Authors
Dominik Dekleva, Alexey Voronov, Jon Paul Janet, Albin Ekborg, Jure Borišek, Martina H Rambaher, Hannes H Loeffler
Published in
Chemical science. Volume 17. Issue 20. Pages 10015-10028. May 27, 2026. Epub Apr 07, 2026.
Abstract
Generating novel, drug-like molecules with realistic synthetic pathways is an essential goal in computer-aided drug discovery, yet generative models often lack synthesis awareness, resulting in compounds that are difficult or impossible to produce. To overcome this limitation, models must optimize not only molecular properties but also synthetic feasibility, which is not fully meaningful unless it incorporates specific factors like preferred reactions and available starting materials. Moreover, generating singleton compounds without respecting possibilities for parallel synthesis greatly increases the cost and complexity of synthesizing multiple proposed molecules. In practice, medicinal chemistry workflows group compounds into families sharing coherent synthetic strategies and common intermediates, enabling efficient parallel and automated synthesis. Here we introduce SynthSense, a reinforcement learning framework that guides molecular design using retrosynthetic feedback. SynthSense offers extrinsic reward functions that assess molecule-level feasibility, such as adherence to available building blocks and preferred reactions, or synthesizability via predefined synthetic routes. It also implements intrinsic, batch-level functions that enforce route coherence across generated compounds. In silico multi-parameter validation demonstrated clear advantages over naïve, synthesis-unaware baselines: SynthSense generated 6.2-fold more synthetically feasible hits than control trained without SynthSense, achieved a 727-fold enrichment in hits synthesizable with a predefined synthetic route, and populated 4.1-fold more virtual parallel synthesis plates. These results demonstrate that by reframing synthesizability from a mere constraint into an active design objective, generative AI can better support the realities of modern medicinal chemistry by enabling personalized synthetic design, accelerating SAR exploration and aligning more naturally with automated parallel synthesis workflows.
PMID:
41953480
Bibliographic data and abstract were imported from PubMed on 16 Sep 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 3
- Comments 0