CA-DEL: Construction and Application of an Intelligent DEL Database for Anti-Cancer Drug Discovery

Hemutian, Hanqun Cao, Cheng Tan, Zijun Gao, Xiaojun Yao, Chunbin Gu, Pheng-Ann Heng

Keywords: DNA-Encoded Library (DEL), Drug Discovery, Anti-Cancer, Database, Cheminformatics

Abstract: The success of machine learning in drug discovery hinges on learning the relationship between a chemical structure and its biological activity. While DNA-Encoded Library (DEL) technology can generate the massive datasets required for this task, its primary signal---sequencing read counts---is an indirect and often noisy proxy for true molecular binding affinity. To address the scarcity of public benchmarks for developing robust models that can overcome this data challenge, we introduce CA-DEL. CA-DEL is a multi-dimensional public benchmark featuring screens against three homologous carbonic anhydrase isoforms. Notably, it is the first public DEL dataset to integrate both 2D chemical structures and pre-computed 3D protein-ligand conformations. Crucially, CA-DEL includes a validation set with experimentally determined binding affinities ($K_i$ values). This unique feature enables the direct evaluation of a model's ability to predict true biological activity, rather than simply modeling the noisy enrichment signal.

Primary Area: datasets and benchmarks

Submission Number: 3981