Retrosynthetic Accessibility Score (RAscore) - Rapid Machine Learned Synthesizability Classification from AI Driven Retrosynthetic Planning

Overview

Journal Chem Sci

Publisher Royal Society of Chemistry

Specialty Chemistry

Date 2021 Jun 24

PMID 34164104

Citations 34

Authors

Amol Thakkar

Veronika Chadimova

Esben Jannik Bjerrum

Ola Engkvist

Jean-Louis Reymond

Affiliations

Soon will be listed here.

Abstract

Computer aided synthesis planning (CASP) is part of a suite of artificial intelligence (AI) based tools that are able to propose synthesis routes to a wide range of compounds. However, at present they are too slow to be used to screen the synthetic feasibility of millions of generated or enumerated compounds before identification of potential bioactivity by virtual screening (VS) workflows. Herein we report a machine learning (ML) based method capable of classifying whether a synthetic route can be identified for a particular compound or not by the CASP tool AiZynthFinder. The resulting ML models return a retrosynthetic accessibility score (RAscore) of any molecule of interest, and computes at least 4500 times faster than retrosynthetic analysis performed by the underlying CASP tool. The RAscore should be useful for pre-screening millions of virtual molecules from enumerated databases or generative models for synthetic accessibility and produce higher quality databases for virtual screening of biological activity.

Citing Articles

Molecular optimization using a conditional transformer for reaction-aware compound exploration with reinforcement learning.

Nakamura S, Yasuo N, Sekijima M Commun Chem. 2025; 8(1):40.

PMID: 39922979 PMC: 11807120. DOI: 10.1038/s42004-025-01437-x.

Accurate Dehydrogenation Enthalpies Dataset for Liquid Organic Hydrogen Carriers.

Harb H, Elliott S, Ward L, Foster I, Klippenstein S, Curtiss L Sci Data. 2025; 12(1):171.

PMID: 39881140 PMC: 11779890. DOI: 10.1038/s41597-025-04468-0.

Simple User-Friendly Reaction Format.

Nippa D, Muller A, Atz K, Konrad D, Grether U, Martin R Mol Inform. 2025; 44(1):e202400361.

PMID: 39846425 PMC: 11755691. DOI: 10.1002/minf.202400361.

Development of Drug-Induced Gene Expression Ranking Analysis (DIGERA) and Its Application to Virtual Screening for Poly (ADP-Ribose) Polymerase 1 Inhibitor.

Cho H, No K, Lim H Int J Mol Sci. 2025; 26(1.

PMID: 39796080 PMC: 11720423. DOI: 10.3390/ijms26010224.

Comparison of new secondgeneration H1 receptor blockers with some molecules; a study involving DFT, molecular docking, ADMET, biological target and activity.

Unsal V, Oner E, Yildiz R, Mert B BMC Chem. 2025; 19(1):4.

PMID: 39755645 PMC: 11700471. DOI: 10.1186/s13065-024-01371-4.

References

Ruddigkeit L, van Deursen R, Blum L, Reymond J . Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J Chem Inf Model. 2012; 52(11):2864-75. DOI: 10.1021/ci300415d. View

Brown N, Fiscato M, Segler M, Vaucher A . GuacaMol: Benchmarking Models for de Novo Molecular Design. J Chem Inf Model. 2019; 59(3):1096-1108. DOI: 10.1021/acs.jcim.8b00839. View

Irwin J, Sterling T, Mysinger M, Bolstad E, Coleman R . ZINC: a free tool to discover chemistry for biology. J Chem Inf Model. 2012; 52(7):1757-68. PMC: 3402020. DOI: 10.1021/ci3001277. View

Gao W, Coley C . The Synthesizability of Molecules Proposed by Generative Models. J Chem Inf Model. 2020; 60(12):5714-5723. DOI: 10.1021/acs.jcim.0c00174. View

Blaschke T, Arus-Pous J, Chen H, Margreitter C, Tyrchan C, Engkvist O . REINVENT 2.0: An AI Tool for De Novo Drug Design. J Chem Inf Model. 2020; 60(12):5918-5922. DOI: 10.1021/acs.jcim.0c00915. View

Mendez-Lucio O, Baillif B, Clevert D, Rouquie D, Wichard J . De novo generation of hit-like molecules from gene expression signatures using artificial intelligence. Nat Commun. 2020; 11(1):10. PMC: 6941972. DOI: 10.1038/s41467-019-13807-w. View

Baber J, Feher M . Predicting synthetic accessibility: application in drug discovery and development. Mini Rev Med Chem. 2004; 4(6):681-92. DOI: 10.2174/1389557043403765. View

Corey E, Long A, Rubenstein S . Computer-assisted analysis in organic synthesis. Science. 1985; 228(4698):408-18. DOI: 10.1126/science.3838594. View

Gaulton A, Hersey A, Nowotka M, Bento A, Chambers J, Mendez D . The ChEMBL database in 2017. Nucleic Acids Res. 2016; 45(D1):D945-D954. PMC: 5210557. DOI: 10.1093/nar/gkw1074. View

10.

Genheden S, Thakkar A, Chadimova V, Reymond J, Engkvist O, Bjerrum E . AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. J Cheminform. 2020; 12(1):70. PMC: 7672904. DOI: 10.1186/s13321-020-00472-1. View

11.

Schneider P, Walters W, Plowright A, Sieroka N, Listgarten J, Goodnow Jr R . Rethinking drug design in the artificial intelligence era. Nat Rev Drug Discov. 2019; 19(5):353-364. DOI: 10.1038/s41573-019-0050-3. View

12.

Polykovskiy D, Zhebrak A, Sanchez-Lengeling B, Golovanov S, Tatanov O, Belyaev S . Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models. Front Pharmacol. 2021; 11:565644. PMC: 7775580. DOI: 10.3389/fphar.2020.565644. View

13.

Chevillard F, Kolb P . SCUBIDOO: A Large yet Screenable and Easily Searchable Database of Computationally Created Chemical Compounds Optimized toward High Likelihood of Synthetic Tractability. J Chem Inf Model. 2015; 55(9):1824-35. DOI: 10.1021/acs.jcim.5b00203. View

14.

Segler M, Preuss M, Waller M . Planning chemical syntheses with deep neural networks and symbolic AI. Nature. 2018; 555(7698):604-610. DOI: 10.1038/nature25978. View

15.

Struble T, Alvarez J, Brown S, Chytil M, Cisar J, DesJarlais R . Current and Future Roles of Artificial Intelligence in Medicinal Chemistry Synthesis. J Med Chem. 2020; 63(16):8667-8682. PMC: 7457232. DOI: 10.1021/acs.jmedchem.9b02120. View

16.

Mikulak-Klucznik B, Golebiowska P, Bayly A, Popik O, Klucznik T, Szymkuc S . Computational planning of the synthesis of complex natural products. Nature. 2020; 588(7836):83-88. DOI: 10.1038/s41586-020-2855-y. View

17.

Schwaller P, Laino T, Gaudin T, Bolgar P, Hunter C, Bekas C . Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction. ACS Cent Sci. 2019; 5(9):1572-1583. PMC: 6764164. DOI: 10.1021/acscentsci.9b00576. View

18.

Sheridan R, Zorn N, Sherer E, Campeau L, Chang C, Cumming J . Modeling a crowdsourced definition of molecular complexity. J Chem Inf Model. 2014; 54(6):1604-16. DOI: 10.1021/ci5001778. View

19.

Rogers D, Hahn M . Extended-connectivity fingerprints. J Chem Inf Model. 2010; 50(5):742-54. DOI: 10.1021/ci100050t. View

20.

Ertl P, Schuffenhauer A . Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J Cheminform. 2010; 1(1):8. PMC: 3225829. DOI: 10.1186/1758-2946-1-8. View