Synthetic feasibility of compounds generated with de novo approaches is one of the main issues, which may limit their applicability. Many of the de novo generation approaches do not address this issue. Here, we studied the recently implemented chemically reasonable mutations approach (CReM) and the ways how one could indirectly control synthetic complexity of generated compounds and how this affected the target scores for Guacamol benchmark tasks. We found a clear trade-off between synthetic complexity and target scores and demonstrated that CReM-based solutions were competitive to reference approaches, which were explicitly biased by synthetic feasibility of generated compounds.

Institute of Molecular and Translational Medicine Faculty of Medicine and Dentistry Palacky University and University Hospital in Olomouc Hnevotinska 5 77900 Olomouc Czech Republic

References provided by Crossref.org

Benchmarks for interpretation of QSAR models