A deep learning approach to evaluate the feasibility of enzymatic reactions generated by retrobiosynthesis. Issue 5 (18th January 2021)

• Record Type: Journal Article
• Authors: Kim, Yeji; Ryu, Jae Yong; Kim, Hyun Uk; Jang, Woo Dae; Lee, Sang Yup
• Is Part Of: Biotechnology journal. Volume 16:Issue 5(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-01-18
• Subjects: deep learning -- DeepRFC -- enzymatic reaction -- reaction feasibility -- retrobiosynthesis; Biotechnology -- Periodicals; 660.605
• DOI: 10.1002/biot.202000605
• Languages: English
• ISSNs: 1860-6768

Abstract

Abstract: Retrobiosynthesis allows the designing of novel biosynthetic pathways for the production of chemicals and materials through metabolic engineering, but generates a large number of reactions beyond the experimental feasibility. Thus, an effective method that can reduce a large number of the initially predicted enzymatic reactions has been needed. Here, we present Deep learning‐based Reaction Feasibility Checker (DeepRFC) to classify the feasibility of a given enzymatic reaction with high performance and speed. DeepRFC is designed to receive Simplified Molecular‐Input Line‐Entry System (SMILES) strings of a reactant pair, which is defined as a substrate and a product of a reaction, as an input, and evaluates whether the input reaction is feasible. A deep neural network is selected for DeepRFC as it leads to better classification performance than five other representative machine learning methods examined. For validation, the performance of DeepRFC is compared with another in‐house reaction feasibility checker that uses the concept of reaction similarity. Finally, the use of DeepRFC is demonstrated for the retrobiosynthesis‐based design of novel one‐carbon assimilation pathways. DeepRFC will allow retrobiosynthesis to be more practical for metabolic engineering applications by efficiently screening a large number of retrobiosynthesis‐derived enzymatic reactions. DeepRFC is freely available at https://bitbucket.org/kaistsystemsbiology/deeprfc . Abstract : To date, reaction feasibility has been primarily examined by comparing similarities between reactions with respect to structures of substrates and products. Although the reaction similarity‐based tools have substantially improved large‐scale in silico pathway design, they take considerable time to determine reaction centers and bond changes. The development of a faster and more robust software program for the prediction of biochemical reaction feasibility is in great demand. To meet this need, we developed a deep learning‐based reaction feasibility checker (DeepRFC), which is a standalone software program using deep learning that automatically evaluates the feasibility of enzymatic reactions with high performance and speed.