Insights into performance evaluation of com-pound-protein interaction prediction methods

TL;DR

This study critically evaluates machine learning methods for predicting compound-protein interactions, highlighting issues in experimental design, and introduces a kernel-based approach that outperforms existing models in accuracy and real-world screening applications.

Contribution

The paper identifies key overlooked factors affecting CPI predictor performance and proposes a simple kernel-based method that surpasses state-of-the-art models in prediction accuracy.

Findings

Similarity between training and test data significantly impacts performance estimates.

Random negative example generation yields better generalization than complex strategies.

Kernel-based approach outperforms CPI-NN in predictive accuracy.

Abstract

Motivation: Machine learning based prediction of compound-protein interactions (CPIs) is important for drug design, screening and repurposing studies and can improve the efficiency and cost-effectiveness of wet lab assays. Despite the publication of many research papers reporting CPI predictors in the recent years, we have observed a number of fundamental issues in experiment design that lead to over optimistic estimates of model performance. Results: In this paper, we analyze the impact of several important factors affecting generalization perfor-mance of CPI predictors that are overlooked in existing work: 1. Similarity between training and test examples in cross-validation 2. The strategy for generating negative examples, in the absence of experimentally verified negative examples. 3. Choice of evaluation protocols and performance metrics and their alignment with real-world use of CPI predictors in screening large compound libraries. Using both an existing state-of-the-art method (CPI-NN) and a proposed kernel based approach, we have found that assessment of predictive performance of CPI predictors requires careful con-trol over similarity between training and test examples. We also show that random pairing for gen-erating synthetic negative examples for training and performance evaluation results in models with better generalization performance in comparison to more sophisticated strategies used in existing studies. Furthermore, we have found that our kernel based approach, despite its simple design, exceeds the prediction performance of CPI-NN. We have used the proposed model for compound screening of several proteins including SARS-CoV-2 Spike and Human ACE2 proteins and found strong evidence in support of its top hits. Availability: Code and raw experimental results available at https://github.com/adibayaseen/HKRCPI Contact: Fayyaz.minhas@warwick.ac.uk