[PRE REVIEW]: FitSNAP: Atomistic machine learning with LAMMPS

[editorialbot]

Submitting author: !--author-handle-->@rohskopf<!--end-author-handle-- (Andrew Rohskopf) Repository: https://github.com/FitSNAP/FitSNAP Branch with paper.md (empty if default branch): Version: 3 Editor: !--editor-->@jmschrei<!--end-editor-- Reviewers: @tpurcell90, @bahung Managing EiC: Kevin M. Moerman

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/daf91b67f1e71277e59f2ba6fc0b694f"><img src="https://joss.theoj.org/papers/daf91b67f1e71277e59f2ba6fc0b694f/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/daf91b67f1e71277e59f2ba6fc0b694f/status.svg)](https://joss.theoj.org/papers/daf91b67f1e71277e59f2ba6fc0b694f)

Author instructions

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

@rohskopf 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]

Software report:

github.com/AlDanial/cloc v 1.88  T=20.92 s (1452.3 files/s, 76861.5 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
JSON                         30182           1802              0        1577055
Python                         139           3520           3537          13169
Jupyter Notebook                 1              0           1826           2381
Markdown                        35            401              0           1648
reStructuredText                11            419            101            951
Cython                           2             87             56            279
TeX                              1             23              0            200
YAML                             2             10             35            109
Bourne Shell                     2              0              3             35
DOS Batch                        1              8              1             26
make                             1              4              7              9
C/C++ Header                     1              3             15              3
-------------------------------------------------------------------------------
SUM:                         30378           6277           5581        1595865
-------------------------------------------------------------------------------

gitinspector failed to run statistical information for the repository

[editorialbot]

Wordcount for paper.md is 2828

[editorialbot]

:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:

[editorialbot]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- None

MISSING DOIs

- 10.1016/j.cpc.2018.03.016 may be a valid DOI for title: DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
- 10.1021/acs.jctc.8b00770.s001 may be a valid DOI for title: Library-based LAMMPS implementation of high-dimensional neural network potentials
- 10.1103/physrevmaterials.6.013804 may be a valid DOI for title: Efficient parametrization of the atomic cluster expansion
- 10.21203/rs.3.rs-244137/v1 may be a valid DOI for title: E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
- 10.1016/j.cpc.2016.05.010 may be a valid DOI for title: Amp: A modular approach to machine learning in atomistic simulations
- 10.26434/chemrxiv.12218294 may be a valid DOI for title: TorchANI: a free and open source PyTorch-based deep learning implementation of the ANI neural network potentials
- 10.1145/3458817.3487400 may be a valid DOI for title: Billion atom molecular dynamics simulations of carbon at extreme conditions and experimental time and length scales
- 10.1038/s41524-021-00617-2 may be a valid DOI for title: Data-driven magneto-elastic predictions with scalable classical spin-lattice dynamics
- 10.1088/1741-4326/abe7bd may be a valid DOI for title: Beryllium-driven structural evolution at the divertor surface
- 10.1021/acs.jpca.0c02450.s001 may be a valid DOI for title: Explicit multielement extension of the spectral neighbor analysis potential for chemically complex systems
- 10.1021/acs.jpca.9b08723.s001 may be a valid DOI for title: Performance and cost assessment of machine learning interatomic potentials
- 10.1016/j.cpc.2021.108171 may be a valid DOI for title: LAMMPS-a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales
- 10.2172/1763572 may be a valid DOI for title: Simple and efficient algorithms for training machine learning potentials to force data
- 10.1103/physrevlett.104.136403 may be a valid DOI for title: Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons
- 10.1063/1.4712397 may be a valid DOI for title: Construction of high-dimensional neural network potentials using environment-dependent atom pairs
- 10.1007/s10853-021-06865-3 may be a valid DOI for title: Dissociating the phononic, magnetic and electronic contributions to thermal conductivity: a computational study in alpha-iron
- 10.1063/1.5017641 may be a valid DOI for title: Extending the accuracy of the SNAP interatomic potential form
- 10.1016/j.jcp.2014.12.018 may be a valid DOI for title: Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials
- 10.1103/physrevb.99.014104 may be a valid DOI for title: Atomic cluster expansion for accurate and transferable interatomic potentials
- 10.1016/j.commatsci.2018.07.043 may be a valid DOI for title: pyiron: An integrated development environment for computational materials science

INVALID DOIs

- None

[rohskopf]

Suggesting reviewers here (without tagging them with a @ as per instructions). tpurcell90 bjmorgan mkhorton lucydot utf

[Kevin-Mattheus-Moerman]

@rohskopf thanks for this submission. I am the AEiC for this track and will be looking for a handling editor. For the moment, can you please address the following minor points:

• [x] Please check those potentially missing DOIs ☝️ ? You can call @editorialbot check references here to check them again.
• [x] Please spell out USA as Unites States of America in your affiliations.
• [x] In your paper you've created custom headings, can you keep them as normal headings? For instance you currently use

### `Scraper`

Which should appear without the symbols "`", and probably be a second level heading e.g.:

## Scraper

Once completed you can update the PDF by calling: @editorialbot generate pdf.

[Kevin-Mattheus-Moerman]

@editorialbot invite @jmschrei as editor

[editorialbot]

Invitation to edit this submission sent!

[rohskopf]

@editorialbot check references

[editorialbot]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- 10.1016/j.cpc.2018.03.016 is OK
- 10.1021/acs.jctc.8b00770.s001 is OK
- 10.1103/physrevmaterials.6.013804 is OK
- 10.21203/rs.3.rs-244137/v1 is OK
- 10.1016/j.cpc.2016.05.010 is OK
- 10.26434/chemrxiv.12218294 is OK
- 10.1145/3458817.3487400 is OK
- 10.1038/s41524-021-00617-2 is OK
- 10.1088/1741-4326/abe7bd is OK
- 10.1021/acs.jpca.0c02450.s001 is OK
- 10.1021/acs.jpca.9b08723.s001 is OK
- 10.1016/j.cpc.2021.108171 is OK
- 10.2172/1763572 is OK
- 10.1103/physrevlett.104.136403 is OK
- 10.1063/1.4712397 is OK
- 10.1007/s10853-021-06865-3 is OK
- 10.1063/1.5017641 is OK
- 10.1016/j.jcp.2014.12.018 is OK
- 10.1103/physrevb.99.014104 is OK
- 10.1016/j.commatsci.2018.07.043 is OK

MISSING DOIs

- None

INVALID DOIs

- None

[rohskopf]

@editorialbot generate pdf

[editorialbot]

:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:

[rohskopf]

@Kevin-Mattheus-Moerman Thank you for the suggestions, I made changes to address your points.

[Kevin-Mattheus-Moerman]

@jmschrei did you see that invite :point_up: can you help edit this one? thanks

[jmschrei]

@editorialbot assign me as editor

[editorialbot]

Assigned! @jmschrei is now the editor

[jmschrei]

@rohskopf sorry about the delay. We were trying to figure out some editorial assignments internally.

[jmschrei]

Hi @neurons and @bahung, would either of you be able to serve as a review for this submission?

[rohskopf]

@jmschrei thanks for the update. In case you want more computational materials science reviewer suggestions, here are some from the JOSS list (not tagging with @): tpurcell90 bjmorgan mkhorton lucydot utf

[jmschrei]

Thanks for the suggestions. I usually try finding a few reviewers on my end first to minimize the chance of conflicts of interest.

[rohskopf]

@jmschrei great. Thanks again.

[jmschrei]

@tpurcell90 or @bjmorgan, would either of you be able to review this submission?

[tpurcell90]

Ya I can review this. Full disclosure I saw the project at a conference and recommended JOSS to the submitter. I don't think that would be a conflict though.

[bjmorgan]

I'm afraid I don't have any hands-on LAMMPS experience (although this submission looks like I might want to get some).

[jmschrei]

@editorialbot add @tpurcell90 as reviewer

[editorialbot]

@tpurcell90 added to the reviewers list!

[jmschrei]

@bjmorgan it's okay if you don't have any experience -- in fact, it's preferred, because part of the review process is how easy it is to use. Are you alright with reviewing, given this?

[rohskopf]

Thanks @jmschrei and @tpurcell90. @bjmorgan no LAMMPS experience required; our tutorial in Google Colab installs everything and walks through examples.

[rohskopf]

@jmschrei more possible reviewers:

srmnitc (very active JOSS submitter and reviewer in my field, but we've met at a workshop before) rangsimanketkaew ranzhengcode HemanthHaridas mkhorton lucydot utf

[jmschrei]

@rohskopf thanks for the suggestions.

@mkhorton or @lucydot, would either of you have time to review this submission? Thanks!

[rohskopf]

@jmschrei wanna try others?

[bahung]

Hi @neurons and @bahung, would either of you be able to serve as a review for this submission?

Sorry for the late reply, I can review this submission

[jmschrei]

Great, thanks!

[jmschrei]

@editorialbot add @bahung as reviewer

[editorialbot]

@bahung added to the reviewers list!

[jmschrei]

@editorialbot start review

[editorialbot]

OK, I've started the review over in https://github.com/openjournals/joss-reviews/issues/5118.

[mkhorton]

I have to opt out of this one, review-over-burdened right now. Good luck with the submission!