AGATHA: Automatic Graph-mining And Transformer based Hypothesis generation Approach

TL;DR

AGATHA is a deep-learning system that leverages graph mining and transformers to predict plausible biomedical hypotheses, enabling earlier insights in drug discovery and research direction identification.

Contribution

It introduces a novel data-driven hypothesis generation approach combining graph mining and transformer models, validated across biomedical sub-domains and relationship types.

Findings

Achieves best-in-class performance on established benchmarks.

Successfully predicts connections introduced after 2015 using prior data.

Demonstrates high recommendation scores across multiple biomedical subdomains.

Abstract

Medical research is risky and expensive. Drug discovery, as an example, requires that researchers efficiently winnow thousands of potential targets to a small candidate set for more thorough evaluation. However, research groups spend significant time and money to perform the experiments necessary to determine this candidate set long before seeing intermediate results. Hypothesis generation systems address this challenge by mining the wealth of publicly available scientific information to predict plausible research directions. We present AGATHA, a deep-learning hypothesis generation system that can introduce data-driven insights earlier in the discovery process. Through a learned ranking criteria, this system quickly prioritizes plausible term-pairs among entity sets, allowing us to recommend new research directions. We massively validate our system with a temporal holdout wherein we predict connections first introduced after 2015 using data published beforehand. We additionally explore biomedical sub-domains, and demonstrate AGATHA's predictive capacity across the twenty most popular relationship types. This system achieves best-in-class performance on an established benchmark, and demonstrates high recommendation scores across subdomains. Reproducibility: All code, experimental data, and pre-trained models are available online: sybrandt.com/2020/agatha