Drug Discovery On Large-Scale Knowledge Graphs Based On Multi-Task Learning

The drug discovery processes（e.g.,new drugs discovering and drug repositioning）play a vital role in human health.However,the process of drug discovery is long and costly.With the accumulation of various biomedical data and the development of artificial intelligence（AI）algorithms since the beginning of the 21^st century,AI has become a tool to assist and accelerate the drug process.Therefore,recent studies have begun to use AI to assist drug discovery.In this paper,the biomedical knowledge graph is used as a tool,and deep learning technology is used to predict drug-target interaction（DTI）,compound-protein interaction（CPI）and drug reposition.The research works are summarized as follows:（1）Molecular interaction prediction is essential in various applications including drug discovery and material science.The problem becomes quite challenging when the interaction is represented by unmapped relationships in molecular networks,namely molecular interaction,because it easily suffers from（i）insufficient labeled data with many false positive samples,and（ii）ignoring a large number of biological entities with rich information in knowledge graph.Most of the existing methods cannot properly exploit the information of knowledge graph and molecule graph simultaneously.In this paper,we propose a large-scale Knowledge Graph enhanced Multi-Task Learning model,namely KG-MTL,which extracts the features from both knowledge graph and molecular graph in a synergistical way.Moreover,we design an effective Shared Unit that helps the model to jointly preserve the semantic relations of drug entity and the neighbor structures of compound in both knowledge graph and molecular graph.Extensive experiments on four real-world datasets demonstrate that our proposed KG-MTL outperforms the state-of-the-art methods on two representative molecular interaction prediction tasks:drug-target interaction prediction and compound-protein interaction prediction.（2）There have been more than 2.2 million confirmed cases and over 120 000deaths from the human coronavirus disease 2019（COVID-19）pandemic,which caused by the novel severe acute respiratory syndrome coronavirus（SARS-Co V-2）,in the United States alone.However,there is currently a lack of proven effective medications against COVID-19.Drug repurposing offers a promising route for the development of prevention and treatment strategies for COVID-19.This study reports an integrative,network-based deep-learning methodology to identify repurposable drugs for COVID-19（termed Co V-KGE）.Specifically,we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs,diseases,proteins/genes,pathways,and expression from a large scientific corpus of 24 million Pub Med publications.Using Amazon’s AWS computing resources and a network based,deep-learning framework,we identified 41 repurposable drugs（including dexamethasone,indomethacin,niclosamide,and toremifene）whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-Co V-2-infected human cells and data from ongoing clinical trials.Whereas this study by no means recommends specific drugs,it demonstrates a powerful deep-learning methodology to prioritize existing drugs for further investigation,which holds the potential to accelerate therapeutic development for COVID-19.