aiqbench analysis
OPDiv addresses the critical optimization challenge of selecting top-K diverse compounds from large virtual screening datasets, balancing high-scoring candidates with structural variety through integer programming. This method serves as a robust benchmark for evaluating structure-based or ligand-based pipelines and generative models in drug discovery contexts. By treating compound selection as a constrained optimization task rather than a simple ranking problem, the algorithm ensures efficient identification of optimal subsets under specific diversity thresholds.
OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds
arXiv:2609.28665v1 Announce Type: new Abstract: A virtual screening campaign may produce thousands of promising candidates, but only a small number can be purchased, synthesized, or tested. The practical question is how to select a set of compounds that both rank well and are diverse enough: this poses a genuine tradeoff, where selecting the highest-scoring molecules yields limited diversity, while diversity selection sacrifices some well-scoring molecules. We introduce OPDiv, a diversity selection and evaluation algorithm solving this tradeoff by finding an optimal subset of molecules using integer optimization. We demonstrate the selection algorithm in practice with fingerprint distance, shape and electrostatic diversity and compare the resulting diversity spectra. We argue that virtual screening is not merely a ranking problem, but also an implicit constrained optimization task: when redundant chemotypes are undesirable, pipelines should be compared based on the top-k compound selections satisfying the desired diversity constraints. OPDiv makes it possible to find the optimal compound set under a given diversity threshold efficiently and serves as a fair benchmark of the best diverse selection achievable by a given structure-based or ligand-based virtual screening pipeline, molecular search or generative model.
Abstract:A virtual screening campaign may produce thousands of promising candidates, but only a small number can be purchased, synthesized, or tested. The practical question is how to select a set of compounds that both rank well and are diverse enough: this poses a genuine tradeoff, where selecting the highest-scoring molecules yields limited diversity, while diversity selection sacrifices some well-scoring molecules. We introduce OPDiv, a diversity selection and evaluation algorithm solving this tradeoff by finding an optimal subset of molecules using integer optimization. We demonstrate the selection algorithm in practice with fingerprint distance, shape and electrostatic diversity and compare the resulting diversity spectra. We argue that virtual screening is not merely a ranking problem, but also an implicit constrained optimization task: when redundant chemotypes are undesirable, pipelines should be compared based on the top-k compound selections satisfying the desired diversity constraints. OPDiv makes it possible to find the optimal compound set under a given diversity threshold efficiently and serves as a fair benchmark of the best diverse selection achievable by a given structure-based or ligand-based virtual screening pipeline, molecular search or generative model.
12 pages, 3 figures. Code: this https URL
Machine Learning (cs.LG)
arXiv:2609.28665 [cs.LG]
(or arXiv:2609.28665v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.28665 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 284 words
Related coverage
Mastering Agentic Techniques: AI Agent Customization
NVIDIA · May 20, 2026
Modernizing and scaling support operations with generative AI on AWS
AWS · Sep 2, 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026
The art and science of hyperparameter optimization on Amazon Nova Forge
AWS · Jun 2, 2026