DTI-GP: Bayesian operations for drug-target interactions using deep kernel Gaussian processes

TL;DR

This paper introduces DTI-GP, a Bayesian deep kernel Gaussian process model that enhances drug-target interaction predictions by providing probabilistic insights, ranking, and rejection capabilities, outperforming existing methods.

Contribution

The paper presents a novel deep kernel Gaussian process architecture for DTI prediction that integrates neural embeddings and Bayesian operations for improved accuracy and interpretability.

Findings

Outperforms state-of-the-art DTI prediction methods

Enables Bayesian ranking and rejection schemes

Provides high-utility top-K selection and ranking

Abstract

Precise probabilistic information about drug-target interaction (DTI) predictions is vital for understanding limitations and boosting predictive performance. Gaussian processes (GP) offer a scalable framework to integrate state-of-the-art DTI representations and Bayesian inference, enabling novel operations, such as Bayesian classification with rejection, top-$K$ selection, and ranking. We propose a deep kernel learning-based GP architecture (DTI-GP), which incorporates a combined neural embedding module for chemical compounds and protein targets, and a GP module. The workflow continues with sampling from the predictive distribution to estimate a Bayesian precedence matrix, which is used in fast and accurate selection and ranking operations. DTI-GP outperforms state-of-the-art solutions, and it allows (1) the construction of a Bayesian accuracy-confidence enrichment score, (2) rejection schemes for improved enrichment, and (3) estimation and search for top-$K$ selections and ranking with high expected utility.