Predicting the outcomes of organic reactions via machine learning: Are current descriptors sufficient?

Scientific Reports

Volumn 7, Issue 1, 2017, Pages

  Skoraczynski G ^a   DIttwald, P ^b   Miasojedow, B ^a   Szymkuc, S ^b   Gajewska, E P ^b   Grzybowski, B A ^b,c   Gambin, A ^a  

^a UNIVERSITY OF WARSAW   (Poland)

^b INSTITUTE OF ORGANIC CHEMISTRY   (Poland)

^c Ulsan National Institute of Science and Technology   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

CHEMICAL BINDING; CHEMISTRY; MACHINE LEARNING;

EID: 85020943110     PISSN: None     EISSN: 20452322     Source Type: Journal    
DOI: 10.1038/s41598-017-02303-0     Document Type: Article

References (40)

1. Marx, V. The big challenges of big data. Nature 498, 255-260, doi:10.1038/498255a (2013).
2. Howe D., et al. Big data: The future of biocuration. Nature 2008, 455, 47-50 (2008).
3. Gibb, B. C. Big (chemistry) data. Nat. Chem. 5, 248-249, doi:10.1038/nchem.1604 (2013).
4. Jones, N. The learning machines. Nature 505, 146-148, doi:10.1038/505146a (2014).
5. Jordan, M. I., Mitchell, T. M. Machine learning: Trends, perspectives, prospects. Science 349, 255-260, doi:10.1126/science. aaa8415 (2015).
6. Hilton, G., et al. Deep neural networks for acoustic modeling in speech recognition. IEEE Sign. Process. Mag. 29, 82-97, doi:10.1109/MSP.2012.2205597 (2012).
7. Sajn, L., Kukar, M. Image processing and machine learning for fully automated probabilistic evaluation of medical images. Comp. Meth. Prog. Biomed. 104, E75-E86, doi:10.1016/j.cmpb.2010.06.021 (2011).
8. Kell, D. B. Metabolomics, modelling and machine learning in systems biology-towards an understanding of the languages of cells. FEBS J. 273, 873-894, doi:10.1111/j.1742-4658.2006.05136.x (2006).
9. Parkes, D. C., Wellman, M. P. Economic reasoning and artificial intelligence. Science 349, 267-272, doi:10.1126/science.aaa8403 (2015).
10. Buchwald, F., Richter, L., Kramer, S. Predicting a small molecule-kinase interaction map: A machine learning approach. J. Cheminf. 3, 22 (2011).
11. Agarwal, S., Dugar, D., Sengupta, S. Ranking chemical structures for drug discovery: A new machine learning approach. J. Chem. Inf. Model. 50, 716-731, doi:10.1021/ci9003865 (2010).
12. Vert, J.-P., Jacob, L. Machine learning for in silico virtual screening and chemical genomics: New strategies. Comb. Chem. High Throughput Screening 11, 677-685, doi:10.2174/138620708785739899 (2008).
13. Lusci, A., Pollastri, G., Baldi, P. Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules. J. Chem. Inf. Model. 53, 1563-1575, doi:10.1021/ci400187y (2013).
14. van de Walle, A. Ab initio modelling-Genesis of crystal structures. Nat. Mater. 4, 362-363, doi:10.1038/nmat1378 (2005).
15. Pyzer-Knapp, E. O., Li, K., Aspuru-Guzik, A. Learning from the Harvard Clean Energy Project: The use of neural networks to accelerate materials discovery. Adv. Funct. Mater. 25, 6495-6502, doi:10.1038/sdata.2016.86 (2015).
16. Raccuglia, R., et al. Machine-learning-assisted materials discovery using failed experiments. Nature 533, 73-76, doi:10.1038/nature17439 (2016).
17. Schneider, N., Lowe, D. M., Sayle, R. A., Landrum, G. A. Development of a novel fingerprint for chemical reactions and its application to large-scale reaction classification and similarity. J. Chem. Inf. Model. 55, 39-53, doi:10.1021/ci5006614 (2015).
18. Gálvez, J., Gálvez-Llompart, M., Garciá-Domenech, R. Application of molecular topology for the prediction of the reaction times and yields under solvent-free conditions. Green Chem. 12, 1056-1061, doi:10.1039/b926047a (2010).
19. Pla-Franco, J., Gálvez-Llompart, M., Gálvez, J., Garciá-Domenech, R. Application of molecular topology for the prediction of reaction yields and anti-Inflammatory activity of heterocyclic amidine derivatives. Int. J. Mol. Sci. 12, 1281-1292, doi:10.3390/ijms12021281 (2011).
20. Kayala, M. A., Baldi, P. ReactionPredictor: Prediction of complex chemical reactions at the mechanistic level using machine learning. J. Chem. Inf. Model. 52, 2526-2540, doi:10.1021/ci3003039 (2012).
21. Wei, J. N., Duvenaud, D., Aspuru-Guzik, A. Neural networks for the prediction organic chemistry reactions. ACS Central Science 2, (725-732 (2016).
22. Emami, F. S., et al. A priori estimation of organic reaction yields. Angew. Chem. Int. Ed. 54, 10797-10801, doi:10.1002/anie.201503890 (2015).
23. Szymku, S., et al. Computer-assisted synthetic planning: The end of the beginning. Angew. Chem. Int. Ed. 55, 5904-5937, doi:10.1002/anie.201506101 (2016).
24. Wilson, E. K. New directions for machine learning. Chem., Eng. News 4, 29-30 (2017).
25. James, G., Witten. D., Hastie, T., Tibshirani, R. An introduction to statistical learning with applications in R, 130 (Springer New York, 2013).
26. Cortes, C., Vapnik, V. Support-vector networks. Mach. Learn. 20, 273-297, doi:10.1007/BF00994018 (1995).
27. Haykin, S. Neural networks: A comprehensive foundation 2nd ed. (Prentice Hall, 1998).
28. Gasteiger, J., Zupan, J. Neural networks in chemistry. Angew. Chem. Int. Ed. 32, 503-527, doi:10.1002/(ISSN)1521-3773 (1993).
29. Geurts, P., Ernst, D., Wehenkel, L. Extremely randomized trees. Mach. Learn. 63, 3-42, doi:10.1007/s10994-006-6226-1 (2006).
30. Breiman, L. Random forests. Mach. Learn. 45, 5-32, doi:10.1023/A:1010933404324 (2001).
31. Hastie, T., Tibshirani, R., Friedman, J. The elements of statistical learning, 587 (Springer, 2009).
32. RDKit: Open-source cheminformatics; http://www.rdkit.org.
33. Carhart, R. E., Smith, D. H., Venkataraghavan, R. J. Atom pairs as molecular features in structure-activity studies: Definition and applications. Chem. Inf. Model. 25, 64-73, doi:10.1021/ci00046a002 (1985).
34. Cadeddu, A., Wylie, E. K., Jurczak, J., Wampler-Doty, M., Grzybowski, B. A. Organic chemistry as a language and the implications of chemical linguistics for structural and retrosynthetic analyses. Angew. Chem. Int. Ed. 53, 8108-8112, doi:10.1002/anie.201403708 (2014).
35. Friedman, J., Hastie, T., Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Soft. 33, 1-22, doi:10.18637/jss.v033.i01 (2010).
36. Menze, B. H., et al. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics 10, 213, doi:10.1186/1471-2105-10-213 (2009).
37. Schkeryantz, J. M., Danishefsky, S. J. Total synthesis of (+/)-FR-900482. J. Am. Chem. Soc. 117, 4722-4723, doi:10.1021/ja00121a037 (1995).
38. Huang, X., Zhou, H. W. Novel tunable CuX2-mediated cyclization reaction of cyclopropylideneacetic acids and esters for the facile synthesis of 4-halomethyl-2(5H)-furanones and 4-halo-5, 6-dihydro-2H-pyran-2-ones. Org. Lett. 4, 4419-4422, doi:10.1021/ol026911q (2002).
39. Overman, L. E. Charge as a key component in reaction design-the invention of cationic cyclization reactions of importance in synthesis. Acc. Chem. Res. 25, 352-359, doi:10.1021/ar00020a005 (1992).
40. Shair, M. D., Yoon, T. Y., Mosny, K. K., Chou, T. C., Danishefsky, S. J. The total synthesis of dynemicin A leading to development of a fully contained bioreductively activated enediyne prodrug. J. Am. Chem. Soc. 118, 9509-9525, doi:10.1021/ja960040w (1996).