AI RESEARCH
KANEL: Kolmogorov-Arnold Network Ensemble Learning Enables Early Hit Enrichment in High-Throughput Virtual Screening
arXiv CS.LG
•
ArXi:2603.25755v1 Announce Type: cross 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) is appropriate and actionable than traditional global metrics such as