Modeling Pharmacological Effects with Multi-Relation Unsupervised Graph Embedding

• Autor(a) principal: Dehua Chen
• Data de Publicação: 2020
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Institucional da UFMG
• Texto Completo: http://hdl.handle.net/1843/42300
• topic: Drug Repositioning; Graph Embedding; Node Embedding; Drug Repurposing; Computação – Teses; Aprendizado do computador – Teses; Aprendizado de Representações – Teses

Drug repositioning (aka repurposing) can be defined as renewing failed drugs (proved safety but failed to show efficacy for their primary indication) and expanding successful ones by developing new therapeutic uses that are beyond their original uses or initial approved indications. Repositioned drugs account for approximately 30\% of the US Food and Drug Administration (FDA) approved drugs in recent years. A repositioned drug uses de-risked compounds, going directly to preclinical testing and clinical trials, thus providing inexpensive alternatives to the costly pipeline associated with the development of new drugs. A pharmacological effect of a drug on cells, organs and systems refers to the specific biochemical interaction produced by a drug substance, which is called its mechanism of action. There are several approaches for novel repositioning opportunities identification, such as signature matching, molecular docking and genetic association in literature. In this work, we present a novel method based on a multi-relation unsupervised graph embedding model that learns latent representations for drugs (mechanisms of action) and diseases so that the distance between these representations reveals repositioning opportunities. Once representations for drugs and diseases are obtained we learn the likelihood of new links (that is, new indications) between drugs and diseases. Known drug indications are used for learning a model that predicts potential indications. Compared with existing unsupervised graph embedding methods our method shows superior prediction performance in terms of area under the ROC curve, and we present examples of repositioning opportunities found on recent biomedical literature that were also predicted by our method.