TIDAL: Topology-Inferred Drug Addiction Learning

Drug addiction or drug overdose is a global public health crisis, and the design of anti-addiction drugs remains a major challenge due to intricate mechanisms. Since experimental drug screening and optimization are too time-consuming and expensive, there is urgent need to develop innovative artifici...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-12
Main Authors: Zhu Zailiang, Dou Bozheng, Cao Yukang, Jiang, Jian, Zhu Yueying, Chen, Dong, Feng Hongsong, Liu, Jie, Zhang Bengong, Zhou Tianshou, Wei, Guowei
Format: Article
Language:English
Subjects:
Addictions
Algebra
Artificial intelligence
Drug addiction
Drug overdose
Invariants
Learning
Neural networks
Optimization
Public health
Side effects
Spectra
Topology
Transformers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Drug addiction or drug overdose is a global public health crisis, and the design of anti-addiction drugs remains a major challenge due to intricate mechanisms. Since experimental drug screening and optimization are too time-consuming and expensive, there is urgent need to develop innovative artificial intelligence (AI) methods for addressing the challenge. We tackle this challenge by topology-inferred drug addiction learning (TIDAL) built from integrating topological Laplacian, deep bidirectional transformer, and ensemble-assisted neural networks (EANNs). The topological Laplacian is a novel algebraic topology tool that embeds molecular topological invariants and algebraic invariants into its harmonic spectra and non-harmonic spectra, respectively. These invariants complement sequence information extracted from a bidirectional transformer. We validate the proposed TIDAL framework on 22 drug addiction related, 4 hERG, and 12 DAT datasets, showing that TIDAL is a state-of-the-art framework for the modeling and analysis of drug addiction data. We carry out cross-target analysis of the current drug addiction candidates to alert their side effects and identify their repurposing potentials, revealing drugmediated linear and bilinear target correlations. Finally, TIDAL is applied to shed light on relative efficacy, repurposing potential, and potential side effects of 12 existing anti-addiction medications. Our results suggest that TIDAL provides a new computational strategy for pressingly-needed anti-substance addiction drug development.
ISSN:2331-8422