Python package for TwinBooster: Synergising Chemical Structures and Bioassay Descriptions for Enhanced Molecular Property Prediction in Drug Discovery
Project description
Python package for TwinBooster
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
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for twinbooster-0.2.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 34a248b4f40ef8b0dc66657b786617190f26bb98c0ec324e4eee44dfe8f04317 |
|
MD5 | 8822e479b188d6b7ffa8d62664fd0912 |
|
BLAKE2b-256 | 829a2511dbdf66be7b3f8b4477bac56c0424e6e50ee10f50734571483d177888 |