2026-10-10T11:51:54Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34021752 2026-09-29T07:05:32Z category_4 category_8 category_13 category_21 category_734 category_931 category_132 category_133 category_135 portal_63 item_type_3 month_year_09_2026

Enzymatic Reaction Feasibility Classification Using Machine Learning Methods Xin Wang (91924) Hongyan Yin (5066285) Yekai Shen (22351183) Yushan Zhu (809017) Igor V. Tetko (13525) Aixia Yan (1957624) Biochemistry Microbiology Genetics Biotechnology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Infectious Diseases Plant Biology Computational Biology stereo ” dataset step biosynthetic pathway previously reported deeprfc numerous biosynthetic pathways improved predictive performance identifying feasible reactions identify feasible reactions highest predictive performance extreme gradient boosting deep neural network 864 feasible reactions optimal individual model “ stereo ” systematic reaction preprocessing infeasible reactions based individual model 1a c_ecfp4 representation achieved consensus model erfc achieving mcc values model 1a reaction representation “ non reaction rules reaction centers tuned chemberta three datasets test sets successfully validated stereochemical information results indicate openly available flexible framework experimental validation equal number effective classifiers drfp ), direct input collected 75 biocatalysis databases aided retrobiosynthesis agnostic version With the advancement of computer-aided retrobiosynthesis, numerous biosynthetic pathways have been predicted, exceeding the capacity of experimental validation. Effective classifiers are needed to identify feasible reactions. In this study, we collected 75,864 feasible reactions from biocatalysis databases and generated an equal number of infeasible reactions based on reaction rules. Following atom mapping focused on reaction centers and systematic reaction preprocessing, three datasets for training were constructed: the “stereo” dataset, which retained reaction stereochemical information; the “non-stereo” dataset, which was a stereochemistry-agnostic version of the “stereo” dataset; and the “mixed” dataset, which comprised both. We established a total of 22 individual enzymatic reaction feasibility classification models, which include: eXtreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) models utilizing Reaction Fingerprints (RXNFP), Differential Reaction Fingerprint (DRFP), and our constructed Combined ECFP4 Reaction Fingerprints (c_ECFP4) for reaction representation, and Transformer models and fine-tuned ChemBERTa-77M-MLM (ChemMLM) models using reaction SMILES strings as the direct input. The results indicate that models utilizing the c_ECFP4 representation achieved the highest predictive performance, which effectively captured underlying enzymatic reaction mechanisms. Among them, Model 1A-M (based on XGBoost and “mixed” dataset) was identified as the optimal individual model, achieving Matthews Correlation Coefficient (MCC) values of 0.865 and 0.853 and Area Under Curve (AUC) values of 0.981 and 0.980 on the “stereo” and “non-stereo” test sets, respectively. Furthermore, a consensus model enzymatic reaction feasibility classification (ERFC) integrating four reaction representations further improved predictive performance, achieving MCC values of 0.894 and 0.886 and an AUC of 0.986 on both test sets. Moreover, both models (Model 1A-M and ERFC) successfully validated a five-step biosynthetic pathway, demonstrating higher prediction accuracy than the previously reported DeepRFC and DORA-XGB models in identifying feasible reactions. All data, the individual Model 1A-M, and the consensus model ERFC are openly available, offering a reliable and flexible framework for predicting enzymatic reaction feasibility in the presence or absence of stereochemical information. 2026-09-29T00:00:00Z Dataset Dataset 10.1021/acs.jcim.6c02294.s005 https://figshare.com/articles/dataset/Enzymatic_Reaction_Feasibility_Classification_Using_Machine_Learning_Methods/34021752 CC BY-NC 4.0