FSscore: A Personalized Machine Learning‐Based Synthetic Feasibility Score
Open Access
- 18 October 2024
- journal article
- research article
- Published by Wiley in Chemistry–Methods
- Vol. 4 (11)
Abstract
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.Keywords
Funding Information
- NCCR Catalysis
This publication has 33 references indexed in Scilit:
- Fake it until you make it? Generative de novo design and virtual screening of synthesizable moleculesCurrent Opinion in Structural Biology, 2023
- Deep generative models for 3D molecular structureCurrent Opinion in Structural Biology, 2023
- Organic Compound Synthetic Accessibility Prediction Based on the Graph Attention MechanismJournal of Chemical Information and Modeling, 2022
- RetroGNN: Fast Estimation of Synthesizability for Virtual Screening and De Novo Design by Learning from Slow Retrosynthesis SoftwareJournal of Chemical Information and Modeling, 2022
- Generative models for molecular discovery: Recent advances and challengesWIREs Computational Molecular Science, 2022
- REINVENT 2.0: An AI Tool for De Novo Drug DesignJournal of Chemical Information and Modeling, 2020
- Evolutionary Multi-objective Design of SARS-CoV-2 Protease Inhibitor Candidates2020
- The Synthesizability of Molecules Proposed by Generative ModelsJournal of Chemical Information and Modeling, 2020
- Estimation of the size of drug-like chemical space based on GDB-17 dataJournal of Computer-Aided Molecular Design, 2013
- Virtual screening—an overviewDrug Discovery Today, 1998