Machine learning yield prediction from NiCOlit, a small-size literature data set of nickel catalyzed C–O couplings
Open accessPublished version of a preprint
Abstract
Synthetic yield prediction using machine learning is intensively studied. Previous work has focused on two categories of data sets: high-throughput experimentation data, as an ideal case study, and data sets extracted from proprietary databases, which are known to have a strong reporting bias toward high yields. However, predicting yields using published reaction data remains elusive. To fill the gap, we built a data set on nickel-catalyzed cross-couplings extracted from organic reaction publications, including scope and optimization information. We demonstrate the importance of including optimization data as a source of failed experiments and emphasize how publication constraints shape the exploration of the chemical space by the synthetic community. While machine learning models still fail to perform out-of-sample predictions, this work shows that adding chemical knowledge enables fair predictions in a low-data regime. Eventually, we hope that this unique public database will foster further improvements of machine learning methods for reaction yield prediction in a more realistic context.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The random forest model significantly outperforms the KNN baseline model when k = 1 across macro recall, accuracy, precision, F1 score and ROC AUC.
“As shown in Fig. S20, the results indicate that when k = 1 (which is particularly relevant as it aligns with chemical intuition) [39], the random forest model significantly outperforms the KNN baseline model across several metrics, including macro recall, accuracy, precision, F1 score and ROC AUC.”
From Automating structure-activity analysis for electrochemical nitrogen reduction catalyst design through multi-agent collaborations (2025) · cites this paper as [39]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
Machine-learning-assisted materials discovery using failed experiments
Raccuglia, P., Elbert, K. C., Adler, P. D. F., Falk, C., Wenny, M. B., Mollo, A., Zeller, M., Friedler, S. A., Schrier, J., & Norquist, A. J. (2016) · Nature · doi:10.1038/nature17439 · Cited by 1,727 · see citing works
Dataset Shift in Machine Learning
(2008) · doi:10.7551/mitpress/9780262170055.001.0001 · Cited by 1,553 · see citing works
Tamao, K., Sumitani, K., & Kumada, M. (1972) · Journal of the American Chemical Society · doi:10.1021/ja00767a075 · Cited by 1,292 · see citing works
Predicting reaction performance in C–N cross-coupling using machine learning
Ahneman, D. T., Estrada, J. G., Lin, S., Dreher, S. D., & Doyle, A. G. (2018) · Science · doi:10.1126/science.aar5169 · Cited by 1,058 · see citing works
Machine Learning in Computer-Aided Synthesis Planning
Coley, C. W., Green, W. H., & Jensen, K. F. (2018) · Accounts of Chemical Research · doi:10.1021/acs.accounts.8b00087 · Cited by 704 · see citing works
A platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flow
Perera, D., Tucker, J. W., Brahmbhatt, S., Helal, C. J., Chong, A., Farrell, W. P., Richardson, P., & Sach, N. W. (2018) · Science · doi:10.1126/science.aap9112 · Cited by 470 · see citing works
Machine Learning Methods in Drug Discovery
Patel, L., Shukla, T., Huang, X., Ussery, D. W., & Wang, S. (2020) · Molecules · doi:10.3390/molecules25225277 · Cited by 460 · see citing works
Mapping the space of chemical reactions using attention-based neural networks
Schwaller, P., Probst, D., Vaucher, A. C., Nair, V. H., Kreutter, D., Laino, T., & Reymond, J. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-020-00284-w · Cited by 360 · see citing works
Kearnes, S. M., Maser, M., Wleklinski, M., Kast, A., Doyle, A. G., Dreher, S. D., Hawkins, J. M., Jensen, K. F., & Coley, C. W. (2021) · Journal of the American Chemical Society · doi:10.1021/jacs.1c09820 · Cited by 341 · see citing works
A Structure-Based Platform for Predicting Chemical Reactivity
Sandfort, F., Strieth‐Kalthoff, F., Kühnemund, M., Beecks, C., & Glorius, F. (2020) · Chem · doi:10.1016/j.chempr.2020.02.017 · Cited by 287 · see citing works
Machine learning the ropes: principles, applications and directions in synthetic chemistry
Strieth‐Kalthoff, F., Sandfort, F., Segler, M., & Glorius, F. (2020) · Chemical Society Reviews · doi:10.1039/c9cs00786e · Cited by 287 · see citing works
Editorial: In silico Methods for Drug Design and Discovery
Brogi, S., Ramalho, T. C., Kuča, K., Medina‐Franco, J. L., & Valko, M. (2020) · Frontiers in Chemistry · doi:10.3389/fchem.2020.00612 · Cited by 280 · see citing works
Nickel and Palladium Catalysis: Stronger Demand than Ever
Chernyshev, V. M., & Ananikov, V. P. (2022) · ACS Catalysis · doi:10.1021/acscatal.1c04705 · Cited by 248 · see citing works
Machine Learning for Chemical Reactivity: The Importance of Failed Experiments
Strieth‐Kalthoff, F., Sandfort, F., Kühnemund, M., Schäfer, F. R., Kuchen, H., & Glorius, F. (2022) · Angewandte Chemie International Edition · doi:10.1002/anie.202204647 · Cited by 219 · see citing works
Schneider, N., Lowe, D. M., Sayle, R. A., & Landrum, G. A. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci5006614 · Cited by 196 · see citing works
Beker, W., Roszak, R., Wołos, A., Angello, N. H., Rathore, V., Burke, M. D., & Grzybowski, B. A. (2022) · Journal of the American Chemical Society · doi:10.1021/jacs.1c12005 · Cited by 190 · see citing works
Predicting Reaction Yields via Supervised Learning
Żurański, A. M., Alvarado, J. I. M., Shields, B. J., & Doyle, A. G. (2021) · Accounts of Chemical Research · doi:10.1021/acs.accounts.0c00770 · Cited by 188 · see citing works
The Evolution of Data-Driven Modeling in Organic Chemistry
Williams, W. L., Zeng, L., Gensch, T., Sigman, M. S., Doyle, A. G., & Anslyn, E. V. (2021) · ACS Central Science · doi:10.1021/acscentsci.1c00535 · Cited by 186 · see citing works
Kariofillis, S. K., Jiang, S., Żurański, A. M., et al. (2022) · Journal of the American Chemical Society · doi:10.1021/jacs.1c12203 · Cited by 186 · see citing works
Reaction classification and yield prediction using the differential reaction fingerprint DRFP
Probst, D., Schwaller, P., & Reymond, J. (2022) · Digital Discovery · doi:10.1039/d1dd00006c · Cited by 179 · see citing works
Organic reactivity from mechanism to machine learning
Jorner, K., Tomberg, A., Bauer, C. A., Sköld, C., & Norrby, P. (2021) · Nature Reviews Chemistry · doi:10.1038/s41570-021-00260-x · Cited by 177 · see citing works
On the use of real-world datasets for reaction yield prediction
Saebi, M., Nan, B., Herr, J. E., Wahlers, J., Guo, Z., Żurański, A. M., Kogej, T., Norrby, P., Doyle, A. G., Chawla, N. V., et al. (2023) · Chemical Science · doi:10.1039/d2sc06041h · Cited by 142 · see citing works
Considerations for implementing electronic laboratory notebooks in an academic research environment
Higgins, S. G., Nogiwa-Valdez, A. A., & Stevens, M. M. (2022) · Nature Protocols · doi:10.1038/s41596-021-00645-8 · Cited by 88 · see citing works
Making the collective knowledge of chemistry open and machine actionable
Jablonka, K. M., Patiny, L., & Smit, B. (2022) · Nature Chemistry · doi:10.1038/s41557-022-00910-7 · Cited by 87 · see citing works
AI in drug development: a multidisciplinary perspective
Gallego, V., Naveiro, R., Roca, C., Insua, D. R., & Campillo, N. E. (2021) · Molecular Diversity · doi:10.1007/s11030-021-10266-8 · Cited by 86 · see citing works
Adaptive Optimization of Chemical Reactions with Minimal Experimental Information
Reker, D., Hoyt, E. A., Bernardes, G. J. L., & Rodrigues, T. (2020) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2020.100247 · Cited by 83 · see citing works
Molecular Machine Learning: The Future of Synthetic Chemistry?
Pflüger, P. M., & Glorius, F. (2020) · Angewandte Chemie International Edition · doi:10.1002/anie.202008366 · Cited by 74 · see citing works
Żurański, A. M., Wang, J. Y., Shields, B. J., & Doyle, A. G. (2022) · Reaction Chemistry & Engineering · doi:10.1039/d2re00030j · Cited by 55 · see citing works
SMILES‐A Language for Molecules and Reactions
Weininger, D. (2003) · doi:10.1002/9783527618279.ch5 · Cited by 17 · see citing works
Data-Driven Analysis of Reactions Catalyzed by [CoCp*(CO)I2]
Pereira, A., Albornoz, C., & Trofymchuk, O. S. (2022) · Organometallics · doi:10.1021/acs.organomet.2c00051 · Cited by 7 · see citing works
Biaryl Construction Based on Nickel-Catalyzed C–O Bond Activation
Liu, F., Diao, H., & Shi, Z. (2021) · Synlett · doi:10.1055/a-1349-3543 · Cited by 6 · see citing works
Bajo, S., Laidlaw, G., Kennedy, A. R., et al. (2017) · Organometallics · doi:10.1021/acs.organomet.7b00307 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 44
- L. Patel, T. Shukla, X. Huang, D. W. Ussery, S. Wang, Molecules 25, 5277 (2020).
- C. W. Coley, W. H. Green, K. F. Jensen, Accounts of Chemical Research 51, 1281 (2018).
- W. Beker, R. Roszak, A. Wołos, N. H. Angello, V. Rathore, M. D. Burke, B. A. Grzybowski, Journal of the American Chemical Society (2022).
- P. Schwaller, A. C. Vaucher, T. Laino, J.-L. Reymond, Machine Learning: Science and Technology 2, 015016 (2021).
- D. M. Lowe, Ph.D. thesis, University of Cambridge (2012).
- D. Perera, J. W. Tucker, S. Brahmbhatt, C. J. Helal, A. Chong, W. Farrell, P. Richardson, N. W. Sach, Science 359, 429 (2018).
- D. T. Ahneman, J. G. Estrada, S. Lin, S. D. Dreher, A. G. Doyle, Science 360, 186 (2018).
- P. M. Pflüger, F. Glorius, Angewandte Chemie International Edition 59, 18860 (2020).
- S. M. Kearnes, M. R. Maser, M. Wleklinski, A. Kast, A. G. Doyle, S. D. Dreher, J. M. Hawkins, K. F. Jensen, C. W. Coley, Journal of the American Chemical Society 143, 18820 (2021).
- S. G. Higgins, A. A. Nogiwa-Valdez, M. M. Stevens, Nature Protocols 17, 179 (2022).
- H. Diao, Z. Shi, F. Liu, Synlett 32, 1494 (2021).
- S. Bajo, G. Laidlaw, A. R. Kennedy, S. Sproules, D. J. Nelson, Organometallics 36, 1880 (2017).
- D. Weininger, Handbook of Chemoinformatics pp. 80 -102 (2008).
- K. Tamao, K. Sumitani, M. Kumada, Journal of the American Chemical Society 94, 4374 (1972).
- M. Saebi, B. Nan, J. Herr, J. Wahlers, Z. Guo, A. Zurański, T. Kogej, P.-O. Norrby, A. Doyle, O. Wiest, N. Chawla, Chemrxiv preprint (2021).
- D. Reker, E. A. Hoyt, G. J. Bernardes, T. Rodrigues, Cell Reports Physical Science 1, 100247 (2020).
- P. Raccuglia, K. C. Elbert, P. D. F. Adler, C. Falk, M. B. Wenny, A. Mollo, M. Zeller, S. A. Friedler, J. Schrier, A. J. Norquist, Nature 533, 73 (2016).
- K. Jorner, A. Tomberg, C. Bauer, C. Sköld, P.-O. Norrby, Nature Reviews Chemistry 5, 240 (2021).
- N. Schneider, D. M. Lowe, R. A. Sayle, G. A. Landrum, Journal of Chemical Information and Modeling 55, 39 (2015).
- P. Schwaller, D. Probst, A. C. Vaucher, V. H. Nair, D. Kreutter, T. Laino, J.-L. Reymond, Nature Machine Intelligence 3, 144 (2021).
- L. Breiman, Machine Learning 45, 5 (2001).
- F. Strieth-Kalthoff, F. Sandfort, M. H. S. Segler, F. Glorius, Chemical Society Reviews 49, 6154 (2020).
- W. L. Williams, L. Zeng, T. Gensch, M. S. Sigman, A. G. Doyle, E. V. Anslyn, ACS Central Science 7, 1622 (2021).
- F. Sandfort, F. Strieth-Kalthoff, M. Kühnemund, C. Beecks, F. Glorius, Chem 6, 1379 (2020).
- V. M. Chernyshev, V. P. Ananikov, ACS Catalysis 12, 1180 (2022).
- S. K. Kariofillis, S. Jiang, A. M. Żurański, S. S. Gandhi, J. I. M. Alvarado, A. G. Doyle, Journal of the American Chemical Society 144, 1045 (2022).
- A. Yada, K. Nagata, Y. Ando, T. Matsumura, S. Ichinoseki, K. Sato, Chemistry Letters 47, 284 (2018).
- S.-J. Kim, K. Koh, M. Lustig, S. Boyd, D. Gorinevsky, IEEE Journal of Selected Topics in Signal Processing 1, 606 (2007).
- J. Friedman, T. Hastie, R. Tibshirani, Journal of Statistic Software 33, 1 (2010).
- B. J. Reizman, Y.-M. Wang, S. L. Buchwald, K. F. Jensen, Reaction Chemistry & Engineering 1, 658 (2016).
- Z. Fu, X. Li, Z. Wang, Z. Li, X. Liu, X. Wu, J. Zhao, X. Ding, X. Wan, F. Zhong, D. Wang, X. Luo, K. Chen, H. Liu, J. Wang, H. Jiang, M. Zheng, Organic Chemistry Frontiers 7, 2269 (2020).
- K. Nakamura, M. Tobisu, N. Chatani, Organic Letters 17, 6142 (2015).
- Z.-C. Cao, Q.-Y. Luo, Z.-J. Shi, Organic Letters 18, 5978 (2016).
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, Édouard Duchesnay, Journal of Machine Learning Research 12, 2825 (2011).
- D. Merk, L. Friedrich, F. Grisoni, G. Schneider, Molecular Informatics 37, 1700153 (2018).
- D. Bajusz, A. Rácz, K. Héberger, Journal of Cheminformatics 7 (2015).
- L. van der Maaten, G. Hinton, Journal of Machine Learning Research 9, 2579 (2008).
- F. Furche, R. Ahlrichs, The Journal of Chemical Physics 117, 7433 (2002).
- M. E. Casida, C. Jamorski, K. C. Casida, D. R. Salahub, The Journal of Chemical Physics 108, 4439 (1998).
- A. D. Becke, The Journal of Chemical Physics 98, 5648 (1993).
- C. Lee, W. Yang, R. G. Parr, Phys. Rev. B 37, 785 (1988).
- S. H. Vosko, L. Wilk, M. Nusair, Canadian Journal of Physics 58, 1200 (1980).
- P. J. Stephens, F. J. Devlin, C. F. Chabalowski, M. J. Frisch, The Journal of Physical Chemistry 98, 11623 (1994).
- M. J. Kamlet, J. L. M. Abboud, M. H. Abraham, R. W. Taft, The Journal of Organic Chemistry 48, 2877 (1983).
Cited by
Sorted by citations
Hu, X., Chen, S., Chen, L., Wang, H., Zhang, X., & Zhou, Z. (2025) · National Science Review · doi:10.1093/nsr/nwaf372 · Cited by 19 · see citing works
- Authors
- Schleinitz, J., Langevin, M., Smail, Y., Wehnert, B., Grimaud, L., & Vuilleumier, R.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Corresponding author
- Schleinitz, Jules
- Langevin, Maxime
- Grimaud, Laurence
- Vuilleumier, Rodolphe
- Venue
- Journal of the American Chemical Society
- Publisher
- American Chemical Society (ACS)
- Published
- 2022-08-08
- Volume
- 144
- Issue
- 32
- Pages
- 14722-14730
- ISSN
- 0002-7863 (ISSN-L)
- 1520-5126
- OpenAlex
- W4290725232
- Cited by
- 88
- References
- 33
- Citations by year
- 2026: 18 · 2025: 32 · 2024: 15 · 2023: 18 · 2022: 5
- FWCI
- 4.92
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- Journal of the American Chemical Society (publishedVersion)
- ChemRxiv (acceptedVersion, cc-by)
- PubMed (publishedVersion)
- HAL (submittedVersion, other-oa)
- Funders
- Sanofi
- Fondation de l'Ecole Normale Superieure
- Association Nationale de la Recherche et de la Technologie (2019/0821)
- Centre National de la Recherche Scientifique
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Physical Sciences › Chemistry › Organic Chemistry › Catalytic Cross-Coupling Reactions
- Keywords
- yield prediction, nickel catalysis, C–O coupling, reporting bias, chemical space exploration, synthetic chemistry, low-data regimes
- MeSH terms
- Machine Learning, Catalysis, Nickel
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
