Machine learning-assisted amidase-catalytic enantioselectivity prediction and rational design of variants for improving enantioselectivity.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
10 Oct 2024
10 Oct 2024
Historique:
received:
26
02
2024
accepted:
30
09
2024
medline:
11
10
2024
pubmed:
11
10
2024
entrez:
10
10
2024
Statut:
epublish
Résumé
Biocatalysis is an attractive approach for the synthesis of chiral pharmaceuticals and fine chemicals, but assessing and/or improving the enantioselectivity of biocatalyst towards target substrates is often time and resource intensive. Although machine learning has been used to reveal the underlying relationship between protein sequences and biocatalytic enantioselectivity, the establishment of substrate fitness space is usually disregarded by chemists and is still a challenge. Using 240 datasets collected in our previous works, we adopt chemistry and geometry descriptors and build random forest classification models for predicting the enantioselectivity of amidase towards new substrates. We further propose a heuristic strategy based on these models, by which the rational protein engineering can be efficiently performed to synthesize chiral compounds with higher ee values, and the optimized variant results in a 53-fold higher E-value comparing to the wild-type amidase. This data-driven methodology is expected to broaden the application of machine learning in biocatalysis research.
Identifiants
pubmed: 39389964
doi: 10.1038/s41467-024-53048-0
pii: 10.1038/s41467-024-53048-0
doi:
Substances chimiques
Amidohydrolases
EC 3.5.-
amidase
EC 3.5.1.4
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
8778Subventions
Organisme : National Natural Science Foundation of China (National Science Foundation of China)
ID : 21977098
Organisme : National Natural Science Foundation of China (National Science Foundation of China)
ID : 22193041
Organisme : National Natural Science Foundation of China (National Science Foundation of China)
ID : 22120102005
Informations de copyright
© 2024. The Author(s).
Références
Faber, K. et al. Biotransformations in Organic Chemistry: A Textbook, 7th, pp 442 (Springer, Berlin, 2018).
Hanefeld, U., Hollmann, F. & Paul, C. E. Biocatalysis making waves in organic chemistry. Chem. Soc. Rev. 51, 594–627 (2022).
doi: 10.1039/D1CS00100K
Wu, S. et al. Biocatalysis: enzymatic synthesis for industrial applications. Angew. Chem. Int. Ed. 60, 88–119 (2021).
doi: 10.1002/anie.202006648
Yi, D. et al. Recent trends in biocatalysis. Chem. Soc. Rev. 50, 8003–8049 (2021).
doi: 10.1039/D0CS01575J
Winkler, C. K., Schrittwieser, J. H. & Kroutil, W. Power of biocatalysis for organic synthesis. ACS Cent. Sci. 7, 55–71 (2021).
doi: 10.1021/acscentsci.0c01496
Devine, P. N. et al. Extending the application of biocatalysis to meet the challenges of drug development. Nat. Rev. Chem. 2, 409–421 (2018).
doi: 10.1038/s41570-018-0055-1
Buller, R. et al. From nature to industry: harnessing enzymes for biocatalysis. Science 382, eadh8615 (2023).
doi: 10.1126/science.adh8615
Hossack, E. J., Hardy, F. J. & Green, A. P. Building enzymes through design and evolution. ACS Catal. 13, 12436–12444 (2023).
doi: 10.1021/acscatal.3c02746
Miller, D. C., Athavale, S. V. & Arnold, F. H. Combining chemistry and protein engineering for new-to-nature biocatalysis. Nat. Synth. 1, 18–23 (2022).
doi: 10.1038/s44160-021-00008-x
Qu, G. et al. The crucial role of methodology development in directed evolution of selective enzymes. Angew. Chem. Int. Ed. 59, 13204–13231 (2020).
doi: 10.1002/anie.201901491
Adams, J. P. et al. Biocatalysis: a pharma perspective. Adv. Synth. Catal. 361, 2421–2432 (2019).
doi: 10.1002/adsc.201900424
Quesne, M. G. et al. Advances in sustainable catalysis: a computational perspective. Front. Chem. 7, 182 (2019).
doi: 10.3389/fchem.2019.00182
Klinman, J. P., Offenbacher, A. R. & Hu, S. Origins of enzyme catalysis: experimental findings for C-H activation, new models, and their relevance to prevailing theoretical constructs. J. Am. Chem. Soc. 139, 18409–18427 (2017).
doi: 10.1021/jacs.7b08418
Lonsdale, R., Harvey, J. N. & Mulholland, A. J. A practical guide to modelling enzyme-catalysed reactions. Chem. Soc. Rev. 41, 3025–3038 (2012).
doi: 10.1039/c2cs15297e
Yang, J., Li, F.-Z. & Arnold, F. H. Opportunities and challenges for machine learning-assisted enzyme engineering. ACS Cent. Sci. 10, 226–241 (2024).
doi: 10.1021/acscentsci.3c01275
Ao, Y.-F. et al. Data-driven protein engineering for improving catalytic activity and selectivity. ChemBioChem 25, e202300754 (2024).
doi: 10.1002/cbic.202300754
Markus, B. et al. Accelerating biocatalysis discovery with machine learning: a paradigm shift in enzyme engineering, discovery, and design. ACS Catal. 13, 14454–14469 (2023).
doi: 10.1021/acscatal.3c03417
Kouba, P. et al. Machine learning-guided protein engineering. ACS Catal. 13, 13863–13895 (2023).
doi: 10.1021/acscatal.3c02743
Dou, B. et al. Machine learning methods for small data challenges in molecular science. Chem. Rev. 123, 8736–8780 (2023).
doi: 10.1021/acs.chemrev.3c00189
Wittmund, M., Cadet, F. & Davari, M. D. Learning epistasis and residue coevolution patterns: current trends and future perspectives for advancing enzyme engineering. ACS Catal. 12, 14243–14263 (2022).
doi: 10.1021/acscatal.2c01426
Jiang, Y., Ran, X. & Yang, Z. J. Data-driven enzyme engineering to identify function-enhancing enzymes. Protein Eng. Des. Sel. 36, gzac009 (2023).
doi: 10.1093/protein/gzac009
Sapoval, N. et al. Current progress and open challenges for applying deep learning across the biosciences. Nat. Commun. 13, 1728 (2022).
doi: 10.1038/s41467-022-29268-7
Hie, B. L. & Yang, K. K. Adaptive machine learning for protein engineering. Curr. Opin. Struct. Biol. 72, 145–152 (2022).
doi: 10.1016/j.sbi.2021.11.002
Lovelock, S. L. et al. The road to fully programmable protein catalysis. Nature 606, 49–58 (2022).
doi: 10.1038/s41586-022-04456-z
Cui, Y., Sun, J. & Wu, B. Computational enzyme redesign: large jumps in function. Trends Chem. 4, 409–419 (2022).
doi: 10.1016/j.trechm.2022.03.001
Xu, Y. et al. Deep dive into machine learning models for protein engineering. J. Chem. Inf. Model. 60, 2773–2790 (2020).
doi: 10.1021/acs.jcim.0c00073
Volk, M. J. et al. Biosystems design by machine learning. ACS Synth. Biol. 9, 1514–1533 (2020).
doi: 10.1021/acssynbio.0c00129
Mazurenko, S., Prokop, Z. & Damborsky, J. Machine learning in enzyme engineering. ACS Catal. 10, 1210–1223 (2020).
doi: 10.1021/acscatal.9b04321
Berman, H. M. et al. The protein data bank. Nucleic Acids Res. 28, 235–242 (2000).
doi: 10.1093/nar/28.1.235
UniProt Consortium, The UniProt: the universal protein knowledgebase in 2023. Nucleic Acids Res. 51, D523–D531 (2023).
doi: 10.1093/nar/gkac1052
Chang, A. et al. BRENDA, the ELIXIR core data resource in 2021: new developments and updates. Nucleic Acids Res. 49, D498–D508 (2021).
doi: 10.1093/nar/gkaa1025
Cadet, F. et al. A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes. Sci. Rep. 8, 16757 (2018).
doi: 10.1038/s41598-018-35033-y
Wu, Z. et al. Machine learning-assisted directed protein evolution with combinatorial libraries. Proc. Natl Acad. Sci. USA. 116, 8852–8858 (2019).
doi: 10.1073/pnas.1901979116
Ma, E. J. et al. Machine-directed evolution of an imine reductase for activity and stereoselectivity. ACS Catal. 11, 12433–12445 (2021).
doi: 10.1021/acscatal.1c02786
Ao, Y.-F. et al. Structure- and data-driven protein engineering of transaminases for improving activity and stereoselectivity. Angew. Chem. Int. Ed. 62, e202301660 (2023).
doi: 10.1002/anie.202301660
Clements, H. D. et al. Using data science for mechanistic insights and selectivity predictions in a non-natural biocatalytic reaction. J. Am. Chem. Soc. 145, 17656–17664 (2023).
doi: 10.1021/jacs.3c03639
Wu, Z. et al. Amidase as a versatile tool in amide-bond cleavage: from molecular features to biotechnological applications. Biotechnol. Adv. 43, 107574 (2020).
doi: 10.1016/j.biotechadv.2020.107574
Ao, Y.-F. et al. Reversal and amplification of the enantioselectivity of biocatalytic desymmetrization toward meso heterocyclic dicarboxamides enabled by rational engineering of amidase. ACS Catal. 11, 6900–6907 (2021).
doi: 10.1021/acscatal.1c01220
Hu, H.-J. et al. Modification of the enantioselectivity of biocatalytic meso-desymmetrization for synthesis of both enantiomers of cis−1,2-disubstituted cyclohexane by amidase engineering. Adv. Synth. Catal. 363, 4538–4543 (2021).
doi: 10.1002/adsc.202100597
Hu, H.-J. et al. Enantioselective biocatalytic desymmetrization for synthesis of enantiopure cis−3,4-disubstituted pyrrolidines. Green. Synth. Catal. 2, 324–327 (2021).
doi: 10.1016/j.gresc.2021.07.002
Hu, H.-J. et al. Highly efficient biocatalytic desymmetrization of meso carbocyclic 1,3-dicarboxamides: a versatile route for enantiopure 1,3-disubstituted cyclohexanes and cyclopentanes. Org. Chem. Front. 6, 808–812 (2019).
doi: 10.1039/C9QO00069K
Ao, Y.-F. et al. Biocatalytic desymmetrization of prochiral 3-aryl and 3-arylmethyl glutaramides: different remote substituent effect on catalytic efficiency and enantioselectivity. Adv. Synth. Catal. 360, 4594–4603 (2018).
doi: 10.1002/adsc.201800956
Wang, M.-X. Enantioselective biotransformations of nitriles in organic synthesis. Acc. Chem. Res. 48, 602–611 (2015).
doi: 10.1021/ar500406s
Janes, L. E., Kazlauskas, R. J. & Quick, E. a fast spectrophotometric method to measure the enantioselectivity of hydrolases. J. Org. Chem. 62, 4560–4561 (1997).
doi: 10.1021/jo9707803
Barnard, T. et al. Less may be more: an informed reflection on molecular descriptors for drug design and discovery. Mol. Syst. Des. Eng. 5, 317–329 (2020).
doi: 10.1039/C9ME00109C
Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. Proceedings of the 35th International Conference on Machine Learning, PMLR 80, 2323–2332 (2018).
Gastegger, M. et al. wACSF—Weighted atom-centered symmetry functions as descriptors in machine learning potentials. J. Chem. Phys. 148, 241709 (2018).
doi: 10.1063/1.5019667
Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).
doi: 10.1103/PhysRevLett.98.146401
Pedregosa, F. et al. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Gaussian 09, Revision D.01, Frisch, M. J. et al. Gaussian, Inc., Wallingford CT, (2013).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
doi: 10.1023/A:1010933404324
Ouyang, R. et al. SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates. Phys. Rev. Mater. 2, 083802 (2018).
doi: 10.1103/PhysRevMaterials.2.083802
Case, D. A. et al. AMBER18, University of California, San Francisco, (2018).
Wang, J. et al. Development and testing of a general amber force field. J. Comput. Chem. 25, 1157–1174 (2004).
doi: 10.1002/jcc.20035
Singh, R. V. & Sambyal, K. Green synthesis aspects of (R)-(-)-mandelic acid; a potent pharmaceutically active agent and its future prospects. Crit. Rev. Biotechnol. 43, 1226–1235 (2023).
doi: 10.1080/07388551.2022.2109004
Borzilleri, R. M., Weinreb, S. M. & Parvez, M. Total synthesis of the unusual marine alkaloid (-)-Papuamine utilizing a novel imino ene reaction. J. Am. Chem. Soc. 117, 10905–10913 (1995).
doi: 10.1021/ja00149a013
Tahil, G. et al. Stereoisomers are not machine learning’s best friends. J. Chem. Inf. Model. 64, 5451–5469 (2024).
doi: 10.1021/acs.jcim.4c00318
Walters, W. P. & Barzilay, R. Applications of deep learning in molecule generation and molecular property prediction. Acc. Chem. Res. 54, 263–270 (2021).
doi: 10.1021/acs.accounts.0c00699
Schütt, K. T. et al. SchNetPack 2.0: a neural network toolbox for atomistic machine learning. J. Chem. Phys. 158, 144801 (2023).
doi: 10.1063/5.0138367
Reid, J. P. & Sigman, M. S. Holistic prediction of enantioselectivity in asymmetric catalysis. Nature 571, 343–348 (2019).
doi: 10.1038/s41586-019-1384-z
Becke, A. D. Density-functional exchange-energy approximation with correct asymptotic behavior. Phys. Rev. A: ., Mol., Opt. Phys. 38, 3098–3100 (1988).
doi: 10.1103/PhysRevA.38.3098
Lee, C., Yang, W. & Parr, R. G. Development of the Colle-Salvetti correlation-energy formula into a functional of the electron density. Phys. Rev. B: Condens. Matter Mater. Phys. 37, 785–789 (1988).
doi: 10.1103/PhysRevB.37.785
Becke, A. D. Density-functional thermochemistry. III. the role of exact exchange. J. Chem. Phys. 98, 5648–5652 (1993).
doi: 10.1063/1.464913
Guyon, I. et al. Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422 (2002).
doi: 10.1023/A:1012487302797
Xue, Z. et al. Overexpression of a recombinant amidase in a complex auto-inducing culture: purification, biochemical characterization, and regio- and stereoselectivity. J. Ind. Microbiol. Biotechnol. 38, 1931–1938 (2011).
doi: 10.1007/s10295-011-0979-7
Li, Z.-L. et al. ML-assisted-amidase-catalytic-enantioselectivity-prediction-and-rational-design. https://doi.org/10.5281/zenodo.13759700 (2024).
The PyMOL molecular graphics system, version 2.3.0. Schrödinger, LLC. New York, (2019).