KANEL: Kolmogorov-Arnold Network Ensemble Learning Enables Early Hit Enrichment in High-Throughput Virtual Screening

TL;DR

KANEL is an ensemble learning workflow that improves early hit enrichment in virtual screening by combining interpretable Kolmogorov-Arnold Networks with other machine learning models trained on diverse molecular representations.

Contribution

It introduces KANEL, a novel ensemble method integrating KANs with popular ML models for better early hit prediction in virtual screening.

Findings

Enhanced early hit enrichment using KANEL

Combines multiple molecular representations for improved accuracy

Demonstrates effectiveness in high-throughput virtual screening

Abstract

Machine learning models of chemical bioactivity are increasingly used for prioritizing a small number of compounds in virtual screening libraries for experimental follow-up. In these applications, assessing model accuracy by early hit enrichment such as Positive Predicted Value (PPV) calculated for top N hits (PPV@N) is more appropriate and actionable than traditional global metrics such as AUC. We present KANEL, an ensemble workflow that combines interpretable Kolmogorov-Arnold Networks (KANs) with XGBoost, random forest, and multilayer perceptron models trained on complementary molecular representations (LillyMol descriptors, RDKit-derived descriptors, and Morgan fingerprints).