A Caltech Library Service

Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions

Maser, Michael R. and Cui, Alexander Y. and Ryou, Serim and DeLano, Travis J. and Yue, Yisong and Reisman, Sarah E. (2021) Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions. Journal of Chemical Information and Modeling, 61 (1). pp. 156-166. ISSN 1549-9596.

[img] PDF - Submitted Version
Creative Commons Attribution Non-commercial No Derivatives.

[img] PDF (Data preparation and reaction dictionaries; computational details and hyperparameters; optimized classifier trellises, mutual information matrices, and reaction dictionaries for all data sets) - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C–N couplings, as well as Pauson–Khand reactions. String, descriptor, and graph encodings were tested as input representations, and models were trained to predict the set of conditions used in a reaction as a binary vector. Unique reagent dictionaries categorized by expert-crafted reaction roles were constructed for each data set, leading to context-aware predictions. We find that relational graph convolutional networks and gradient-boosting machines are very effective for this learning task, and we disclose a novel reaction-level graph attention operation in the top-performing model.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
DeLano, Travis J.0000-0002-2052-611X
Yue, Yisong0000-0001-9127-1989
Reisman, Sarah E.0000-0001-8244-9300
Alternate Title:Multi-Label Classification Models for the Prediction of Cross-Coupling Reaction Conditions
Additional Information:© 2021 American Chemical Society. Received: October 23, 2020; Publication Date: January 8, 2021. We thank Prof Pietro Perona for mentorship guidance and helpful project discussions and Chase Blagden for help in structuring the GBM experiments. Fellowship support was provided by the NSF (M.R.M., T.J.D. Grant No. DGE-1144469). S.E.R. is a Heritage Medical Research Institute Investigator. Y.Y. is supported in part by NSF 1645832 and NSF 1918839 and funding from Raytheon and Beyond Limits. S.R. is supported by grants from Disney Research and from Nissan Corporation. Financial support from Research Corporation is warmly acknowledged. Author Contributions: M.R.M., A.Y.C., and S.R. contributed equally to this work. The authors declare no competing financial interest.
Group:Heritage Medical Research Institute
Funding AgencyGrant Number
NSF Graduate Research FellowshipDGE-1144469
Heritage Medical Research InstituteUNSPECIFIED
Raytheon CompanyUNSPECIFIED
Disney ResearchUNSPECIFIED
Nissan CorporationUNSPECIFIED
Research CorporationUNSPECIFIED
Subject Keywords:machine learning; graph neural network; graph attention; gradient-boosting machines; reaction condition prediction; cross-coupling; predictive modeling; molecular machine learning
Issue or Number:1
Record Number:CaltechAUTHORS:20201015-152733539
Persistent URL:
Official Citation:Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions. Michael R. Maser, Alexander Y. Cui, Serim Ryou, Travis J. DeLano, Yisong Yue, and Sarah E. Reisman. Journal of Chemical Information and Modeling 2021 61 (1), 156-166; DOI: 10.1021/acs.jcim.0c01234
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:106094
Deposited By: George Porter
Deposited On:16 Oct 2020 16:22
Last Modified:26 Jan 2021 18:30

Repository Staff Only: item control page