chemprop

Message Passing Neural Networks for Molecule Property Prediction

https://github.com/chemprop/chemprop

Science Score: 59.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 11 DOI reference(s) in README
✓
Academic publication links
Links to: arxiv.org, nature.com, acs.org
✓
Committers with academic emails
35 of 75 committers (46.7%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (15.7%) to scientific vocabulary

Keywords

chemistry drug-discovery machine-learning neural-networks

Keywords from Contributors

virtual-screening active-learning bayesian-optimization evidential-deep-learning molecule uncertainty

Last synced: 6 months ago · JSON representation

Repository

Message Passing Neural Networks for Molecule Property Prediction

Basic Info

Host: GitHub
Owner: chemprop
License: other
Language: Python
Default Branch: main
Homepage: https://chemprop.csail.mit.edu
Size: 856 MB

Statistics

Stars: 2,066
Watchers: 34
Forks: 668
Open Issues: 57
Releases: 29

Topics

chemistry drug-discovery machine-learning neural-networks

Created about 7 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License Citation

Chemprop

Chemprop is a repository containing message passing neural networks for molecular property prediction.

Documentation can be found here.

There are tutorial notebooks in the examples/ directory.

Chemprop recently underwent a ground-up rewrite and new major release (v2.0.0). A helpful transition guide from Chemprop v1 to v2 can be found here. This includes a side-by-side comparison of CLI argument options, a list of which arguments will be implemented in later versions of v2, and a list of changes to default hyperparameters.

License: Chemprop is free to use under the MIT License. The Chemprop logo is free to use under CC0 1.0.

References: Please cite the appropriate papers if Chemprop is helpful to your research.

Chemprop was initially described in the papers Analyzing Learned Molecular Representations for Property Prediction for molecules and Machine Learning of Reaction Properties via Learned Representations of the Condensed Graph of Reaction for reactions.
The interpretation functionality (available in v1, but not yet implemented in v2) is based on the paper Multi-Objective Molecule Generation using Interpretable Substructures.
Chemprop now has its own dedicated manuscript that describes and benchmarks it in more detail: Chemprop: A Machine Learning Package for Chemical Property Prediction.
A paper describing and benchmarking the changes in v2.0.0 is forthcoming.
Support for atom and bond predictions is based on the paper When Do Quantum Mechanical Descriptors Help Graph Neural Networks to Predict Chemical Properties?

Selected Applications: Chemprop has been successfully used in the following works.

A Deep Learning Approach to Antibiotic Discovery - Cell (2020): Chemprop was used to predict antibiotic activity against E. coli, leading to the discovery of Halicin, a novel antibiotic candidate. Model checkpoints are availabile on Zenodo.
Discovery of a structural class of antibiotics with explainable deep learning - Nature (2023): Identified a structural class of antibiotics selective against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci using ensembles of Chemprop models, and explained results using Chemprop's interpret method.
ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries: Chemprop was trained on 41 absorption, distribution, metabolism, excretion, and toxicity (ADMET) datasets from the Therapeutics Data Commons. The Chemprop models in ADMET-AI are available both as a web server at admet.ai.greenstonebio.com and as a Python package at github.com/swansonk14/admet_ai.
A more extensive list of successful Chemprop applications is given in our 2023 paper

Version 1.x

For users who have not yet made the switch to Chemprop v2.0, please reference the following resources.

v1 Documentation

Documentation of Chemprop v1 is available here. Note that the content of this site is several versions behind the final v1 release (v1.7.1) and does not cover the full scope of features available in chemprop v1.
The v1 README is the best source for documentation on more recently-added features.
Please also see descriptions of all the possible command line arguments in the v1 args.py file.

v1 Tutorials and Examples

Benchmark scripts - scripts from our 2023 paper, providing examples of many features using Chemprop v1.6.1
ACS Fall 2023 Workshop - presentation, interactive demo, exercises on Google Colab with solution key
Google Colab notebook - several examples, intended to be run in Google Colab rather than as a Jupyter notebook on your local machine
nanoHUB tool - a notebook of examples similar to the Colab notebook above, doesn't require any installation
- YouTube video - lecture accompanying nanoHUB tool
These slides provide a Chemprop tutorial and highlight additions as of April 28th, 2020

v1 Known Issues

We have discontinued support for v1 since v2 has been released, but we still appreciate v1 bug reports and will tag them as v1-wontfix so the community can find them easily.

Owner

Name: chemprop
Login: chemprop
Kind: organization
Location: MIT

Repositories: 1
Profile: https://github.com/chemprop

Home of the official chemprop project

Committers

Last synced: 10 months ago

All Time

Total Commits: 3,041
Total Committers: 75
Avg Commits per committer: 40.547
Development Distribution Score (DDS): 0.754

Past Year

Commits: 133
Committers: 17
Avg Commits per committer: 7.824
Development Distribution Score (DDS): 0.722

Top Committers

Name	Email	Commits
Hao-Wei Pang	h**g@m**u	747
Kyle Swanson	s**4@g**m	648
david graff	d**1@g**u	344
Nathan Morgan	n**n@g**m	204
Kevin Yang	y**k@m**u	175
Kevin Greenman	k**g@m**u	165
Jackson Burns	3****s	117
shihchengli	s**i@m**u	101
lhirschfeld	l**p@g**m	51
Chas	c**l@g**m	42
jonwzheng	j**g@m**u	40
am2145	a**n@g**m	40
Florence Vermeire	f**i@m**u	33
fhvermei	f**e@u**e	32
Xiaorui Dong	x**i@m**u	31
Anna Doner	d**a@m**u	25
Esther Heid	e**d@w**e	21
Wengong Jin	a**n@g**m	21
Joel Manu	j**u@m**u	18
Yanfei Guan	y**g@m**u	14
Oscar Wu	o**u@m**u	14
Wengong Jin	w**g@r**u	13
Kevin Yang	y**k@3**u	12
Kevin Yang	y**k@K**l	11
Kevin Yang	y**k@3**u	8
Esther Heid	e**r@m**t	7
Max Liu	m**u@m**u	7
Allison Tam	a**m@r**u	5
Angiras Menon	a**5@g**m	5
Kevin Yang	y**k@3**u	5
and 45 more...

Committer Domains (Top 20 + Academic)

mit.edu: 13 g.harvard.edu: 1 ugent.be: 1 rosetta5.csail.mit.edu: 1 31-39-59.wireless.csail.mit.edu: 1 31-35-182.wireless.csail.mit.edu: 1 mdy.univie.ac.at: 1 rosetta10.csail.mit.edu: 1 github.com: 1 31-33-76.wireless.csail.mit.edu: 1 novartis.com: 1 31-36-24.wireless.csail.mit.edu: 1 rosetta11.csail.mit.edu: 1 dhcp-18-40-65-165.dyn.mit.edu: 1 30-10-111.wireless.csail.mit.edu: 1 30-10-100.wireless.csail.mit.edu: 1 31-35-90.wireless.csail.mit.edu: 1 31-39-51.wireless.csail.mit.edu: 1 dhcp-18-30-125-141.dyn.mit.edu: 1 dhcp-18-40-122-81.dyn.mit.edu: 1 dhcp-18-40-7-157.dyn.mit.edu: 1 31-36-224.wireless.csail.mit.edu: 1 post.bgu.ac.il: 1 dhcp-18-40-2-185.dyn.mit.edu: 1 31-33-193.wireless.csail.mit.edu: 1 30-9-42.wireless.csail.mit.edu: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 474
Total pull requests: 529
Average time to close issues: 3 months
Average time to close pull requests: about 1 month
Total issue authors: 158
Total pull request authors: 51
Average comments per issue: 3.02
Average comments per pull request: 2.85
Merged pull requests: 398
Bot issues: 0
Bot pull requests: 1

Past Year

Issues: 113
Pull requests: 181
Average time to close issues: 22 days
Average time to close pull requests: 24 days
Issue authors: 61
Pull request authors: 18
Average comments per issue: 2.47
Average comments per pull request: 1.72
Merged pull requests: 112
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

kevingreenman (42)
KnathanM (37)
davidegraff (21)
SoodabehGhaffari (19)
hwpang (16)
shihchengli (16)
spyda90 (12)
JacksonBurns (10)
Rhys-McAlister (9)
am2145 (8)
GLPG-GT (7)
muammar (6)
jia-huang (6)
DengFeng-Zuo (6)
yunsiechung (5)

Pull Request Authors

KnathanM (180)
hwpang (105)
shihchengli (100)
JacksonBurns (67)
kevingreenman (50)
davidegraff (38)
am2145 (25)
twinbrian (25)
cjmcgill (19)
jonwzheng (16)
craabreu (16)
akshatzalte (14)
joelnkn (13)
donerancl (11)
c-w-feldmann (11)

Top Labels

Issue Labels

question (167) bug (120) todo (79) enhancement (69) mlpds (17) v1-wontfix (11) wontfix (8) duplicate (1) help wanted (1)

Pull Request Labels

bug (20) enhancement (19) mlpds (7) duplicate (1)

Packages

Total packages: 3
Total downloads:
- pypi 16,318 last-month

Total dependent packages: 2
(may contain duplicates)
Total dependent repositories: 15
(may contain duplicates)
Total versions: 61
Total maintainers: 2

pypi.org: chemprop

Molecular Property Prediction with Message Passing Neural Networks

Documentation: https://chemprop.readthedocs.io/
License: MIT
Latest release: 2.2.1
published 7 months ago

Versions: 28
Dependent Packages: 2
Dependent Repositories: 7
Downloads: 16,318 Last month

Rankings

Downloads: 1.1%

Stargazers count: 1.9%

Forks count: 2.4%

Average: 3.7%

Dependent repos count: 5.7%

Dependent packages count: 7.4%

Maintainers (2)

chemprop kevinpgreenman

Last synced: 6 months ago

proxy.golang.org: github.com/chemprop/chemprop

Documentation: https://pkg.go.dev/github.com/chemprop/chemprop#section-documentation
License: other
Latest release: v2.2.1+incompatible
published 7 months ago

Versions: 27
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 5.7%

Average: 5.9%

Dependent repos count: 6.0%

Last synced: 6 months ago

conda-forge.org: chemprop

This repository contains message passing neural networks for molecular property prediction as described in the paper Analyzing Learned Molecular Representations for Property Prediction and as used in the paper A Deep Learning Approach to Antibiotic Discovery.

Homepage: https://github.com/chemprop/chemprop
License: MIT
Latest release: 1.5.2
published over 3 years ago

Versions: 6
Dependent Packages: 0
Dependent Repositories: 8

Rankings

Forks count: 8.0%

Dependent repos count: 12.0%

Stargazers count: 12.6%

Average: 21.0%

Dependent packages count: 51.4%

Last synced: 6 months ago

Dependencies

.github/workflows/codeql.yml actions

actions/checkout v3 composite
github/codeql-action/analyze v2 composite
github/codeql-action/autobuild v2 composite
github/codeql-action/init v2 composite

.github/workflows/tests.yml actions

actions/checkout v2 composite
actions/checkout master composite
actions/setup-python v1 composite
actions/setup-python v3 composite
pypa/gh-action-pypi-publish release/v1 composite

Dockerfile docker

mambaorg/micromamba 0.23.0 build

setup.py pypi

descriptastorus >=2.6.1
descriptastorus <2.6.1
flask >=1.1.2
hyperopt >=0.2.3
matplotlib >=3.1.3
numpy >=1.18.1
pandas >=1.0.3
pandas-flavor >=0.2.0
rdkit >=2020.03.1.0
scikit-learn >=0.22.2.post1
scipy >=1.9
scipy <1.11
sphinx >=3.1.2
tensorboardX >=2.0
torch >=1.4.0
tqdm >=4.45.0
typed-argument-parser >=1.6.1

environment.yml conda

flask >=1.1.2
gunicorn >=20.0.4
hyperopt >=0.2.3
matplotlib >=3.1.3
numpy >=1.18.1
pandas >=1.0.3
pandas-flavor >=0.2.0
pip >=20.0.2
python >=3.7
pytorch >=1.4.0
rdkit >=2020.03.1.0
scikit-learn >=0.22.2.post1
scipy >=1.4.1
tensorboardx >=2.0
torchvision >=0.5.0
tqdm >=4.45.0

chemprop

Science Score: 59.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

Chemprop

Version 1.x

v1 Documentation

v1 Tutorials and Examples

v1 Known Issues

Owner

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: chemprop

Rankings

Maintainers (2)

proxy.golang.org: github.com/chemprop/chemprop

Rankings

conda-forge.org: chemprop

Rankings

Dependencies