Abstract
Compound screening by in silico approaches has advantages in identifying high-activity leading compounds and can predict the safety of the drug. A key challenge is that the number of observations of drug activity and toxicity accumulation varies by target in different datasets, some of which are more understudied than others. Owing to an overall insufficiency and imbalance of drug data, it is hard to accurately predict drug activity and toxicity of multiple tasks by the existing models. To solve this problem, this paper proposed a two-stage transfer learning workflow to develop a novel prediction model, which can accurately predict drug activity and toxicity of the targets with insufficient observations. We built a balanced dataset based on the Tox21 dataset and developed a drug activity and toxicity prediction model based on Siamese networks and graph convolution to produce multitasking output. We also took advantage of transfer learning from data-rich targets to data-poor targets. We showed greater accuracy in predicting the activity and toxicity of compounds to targets with rich data and poor data. In Tox21, a relatively rich dataset, the prediction model accuracy for classification tasks was 0.877 AUROC. In the other five unbalanced datasets, we also found that transfer learning strategies brought the accuracy of models to a higher level in understudied targets. Our models can overcome the imbalance in target data and predict the compound activity and toxicity of understudied targets to help prioritize upcoming biological experiments.
Funder
Shenzhen Science and Technology Research Fund
Talent Development Starting Fund from Shenzhen Government
Guangdong Province Basic and Applied Basic Research Fund Project
Publisher
Public Library of Science (PLoS)
Reference39 articles.
1. Recent Developments of In Silico Predictions of Intestinal Absorption and Oral Bioavailability;TJ Hou;CCHTS,2009
2. Artificial Intelligence for Drug Toxicity and Safety;AO Basile;Trends Pharmacol Sci,2019
3. Improving Small Molecule Virtual Screening Strategies for the next Generation of Therapeutics;BM Wingert;Curr Opin Chem Biol,2018
4. Virtual Screening Meets Deep Learning;PS Javier;Curr Comput-aid Drug,2019
5. The Light and Dark Sides of Virtual Screening: What Is There to Know?;A Gimeno;IJMS,2019
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献