Bayesian tensor factorization for predicting clinical outcomes using integrated human genetics evidence

TL;DR

This paper demonstrates that integrating multiple types of human genetics evidence via Bayesian tensor factorization modestly improves the prediction of clinical outcomes for drug targets, offering insights into the relative importance of different genetic data types.

Contribution

The study revisits tensor factorization for clinical outcome prediction by integrating diverse human genetics evidence, showing improved accuracy and providing insights into data type importance.

Findings

Models with all genetics evidence outperform single evidence models.

Different types of genetics evidence have varying predictive power.

Bayesian tensor factorization effectively integrates multiple data sources.

Abstract

The approval success rate of drug candidates is very low with the majority of failure due to safety and efficacy. Increasingly available high dimensional information on targets, drug molecules and indications provides an opportunity for ML methods to integrate multiple data modalities and better predict clinically promising drug targets. Notably, drug targets with human genetics evidence are shown to have better odds to succeed. However, a recent tensor factorization-based approach found that additional information on targets and indications might not necessarily improve the predictive accuracy. Here we revisit this approach by integrating different types of human genetics evidence collated from publicly available sources to support each target-indication pair. We use Bayesian tensor factorization to show that models incorporating all available human genetics evidence (rare disease, gene burden, common disease) modestly improves the clinical outcome prediction over models using single line of genetics evidence. We provide additional insight into the relative predictive power of different types of human genetics evidence for predicting the success of clinical outcomes.