A Graph-convolutional Neural Network Model for the Prediction of Chemical Reactivity

Overview

Journal Chem Sci

Publisher Royal Society of Chemistry

Specialty Chemistry

Date 2019 Feb 13

PMID 30746086

Citations 137

Authors

Connor W Coley

Wengong Jin

Luke Rogers

Timothy F Jamison

Tommi S Jaakkola

William H Green

Regina Barzilay

Klavs F Jensen

Affiliations

Soon will be listed here.

Abstract

We present a supervised learning approach to predict the products of organic reactions given their reactants, reagents, and solvent(s). The prediction task is factored into two stages comparable to manual expert approaches: considering possible sites of reactivity and evaluating their relative likelihoods. By training on hundreds of thousands of reaction precedents covering a broad range of reaction types from the patent literature, the neural model makes informed predictions of chemical reactivity. The model predicts the major product correctly over 85% of the time requiring around 100 ms per example, a significantly higher accuracy than achieved by previous machine learning approaches, and performs on par with expert chemists with years of formal training. We gain additional insight into predictions the design of the neural model, revealing an understanding of chemistry qualitatively consistent with manual approaches.

Citing Articles

Generative Deep Learning-Based Efficient Design of Organic Molecules with Tailored Properties.

Han M, Joung J, Jeong M, Choi D, Park S ACS Cent Sci. 2025; 11(2):219-227.

PMID: 40028364 PMC: 11869130. DOI: 10.1021/acscentsci.4c00656.

Application of Transformers to Chemical Synthesis.

Jin D, Liang Y, Xiong Z, Yang X, Wang H, Zeng J Molecules. 2025; 30(3).

PMID: 39942600 PMC: 11821105. DOI: 10.3390/molecules30030493.

Chemically Informed Deep Learning for Interpretable Radical Reaction Prediction.

Tavakoli M, Chiu Y, Carlton A, Van Vranken D, Baldi P J Chem Inf Model. 2025; 65(3):1228-1242.

PMID: 39871741 PMC: 11815866. DOI: 10.1021/acs.jcim.4c01901.

A review of large language models and autonomous agents in chemistry.

Ramos M, Collison C, White A Chem Sci. 2025; 16(6):2514-2572.

PMID: 39829984 PMC: 11739813. DOI: 10.1039/d4sc03921a.

Applying statistical modeling strategies to sparse datasets in synthetic chemistry.

Haas B, Kalyani D, Sigman M Sci Adv. 2025; 11(1):eadt3013.

PMID: 39742471 PMC: 11691635. DOI: 10.1126/sciadv.adt3013.

References

Coley C, Green W, Jensen K . Machine Learning in Computer-Aided Synthesis Planning. Acc Chem Res. 2018; 51(5):1281-1289. DOI: 10.1021/acs.accounts.8b00087. View

Segler M, Waller M . Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction. Chemistry. 2017; 23(25):5966-5971. DOI: 10.1002/chem.201605499. View

Engkvist O, Norrby P, Selmi N, Lam Y, Peng Z, Sherer E . Computational prediction of chemical reactions: current status and outlook. Drug Discov Today. 2018; 23(6):1203-1218. DOI: 10.1016/j.drudis.2018.02.014. View

Warr W . A Short Review of Chemical Reaction Database Systems, Computer-Aided Synthesis Design, Reaction Prediction and Synthetic Feasibility. Mol Inform. 2016; 33(6-7):469-76. DOI: 10.1002/minf.201400052. View

Perera D, Tucker J, Brahmbhatt S, Helal C, Chong A, Farrell W . A platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flow. Science. 2018; 359(6374):429-434. DOI: 10.1126/science.aap9112. View

Coley C, Barzilay R, Jaakkola T, Green W, Jensen K . Prediction of Organic Reaction Outcomes Using Machine Learning. ACS Cent Sci. 2017; 3(5):434-443. PMC: 5445544. DOI: 10.1021/acscentsci.7b00064. View

Szymkuc S, Gajewska E, Klucznik T, Molga K, Dittwald P, Startek M . Computer-Assisted Synthetic Planning: The End of the Beginning. Angew Chem Int Ed Engl. 2016; 55(20):5904-37. DOI: 10.1002/anie.201506101. View

Ahneman D, Estrada J, Lin S, Dreher S, Doyle A . Predicting reaction performance in C-N cross-coupling using machine learning. Science. 2018; 360(6385):186-190. DOI: 10.1126/science.aar5169. View

Christ C, Zentgraf M, Kriegl J . Mining electronic laboratory notebooks: analysis, retrosynthesis, and reaction based enumeration. J Chem Inf Model. 2012; 52(7):1745-56. DOI: 10.1021/ci300116p. View

10.

Law J, Zsoldos Z, Simon A, Reid D, Liu Y, Khew S . Route Designer: a retrosynthetic analysis tool utilizing automated retrosynthetic rule generation. J Chem Inf Model. 2009; 49(3):593-602. DOI: 10.1021/ci800228y. View

11.

Lin S, Dikler S, Blincoe W, Ferguson R, Sheridan R, Peng Z . Mapping the dark space of chemical reactions with extended nanomole synthesis and MALDI-TOF MS. Science. 2018; 361(6402). DOI: 10.1126/science.aar6236. View

12.

Kayala M, Baldi P . ReactionPredictor: prediction of complex chemical reactions at the mechanistic level using machine learning. J Chem Inf Model. 2012; 52(10):2526-40. DOI: 10.1021/ci3003039. View

13.

Wei J, Duvenaud D, Aspuru-Guzik A . Neural Networks for the Prediction of Organic Chemistry Reactions. ACS Cent Sci. 2016; 2(10):725-732. PMC: 5084081. DOI: 10.1021/acscentsci.6b00219. View

14.

Socorro I, Taylor K, Goodman J . ROBIA: a reaction prediction program. Org Lett. 2005; 7(16):3541-4. DOI: 10.1021/ol0512738. View

15.

Kayala M, Azencott C, Chen J, Baldi P . Learning to predict chemical reactions. J Chem Inf Model. 2011; 51(9):2209-22. PMC: 3193800. DOI: 10.1021/ci200207y. View

16.

Shemetulskis N, Weininger D, Blankley C, Yang J, Humblet C . Stigmata: an algorithm to determine structural commonalities in diverse datasets. J Chem Inf Comput Sci. 1996; 36(4):862-71. DOI: 10.1021/ci950169+. View

17.

Buitrago Santanilla A, Regalado E, Pereira T, Shevlin M, Bateman K, Campeau L . Organic chemistry. Nanomole-scale high-throughput chemistry for the synthesis of complex molecules. Science. 2015; 347(6217):49-53. DOI: 10.1126/science.1259203. View

18.

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