Meta-model for ADMET Property Prediction Analysis

Published

December 7, 2023

Author(s)

Sarala Padi, Antonio Cardone, Ram Sriram

Abstract

In drug discovery analysis ADMET properties, such as chemical absorption, distribution, metabolism, excretion, and toxicity, play a critical role. They allow the quantitative evaluation of a designed drug's efficacy. Several machine learning models have been designed for the prediction of ADMET properties. However, no single method seems to enable the accurate prediction of these properties. In this paper, we build a meta-model that combines scores from multiple machine learning models to predict ADMET properties more accurately. We evaluate the performance of our proposed model against the Therapeutics Data Commons (TDC) ADMET benchmark dataset. The proposed meta-model outperforms state-of-the-art methods such as XGBoost in the TDC leaderboard, and it ranks first in six prediction tasks and in the top three positions for fifteen prediction tasks.

Citation

BioArxiv

Pub Weblink

https://www.biorxiv.org/

Pub Type

Websites

Download Paper

Local Download

Keywords

Meta-model, Drug design, ADMET Prediciton, machine learning

Citation

Padi, S. , Cardone, A. and Sriram, R. (2023), Meta-model for ADMET Property Prediction Analysis, BioArxiv, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=936880, https://www.biorxiv.org/ (Accessed December 11, 2024)