APEX: Approximate-but-exhaustive search for ultra-large combinatorial synthesis libraries

TL;DR

APEX is a neural network-based method that enables near-exhaustive virtual screening of ultra-large chemical libraries by predicting compound scores rapidly, improving the identification of top candidates in drug discovery.

Contribution

This work introduces APEX, a novel approximate-but-exhaustive search protocol that leverages neural networks for fast, near-complete enumeration of large chemical libraries, outperforming existing methods.

Findings

APEX achieves full enumeration of 10 million compounds in under a minute.

APEX accurately retrieves top-scoring compounds compared to alternative algorithms.

APEX demonstrates strong performance in both accuracy and runtime across benchmark datasets.

Abstract

Make-on-demand combinatorial synthesis libraries (CSLs) like Enamine REAL have significantly enabled drug discovery efforts. However, their large size presents a challenge for virtual screening, where the goal is to identify the top compounds in a library according to a computational objective (e.g., optimizing docking score) subject to computational constraints under a limited computational budget. For current library sizes -- numbering in the tens of billions of compounds -- and scoring functions of interest, a routine virtual screening campaign may be limited to scoring fewer than 0.1% of the available compounds, leaving potentially many high scoring compounds undiscovered. Furthermore, as constraints (and sometimes objectives) change during the course of a virtual screening campaign, existing virtual screening algorithms typically offer little room for amortization. We propose the approximate-but-exhaustive search protocol for CSLs, or APEX. APEX utilizes a neural network surrogate that exploits the structure of CSLs in the prediction of objectives and constraints to make full enumeration on a consumer GPU possible in under a minute, allowing for exact retrieval of approximate top-$k$ sets. To demonstrate APEX's capabilities, we develop a benchmark CSL comprised of more than 10 million compounds, all of which have been annotated with their docking scores on five medically relevant targets along with physicohemical properties measured with RDKit such that, for any objective and set of constraints, the ground truth top-$k$ compounds can be identified and compared against the retrievals from any virtual screening algorithm. We show APEX's consistently strong performance both in retrieval accuracy and runtime compared to alternative methods.