Skip to main content

Python package for TwinBooster: Synergising Chemical Structures and Bioassay Descriptions for Enhanced Molecular Property Prediction in Drug Discovery

Project description

Python package for TwinBooster

arXiv Code style: black Python version License

Synergising Chemical Structures and Bioassay Descriptions for Enhanced Molecular Property Prediction in Drug Discovery

Maximilian G. Schuh, Davide Boldini, Stephan A. Sieber

@ Technical University of Munich, TUM School of Natural Sciences, Department of Bioscience, Center for Functional Protein Assemblies (CPA)

Installation

Install the package with pip install twinbooster. Then you can download the pretrained models with twinbooster.download_models(). For FS-Mol, you can download the data with twinbooster.download_data().

An example script can be found here ./twinbooster/twinbooster_example.ipynb.

Citation

If you use TwinBooster in your research, please cite our preprint:

@misc{schuh2024twinbooster,
      title={TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction}, 
      author={Maximilian G. Schuh and Davide Boldini and Stephan A. Sieber},
      year={2024},
      eprint={2401.04478},
      archivePrefix={arXiv},
      primaryClass={q-bio.BM}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

twinbooster-0.3.1.tar.gz (34.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

twinbooster-0.3.1-py3-none-any.whl (43.0 kB view details)

Uploaded Python 3

File details

Details for the file twinbooster-0.3.1.tar.gz.

File metadata

  • Download URL: twinbooster-0.3.1.tar.gz
  • Upload date:
  • Size: 34.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.18

File hashes

Hashes for twinbooster-0.3.1.tar.gz
Algorithm Hash digest
SHA256 89e42e8eb1e4e647477849452d1a8301c7305ebee8579cc1afd91dbd876d8bf8
MD5 c863679fd7e3315e59b8e1480b296b0d
BLAKE2b-256 2ca10c4968ea31af5136a227f93d480c05c106c8127ddf68638f8938e170aa70

See more details on using hashes here.

File details

Details for the file twinbooster-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: twinbooster-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 43.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.18

File hashes

Hashes for twinbooster-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 da6e44eca2e9d2817ac92e80ff2efccd7fcc3565e03c77c05b36969cb15523cc
MD5 b3b2a4384e0ca75fb8f5dc5ddc959f3f
BLAKE2b-256 11e4efa4d73ad7b0744e1731962599a3c2e553948ccd30dbfb98fe3424a8e68b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page