Closed editorialbot closed 4 months ago
Hello humans, I'm @editorialbot, a robot that can help you with some common editorial tasks.
For a list of things I can do to help you, just type:
@editorialbot commands
For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:
@editorialbot generate pdf
Software report:
github.com/AlDanial/cloc v 1.88 T=0.03 s (531.6 files/s, 58705.1 lines/s)
-------------------------------------------------------------------------------
Language files blank comment code
-------------------------------------------------------------------------------
Python 7 109 170 872
Markdown 3 83 0 152
TeX 1 15 0 99
YAML 2 1 3 29
Dockerfile 1 4 3 6
-------------------------------------------------------------------------------
SUM: 14 212 176 1158
-------------------------------------------------------------------------------
gitinspector failed to run statistical information for the repository
Reference check summary (note 'MISSING' DOIs are suggestions that need verification):
OK DOIs
- 10.1038/s41598-019-53663-8 is OK
- 10.1038/s41467-021-26320-w is OK
- 10.1039/C4CP03465A is OK
- 10.1109/TMI.1986.4307764 is OK
- 10.7554/eLife.33125 is OK
- 10.1371/journal.pone.0170165 is OK
- 10.1073/pnas.2104624118 is OK
- 10.1109/ISBI52829.2022.9761672 is OK
MISSING DOIs
- 10.1163/1574-9347_dnp_e612900 may be a valid DOI for title: Keras
INVALID DOIs
- None
Wordcount for paper.md
is 1068
:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:
@imagejan, @ajasja this is where the review takes place! This submission has had some delays. I am aware of the holiday period coming up for many. However I would be very grateful if this review could be conducted as streamlined as possible. So please do keep an eye on github notifications from this thread over the coming weeks.
To get started, please call @editorialbot generate my checklist
.
Thanks again for your help!
@imagejan, @ajasja I hope you are getting on well with the review. Let me know if there are any updates on review progress. Thanks!
@imagejan, @ajasja, 👋 how are you getting on with the review?
@imagejan, @ajasja, 👋 could you please provide an update? Thanks again for helping with this review.
@Kevin-Mattheus-Moerman sorry, I was delayed by sickness the past two weeks. Will try to finish reviewing this in the next few days.
@imagejan, @ajasja, 👋 thanks again for the help with this review. Are you able to resume at this point?
I've opened these issues on the TrackSegNet repository:
My main concerns are:
Thank you for your inputs @imagejan, I will try to address these issues!
Dear @Kevin-Mattheus-Moerman,
I finished implementing the suggestions from @imagejan, the modifications include:
Regarding the related methods mentioned in the field, there are only a few at the moment and the methodologies are quite different from each other. The related software are not always user-friendly, making a fair comparison difficult to achieve, which was also not the initial purpose of this submission.
@imagejan, @ajasja please can you resume (and perhaps finalise if possible) your review at your earliest convenience? Thanks again for your help here!!
@imagejan, @ajasja please can you resume (and perhaps finalise if possible) your review at your earliest convenience? Thanks again for your help here!!
@imagejan, @ajasja :wave:
All my concerns have been addressed, and I can endorse the paper. Please excuse the delayed response.
@Kevin-Mattheus-Moerman Is there anything else I need to do to finalize the review process?
@imagejan thanks for your help In that case your role here is compete. Thanks again!
@ajasja please can you resume and complete this review at your earliest convenience? Thanks
@Kevin-Mattheus-Moerman @hkabbech First, I would like to apologize for my slow response.
I have opened the following two minor issues dealing with installation problems: https://github.com/hkabbech/TrackSegNet/issues/24 https://github.com/hkabbech/TrackSegNet/issues/22
My main concerns are:
which major changes include the computation of angles as an additional feature for better distinction of the trajectory confinement, the choice of using the MSD analysis instead of the moment scaling spectrum (MSS) analysis, and the development of a user-friendly python software for replicability on other datasets.
Minor concerns:
This may be outside the scope of the review, but I'm curious -- it seems that the parameters of the states need to be set in advance. Are these just initial values that are adjusted during the training? Probably not, as they seem to be used to create the synthetic trajectories. Is there a way to obtain these parameters from the experimental data? How would one obtain the parameters of the states for an unknown system?
Also, I forgot one more thing -- since the package is on pip now (which is great), it would be nice is this was mentioned in the installation instructions in the Readme.
@hkabbech can you address this reviewer's comments/feedback? Thanks!
Dear all,
Apologies for this late reply, I had other priorities and couldn't find the time to finish this revision.
I have made some changes based on @ajsja comments.
In paper.md
:
It would be great if the raw tiff files were available in the toy examples (and not just the projection). I tried to open the tracks in MTrackJ, but was unable to do so as only one frame was available.
I am only in possession of the max. projection of the raw stack images which can be found in the data folder. The raw images would have been too large to upload in GitHub. To preview the trajectories in MTrackJ, you can create a hyperstack in imageJ (image>Hyperstacks>New Hyperstack...) with width=300px, height=50px, channels=1, slices=1 and frames=10,000. This could do the trick to visualize the tracks in time.
This may be outside the scope of the review, but I'm curious -- it seems that the parameters of the states need to be set in advance. Are these just initial values that are adjusted during the training? Probably not, as they seem to be used to create the synthetic trajectories. Is there a way to obtain these parameters from the experimental data? How would one obtain the parameters of the states for an unknown system?
This is somewhat disadvantage of a supervised learning method, the experimental data must be generated based on the experimental data, however not much is known about their dynamics. During my PhD, I developed another method which is unsupervised (no need for synthetic data) based on the noise2noise denoising technique. The description of this other method can be found here, however this method is not yet available as a software tool since it requires more developments and tests from our side.
Thank you for all your inputs!
If there is no more changes to be made, I will update the documentation and the pypi link with a new version.
@hkabbech Thank you for the changes! Looks good to me @Kevin-Mattheus-Moerman
@Kevin-Mattheus-Moerman Just checking -- is there anything else that I have to do in the review process?
@ajasja no thanks, all looks good now. Thanks for your help!
@editorialbot set <DOI here> as archive
@editorialbot set <version here> as version
@editorialbot generate pdf
@editorialbot check references
and ask author(s) to update as needed@editorialbot recommend-accept
@hkabbech Apologies for the delay over the last two weeks as I was traveling. Given the positive reviews I am now happy to proceed to process this work for acceptance in JOSS. Please can you look at the above post-review checklist and process your steps? Please let me know if you have any questions. Thanks.
@editorialbot check references
Reference check summary (note 'MISSING' DOIs are suggestions that need verification):
OK DOIs
- 10.1038/s41598-019-53663-8 is OK
- 10.1038/s41467-021-26320-w is OK
- 10.1039/C4CP03465A is OK
- 10.1109/TMI.1986.4307764 is OK
- 10.7554/eLife.33125 is OK
- 10.1371/journal.pone.0170165 is OK
- 10.1073/pnas.2104624118 is OK
- 10.1109/ISBI52829.2022.9761672 is OK
MISSING DOIs
- 10.1163/2214-8647_dnp_e612900 may be a valid DOI for title: Keras
INVALID DOIs
- None
@hkabbech can you work on your points above, and also check that potential DOI issue :point_up:
@editorialbot check references
Reference check summary (note 'MISSING' DOIs are suggestions that need verification):
OK DOIs
- 10.1038/s41598-019-53663-8 is OK
- 10.1038/s41467-021-26320-w is OK
- 10.1039/C4CP03465A is OK
- 10.1109/TMI.1986.4307764 is OK
- 10.7554/eLife.33125 is OK
- 10.1371/journal.pone.0170165 is OK
- 10.1073/pnas.2104624118 is OK
- 10.1109/ISBI52829.2022.9761672 is OK
MISSING DOIs
- None
INVALID DOIs
- None
Done! The latest version is 1.3.0, and the DOI is 10.5281/zenodo.7767749.
@editorialbot set 10.5281/zenodo.7767749 as archive
Done! archive is now 10.5281/zenodo.7767749
@editorialbot set v1.3.0 as version
Done! version is now v1.3.0
@editorialbot generate pdf
:warning: An error happened when generating the pdf. Author (Hélène Kabbech) is missing affiliation.
@hkabbech looks like this PR might fix the paper compilation error: https://github.com/hkabbech/TrackSegNet/pull/27
Sorry about that! Thanks!
@editorialbot generate pdf
:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:
@editorialbot recommend-accept
Attempting dry run of processing paper acceptance...
Submitting author: !--author-handle-->@hkabbech<!--end-author-handle-- (Hélène Kabbech) Repository: https://github.com/hkabbech/TrackSegNet Branch with paper.md (empty if default branch): Version: v1.3.0 Editor: !--editor-->@Kevin-Mattheus-Moerman<!--end-editor-- Reviewers: @imagejan, @ajasja Archive: 10.5281/zenodo.7767749
Status
Status badge code:
Reviewers and authors:
Please avoid lengthy details of difficulties in the review thread. Instead, please create a new issue in the target repository and link to those issues (especially acceptance-blockers) by leaving comments in the review thread below. (For completists: if the target issue tracker is also on GitHub, linking the review thread in the issue or vice versa will create corresponding breadcrumb trails in the link target.)
Reviewer instructions & questions
@imagejan & @ajasja, your review will be checklist based. Each of you will have a separate checklist that you should update when carrying out your review. First of all you need to run this command in a separate comment to create the checklist:
The reviewer guidelines are available here: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html. Any questions/concerns please let @Kevin-Mattheus-Moerman know.
✨ Please start on your review when you are able, and be sure to complete your review in the next six weeks, at the very latest ✨
Checklists
📝 Checklist for @imagejan
📝 Checklist for @ajasja