A Comparative Analysis of the Ensemble Methods for Drug Design

TL;DR

This paper compares various ensemble machine learning methods with basic algorithms for QSAR-based drug design, demonstrating that ensemble models, while not always superior individually, enhance predictive reliability when combined.

Contribution

It introduces a comprehensive comparative analysis of 57 ensemble and basic algorithms on multiple datasets, proposing a complex ensemble technique for drug activity prediction.

Findings

Ensemble models improve prediction reliability when combined.

Basic algorithms alone did not perform as well as ensembles.

The study provides a framework for complex ensemble model construction.

Abstract

Quantitative structure-activity relationship (QSAR) is a computer modeling technique for identifying relationships between the structural properties of chemical compounds and biological activity. QSAR modeling is necessary for drug discovery, but it has many limitations. Ensemble-based machine learning approaches have been used to overcome limitations and generate reliable predictions. Ensemble learning creates a set of diverse models and combines them. In our comparative analysis, each ensemble algorithm was paired with each of the basic algorithms, but the basic algorithms were also investigated separately. In this configuration, 57 algorithms were developed and compared on 4 different datasets. Thus, a technique for complex ensemble method is proposed that builds diversified models and integrates them. The proposed individual models did not show impressive results as a unified model, but it was considered the most important predictor when combined. We assessed whether ensembles always give better results than individual algorithms. The Python code written to get experimental results in this article has been uploaded to Github (https://github.com/rifqat/Comparative-Analysis).