ADMET property prediction through combinations of molecular fingerprints

James H. Notwell, Michael W. Wood
9/29/2023
q-bio.BMcs.LG

Official code: maplightrx/MapLight-TDC (23 stars, MIT, last commit 2023-11-06).

Abstract

While investigating methods to predict small molecule potencies, we found random forests or support vector machines paired with extended-connectivity fingerprints (ECFP) consistently outperformed recently developed methods. A detailed investigation into regression algorithms and molecular fingerprints revealed gradient-boosted decision trees, particularly CatBoost, in conjunction with a combination of ECFP, Avalon, and ErG fingerprints, as well as 200 molecular properties, to be most effective. Incorporating a graph neural network fingerprint further enhanced performance. We successfully validated our model across 22 Therapeutics Data Commons ADMET benchmarks. Our findings underscore the significance of richer molecular representations for accurate property prediction.

View on arXivView PDF

Code Implementations(1)

maplightrx/MapLight-TDCOfficial
MIT
235Python, Jupyter NotebookSep 29, 20232 years agoMIT

Similar Papers

Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction

84% match2024

Linear to Neural Networks Regression: QSPR of Drugs via Degree-Distance Indices

83% match2025

QUBO-inspired Molecular Fingerprint for Chemical Property Prediction

83% match2023

Graph Residual based Method for Molecular Property Prediction

83% match2024

Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey

83% match2024

Advancements in Molecular Property Prediction: A Survey of Single and Multimodal Approaches

83% match2024

Cite this paper

@article{notwell2023admet,
  title  = {ADMET property prediction through combinations of molecular fingerprints},
  author = {James H. Notwell and Michael W. Wood},
  year   = {2023},
  eprint = {2310.00174},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.00174v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.00174.svg)](https://codeofpaper.com/paper/2310.00174)

Discussion