APOSM: Pairwise preference learning improves generative small-molecule design
Preprint
Abstract
Small-molecule lead refinement is constrained by the cost of synthesizing and assaying candidates, making the surrogate models that prioritize compounds for experimental testing central to the design process. The reliability of such surrogates is limited by the noise and sparsity of screening measurements. We show that training the surrogate on pairwise comparisons between candidate molecules, rather than on absolute predicted scores, yields a substantially more reliable signal for active candidate selection in this regime. We develop APOSM, an active-learning algorithm that combines a fragment-based generator, a pairwise message-passing graph neural network surrogate, and probabilistic ranking inside a batched acquisition loop. On the Practical Molecular Optimization benchmark and a GPCR ligand rediscovery task, APOSM improves target attainment and sampling efficiency over unguided fragment-based optimization, the Graph-GA genetic algorithm, and a pointwise-regression ablation, with the largest gains on tasks where absolute scores are hardest to calibrate.Keywords
Funding Information
- Novo Nordisk Fonden (NNF23OC0081287)
- Novo Nordisk Fonden (NNF20OC0062606)
- Villum Fonden (40578)
- Villum Fonden (40516)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (310030M_204518)
This publication has 49 references indexed in Scilit:
- Extrapolation is not the same as interpolationMachine Learning, 2024
- Generative models for molecular discovery: Recent advances and challengesWIREs Computational Molecular Science, 2022
- How Much Does It Cost to Research and Develop a New Drug? A Systematic Review and AssessmentPharmacoEconomics, 2021
- Automated De Novo Drug Design: Are We Nearly There Yet?Angewandte Chemie, 2019
- Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settingsAdvanced Drug Delivery Reviews, 2012
- The cost of drug development: A systematic reviewHealth Policy, 2011
- De Novo Drug Design2010
- Best Practices for QSAR Model Development, Validation, and ExploitationMolecular Informatics, 2010
- Physiochemical drug properties associated with in vivo toxicological outcomesBioorganic & Medicinal Chemistry Letters, 2008
- f-dissimilarity: A generalization of the affinity of several distributionsAnnals of the Institute of Statistical Mathematics, 1978