Finding Relevant Retrosynthetic Disconnections for Stereocontrolled Reactions.

Machine learning-driven computer-aided synthesis planning (CASP) tools have become important tools for idea generation in the design of complex molecule synthesis but do not adequately address the stereochemical features of the target compounds. A novel approach to automated extraction of templates used in CASP that includes stereochemical information included in the US Patent and Trademark Office (USPTO) and an internal AstraZeneca database containing reactions from Reaxys, Pistachio, and AstraZeneca electronic lab notebooks is implemented in the freely available AiZynthFinder software. Three hundred sixty-seven templates covering reagent- and substrate-controlled as well as stereospecific reactions were extracted from the USPTO, while 20,724 templates were from the AstraZeneca database. The performance of these templates in multistep CASP is evaluated for 936 targets from the ChEMBL database and an in-house selection of 791 AZ designs. The potential and limitations are discussed for four case studies from ChEMBL and examples of FDA-approved drugs.

[1]  Robert E. Ziegler,et al.  AiZynth impact on medicinal chemistry practice at AstraZeneca. , 2024, RSC medicinal chemistry.

[2]  B. Grzybowski,et al.  Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge. , 2024, Journal of the American Chemical Society.

[3]  O. Wiest,et al.  Interplay of Computation and Experiment in Enantioselective Catalysis: Rationalization, Prediction, and─Correction? , 2023, ACS Catalysis.

[4]  Wenjun Tang,et al.  Enantioselective Transformations in the Synthesis of Therapeutic Agents. , 2023, Chemical reviews.

[5]  Connor W. Coley,et al.  Data Sharing in Chemistry: Lessons Learned and a Case for Mandating Structured Reaction Data , 2023, J. Chem. Inf. Model..

[6]  O. Engkvist,et al.  AiZynthTrain: Robust, Reproducible, and Extensible Pipelines for Training Synthesis Prediction Models , 2023, J. Chem. Inf. Model..

[7]  Lewis H. Mervin,et al.  AI for drug design from explicit rules to deep learning , 2022, Artificial Intelligence in the Life Sciences.

[8]  Alain C. Vaucher,et al.  Machine intelligence for chemical reaction space , 2022, WIREs Computational Molecular Science.

[9]  Marwin H. S. Segler,et al.  Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks , 2022, J. Chem. Inf. Model..

[10]  Melissa A. Hardy,et al.  Strategic elements in computer-assisted retrosynthesis: A case study of the pupukeanane natural products. , 2021, Tetrahedron.

[11]  Connor W. Coley,et al.  The Open Reaction Database. , 2021, Journal of the American Chemical Society.

[12]  Shuan Chen,et al.  Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global Attention , 2021, JACS Au.

[13]  Esben Bjerrum,et al.  Chemformer: a pre-trained transformer for computational chemistry , 2021, Mach. Learn. Sci. Technol..

[14]  H. Waldmann,et al.  Dynamic Catalytic Highly Enantioselective 1,3‐Dipolar Cycloadditions , 2021, Angewandte Chemie.

[15]  Ola Engkvist,et al.  Fast prediction of distances between synthetic routes with deep learning , 2021, Mach. Learn. Sci. Technol..

[16]  O. Engkvist,et al.  Clustering of Synthetic Routes Using Tree Edit Distance , 2020, J. Chem. Inf. Model..

[17]  Piotr Dittwald,et al.  Computational planning of the synthesis of complex natural products , 2020, Nature.

[18]  Jean-Louis Reymond,et al.  Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates , 2020, Nature Communications.

[19]  R. Kempe,et al.  Transition-Metal-Catalyzed Reductive Amination Employing Hydrogen. , 2020, Chemical reviews.

[20]  Ola Engkvist,et al.  AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning , 2020, Journal of Cheminformatics.

[21]  I. Tetko,et al.  State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis , 2020, Nature Communications.

[22]  R. Koenigs,et al.  Artificial-Intelligence-Driven Organic Synthesis-En Route towards Autonomous Synthesis? , 2019, Angewandte Chemie.

[23]  Pieter P. Plehiers,et al.  A robotic platform for flow synthesis of organic compounds informed by AI planning , 2019, Science.

[24]  Connor W. Coley,et al.  RDChiral: An RDKit Wrapper for Handling Stereochemistry in Retrosynthetic Template Extraction and Application , 2019, J. Chem. Inf. Model..

[25]  Rebecca E. Meadows,et al.  Rapid virtual screening of enantioselective catalysts using CatVS , 2018, Nature Catalysis.

[26]  Christopher A. Hunter,et al.  Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction , 2018, ACS central science.

[27]  Connor W. Coley,et al.  Machine Learning in Computer-Aided Synthesis Planning. , 2018, Accounts of chemical research.

[28]  Sara Szymkuć,et al.  Chematica: A Story of Computer Code That Started to Think like a Chemist , 2018 .

[29]  D. Usanov,et al.  Dichotomy of Atom-Economical Hydrogen-Free Reductive Amidation vs Exhaustive Reductive Amination. , 2017, Organic letters.

[30]  Piotr Dittwald,et al.  Computer-Assisted Synthetic Planning: The End of the Beginning. , 2016, Angewandte Chemie.

[31]  Per-Ola Norrby,et al.  Prediction of Stereochemistry using Q2MM , 2016, Accounts of chemical research.

[32]  David R. J. Hose,et al.  Toward a More Holistic Framework for Solvent Selection , 2016 .

[33]  D. Plattner,et al.  Mechanistic investigations of the rhodium catalyzed propargylic CH activation. , 2014, Journal of the American Chemical Society.

[34]  F. Lovering,et al.  Escape from Flatland 2: complexity and promiscuity , 2013 .

[35]  M. Hahn,et al.  Extended-Connectivity Fingerprints , 2010, J. Chem. Inf. Model..

[36]  C. Humblet,et al.  Escape from flatland: increasing saturation as an approach to improving clinical success. , 2009, Journal of medicinal chemistry.

[37]  E. Balaraman,et al.  Mitsunobu and related reactions: advances and applications. , 2009, Chemical reviews.

[38]  Q. Xia,et al.  Advances in homogeneous and heterogeneous catalytic asymmetric epoxidation. , 2005, Chemical reviews.

[39]  David Adam.  Chemistry Nobel 2001 , 2001 .

[40]  M. Jung,et al.  Use of optically active cyclic N,N-dialkyl aminals in asymmetric induction. , 2000, Organic letters.

[41]  James B. Hendrickson,et al.  SYNGEN program for synthesis design: basic computing techniques , 1989, J. Chem. Inf. Comput. Sci..

[42]  S. Krishnan,et al.  Simulation and Evaluation of Chemical Synthesis - SECS: An Application of Artificial Intelligence Techniques , 1978, Artif. Intell..

[43]  A F Sanders,et al.  Empirical Explorations of SYNCHEM , 1977, Science.