Towards explainable interaction prediction: Embedding biological hierarchies into hyperbolic interaction space

Author:

Pogány DomonkosORCID,Antal Péter

Abstract

Given the prolonged timelines and high costs associated with traditional approaches, accelerating drug development is crucial. Computational methods, particularly drug-target interaction prediction, have emerged as efficient tools, yet the explainability of machine learning models remains a challenge. Our work aims to provide more interpretable interaction prediction models using similarity-based prediction in a latent space aligned to biological hierarchies. We investigated integrating drug and protein hierarchies into a joint-embedding drug-target latent space via embedding regularization by conducting a comparative analysis between models employing traditional flat Euclidean vector spaces and those utilizing hyperbolic embeddings. Besides, we provided a latent space analysis as an example to show how we can gain visual insights into the trained model with the help of dimensionality reduction. Our results demonstrate that hierarchy regularization improves interpretability without compromising predictive performance. Furthermore, integrating hyperbolic embeddings, coupled with regularization, enhances the quality of the embedded hierarchy trees. Our approach enables a more informed and insightful application of interaction prediction models in drug discovery by constructing an interpretable hyperbolic latent space, simultaneously incorporating drug and target hierarchies and pairing them with available interaction information. Moreover, compatible with pairwise methods, the approach allows for additional transparency through existing explainable AI solutions.

Funder

National Research, Development and Innovation Office

J. Heim Student Scholarship

European Union (EU) Joint Program on Neurodegenerative Disease

National Research, Development, and Innovation Fund of Hungary

European Union

Publisher

Public Library of Science (PLoS)

Reference66 articles.

1. Estimated research and development investment needed to bring a new medicine to market, 2009-2018;OJ Wouters;Jama,2020

2. Artificial intelligence for clinical trial design;S Harrer;Trends in pharmacological sciences,2019

3. Machine learning approaches and databases for prediction of drug–target interaction: a survey paper;M Bagherian;Briefings in bioinformatics,2021

4. Nickel M, Kiela D. Poincaré embeddings for learning hierarchical representations. Advances in neural information processing systems. 2017;30.

5. Hyperbolic matrix factorization improves prediction of drug-target associations;A Poleksic;Scientific Reports,2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3