[PRE REVIEW]: TrackSegNet: a tool for trajectory segmentation into diffusive states using supervised deep learning

[editorialbot]

Submitting author: @hkabbech (Hélène Kabbech)
Repository: https://github.com/hkabbech/TrackSegNet
Branch with paper.md (empty if default branch):
Version: v1.0.0
Editor: @Kevin-Mattheus-Moerman
Reviewers: @imagejan, @ajasja
Managing EiC: Kevin M. Moerman

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/e15328db72dcaf7ca7068f171005ad49"><img src="https://joss.theoj.org/papers/e15328db72dcaf7ca7068f171005ad49/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/e15328db72dcaf7ca7068f171005ad49/status.svg)](https://joss.theoj.org/papers/e15328db72dcaf7ca7068f171005ad49)

Author instructions

Thanks for submitting your paper to JOSS @hkabbech. Currently, there isn't a JOSS editor assigned to your paper.

@hkabbech if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). In addition, this list of people have already agreed to review for JOSS and may be suitable for this submission (please start at the bottom of the list).

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

[editorialbot]

Hello human, 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

[editorialbot]

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

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.88  T=0.03 s (1153.7 files/s, 56281.6 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
Python                          31            110            194           1030
Markdown                         2             57              0            121
TeX                              1             15              0             99
Fish Shell                       1             18             14             68
C Shell                          1             13              7             35
YAML                             1              1              3             20
-------------------------------------------------------------------------------
SUM:                            37            214            218           1373
-------------------------------------------------------------------------------


gitinspector failed to run statistical information for the repository

[editorialbot]

Wordcount for paper.md is 1068

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[Kevin-Mattheus-Moerman]

@editorialbot query scope

[editorialbot]

Submission flagged for editorial review.

[Kevin-Mattheus-Moerman]

@hkabbech thanks for this submission. I am the AEiC for this track and here to help process initial steps. I have just triggered a scope review by the editorial board, to see if this work is deemed in scope. This is normal for submissions that are rather small e.g. in terms of lines of code. Over the coming ~2 weeks we'll review if this work conforms to our substantial scholarly effort criteria .

In the meantime you can start fixing the potentially missing/invalid DOIs pointed out above ☝️ , you can call @editorialbot check references to check them again, and use @editorialbot generate pdf to update the paper.

[hkabbech]

Thank you @Kevin-Mattheus-Moerman.

FYI this is a resubmission. I have added substantial analysis plots to the pipeline.

Regarding the missing DOI, I believe that there is no associated DOI to cite the keras library.

I am looking forward for your final decision.

[Kevin-Mattheus-Moerman]

@hkabbech thanks for the reminder that this is a resubmission. Would you be able to clearly summarise what changes have been made since the previous submission?

For the record, the pre-review link for the initial submission is here: #5270.

[hkabbech]

Below is the note to editor when resubmitting:

Notes to editor: Dear editors, TrackSegNet is a command-line tool permitting the segmentation of trajectories into diffusive states (using a deep neural network) and further dynamics analysis for each tracklet state. We believe in the major importance of our software for the understanding of particle dynamics (primarily protein dynamics, but its use can be extended to any type of trajectory dataset). The method was initially developed in our research group and published in 2019 (10.1038/s41598-019-53663-8). TrackSegNet presents major improvements of our method, and permits easy replicability on other trajectory datasets with additional analysis measurements. TrackSegNet was recently applied for the biophysical motion analysis of the androgen receptor in the nuclear environment (manuscript currently under revision at the Nucleic Acids Research journal). This is a resubmission, we have expended the functionality of TrackSegNet by adding major geometrical analysis plots per tracklet state (velocity autocorrelation curves and distributions of displacement and angle), since the initial submission was judged as "not conform to the substantial scholarly effort criteria of JOSS, due to its relatively small size, and narrow functionality". Hopefully, this time, TrackSegNet is conform to the criteria of JOSS and will be able to go through the revision stage. Kind regards, Helene and Ihor

[Kevin-Mattheus-Moerman]

@hkabbech I have just removed the query-scope flag as the scope review concluded this work may be in scope for JOSS. However it does appear "borderline" in terms of what we typically accept (currently), and the reviewers and handling editor may still raise concerns on scope.

[hkabbech]

Thank you @Kevin-Mattheus-Moerman.
I would like to get some updates on this, are there reviewers assigned?

[Kevin-Mattheus-Moerman]

@hkabbech I've been looking for a handling editor. I think some might now be available, so I'll invite them now. Thanks for your patience.

[Kevin-Mattheus-Moerman]

@editorialbot invite @jmschrei as editor

[editorialbot]

Invitation to edit this submission sent!

[jmschrei]

Unfortunately, I can't take this on right now. Sorry.

[Kevin-Mattheus-Moerman]

@editorialbot invite @pdebuyl as editor

[editorialbot]

Invitation to edit this submission sent!

[Kevin-Mattheus-Moerman]

👋 @pdebuyl

[Kevin-Mattheus-Moerman]

@editorialbot invite @pdebuyl as editor

[editorialbot]

Invitation to edit this submission sent!

[Kevin-Mattheus-Moerman]

@editorialbot invite @pibion as editor

[editorialbot]

Five most similar historical JOSS papers:

MCSD: A MATLAB Tool for Monte-Carlo Simulations of Diffusion in biological Tissues
Submitting author: @davidnsousa
Handling editor: @Kevin-Mattheus-Moerman (Active)
Reviewers: @nnadeau, @mwacaan
Similarity score: 0.8207

Volume Segmantics: A Python Package for Semantic Segmentation of Volumetric Data Using Pre-trained PyTorch Deep Learning
Models
Submitting author: @OllyK
Handling editor: @osorensen (Active)
Reviewers: @jingpengw, @estenhl
Similarity score: 0.8184

OrNet - a Python Toolkit to Model the Diffuse Structure of Organelles as Social Networks
Submitting author: @Marcdh3
Handling editor: @akeshavan (Retired)
Reviewers: @serine, @vc1492a
Similarity score: 0.8122

skedm: Empirical Dynamic Modeling
Submitting author: @nickc1
Handling editor: @jakevdp (Retired)
Reviewers: @johnh2o2
Similarity score: 0.8110

ParticleTracker: a gui based particle tracking software
Submitting author: @mikesmithlab
Handling editor: @Kevin-Mattheus-Moerman (Active)
Reviewers: @alexlib, @nkeim
Similarity score: 0.8065

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before before considering asking the reviewers of these papers to review again for JOSS.

[arfon]

@pibion – this list of most similar previous papers ☝️ might be a good source of reviewers for this submission. Suggest starting with the authors of past similar papers first.

[hkabbech]

Hello @pibion and @Kevin-Mattheus-Moerman
Can I get some updates on this..? Still no reviewers found? Thanks!

[Kevin-Mattheus-Moerman]

@pibion please continue your search for reviewers here.

[Kevin-Mattheus-Moerman]

@hkabbech Our sincere apologies for the severe delays this submission has encountered. I have also emailed @pibion to ask them to pick this up. If they are no longer available I will pick this up as editor to proceed as soon as possible.

[Kevin-Mattheus-Moerman]

@editorialbot remove @pibion as editor

[editorialbot]

I'm sorry human, I don't understand that. You can see what commands I support by typing:

@editorialbot commands

[Kevin-Mattheus-Moerman]

@editorialbot assign me as editor

[editorialbot]

Assigned! @Kevin-Mattheus-Moerman is now the editor

[Kevin-Mattheus-Moerman]

@hkabbech I am currently trying to find reviewers for this submission. If you would like to suggest any reviewers at this point, that would be hepful. Please mention their GitHub handles, but leave out the @ symbol.

In addition, please consider the below points:

• Please extend your README with a clear paragraph describing the software purpose/functionality.
• Please add contributing guidelines to your project. You can write a basic section in your README or you could link to a dedicated CONTRIBUTING.md file (see also: https://contributing.md/how-to-build-contributing-md/).

[Kevin-Mattheus-Moerman]

@thorstenwagner @GavinR1 @imagejan @Oxer11 @jkoefinger @ajasja @VincentStimper would you be interested in reviewing a submission entitled TrackSegNet: a tool for trajectory segmentation into diffusive states using supervised deep learning, for Journal of Open Source Software (JOSS)?

JOSS features a streamlined review process which take place here on GitHub. The review will feature the testing/evaluation of the software, and the review of a short paper.

If you are interested in helping, you can let us know by commenting here.

Thanks!

[imagejan]

Thanks for the invitation, @Kevin-Mattheus-Moerman.
Yes, please count me in as reviewer.

[Kevin-Mattheus-Moerman]

@editorialbot add @imagejan as reviewer

[editorialbot]

@imagejan added to the reviewers list!

[Kevin-Mattheus-Moerman]

@imagejan that is great thanks. Note this is a so-called "pre-review" issue where we'll assign reviewers. The actual review takes place in a dedicated "review" issue. I'll let you know when we'll get started.

[Kevin-Mattheus-Moerman]

@thorstenwagner @GavinR1 @Oxer11 @jkoefinger @ajasja @VincentStimper would you be interested in reviewing a submission entitled TrackSegNet: a tool for trajectory segmentation into diffusive states using supervised deep learning, for Journal of Open Source Software (JOSS)?

JOSS features a streamlined review process which take place here on GitHub. The review will feature the testing/evaluation of the software, and the review of a short paper.

If you are interested in helping, you can let us know by commenting here.

Thanks!

[VincentStimper]

I think somebody with a background in experimental cell biology or bioinformatics might be better suited than me to review this paper. Ideally, one of the authors of the paper that the method is based on could do it.

[hkabbech]

@Kevin-Mattheus-Moerman, many thanks for the updates!

@hkabbech I am currently trying to find reviewers for this submission. If you would like to suggest any reviewers at this point, that would be hepful. Please mention their GitHub handles, but leave out the @ symbol.

Unfortunately, I'm not sure if I know people who might help review my submission.

In addition, please consider the below points:

* [x]  Please extend your README with a clear paragraph describing the software purpose/functionality.

* [x]  Please add contributing guidelines to your project. You can write a basic section in your README or you could link to a dedicated CONTRIBUTING.md file (see also: https://contributing.md/how-to-build-contributing-md/).

I modified the README accordingly and added a CONTRIBUTING.md file.
I also added a Dockerfile and docker-compose.yaml for the creation of a docker container running the code.

[ajasja]

@Kevin-Mattheus-Moerman Yes, I could do it.
Does it matter that the method was already described in this article:
https://academic.oup.com/nar/article/51/20/10992/7288829

[Kevin-Mattheus-Moerman]

@editorialbot add @ajasja as reviewer

[editorialbot]

@ajasja added to the reviewers list!

[Kevin-Mattheus-Moerman]

@ajasja thanks for volunteering to review. At first sight it looks like the core purpose of that newer paper is to describe the application of this work to a particular scientific research topic. I will review this in more detail. For the moment I'll ask the authors to point out the key difference/purpose for these papers.

@hkabbech could you please provide a brief but clear description of the major advances you've made to the software since this paper: doi.org/10.1038/s41598-019-53663-8 (I have this in the notes to the editor but would be good to reiterate this clearly here for the reviewers too), and could you clarify the key differences with the current paper and this new one: https://academic.oup.com/nar/article/51/20/10992/7288829 thanks.

[hkabbech]

At the moment of submitting our work, the idea was to submit the software to JOSS for a better review of the tool/method, and a particular application (together with other experiments) to a biology journal where reviewers focus more on the discovery and biological methods employed. Both papers were submitted around the same time this year, while the biology paper got reviewed and published in only a few months (https://doi.org/10.1093/nar/gkad803), the pre-review process of the software paper was severely delayed.. Thus, in the meantime, we had to publish the code on Zenodo (https://zenodo.org/records/7767750).

The method was initially developed in our research group and published in 2019 (https://doi.org/10.1038/s41598-019-53663-8). The current software presents major improvements of our method and permits the replicability on other trajectory datasets. It contains also additional plotting measurements for interpretability of trajectory segmentation results.

We are still interested in getting our software reviewed by JOSS and hope this will still be possible.

[Kevin-Mattheus-Moerman]

@editorialbot start review

[editorialbot]

OK, I've started the review over in #6157.