed \n\n\f7) Supplementary Table 4: The table seems not showing the angles of alfa-helices, but their 3D \npositions. I am afraid that the title and legend are confused with those in Supplementary Table 3. \n\nReviewer #2 (Remarks to the Author): \n\nIn the manuscript entitled \"Visualizing the Enzyme Mechanism of Mevalonate Diphosphate \nDecarboxylase\" by Chen et al. (Manuscript NCOMMS-19-27996-T) the authors describe that two \nMg2+ ions are bound to the enzyme preloaded with substrate and ATP. By this sequential binding, \nthe active site is shaped for catalysis. \nThe authors used X-ray crystallography to visualize the Mg2+ ions plus structures with transition \nstate analogues. The resolution of the diffraction data is very high and the quality of the refined \nstructures is very good. Surprised by the localization of the two Mg2+ ions, the authors generated \nstructure-based variants of the MDD protein. \nTo the reviewer’s point of view the current version of the manuscript is very well written and \ncomprehensive. Nevertheless, I have the impression that most of the techniques described were \nalready very well established in the lab and for instance described in earlier publications (Chen et \nal. (2017) JBC. For instance, the crystallization system has been described in the JBC publication. \nProbably in many instances, the described methods could be drastically shortened. Most of the \ndesigned variants have already been shown, to have functional implications. It is not proven, that \nthe proposed mechanism is valid in other organisms than S. faecalis as well. In particular, the \nbeta10-alpha4 loops show very little conservation. What is the function of R192? It seems to be \nconserved in bacteria, where as in higher organisms it seems to be a strict threonine residue. Is \nthe catalytic side in both monomers identical? \n\nMinor points: \n- Throughout the manuscript, there is a mixture of one-letter and three-letter code for amino \nacids. \n- Page 5, line 13: Space is missing 1.6 M \n- Page 7, line 7: “extra density”. Please be more precise “extra electron density” \n- Page 7, line 19: probably “…next section” is meant \n- Page 19, line 8: Space is missing after 30 \n- Page 19, line 18: please remove dot after Mus \n- Figure 1, panel a: I do not think that the topology diagram is necessary. The overall structure of \nMDDs is very well known \n- Figure 6, panel a: please carefully check the numbering of the alignment. I see some \ninconsistencies between the numbers of amino acids mentioned in the body of the text the \nprovided numbering in the figure. Names of organism should be in italic. \n\n\f\t\n\n\f\n",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Distinct Cdk9-phosphatase switches act at the beginning and end of elongation by RNA
|
Reviewer #1 (Remarks to the Author):
The work by Parua et all demonstrates a conserved role of distinct phosphatases that work on SPT5 at
distinct steps of the transcription cycle. By combining in vitro phosphatase assays with in vivo
distribution of transcriptional components following perturbation (by mutation or drug), this work
makes a compelling case for further dissection of transcription elongation. As much as genomics is
powerful, it is Figure 1 that is the highlight of the manuscript. Overall, it is a well thought out and well
controlled piece that merits publication once minor questions are addressed.
Minor points.
55-74. The introduction is hard to follow in places in the last two paragraphs, but especially the one
containing lines 55-74. I read it several times and could not quite grasp it. Is there a way to shorten
it?
84. Introduce the abbreviation in the Abstract for consistency?
128. Higher sensitivity of Spt5 “CTD” phosphorylation compared to RPB1’s is intriguing. Flavopiridol
has been shown in several systems to lead to a decrease in Ser2 phosphorylation. This is also stated
in lines 194-195. Is this discrepancy due to technicalities (such as timing of treatment and the use of
a more specific CDK9 inhibitor) or something else such as functional heterogeneity of Pol II Ser2p
populations, differential requirements for CDK9 for Ser2 phosphorylation in different cells, etc?
166-167. The sentence “Reactivity with Spt5…” may be correct technically, but it is not clear what to
make of it in Supplementary Fig 2B. It seems to me that the effect of 806 substitution is not only
modest (and may be should be quantified), but the IP datapoints do not appear to add useful
information.
Supplementary 2d and 2e. These appear to be shown in linear scale. Would it be better to show these
in log scale? Secondly, I could not find information (which I may have missed) what signal was
quantified for these plots: signal around genes or gene-agnostic data centric peaks?
182. Principal component analysis is highly sensitive to normalization. Normalization is impossible to
obtain for ChIP comparing different antibodies. PCA has limited use for samples (such as RNA-seq)
that are highly similar and where normalization is straightforward, but it has no use for ChIP-seq. This
panel should be removed. Perhaps clustering analysis that is less sensitive to normalization could be
used? Overall, this panel does not add much to the manuscript anyway so deleting this will not harm
it.
212-214. Heatmaps of different versions of Spt5 are disjointed between figures 3 and 4. I understand
that this is done to preserve the flow of the manuscript, but it possible to add a metagene plot
overlapping the profiles of wild type and two mutants? It may be worthwhile to make the overlap plot
a new 4A and move the orphan heatmap to supplementary, for example.
Lines 221-230. Authors mention transcription induction of CDKN1A. Is transcriptional induction shown
somewhere by RT-qPCR? I apologize in advance if I’d missed it.
Lines 233-240. Along the same lines, what is happening to expression and ChIP-seq signal on genes
that are not induced by P53 stabilization?
Figure 5B. Metagene plots in 5B are not convincing along the vertical axis. Spike-in based
normalization for ChIP-seq is impossible to very difficult with a notable exception of recombinant
nucleosomes. A better figure would be to show the same metaplots, but for genes that are not
upregulated by Nutlin. These must show less to no increase of light blue signal relatively to genes
shown in 5b. This control is also essential.
Figure 7a-c. The gene identity (MYC) is better to be labeled in the figure itself rather than only in a
legend to 7B. It takes a moment to decipher that 7C probably shows MYC based on matching primer
numbers.
326. Should it be ‘marks’ (plural)?
380-390. Because these are important statements, these should almost be placed to the beginning of
discussion?
392. Delete ‘Therefore’.
512. Was Fisher formaldehyde regular or methanol-free that is sold in ampules?
516. Specify the power number for Bioruptor? The high setting for ChIP is considered to be 140 if I
recall correctly, but the instrument can go higher.
Data handling. Which samples contained spike-ins?
Data handling. How Sacharomyces spike-ins are helpful when added to immunoprecipitation
reactions? The antibodies used will not recognize yeast proteins and will result in unknown and highly
variable signal recovery for yeast read among samples that is likely driven by noise.
Reviewer #2 (Remarks to the Author):
Papua et al. address an interesting and important question in gene expression regulation by
investigating how SPT5 phosphorylation varies across gene bodies. The authors previously showed in
fission yeast that P-TEFb dependent SPT5 phosphorylations were lost at transcription termination sites
through competition between the P-TEFb kinase and PP1 phosphatase. Here they have extended these
studies to look at the role of various phosphatases during transcription elongation in human cells. The
authors probe two different SPT5 phosphorylation sites, Ser666 and Thr806. They find that these
phosphorylations are added and lost at different points during transcription. PP1 phosphatases are
responsible for removing the phosphorylation on CTR-I at termination sites and PP4 phosphatase
removes Ser666 phosphorylation at promoter-proximal sites. This paper is highly important because it
shows that in addition to RNA polymerase II, specific sites on SPT5 are phosphorylated in response to
its spatial location on a gene body. The study poses an enticing question as to whether other
transcription elongation factors are regulated in a similar way. If true, this would provide an additional
mechanism to carefully regulate spatial recruitment of additional factors to the elongation machinery.
Overall, the manuscript is well written, and the data are clear. If some specific issues are addressed
(see below), the reviewer fully supports publication of this important work in Nature Communications.
Specific comments
-Line 49: P-TEFb phosphorylates components of elongation and pausing complexes. The reviewer does
not know of additional pausing factors that P-TEFb phosphorylates (NELF and DSIF are already
mentioned). The authors should change “the paused complex” to “elongation factors”.
-Line 128: The authors should cite the work of Matthias Geyer (2012 Czudnochowski et al., Nature
Communications) where it was shown that P-TEFb is not a Ser2 kinase in vitro, specifically because
the authors use P-TEFb in vitro in this work.
-Supplementary Fig 1e: Not obvious that chromatin bound Thr806 phosphorylation level is changing in
the PP1 depleted sample. It is also not clear that this blot is necessary given the other data in the
manuscript.
-Supplementary Fig 2a- Loading controls suggest that there is more GST-CTR1 input than the other
peptides (significantly more). The authors comment in the legend that this is due to incomplete
stripping of the membrane. This is a really important control, so it is advised the experiment is
repeated and the sample is evenly split onto two gels/membranes to show the same amount of
sample was indeed used, specifically because some faint bands appear on the phosphoblot for the
other CTR constructs. The blots with the full-length protein look good.
-Figure 2B: Are the ChIP plots scaled the same way? Add Y value to plots or state in figure legend that
the scaling is the same.
-Figure 2C, 3C: Plot the curves with the same Y axis boundaries to show the extent of differences.
-Figure 3A, 4D, 7A S3A, S4 C, D: Mark termination sites or CPS sites on gene overview. There are
probably multiple sites, but it helps to know where transcription may stop on a particular gene.
-Figure 5C: Is it possible to comment on why Nutlin has a greater effect on non-paused genes? The
model posited by the authors suggests that Ser666 phosphorylation follows pause release, and it
would be naively thought that the effect of Nutlin would be greater on such genes.
-Figure 7e: The authors see increased Pol II in the gene body when PP4R2 is depleted. This can come
from enhanced transcription but can also arise from slow Pol II. If at all possible, the authors should
investigate Pol II elongation rates in PP4R2 depleted cells using Gro-seq or TT-seq. This would confirm
that enhanced Spt5 Ser666 phosphorylation leads to pause release and faster elongation rates.
Minor comment
-Supplementary Figure 3: Flip panel order so they match Figure 3.
|
Reviewer #1 (Remarks to the Author):
The work by Parua et all demonstrates a conserved role of distinct phosphatases that work on SPT5 at
distinct steps of the transcription cycle. By combining in vitro phosphatase assays with in vivo
distribution of transcriptional components following perturbation (by mutation or drug), this work
makes a compelling case for further dissection of transcription elongation. As much as genomics is
powerful, it is Figure 1 that is the highlight of the manuscript. Overall, it is a well thought out and well
controlled piece that merits publication once minor questions are addressed.
Minor points.
55-74. The introduction is hard to follow in places in the last two paragraphs, but especially the one
containing lines 55-74. I read it several times and could not quite grasp it. Is there a way to shorten
it?
84. Introduce the abbreviation in the Abstract for consistency?
128. Higher sensitivity of Spt5 “CTD” phosphorylation compared to RPB1’s is intriguing. Flavopiridol
has been shown in several systems to lead to a decrease in Ser2 phosphorylation. This is also stated
in lines 194-195. Is this discrepancy due to technicalities (such as timing of treatment and the use of
a more specific CDK9 inhibitor) or something else such as functional heterogeneity of Pol II Ser2p
populations, differential requirements for CDK9 for Ser2 phosphorylation in different cells, etc?
166-167. The sentence “Reactivity with Spt5…” may be correct technically, but it is not clear what to
make of it in Supplementary Fig 2B. It seems to me that the effect of 806 substitution is not only
modest (and may be should be quantified), but the IP datapoints do not appear to add useful
information.
Supplementary 2d and 2e. These appear to be shown in linear scale. Would it be better to show these
in log scale? Secondly, I could not find information (which I may have missed) what signal was
quantified for these plots: signal around genes or gene-agnostic data centric peaks?
182. Principal component analysis is highly sensitive to normalization. Normalization is impossible to
obtain for ChIP comparing different antibodies. PCA has limited use for samples (such as RNA-seq)
that are highly similar and where normalization is straightforward, but it has no use for ChIP-seq. This
panel should be removed. Perhaps clustering analysis that is less sensitive to normalization could be
used? Overall, this panel does not add much to the manuscript anyway so deleting this will not harm
it.
212-214. Heatmaps of different versions of Spt5 are disjointed between figures 3 and 4. I understand
that this is done to preserve the flow of the manuscript, but it possible to add a metagene plot
overlapping the profiles of wild type and two mutants? It may be worthwhile to make the overlap plot
a new 4A and move the orphan heatmap to supplementary, for example.
Lines 221-230. Authors mention transcription induction of CDKN1A. Is transcriptional induction shown
somewhere by RT-qPCR? I apologize in advance if I’d missed it.
Lines 233-240. Along the same lines, what is happening to expression and ChIP-seq signal on genes
that are not induced by P53 stabilization?
Figure 5B. Metagene plots in 5B are not convincing along the vertical axis. Spike-in based
normalization for ChIP-seq is impossible to very difficult with a notable exception of recombinant
nucleosomes. A better figure would be to show the same metaplots, but for genes that are not
upregulated by Nutlin. These must show less to no increase of light blue signal relatively to genes
shown in 5b. This control is also essential.
Figure 7a-c. The gene identity (MYC) is better to be labeled in the figure itself rather than only in a
legend to 7B. It takes a moment to decipher that 7C probably shows MYC based on matching primer
numbers.
326. Should it be ‘marks’ (plural)?
380-390. Because these are important statements, these should almost be placed to the beginning of
discussion?
392. Delete ‘Therefore’.
512. Was Fisher formaldehyde regular or methanol-free that is sold in ampules?
516. Specify the power number for Bioruptor? The high setting for ChIP is considered to be 140 if I
recall correctly, but the instrument can go higher.
Data handling. Which samples contained spike-ins?
Data handling. How Sacharomyces spike-ins are helpful when added to immunoprecipitation
reactions? The antibodies used will not recognize yeast proteins and will result in unknown and highly
variable signal recovery for yeast read among samples that is likely driven by noise.
Reviewer #2 (Remarks to the Author):
Papua et al. address an interesting and important question in gene expression regulation by
investigating how SPT5 phosphorylation varies across gene bodies. The authors previously showed in
fission yeast that P-TEFb dependent SPT5 phosphorylations were lost at transcription termination sites
through competition between the P-TEFb kinase and PP1 phosphatase. Here they have extended these
studies to look at the role of various phosphatases during transcription elongation in human cells. The
authors probe two different SPT5 phosphorylation sites, Ser666 and Thr806. They find that these
phosphorylations are added and lost at different points during transcription. PP1 phosphatases are
responsible for removing the phosphorylation on CTR-I at termination sites and PP4 phosphatase
removes Ser666 phosphorylation at promoter-proximal sites. This paper is highly important because it
shows that in addition to RNA polymerase II, specific sites on SPT5 are phosphorylated in response to
its spatial location on a gene body. The study poses an enticing question as to whether other
transcription elongation factors are regulated in a similar way. If true, this would provide an additional
mechanism to carefully regulate spatial recruitment of additional factors to the elongation machinery.
Overall, the manuscript is well written, and the data are clear. If some specific issues are addressed
(see below), the reviewer fully supports publication of this important work in Nature Communications.
Specific comments
-Line 49: P-TEFb phosphorylates components of elongation and pausing complexes. The reviewer does
not know of additional pausing factors that P-TEFb phosphorylates (NELF and DSIF are already
mentioned). The authors should change “the paused complex” to “elongation factors”.
-Line 128: The authors should cite the work of Matthias Geyer (2012 Czudnochowski et al., Nature
Communications) where it was shown that P-TEFb is not a Ser2 kinase in vitro, specifically because
the authors use P-TEFb in vitro in this work.
-Supplementary Fig 1e: Not obvious that chromatin bound Thr806 phosphorylation level is changing in
the PP1 depleted sample. It is also not clear that this blot is necessary given the other data in the
manuscript.
-Supplementary Fig 2a- Loading controls suggest that there is more GST-CTR1 input than the other
peptides (significantly more). The authors comment in the legend that this is due to incomplete
stripping of the membrane. This is a really important control, so it is advised the experiment is
repeated and the sample is evenly split onto two gels/membranes to show the same amount of
sample was indeed used, specifically because some faint bands appear on the phosphoblot for the
other CTR constructs. The blots with the full-length protein look good.
-Figure 2B: Are the ChIP plots scaled the same way? Add Y value to plots or state in figure legend that
the scaling is the same.
-Figure 2C, 3C: Plot the curves with the same Y axis boundaries to show the extent of differences.
-Figure 3A, 4D, 7A S3A, S4 C, D: Mark termination sites or CPS sites on gene overview. There are
probably multiple sites, but it helps to know where transcription may stop on a particular gene.
-Figure 5C: Is it possible to comment on why Nutlin has a greater effect on non-paused genes? The
model posited by the authors suggests that Ser666 phosphorylation follows pause release, and it
would be naively thought that the effect of Nutlin would be greater on such genes.
-Figure 7e: The authors see increased Pol II in the gene body when PP4R2 is depleted. This can come
from enhanced transcription but can also arise from slow Pol II. If at all possible, the authors should
investigate Pol II elongation rates in PP4R2 depleted cells using Gro-seq or TT-seq. This would confirm
that enhanced Spt5 Ser666 phosphorylation leads to pause release and faster elongation rates.
Minor comment
-Supplementary Figure 3: Flip panel order so they match Figure 3.
|
TPR
|
NC_BS_BIOCH_004_RR1.txt
|
{
"criticism": 12,
"example": 20,
"importance_and_relevance": 3,
"materials_and_methods": 39,
"praise": 4,
"presentation_and_reporting": 24,
"results_and_discussion": 3,
"suggestion_and_solution": 23,
"total": 99
}
|
{
"criticism": 0.12121212121212122,
"example": 0.20202020202020202,
"importance_and_relevance": 0.030303030303030304,
"materials_and_methods": 0.3939393939393939,
"praise": 0.04040404040404041,
"presentation_and_reporting": 0.24242424242424243,
"results_and_discussion": 0.030303030303030304,
"suggestion_and_solution": 0.23232323232323232
}
| 1.292929
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "Reviewer #1 (Remarks to the Author): \n\nThe work by Parua et all demonstrates a conserved role of distinct phosphatases that work on SPT5 at \ndistinct steps of the transcription cycle. By combining in vitro phosphatase assays with in vivo \ndistribution of transcriptional components following perturbation (by mutation or drug), this work \nmakes a compelling case for further dissection of transcription elongation. As much as genomics is \npowerful, it is Figure 1 that is the highlight of the manuscript. Overall, it is a well thought out and well \ncontrolled piece that merits publication once minor questions are addressed. \n\nMinor points. \n55-74. The introduction is hard to follow in places in the last two paragraphs, but especially the one \ncontaining lines 55-74. I read it several times and could not quite grasp it. Is there a way to shorten \nit? \n\n84. Introduce the abbreviation in the Abstract for consistency? \n\n128. Higher sensitivity of Spt5 “CTD” phosphorylation compared to RPB1’s is intriguing. Flavopiridol \nhas been shown in several systems to lead to a decrease in Ser2 phosphorylation. This is also stated \nin lines 194-195. Is this discrepancy due to technicalities (such as timing of treatment and the use of \na more specific CDK9 inhibitor) or something else such as functional heterogeneity of Pol II Ser2p \npopulations, differential requirements for CDK9 for Ser2 phosphorylation in different cells, etc? \n\n166-167. The sentence “Reactivity with Spt5…” may be correct technically, but it is not clear what to \nmake of it in Supplementary Fig 2B. It seems to me that the effect of 806 substitution is not only \nmodest (and may be should be quantified), but the IP datapoints do not appear to add useful \ninformation. \n\nSupplementary 2d and 2e. These appear to be shown in linear scale. Would it be better to show these \nin log scale? Secondly, I could not find information (which I may have missed) what signal was \nquantified for these plots: signal around genes or gene-agnostic data centric peaks? \n\n182. Principal component analysis is highly sensitive to normalization. Normalization is impossible to \nobtain for ChIP comparing different antibodies. PCA has limited use for samples (such as RNA-seq) \nthat are highly similar and where normalization is straightforward, but it has no use for ChIP-seq. This \npanel should be removed. Perhaps clustering analysis that is less sensitive to normalization could be \nused? Overall, this panel does not add much to the manuscript anyway so deleting this will not harm \nit. \n\n212-214. Heatmaps of different versions of Spt5 are disjointed between figures 3 and 4. I understand \nthat this is done to preserve the flow of the manuscript, but it possible to add a metagene plot \noverlapping the profiles of wild type and two mutants? It may be worthwhile to make the overlap plot \na new 4A and move the orphan heatmap to supplementary, for example. \n\nLines 221-230. Authors mention transcription induction of CDKN1A. Is transcriptional induction shown \nsomewhere by RT-qPCR? I apologize in advance if I’d missed it. \n\nLines 233-240. Along the same lines, what is happening to expression and ChIP-seq signal on genes \nthat are not induced by P53 stabilization? \n\nFigure 5B. Metagene plots in 5B are not convincing along the vertical axis. Spike-in based \nnormalization for ChIP-seq is impossible to very difficult with a notable exception of recombinant \nnucleosomes. A better figure would be to show the same metaplots, but for genes that are not \nupregulated by Nutlin. These must show less to no increase of light blue signal relatively to genes \nshown in 5b. This control is also essential. \n\n\fFigure 7a-c. The gene identity (MYC) is better to be labeled in the figure itself rather than only in a \nlegend to 7B. It takes a moment to decipher that 7C probably shows MYC based on matching primer \nnumbers. \n\n326. Should it be ‘marks’ (plural)? \n\n380-390. Because these are important statements, these should almost be placed to the beginning of \ndiscussion? \n\n392. Delete ‘Therefore’. \n\n512. Was Fisher formaldehyde regular or methanol-free that is sold in ampules? \n\n516. Specify the power number for Bioruptor? The high setting for ChIP is considered to be 140 if I \nrecall correctly, but the instrument can go higher. \n\nData handling. Which samples contained spike-ins? \n\nData handling. How Sacharomyces spike-ins are helpful when added to immunoprecipitation \nreactions? The antibodies used will not recognize yeast proteins and will result in unknown and highly \nvariable signal recovery for yeast read among samples that is likely driven by noise. \n\nReviewer #2 (Remarks to the Author): \n\nPapua et al. address an interesting and important question in gene expression regulation by \ninvestigating how SPT5 phosphorylation varies across gene bodies. The authors previously showed in \nfission yeast that P-TEFb dependent SPT5 phosphorylations were lost at transcription termination sites \nthrough competition between the P-TEFb kinase and PP1 phosphatase. Here they have extended these \nstudies to look at the role of various phosphatases during transcription elongation in human cells. The \nauthors probe two different SPT5 phosphorylation sites, Ser666 and Thr806. They find that these \nphosphorylations are added and lost at different points during transcription. PP1 phosphatases are \nresponsible for removing the phosphorylation on CTR-I at termination sites and PP4 phosphatase \nremoves Ser666 phosphorylation at promoter-proximal sites. This paper is highly important because it \nshows that in addition to RNA polymerase II, specific sites on SPT5 are phosphorylated in response to \nits spatial location on a gene body. The study poses an enticing question as to whether other \ntranscription elongation factors are regulated in a similar way. If true, this would provide an additional \nmechanism to carefully regulate spatial recruitment of additional factors to the elongation machinery. \nOverall, the manuscript is well written, and the data are clear. If some specific issues are addressed \n(see below), the reviewer fully supports publication of this important work in Nature Communications. \n\nSpecific comments \n-Line 49: P-TEFb phosphorylates components of elongation and pausing complexes. The reviewer does \nnot know of additional pausing factors that P-TEFb phosphorylates (NELF and DSIF are already \nmentioned). The authors should change “the paused complex” to “elongation factors”. \n\n-Line 128: The authors should cite the work of Matthias Geyer (2012 Czudnochowski et al., Nature \nCommunications) where it was shown that P-TEFb is not a Ser2 kinase in vitro, specifically because \nthe authors use P-TEFb in vitro in this work. \n\n\f-Supplementary Fig 1e: Not obvious that chromatin bound Thr806 phosphorylation level is changing in \nthe PP1 depleted sample. It is also not clear that this blot is necessary given the other data in the \nmanuscript. \n\n-Supplementary Fig 2a- Loading controls suggest that there is more GST-CTR1 input than the other \npeptides (significantly more). The authors comment in the legend that this is due to incomplete \nstripping of the membrane. This is a really important control, so it is advised the experiment is \nrepeated and the sample is evenly split onto two gels/membranes to show the same amount of \nsample was indeed used, specifically because some faint bands appear on the phosphoblot for the \nother CTR constructs. The blots with the full-length protein look good. \n\n-Figure 2B: Are the ChIP plots scaled the same way? Add Y value to plots or state in figure legend that \nthe scaling is the same. \n\n-Figure 2C, 3C: Plot the curves with the same Y axis boundaries to show the extent of differences. \n\n-Figure 3A, 4D, 7A S3A, S4 C, D: Mark termination sites or CPS sites on gene overview. There are \nprobably multiple sites, but it helps to know where transcription may stop on a particular gene. \n\n-Figure 5C: Is it possible to comment on why Nutlin has a greater effect on non-paused genes? The \nmodel posited by the authors suggests that Ser666 phosphorylation follows pause release, and it \nwould be naively thought that the effect of Nutlin would be greater on such genes. \n\n-Figure 7e: The authors see increased Pol II in the gene body when PP4R2 is depleted. This can come \nfrom enhanced transcription but can also arise from slow Pol II. If at all possible, the authors should \ninvestigate Pol II elongation rates in PP4R2 depleted cells using Gro-seq or TT-seq. This would confirm \nthat enhanced Spt5 Ser666 phosphorylation leads to pause release and faster elongation rates. \n\nMinor comment \n-Supplementary Figure 3: Flip panel order so they match Figure 3. \n\n\f",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Ion mobility collision cross-section atlas for known and unknown metabolite annotation in
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
The authors have done a very thorough job of responding to my comments. I particularly welcome
the additional results, especially those that show the improved performance with real MS/MS data
(which is, I think, a more common use-case).
I would be happy to see the manuscript published now.
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
The authors have done a very thorough job of responding to my comments. I particularly welcome
the additional results, especially those that show the improved performance with real MS/MS data
(which is, I think, a more common use-case).
I would be happy to see the manuscript published now.
|
TPR
|
NC_BS_BIOCH_005_RR2.txt
|
{
"criticism": 0,
"example": 0,
"importance_and_relevance": 0,
"materials_and_methods": 1,
"praise": 3,
"presentation_and_reporting": 0,
"results_and_discussion": 1,
"suggestion_and_solution": 0,
"total": 3
}
|
{
"criticism": 0,
"example": 0,
"importance_and_relevance": 0,
"materials_and_methods": 0.3333333333333333,
"praise": 1,
"presentation_and_reporting": 0,
"results_and_discussion": 0.3333333333333333,
"suggestion_and_solution": 0
}
| 1.666667
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "\n \n\n\fREVIEWERS' COMMENTS: \n\n \n\nReviewer #1 (Remarks to the Author): \n\n \n\nThe authors have done a very thorough job of responding to my comments. I particularly welcome \nthe additional results, especially those that show the improved performance with real MS/MS data \n(which is, I think, a more common use-case). \n\nI would be happy to see the manuscript published now. \n\n \n\n\f\n",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Ion mobility collision cross-section atlas for known and unknown metabolite annotation in
|
REVIEWER COMMENTS
Reviewer #1 (Remarks to the Author):
This paper described the creation and validation of an atlas of CCS values. The atlas is created using a
combination of experimental CCS (merged from multiple databases) and in-silico predicted CCS. The
authors show that they are able to predict CCS better than current systems, and that combining
predicted CCS with other data (m/z, predicted MS/MS) improved candidate ranking. The atlas looks
to be a resource that has practical utility and the authors do a good job showing that it performs
well.
1. Overall I enjoyed reading this paper. I think it does a good job in setting out the system, evaluating
it, and describing the benefits it brings. There are quite a few places in the text though in which
more thorough proof-reading is required (too numerous to list here).
2. The improvement in CCS prediction is good, and the ML methodology looks sound. I would
welcome a little more discussion on where the authors think this improvement comes from. Is it
simply the larger unified database?
3. The SVM regression for CCS prediction: the gamma parameters (note: radial basis, not radio basis)
seem extraordinarily high (2^8 and 2^13). Depending on the way the RBF function is parameterised,
this effectively becomes either a linear regression, or something akin to a nearest neighbours
scheme. Not necessarily a problem, but something that if I saw it in an analysis, would ring some
alarm bells for me. Have the authors looked into this?
4. When combining with MS/MS, the authors use only in-silico MS/MS on their side. Why is this? in-
silico MS/MS prediction is still not great. For the "unknown" experiments, predicted MS/MS is
obviously the only route. However, could the authors not have done some experiments with real
MS/MS library spectra? Playing devils advocate: perhaps the improvement CCS gives about in-silico
MS/MS is because in-silico MS/MS is not reliable. Would we see the same improvements with real
MS/MS libraries? There are plenty in the public domain (Massbank, GNPS, HMDB, etc).
5. Reproducibility: the authors do a good job of providing the supplementary material to allow
another to produce their results. One thing that I cannot find are the in-silico predicted spectra that
were used in the experimental section. Recreating these would be challenging (e.g. CFM-ID takes a
long time to run) and could prohibit reproduction. I think they should be included as, e.g., one or
more .mgf files.
Reviewer #2 (Remarks to the Author):
The manuscript by Zhou and colleagues describes a software tool for the large scale deployment of
ion mobility collision cross-section data for metabolite identification of both known and unknown
metabolites. While a number of tools have been created previously, including by the senior author,
to search databases of known standards and also predict CCS values for metabolites without CCS
measures, AllCCS dramatically extends the use of CCS values and ion mobility for metabolite
identification and annotation by unifying a number of experimental CCS values to produce
consensus values and predicting CCS values for an impressive database of putative metabolites. The
authors demonstrate the use of AllCCS for a number of biological applications and I was impressed
with the identification of novel metabolites.
My major comment is that if I have understood AllCCS it is available through a webserver maintained
by the group and people need to register for access. While the authors make some data available a
lot of what is generated is behind the webserver interface. What are the plans to making this
available for the wider community? The database of putative metabolites looks particularly useful.
Also, if the tools are made freely available to the community they can be greatly improved in terms
of versatility – as an example I think about the developments of xcms by the community. Have the
authors considered this? Also, how does the server cope with large datasets as can be generated by
ion mobility data?
As a follow up comment while its impressive how well CCS values can be estimated – in many cases
its less than 2% - can the authors discuss examples where this is not enough. Some discussion of
what can be separated in terms of structural isomers would help. I am thinking of metabolites such
as glucose-6-P, glucose-1-P and fructose-6-P which are poorly separated by both chromatography
and ion mobility. Some examples of where an annotation can be made but not an identification
would be useful.
In addition, I do have some specific comments.
Abstract, line 17. The first sentence should be “the metabolome” rather than just metabolome. I
think the paper would benefit from a careful read to fix some of the grammar errors that creep in.
Introduction, line 32. This first sentence is also odd and should be re-written. Similarly for the
sentences on lines 54, 58 and 66.
Results. Line 94 – should be laboratories.
Line 98 “As a result, a total of 3,539 unified CCS values were calculated for 2,193 compounds…” I
think from what the authors say elsewhere the discrepancy in numbers is down to ionisation mode
rather than different conformers – its probably worth stating this for the reader and the authors are
largely annotating one conformer.
Lines 138-141 also need re-writing.
Line 283. Is KEGG the best choice for metabolic reconstructions? Is RECON a better alternative for
human metabolism?
A minor point – Student’s t-test and student’s t-test are written. I think the correct form is with a
capital S but needs to be consistent one way or the other depending on whether you believe Student
was a genuine author or not!
“All other data supporting the findings of this study are available from the corresponding author on
reasonable 602 request.” Should the data be made openly available?
Something is wrong with reference 9.
Reviewer #3 (Remarks to the Author):
The manuscript by Zhu et al. describes a curated atlas of ion mobility collision cross sections (CCS).
These collision cross sections are being increasingly used for the purpose of metabolite annotation
as a complementary parameter by which unknown molecules, as particularly metabolites in
untargeted metabolomics studies, can be better annotated. Although the number of databases with
collision cross sections is growing steadily both in number and in size, the dearth of comprehensive
CCS databases has prompted many scientists to also look into predicting such CCS values using
machine learning approaches. The authors of this manuscript have, in the past, presented several
aspects of the work covered in this new manuscript in a number of articles. These include the
following: Anal. Chem. 2016, 88, 11084−11091 (MetCCS); Anal. Chem. 2017, 89, 9559−9566
(LipidCCS); Bioinformatics, 33(14), 2017, 2235–2237 (MetCCS) etc. Similar work has also been
published by other teams, including: Anal. Chem. 2020, 92, 1720−1729; Anal. Chem. 2019, 91,
5191−5199; Anal. Chem. 2017, 89, 6583−6589; Chem. Commun., 2017,53, 7624-7627; Journal of
Chromatography A, 1542 (2018) 82–88; Analytica Chimica Acta 924 (2016) 68e76. In that sense, and
despite the interesting nature of what is being described in the manuscript, the work is seen as
incremental, but not transformative, so publication in Nature Communications is not seen as a good
option, and a more specialized Journal such as Analytical Chemistry or The Analyst is recommended.
|
REVIEWER COMMENTS
Reviewer #1 (Remarks to the Author):
This paper described the creation and validation of an atlas of CCS values. The atlas is created using a
combination of experimental CCS (merged from multiple databases) and in-silico predicted CCS. The
authors show that they are able to predict CCS better than current systems, and that combining
predicted CCS with other data (m/z, predicted MS/MS) improved candidate ranking. The atlas looks
to be a resource that has practical utility and the authors do a good job showing that it performs
well.
1. Overall I enjoyed reading this paper. I think it does a good job in setting out the system, evaluating
it, and describing the benefits it brings. There are quite a few places in the text though in which
more thorough proof-reading is required (too numerous to list here).
2. The improvement in CCS prediction is good, and the ML methodology looks sound. I would
welcome a little more discussion on where the authors think this improvement comes from. Is it
simply the larger unified database?
3. The SVM regression for CCS prediction: the gamma parameters (note: radial basis, not radio basis)
seem extraordinarily high (2^8 and 2^13). Depending on the way the RBF function is parameterised,
this effectively becomes either a linear regression, or something akin to a nearest neighbours
scheme. Not necessarily a problem, but something that if I saw it in an analysis, would ring some
alarm bells for me. Have the authors looked into this?
4. When combining with MS/MS, the authors use only in-silico MS/MS on their side. Why is this? in-
silico MS/MS prediction is still not great. For the "unknown" experiments, predicted MS/MS is
obviously the only route. However, could the authors not have done some experiments with real
MS/MS library spectra? Playing devils advocate: perhaps the improvement CCS gives about in-silico
MS/MS is because in-silico MS/MS is not reliable. Would we see the same improvements with real
MS/MS libraries? There are plenty in the public domain (Massbank, GNPS, HMDB, etc).
5. Reproducibility: the authors do a good job of providing the supplementary material to allow
another to produce their results. One thing that I cannot find are the in-silico predicted spectra that
were used in the experimental section. Recreating these would be challenging (e.g. CFM-ID takes a
long time to run) and could prohibit reproduction. I think they should be included as, e.g., one or
more .mgf files.
Reviewer #2 (Remarks to the Author):
The manuscript by Zhou and colleagues describes a software tool for the large scale deployment of
ion mobility collision cross-section data for metabolite identification of both known and unknown
metabolites. While a number of tools have been created previously, including by the senior author,
to search databases of known standards and also predict CCS values for metabolites without CCS
measures, AllCCS dramatically extends the use of CCS values and ion mobility for metabolite
identification and annotation by unifying a number of experimental CCS values to produce
consensus values and predicting CCS values for an impressive database of putative metabolites. The
authors demonstrate the use of AllCCS for a number of biological applications and I was impressed
with the identification of novel metabolites.
My major comment is that if I have understood AllCCS it is available through a webserver maintained
by the group and people need to register for access. While the authors make some data available a
lot of what is generated is behind the webserver interface. What are the plans to making this
available for the wider community? The database of putative metabolites looks particularly useful.
Also, if the tools are made freely available to the community they can be greatly improved in terms
of versatility – as an example I think about the developments of xcms by the community. Have the
authors considered this? Also, how does the server cope with large datasets as can be generated by
ion mobility data?
As a follow up comment while its impressive how well CCS values can be estimated – in many cases
its less than 2% - can the authors discuss examples where this is not enough. Some discussion of
what can be separated in terms of structural isomers would help. I am thinking of metabolites such
as glucose-6-P, glucose-1-P and fructose-6-P which are poorly separated by both chromatography
and ion mobility. Some examples of where an annotation can be made but not an identification
would be useful.
In addition, I do have some specific comments.
Abstract, line 17. The first sentence should be “the metabolome” rather than just metabolome. I
think the paper would benefit from a careful read to fix some of the grammar errors that creep in.
Introduction, line 32. This first sentence is also odd and should be re-written. Similarly for the
sentences on lines 54, 58 and 66.
Results. Line 94 – should be laboratories.
Line 98 “As a result, a total of 3,539 unified CCS values were calculated for 2,193 compounds…” I
think from what the authors say elsewhere the discrepancy in numbers is down to ionisation mode
rather than different conformers – its probably worth stating this for the reader and the authors are
largely annotating one conformer.
Lines 138-141 also need re-writing.
Line 283. Is KEGG the best choice for metabolic reconstructions? Is RECON a better alternative for
human metabolism?
A minor point – Student’s t-test and student’s t-test are written. I think the correct form is with a
capital S but needs to be consistent one way or the other depending on whether you believe Student
was a genuine author or not!
“All other data supporting the findings of this study are available from the corresponding author on
reasonable 602 request.” Should the data be made openly available?
Something is wrong with reference 9.
Reviewer #3 (Remarks to the Author):
The manuscript by Zhu et al. describes a curated atlas of ion mobility collision cross sections (CCS).
These collision cross sections are being increasingly used for the purpose of metabolite annotation
as a complementary parameter by which unknown molecules, as particularly metabolites in
untargeted metabolomics studies, can be better annotated. Although the number of databases with
collision cross sections is growing steadily both in number and in size, the dearth of comprehensive
CCS databases has prompted many scientists to also look into predicting such CCS values using
machine learning approaches. The authors of this manuscript have, in the past, presented several
aspects of the work covered in this new manuscript in a number of articles. These include the
following: Anal. Chem. 2016, 88, 11084−11091 (MetCCS); Anal. Chem. 2017, 89, 9559−9566
(LipidCCS); Bioinformatics, 33(14), 2017, 2235–2237 (MetCCS) etc. Similar work has also been
published by other teams, including: Anal. Chem. 2020, 92, 1720−1729; Anal. Chem. 2019, 91,
5191−5199; Anal. Chem. 2017, 89, 6583−6589; Chem. Commun., 2017,53, 7624-7627; Journal of
Chromatography A, 1542 (2018) 82–88; Analytica Chimica Acta 924 (2016) 68e76. In that sense, and
despite the interesting nature of what is being described in the manuscript, the work is seen as
incremental, but not transformative, so publication in Nature Communications is not seen as a good
option, and a more specialized Journal such as Analytical Chemistry or The Analyst is recommended.
|
TPR
|
NC_BS_BIOCH_005_RR1.txt
|
{
"criticism": 7,
"example": 8,
"importance_and_relevance": 5,
"materials_and_methods": 29,
"praise": 10,
"presentation_and_reporting": 17,
"results_and_discussion": 8,
"suggestion_and_solution": 16,
"total": 83
}
|
{
"criticism": 0.08433734939759036,
"example": 0.0963855421686747,
"importance_and_relevance": 0.060240963855421686,
"materials_and_methods": 0.3493975903614458,
"praise": 0.12048192771084337,
"presentation_and_reporting": 0.20481927710843373,
"results_and_discussion": 0.0963855421686747,
"suggestion_and_solution": 0.1927710843373494
}
| 1.204819
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "REVIEWER COMMENTS \n\n \n\nReviewer #1 (Remarks to the Author): \n\n \n\nThis paper described the creation and validation of an atlas of CCS values. The atlas is created using a \ncombination of experimental CCS (merged from multiple databases) and in-silico predicted CCS. The \nauthors show that they are able to predict CCS better than current systems, and that combining \npredicted CCS with other data (m/z, predicted MS/MS) improved candidate ranking. The atlas looks \nto be a resource that has practical utility and the authors do a good job showing that it performs \nwell. \n\n \n\n1. Overall I enjoyed reading this paper. I think it does a good job in setting out the system, evaluating \nit, and describing the benefits it brings. There are quite a few places in the text though in which \nmore thorough proof-reading is required (too numerous to list here). \n\n \n\n2. The improvement in CCS prediction is good, and the ML methodology looks sound. I would \nwelcome a little more discussion on where the authors think this improvement comes from. Is it \nsimply the larger unified database? \n\n \n\n3. The SVM regression for CCS prediction: the gamma parameters (note: radial basis, not radio basis) \nseem extraordinarily high (2^8 and 2^13). Depending on the way the RBF function is parameterised, \nthis effectively becomes either a linear regression, or something akin to a nearest neighbours \nscheme. Not necessarily a problem, but something that if I saw it in an analysis, would ring some \nalarm bells for me. Have the authors looked into this? \n\n \n\n4. When combining with MS/MS, the authors use only in-silico MS/MS on their side. Why is this? in-\nsilico MS/MS prediction is still not great. For the \"unknown\" experiments, predicted MS/MS is \nobviously the only route. However, could the authors not have done some experiments with real \nMS/MS library spectra? Playing devils advocate: perhaps the improvement CCS gives about in-silico \nMS/MS is because in-silico MS/MS is not reliable. Would we see the same improvements with real \nMS/MS libraries? There are plenty in the public domain (Massbank, GNPS, HMDB, etc). \n\n \n\n5. Reproducibility: the authors do a good job of providing the supplementary material to allow \nanother to produce their results. One thing that I cannot find are the in-silico predicted spectra that \nwere used in the experimental section. Recreating these would be challenging (e.g. CFM-ID takes a \n\n\flong time to run) and could prohibit reproduction. I think they should be included as, e.g., one or \nmore .mgf files. \n\n \n\n \n\nReviewer #2 (Remarks to the Author): \n\n \n\nThe manuscript by Zhou and colleagues describes a software tool for the large scale deployment of \nion mobility collision cross-section data for metabolite identification of both known and unknown \nmetabolites. While a number of tools have been created previously, including by the senior author, \nto search databases of known standards and also predict CCS values for metabolites without CCS \nmeasures, AllCCS dramatically extends the use of CCS values and ion mobility for metabolite \nidentification and annotation by unifying a number of experimental CCS values to produce \nconsensus values and predicting CCS values for an impressive database of putative metabolites. The \nauthors demonstrate the use of AllCCS for a number of biological applications and I was impressed \nwith the identification of novel metabolites. \n\nMy major comment is that if I have understood AllCCS it is available through a webserver maintained \nby the group and people need to register for access. While the authors make some data available a \nlot of what is generated is behind the webserver interface. What are the plans to making this \navailable for the wider community? The database of putative metabolites looks particularly useful. \nAlso, if the tools are made freely available to the community they can be greatly improved in terms \nof versatility – as an example I think about the developments of xcms by the community. Have the \nauthors considered this? Also, how does the server cope with large datasets as can be generated by \nion mobility data? \n\nAs a follow up comment while its impressive how well CCS values can be estimated – in many cases \nits less than 2% - can the authors discuss examples where this is not enough. Some discussion of \nwhat can be separated in terms of structural isomers would help. I am thinking of metabolites such \nas glucose-6-P, glucose-1-P and fructose-6-P which are poorly separated by both chromatography \nand ion mobility. Some examples of where an annotation can be made but not an identification \nwould be useful. \n\nIn addition, I do have some specific comments. \n\nAbstract, line 17. The first sentence should be “the metabolome” rather than just metabolome. I \nthink the paper would benefit from a careful read to fix some of the grammar errors that creep in. \n\nIntroduction, line 32. This first sentence is also odd and should be re-written. Similarly for the \nsentences on lines 54, 58 and 66. \n\nResults. Line 94 – should be laboratories. \n\nLine 98 “As a result, a total of 3,539 unified CCS values were calculated for 2,193 compounds…” I \nthink from what the authors say elsewhere the discrepancy in numbers is down to ionisation mode \n\n\frather than different conformers – its probably worth stating this for the reader and the authors are \nlargely annotating one conformer. \n\nLines 138-141 also need re-writing. \n\nLine 283. Is KEGG the best choice for metabolic reconstructions? Is RECON a better alternative for \nhuman metabolism? \n\nA minor point – Student’s t-test and student’s t-test are written. I think the correct form is with a \ncapital S but needs to be consistent one way or the other depending on whether you believe Student \nwas a genuine author or not! \n\n“All other data supporting the findings of this study are available from the corresponding author on \nreasonable 602 request.” Should the data be made openly available? \n\nSomething is wrong with reference 9. \n\n \n\n \n\n \n\nReviewer #3 (Remarks to the Author): \n\n \n\nThe manuscript by Zhu et al. describes a curated atlas of ion mobility collision cross sections (CCS). \nThese collision cross sections are being increasingly used for the purpose of metabolite annotation \nas a complementary parameter by which unknown molecules, as particularly metabolites in \nuntargeted metabolomics studies, can be better annotated. Although the number of databases with \ncollision cross sections is growing steadily both in number and in size, the dearth of comprehensive \nCCS databases has prompted many scientists to also look into predicting such CCS values using \nmachine learning approaches. The authors of this manuscript have, in the past, presented several \naspects of the work covered in this new manuscript in a number of articles. These include the \nfollowing: Anal. Chem. 2016, 88, 11084−11091 (MetCCS); Anal. Chem. 2017, 89, 9559−9566 \n(LipidCCS); Bioinformatics, 33(14), 2017, 2235–2237 (MetCCS) etc. Similar work has also been \npublished by other teams, including: Anal. Chem. 2020, 92, 1720−1729; Anal. Chem. 2019, 91, \n5191−5199; Anal. Chem. 2017, 89, 6583−6589; Chem. Commun., 2017,53, 7624-7627; Journal of \nChromatography A, 1542 (2018) 82–88; Analytica Chimica Acta 924 (2016) 68e76. In that sense, and \ndespite the interesting nature of what is being described in the manuscript, the work is seen as \nincremental, but not transformative, so publication in Nature Communications is not seen as a good \noption, and a more specialized Journal such as Analytical Chemistry or The Analyst is recommended. \n\n\f",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Complete chemical structures of human mitochondrial tRNAs
|
Reviewers' comments:
Reviewer #1 (Remarks to the Author):
tRNAs are central to the decoding process and the post-transcriptional modifications of tRNA are critical
for tRNA function including stability, folding and decoding. It is known that disorders of mitochondrial
translation may lead to the mitochondria dysfunction and some point mutations in mt-tRNA have been
reported to be associated with mitochondrial diseases. But the molecular pathogenesis of human
mitochondrial diseases caused by aberrant tRNA modifications has lagged behind due to the lack of the
complete landscape of modifications in mt-tRNA and the list of responsible modifying enzymes. In this
manuscript, Suzuki and his colleagues identified the majority of modifications in all 22 human mt-tRNA
using mass spectrometric analyses. Further, a comprehensive analysis including CE-Ψ-MS, CMC-PE and
tRNA-Ψ-seq were employed to detect Ψ (a mass-silent modification) in mt-tRNA. In addition, the
modifying enzymes responsible for these mt-tRNA are also listed. Thus, the collective results represent a
very comprehensive resource that will be a key reference for the field. The study will certainly benefit
future molecular mechanism studies of human mitochondrial diseases caused by mt-tRNA
modifications. The study is also very well designed, performed and written. Hence, I strongly
recommend the publication of this paper at Nature communications. I only have a few minor points as
listed.
1. In this study, tRNA-Ψ-seq was used to detect Ψ sites in mt-tRNA. Recently a similar approach named
DM–Ψ-seq is also developed and identified Ψ sites in cytoplasmic and mitochondrial tRNA (Song et al.,
2020, Nat Chem Biol 16, 160-169). It would be nice to also compare the psiU sites (since it is a mass-
silent modification) identified in this study with the reference.
2. The authors have listed RNase T1- or A-digested fragments of 22 human mt-tRNAs in supplementary
table 1; all the original fragment analysis maps (as Figure 2C) are also desired to be included, which can
be used to evaluate the stoichiometry of modified nucleosides.
3. 2D-TLC cannot discriminate Ψ in different positions of mt-tRNAGlu and hence the label in
Supplementary 4 is not accurate.
Reviewer #2 (Remarks to the Author):
In this study, Suzuki et al, performed a comprehensive analysis of post-transcriptional modifications of
all human mt-tRNAs. In a previous analysis, the authors mapped 15 types of modified bases at 118
positions in all species of bovine mt-tRNAs. Here, the authors isolated 22 species of human mt-tRNAs
and analyzed the primary sequence and post-transcriptional modifications for each tRNA using mass
spectrometry in combination with biochemical analyses to map pseudouridines. In total, the authors
found 16 kinds of RNA modifications at 136 positions in 22 species of human mt-tRNAs. The results
provide a complete list of modifications in human mt-tRNA. This is an interesting study and should
facilitate investigations of their physiological roles in the future.
1. The authors isolated 22 species of human mt-tRNAs from human placenta, but only several species of
mt-tRNA from HeLa cells. Why not isolate the all 22 species of human mt-tRNA from HeLa cells? I
suggest the authors to compare the modifications in mt-tRNA between human placenta and HeLa cells.
2. How about the frequency (or stoichiometry) of specific modifications in given sites of human mt-
tRNA? I suggest the authors to provide this information for each identified modification in mt-tRNA.
3. How to confirm the purity of the isolated individual mt-tRNA? The lengths of mt-tRNA are similar and
they also show similar gel-shift on the gel. Single band in gel may not indicate the single mt-tRNA. The
impure mt-tRNA may affect the determination of the modifications in mt-tRNA.
4. There are some modifications that have the same molecular weights, such as m5C and m3C, m1G and
m2G, m1A and m6A. How to confirm these modifications? The authors need to provide detailed
experimental evidence.
5. The MS fragment ions of 15 species of mt-tRNA were listed in Table S1. But in this study the authors
measured 22 species of mt-tRNA. The authors need to supply the rest part of mt-tRNA of the MS
fragment ions.
6. The authors need to provide the sequence and Western blotting data for supporting the knockout
experiments.
7. In Figure 3b, the Ψs at positions 66 and 67 in human mt-tRNAPro were identified. If these two sites
are both Ψs, why there are two possibilities, i.e. the existence of c6 and y6 ions?
8. Figure 4 and Figure S5 are somehow similar. Figure 4 includes 14 species of mt-tRNA and Figure S5
includes 22. The authors may only provide the full 22 species of mt-tRNA in main text.
Reviewer #3 (Remarks to the Author):
In this manuscript by Suzuki et al., the authors map the chemical structures of the remaining
uncharacterized tRNAs encoded by the human mitochondrial genome. Using previously-developed tRNA
purification and mass spectrometry techniques, the authors identify the repertoire of modifications in
human mitochondrial tRNAs. The data is technically sound and the authors provide independent assays
to validate a subset of modifications. Moreover, the authors provide evidence that the QTRT1 and
QTRT2 proteins are required for the queuosine modification in certain human mitochondrial tRNAs. The
manuscript is clearly written and have provided extensive Supplemental Data to support their findings.
Unfortunately, there is a lack of novelty in this manuscript since no new types of modifications were
found. The approach and results are similar to the conclusions published by the group using bovine
mitochondrial tRNAs in their 2014 paper in Nucleic Acids Research. Thus, many of the modifications in
mitochondrial tRNA could have been predicted and this manuscript serves as validation rather than
discovery. Moreover, there is little functional characterization of the modifications and their biological
roles. Table 1 is just a list of codons and the cognate tRNA anticodons while Table 2 is a list of the known
and confirmed tRNA modifications and their cognate enzymes. While the results represent a complete
inventory of human mitochondrial tRNA modifications, no new insight is gained that changes how we
think about mitochondrial tRNA modifications or mitochondrial tRNA biology.
To elevate this manuscript beyond just simply mapping tRNA modifications, the authors should
characterize the consequences of lacking a mitochondrial tRNA modification. For example, the Authors
have made a knockout of QTRT1 or QTRT2 but there is no follow-up on the function of queuosine
modification in mitochondrial tRNAs. Biological insight could also be gained by monitoring the function
of the numerous pseudouridine modifications in mitochondrial tRNAs. Currently, the manuscript
describes a list of modifications without providing any biological relevance or significance of the
modifications.
Minor points:
• Figure 1 shows a denaturing gel of isolated tRNAs. Since the RNAs are imaged using a general nucleic
acid stain, there is no follow-up on the relative purity of the isolated tRNA fractions. The Authors could
perform Northern blotting on an aliquot of the isolated tRNAs to determine whether there are
contaminating tRNAs in the fractions. This could be important since any contaminating tRNAs could
contribute significantly to the modification signal detected by mass spectrometry.
• As mentioned above, there is no follow-up on the QTRT1 or QTRT2-knockout (KO) cell lines. The
addition of molecular or biological effects caused by lack of Q modification would have greatly
strengthened the manuscript and provided insight into the function of the Q modification in
mitochondrial tRNAs.
|
Reviewers' comments:
Reviewer #1 (Remarks to the Author):
tRNAs are central to the decoding process and the post-transcriptional modifications of tRNA are critical
for tRNA function including stability, folding and decoding. It is known that disorders of mitochondrial
translation may lead to the mitochondria dysfunction and some point mutations in mt-tRNA have been
reported to be associated with mitochondrial diseases. But the molecular pathogenesis of human
mitochondrial diseases caused by aberrant tRNA modifications has lagged behind due to the lack of the
complete landscape of modifications in mt-tRNA and the list of responsible modifying enzymes. In this
manuscript, Suzuki and his colleagues identified the majority of modifications in all 22 human mt-tRNA
using mass spectrometric analyses. Further, a comprehensive analysis including CE-Ψ-MS, CMC-PE and
tRNA-Ψ-seq were employed to detect Ψ (a mass-silent modification) in mt-tRNA. In addition, the
modifying enzymes responsible for these mt-tRNA are also listed. Thus, the collective results represent a
very comprehensive resource that will be a key reference for the field. The study will certainly benefit
future molecular mechanism studies of human mitochondrial diseases caused by mt-tRNA
modifications. The study is also very well designed, performed and written. Hence, I strongly
recommend the publication of this paper at Nature communications. I only have a few minor points as
listed.
1. In this study, tRNA-Ψ-seq was used to detect Ψ sites in mt-tRNA. Recently a similar approach named
DM–Ψ-seq is also developed and identified Ψ sites in cytoplasmic and mitochondrial tRNA (Song et al.,
2020, Nat Chem Biol 16, 160-169). It would be nice to also compare the psiU sites (since it is a mass-
silent modification) identified in this study with the reference.
2. The authors have listed RNase T1- or A-digested fragments of 22 human mt-tRNAs in supplementary
table 1; all the original fragment analysis maps (as Figure 2C) are also desired to be included, which can
be used to evaluate the stoichiometry of modified nucleosides.
3. 2D-TLC cannot discriminate Ψ in different positions of mt-tRNAGlu and hence the label in
Supplementary 4 is not accurate.
Reviewer #2 (Remarks to the Author):
In this study, Suzuki et al, performed a comprehensive analysis of post-transcriptional modifications of
all human mt-tRNAs. In a previous analysis, the authors mapped 15 types of modified bases at 118
positions in all species of bovine mt-tRNAs. Here, the authors isolated 22 species of human mt-tRNAs
and analyzed the primary sequence and post-transcriptional modifications for each tRNA using mass
spectrometry in combination with biochemical analyses to map pseudouridines. In total, the authors
found 16 kinds of RNA modifications at 136 positions in 22 species of human mt-tRNAs. The results
provide a complete list of modifications in human mt-tRNA. This is an interesting study and should
facilitate investigations of their physiological roles in the future.
1. The authors isolated 22 species of human mt-tRNAs from human placenta, but only several species of
mt-tRNA from HeLa cells. Why not isolate the all 22 species of human mt-tRNA from HeLa cells? I
suggest the authors to compare the modifications in mt-tRNA between human placenta and HeLa cells.
2. How about the frequency (or stoichiometry) of specific modifications in given sites of human mt-
tRNA? I suggest the authors to provide this information for each identified modification in mt-tRNA.
3. How to confirm the purity of the isolated individual mt-tRNA? The lengths of mt-tRNA are similar and
they also show similar gel-shift on the gel. Single band in gel may not indicate the single mt-tRNA. The
impure mt-tRNA may affect the determination of the modifications in mt-tRNA.
4. There are some modifications that have the same molecular weights, such as m5C and m3C, m1G and
m2G, m1A and m6A. How to confirm these modifications? The authors need to provide detailed
experimental evidence.
5. The MS fragment ions of 15 species of mt-tRNA were listed in Table S1. But in this study the authors
measured 22 species of mt-tRNA. The authors need to supply the rest part of mt-tRNA of the MS
fragment ions.
6. The authors need to provide the sequence and Western blotting data for supporting the knockout
experiments.
7. In Figure 3b, the Ψs at positions 66 and 67 in human mt-tRNAPro were identified. If these two sites
are both Ψs, why there are two possibilities, i.e. the existence of c6 and y6 ions?
8. Figure 4 and Figure S5 are somehow similar. Figure 4 includes 14 species of mt-tRNA and Figure S5
includes 22. The authors may only provide the full 22 species of mt-tRNA in main text.
Reviewer #3 (Remarks to the Author):
In this manuscript by Suzuki et al., the authors map the chemical structures of the remaining
uncharacterized tRNAs encoded by the human mitochondrial genome. Using previously-developed tRNA
purification and mass spectrometry techniques, the authors identify the repertoire of modifications in
human mitochondrial tRNAs. The data is technically sound and the authors provide independent assays
to validate a subset of modifications. Moreover, the authors provide evidence that the QTRT1 and
QTRT2 proteins are required for the queuosine modification in certain human mitochondrial tRNAs. The
manuscript is clearly written and have provided extensive Supplemental Data to support their findings.
Unfortunately, there is a lack of novelty in this manuscript since no new types of modifications were
found. The approach and results are similar to the conclusions published by the group using bovine
mitochondrial tRNAs in their 2014 paper in Nucleic Acids Research. Thus, many of the modifications in
mitochondrial tRNA could have been predicted and this manuscript serves as validation rather than
discovery. Moreover, there is little functional characterization of the modifications and their biological
roles. Table 1 is just a list of codons and the cognate tRNA anticodons while Table 2 is a list of the known
and confirmed tRNA modifications and their cognate enzymes. While the results represent a complete
inventory of human mitochondrial tRNA modifications, no new insight is gained that changes how we
think about mitochondrial tRNA modifications or mitochondrial tRNA biology.
To elevate this manuscript beyond just simply mapping tRNA modifications, the authors should
characterize the consequences of lacking a mitochondrial tRNA modification. For example, the Authors
have made a knockout of QTRT1 or QTRT2 but there is no follow-up on the function of queuosine
modification in mitochondrial tRNAs. Biological insight could also be gained by monitoring the function
of the numerous pseudouridine modifications in mitochondrial tRNAs. Currently, the manuscript
describes a list of modifications without providing any biological relevance or significance of the
modifications.
Minor points:
• Figure 1 shows a denaturing gel of isolated tRNAs. Since the RNAs are imaged using a general nucleic
acid stain, there is no follow-up on the relative purity of the isolated tRNA fractions. The Authors could
perform Northern blotting on an aliquot of the isolated tRNAs to determine whether there are
contaminating tRNAs in the fractions. This could be important since any contaminating tRNAs could
contribute significantly to the modification signal detected by mass spectrometry.
• As mentioned above, there is no follow-up on the QTRT1 or QTRT2-knockout (KO) cell lines. The
addition of molecular or biological effects caused by lack of Q modification would have greatly
strengthened the manuscript and provided insight into the function of the Q modification in
mitochondrial tRNAs.
|
TPR
|
NC_BS_BIOCH_006_RR1.txt
|
{
"criticism": 7,
"example": 6,
"importance_and_relevance": 4,
"materials_and_methods": 45,
"praise": 7,
"presentation_and_reporting": 10,
"results_and_discussion": 4,
"suggestion_and_solution": 15,
"total": 76
}
|
{
"criticism": 0.09210526315789473,
"example": 0.07894736842105263,
"importance_and_relevance": 0.05263157894736842,
"materials_and_methods": 0.5921052631578947,
"praise": 0.09210526315789473,
"presentation_and_reporting": 0.13157894736842105,
"results_and_discussion": 0.05263157894736842,
"suggestion_and_solution": 0.19736842105263158
}
| 1.289474
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "Reviewers' comments: \n\nReviewer #1 (Remarks to the Author): \n\ntRNAs are central to the decoding process and the post-transcriptional modifications of tRNA are critical \nfor tRNA function including stability, folding and decoding. It is known that disorders of mitochondrial \ntranslation may lead to the mitochondria dysfunction and some point mutations in mt-tRNA have been \nreported to be associated with mitochondrial diseases. But the molecular pathogenesis of human \nmitochondrial diseases caused by aberrant tRNA modifications has lagged behind due to the lack of the \ncomplete landscape of modifications in mt-tRNA and the list of responsible modifying enzymes. In this \nmanuscript, Suzuki and his colleagues identified the majority of modifications in all 22 human mt-tRNA \nusing mass spectrometric analyses. Further, a comprehensive analysis including CE-Ψ-MS, CMC-PE and \ntRNA-Ψ-seq were employed to detect Ψ (a mass-silent modification) in mt-tRNA. In addition, the \nmodifying enzymes responsible for these mt-tRNA are also listed. Thus, the collective results represent a \nvery comprehensive resource that will be a key reference for the field. The study will certainly benefit \nfuture molecular mechanism studies of human mitochondrial diseases caused by mt-tRNA \nmodifications. The study is also very well designed, performed and written. Hence, I strongly \nrecommend the publication of this paper at Nature communications. I only have a few minor points as \nlisted. \n\n1. In this study, tRNA-Ψ-seq was used to detect Ψ sites in mt-tRNA. Recently a similar approach named \nDM–Ψ-seq is also developed and identified Ψ sites in cytoplasmic and mitochondrial tRNA (Song et al., \n2020, Nat Chem Biol 16, 160-169). It would be nice to also compare the psiU sites (since it is a mass-\nsilent modification) identified in this study with the reference. \n\n2. The authors have listed RNase T1- or A-digested fragments of 22 human mt-tRNAs in supplementary \ntable 1; all the original fragment analysis maps (as Figure 2C) are also desired to be included, which can \nbe used to evaluate the stoichiometry of modified nucleosides. \n\n3. 2D-TLC cannot discriminate Ψ in different positions of mt-tRNAGlu and hence the label in \nSupplementary 4 is not accurate. \n\nReviewer #2 (Remarks to the Author): \n\nIn this study, Suzuki et al, performed a comprehensive analysis of post-transcriptional modifications of \nall human mt-tRNAs. In a previous analysis, the authors mapped 15 types of modified bases at 118 \npositions in all species of bovine mt-tRNAs. Here, the authors isolated 22 species of human mt-tRNAs \nand analyzed the primary sequence and post-transcriptional modifications for each tRNA using mass \n\n\fspectrometry in combination with biochemical analyses to map pseudouridines. In total, the authors \nfound 16 kinds of RNA modifications at 136 positions in 22 species of human mt-tRNAs. The results \nprovide a complete list of modifications in human mt-tRNA. This is an interesting study and should \nfacilitate investigations of their physiological roles in the future. \n\n1. The authors isolated 22 species of human mt-tRNAs from human placenta, but only several species of \nmt-tRNA from HeLa cells. Why not isolate the all 22 species of human mt-tRNA from HeLa cells? I \nsuggest the authors to compare the modifications in mt-tRNA between human placenta and HeLa cells. \n\n2. How about the frequency (or stoichiometry) of specific modifications in given sites of human mt-\ntRNA? I suggest the authors to provide this information for each identified modification in mt-tRNA. \n\n3. How to confirm the purity of the isolated individual mt-tRNA? The lengths of mt-tRNA are similar and \nthey also show similar gel-shift on the gel. Single band in gel may not indicate the single mt-tRNA. The \nimpure mt-tRNA may affect the determination of the modifications in mt-tRNA. \n\n4. There are some modifications that have the same molecular weights, such as m5C and m3C, m1G and \nm2G, m1A and m6A. How to confirm these modifications? The authors need to provide detailed \nexperimental evidence. \n\n5. The MS fragment ions of 15 species of mt-tRNA were listed in Table S1. But in this study the authors \nmeasured 22 species of mt-tRNA. The authors need to supply the rest part of mt-tRNA of the MS \nfragment ions. \n\n6. The authors need to provide the sequence and Western blotting data for supporting the knockout \nexperiments. \n\n7. In Figure 3b, the Ψs at positions 66 and 67 in human mt-tRNAPro were identified. If these two sites \nare both Ψs, why there are two possibilities, i.e. the existence of c6 and y6 ions? \n\n8. Figure 4 and Figure S5 are somehow similar. Figure 4 includes 14 species of mt-tRNA and Figure S5 \nincludes 22. The authors may only provide the full 22 species of mt-tRNA in main text. \n\nReviewer #3 (Remarks to the Author): \n\nIn this manuscript by Suzuki et al., the authors map the chemical structures of the remaining \nuncharacterized tRNAs encoded by the human mitochondrial genome. Using previously-developed tRNA \npurification and mass spectrometry techniques, the authors identify the repertoire of modifications in \nhuman mitochondrial tRNAs. The data is technically sound and the authors provide independent assays \nto validate a subset of modifications. Moreover, the authors provide evidence that the QTRT1 and \nQTRT2 proteins are required for the queuosine modification in certain human mitochondrial tRNAs. The \n\n\fmanuscript is clearly written and have provided extensive Supplemental Data to support their findings. \n\nUnfortunately, there is a lack of novelty in this manuscript since no new types of modifications were \nfound. The approach and results are similar to the conclusions published by the group using bovine \nmitochondrial tRNAs in their 2014 paper in Nucleic Acids Research. Thus, many of the modifications in \nmitochondrial tRNA could have been predicted and this manuscript serves as validation rather than \ndiscovery. Moreover, there is little functional characterization of the modifications and their biological \nroles. Table 1 is just a list of codons and the cognate tRNA anticodons while Table 2 is a list of the known \nand confirmed tRNA modifications and their cognate enzymes. While the results represent a complete \ninventory of human mitochondrial tRNA modifications, no new insight is gained that changes how we \nthink about mitochondrial tRNA modifications or mitochondrial tRNA biology. \n\nTo elevate this manuscript beyond just simply mapping tRNA modifications, the authors should \ncharacterize the consequences of lacking a mitochondrial tRNA modification. For example, the Authors \nhave made a knockout of QTRT1 or QTRT2 but there is no follow-up on the function of queuosine \nmodification in mitochondrial tRNAs. Biological insight could also be gained by monitoring the function \nof the numerous pseudouridine modifications in mitochondrial tRNAs. Currently, the manuscript \ndescribes a list of modifications without providing any biological relevance or significance of the \nmodifications. \n\nMinor points: \n\n• Figure 1 shows a denaturing gel of isolated tRNAs. Since the RNAs are imaged using a general nucleic \nacid stain, there is no follow-up on the relative purity of the isolated tRNA fractions. The Authors could \nperform Northern blotting on an aliquot of the isolated tRNAs to determine whether there are \ncontaminating tRNAs in the fractions. This could be important since any contaminating tRNAs could \ncontribute significantly to the modification signal detected by mass spectrometry. \n• As mentioned above, there is no follow-up on the QTRT1 or QTRT2-knockout (KO) cell lines. The \naddition of molecular or biological effects caused by lack of Q modification would have greatly \nstrengthened the manuscript and provided insight into the function of the Q modification in \nmitochondrial tRNAs. \n\n\f\n\n \n\n",
"role": "assistant"
}
] | 2,020
|
|||
0
| 0
|
Complete chemical structures of human mitochondrial tRNAs
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
The authors have addressed all my previous concerns and the revised manuscript has been improved. I
thus strongly support the publication in Nature Communications.
Reviewer #2 (Remarks to the Author):
The authors addressed my questions. I have no further questions.
Reviewer #3 (Remarks to the Author):
The Authors have addressed all concerns from the original review. The authors have provided a reason
for why a comprehensive map of human tRNA modifications is important since bovine and human mt-
tRNAs differ fairly significantly in sequence so simple prediction is not sufficient. In addition, the authors
provide evidence for new modifications, cmnm5U and cmnm5s2U. The authors also add ribosome
profiling data and protein folding reporter plasmids to provide functional relevance for the findings.
Based upon these clarifications and additions, the paper has provided novelty and biological insight that
would be of broad interest in the field of RNA biology. Thus, I recommend the manuscript for
publication.
|
REVIEWERS' COMMENTS:
Reviewer #1 (Remarks to the Author):
The authors have addressed all my previous concerns and the revised manuscript has been improved. I
thus strongly support the publication in Nature Communications.
Reviewer #2 (Remarks to the Author):
The authors addressed my questions. I have no further questions.
Reviewer #3 (Remarks to the Author):
The Authors have addressed all concerns from the original review. The authors have provided a reason
for why a comprehensive map of human tRNA modifications is important since bovine and human mt-
tRNAs differ fairly significantly in sequence so simple prediction is not sufficient. In addition, the authors
provide evidence for new modifications, cmnm5U and cmnm5s2U. The authors also add ribosome
profiling data and protein folding reporter plasmids to provide functional relevance for the findings.
Based upon these clarifications and additions, the paper has provided novelty and biological insight that
would be of broad interest in the field of RNA biology. Thus, I recommend the manuscript for
publication.
|
TPR
|
NC_BS_BIOCH_006_RR2.txt
|
{
"criticism": 1,
"example": 0,
"importance_and_relevance": 2,
"materials_and_methods": 2,
"praise": 4,
"presentation_and_reporting": 0,
"results_and_discussion": 2,
"suggestion_and_solution": 1,
"total": 10
}
|
{
"criticism": 0.1,
"example": 0,
"importance_and_relevance": 0.2,
"materials_and_methods": 0.2,
"praise": 0.4,
"presentation_and_reporting": 0,
"results_and_discussion": 0.2,
"suggestion_and_solution": 0.1
}
| 1.2
| 0
|
[
{
"content": "Please review this paper.",
"role": "user"
},
{
"content": "\n\n\fREVIEWERS' COMMENTS: \n\nReviewer #1 (Remarks to the Author): \n\nThe authors have addressed all my previous concerns and the revised manuscript has been improved. I \nthus strongly support the publication in Nature Communications. \n\nReviewer #2 (Remarks to the Author): \n\nThe authors addressed my questions. I have no further questions. \n\nReviewer #3 (Remarks to the Author): \n\nThe Authors have addressed all concerns from the original review. The authors have provided a reason \nfor why a comprehensive map of human tRNA modifications is important since bovine and human mt-\ntRNAs differ fairly significantly in sequence so simple prediction is not sufficient. In addition, the authors \nprovide evidence for new modifications, cmnm5U and cmnm5s2U. The authors also add ribosome \nprofiling data and protein folding reporter plasmids to provide functional relevance for the findings. \nBased upon these clarifications and additions, the paper has provided novelty and biological insight that \nwould be of broad interest in the field of RNA biology. Thus, I recommend the manuscript for \npublication. \n\n\f\n",
"role": "assistant"
}
] | 2,020
|
End of preview. Expand
in Data Studio
Transparent Peer Review (TPR) Dataset
This dataset contains peer reviews from TPR, standardized to match the format of the pawin205/PeerRT dataset.
Dataset Structure
Each record contains the following attributes:
relative_rank: Default value (0).win_prob: Default value (0.0).title: Title of the paper.abstract: Abstract of the paper.full_text: Full text of the paper (or review text if unavailable).review: The peer review text.source: Source of the data ('TPR').review_src: Original filename of the review.criteria_count: Dictionary containing counts of specific criteria in the review (e.g., criticism, praise).dimension_scores: Dictionary containing scores for various dimensions.overall_score: Computed overall score (reward value).thinking_trace: Placeholder (empty).prompt: Placeholder (empty).prompt_length: Placeholder (0).conversations: List of dictionaries representing the conversation (User/Assistant format).year: Year of publication (if available).
Usage
from datasets import load_dataset
dataset = load_dataset("JerMa88/TPR_Peer_Reviews")
print(dataset['train'][0])
- Downloads last month
- 16