FSscore: A Machine Learning-based Synthetic Feasibility Score Leveraging Human Expertise
This work addresses a domain-specific problem for chemists and drug discovery researchers by providing a more accurate tool for prioritizing molecules, though it is incremental as it builds on existing methods with targeted fine-tuning.
The paper tackled the problem of assessing synthetic feasibility of molecules in chemistry and drug discovery by introducing FSscore, a machine learning-based score that leverages human expertise to rank structures by ease of synthesis, improving accuracy in differentiating hard and easy molecules.
Determining whether a molecule can be synthesized is crucial in chemistry and drug discovery, as it guides experimental prioritization and molecule ranking in de novo design tasks. Existing scoring approaches to assess synthetic feasibility struggle to extrapolate to new chemical spaces or fail to discriminate based on subtle differences such as chirality. This work addresses these limitations by introducing the Focused Synthesizability score~(FSscore), which uses machine learning to rank structures based on their relative ease of synthesis. First, a baseline trained on an extensive set of reactant-product pairs is established, which is then refined with expert human feedback tailored to specific chemical spaces. This targeted fine-tuning improves performance on these chemical scopes, enabling more accurate differentiation between molecules that are hard and easy to synthesize. The FSscore showcases how a human-in-the-loop framework can be utilized to optimize the assessment of synthetic feasibility for various chemical applications.