MOZAIC: Compound Growth via In Silico Reactions and Global Optimization using Conformational Space Annealing

Fragment-based drug discovery (FBDD) efficiently explores chemical space by combining small molecular fragments. Advances in computational methods are accelerating the development of algorithm- and AI-based approaches in FBDD. However, it should be noted that certain methods do not provide synthetic pathways to obtain the proposed compounds. Consequently, these molecules might not be synthesized easily.

We present MOZAIC, a reaction-based fragment-growing framework that combines in silico reactions with Conformational Space Annealing for global molecular optimization. MOZAIC generates compounds through SMARTS-defined organic reactions, preserving reaction histories and providing putative synthetic routes. Across benchmark targets, MOZAIC produced chemically diverse molecules with balanced improvements in predicted binding affinity, drug-likeness, and synthetic accessibility. Compared with existing fragment-growing and generative approaches, MOZAIC achieved broad scaffold coverage while maintaining target-directed optimization. Its modular objective function also enabled alternative design goals, such as improving predicted solubility while maintaining binding affinity.

MOZAIC is available at https://github.com/kucm-lsbi/MOZAIC.

Supplementary data are available at Bioinformatics online.