https://github.com/bytedance/markov-molecular-sampling

https://github.com/bytedance/markov-molecular-sampling

Science Score: 36.0%

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
  • Academic publication links
  • Committers with academic emails
    1 of 1 committers (100.0%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.8%) to scientific vocabulary

Keywords

research
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: bytedance
  • License: other
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 37.6 MB
Statistics
  • Stars: 54
  • Watchers: 4
  • Forks: 13
  • Open Issues: 2
  • Releases: 0
Topics
research
Created over 4 years ago · Last pushed over 4 years ago
Metadata Files
Readme License

README.md

MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

Thanks for your interest! This is the code repository for our ICLR 2021 paper MARS: Markov Molecular Sampling for Multi-objective Drug Discovery.

Dependencies

The conda environment is exported as environment.yml. You can also manually install these packages:

```bash conda install -c conda-forge rdkit conda install tqdm tensorboard scikit-learn conda install pytorch cudatoolkit=11.1 -c pytorch -c conda-forge conda install -c dglteam dgl-cuda11.1

for cpu only

conda install pytorch cpuonly -c pytorch conda install -c dglteam dgl ```

Run

Note: Run the commands outside the MARS directory.

To extract molecular fragments from a database:

bash python -m MARS.datasets.prepro_vocab

To sample molecules:

bash python -m MARS.main --train --run_dir runs/RUN_DIR

Evaluation and Generated Molecules

The generated molecules are evaluated at each step and the results are stored in runs/RUN_DIR (runs/debug by default). Please refer to tensorboard files for the evaluation results and mols.txt for all the molecules generated during sampling.

The experiment results we listed in the paper are obtained by averaging the outcomes of 10 independent sampling paths. For each sampling path, we record the evaluation results of the step that produces the highest PM score.

Citation

@inproceedings{ xie2021mars, title={MARS: Markov Molecular Sampling for Multi-objective Drug Discovery}, author={Yutong Xie and Chence Shi and Hao Zhou and Yuwei Yang and Weinan Zhang and Yong Yu and Lei Li}, booktitle={International Conference on Learning Representations}, year={2021}, url={https://openreview.net/forum?id=kHSu4ebxFXY} }

Owner

  • Name: Bytedance Inc.
  • Login: bytedance
  • Kind: organization
  • Location: Singapore

GitHub Events

Total
  • Watch event: 9
Last Year
  • Watch event: 9

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 2
  • Total Committers: 1
  • Avg Commits per committer: 2.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
yuweiy y****4@n****u 2
Committer Domains (Top 20 + Academic)
nyu.edu: 1

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 2
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 2
  • Total pull request authors: 0
  • Average comments per issue: 0.5
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • 1200Caixia (1)
  • TryLittleHarder (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels