Identification of bioactive compounds with popular single-atom modifications: comprehensive analysis and implications for compound design

Abstract

The extensive bioactivity data available in public databases, such as ChEMBL, has facilitated in-depth structure-activity relationship (SAR) analyses, which are essential for understanding the impact of molecular modifications on biological activity. A central strategy in SAR analysis is the assessment of molecular similarity. Several approaches preferred by medicinal chemists have been developed to efficiently capture structurally related compounds on a large scale. Represented as a popular molecular editing strategy in hit-to-lead and lead optimization processes, we previously introduced four types of single-atom modifications (SAMs) and conducted a systematic analysis of their application in compound design. In this study, we expanded the analysis to cover 10 common SAMs, including carbon-nitrogen (N↔C), O↔C, N↔O, S↔O, as well as simpler modifications such as OH↔H, CH₃↔H, and halogen-hydrogen (F, Cl, Br, I ↔ H) exchanges. Leveraging high-confidence bioactivity data from ChEMBL (version 34), we assembled the largest dataset of SAM pairs to date, comprising 374,979 pairs. Following an evaluation of the frequency of these SAM types in medicinal chemistry, we focused on SAM-induced activity cliffs (ACs), yielding over 7,400 ACs involving SAMs, substantially expanding the current knowledgebase of ACs associated with single-atom changes. Furthermore, structural analysis of these ACs, supported by experimental data, provides critical insights into the role of single-atom modifications in modulating compound activity, offering practical guidance for the structure-based optimization of molecular properties in drug development. As a result, we are providing open access to all identified ACs along with their associated structural information.