Exploration and Evaluation of Machine Learning-Based Models for Predicting Enzymatic Reactions
- 13 February 2020
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 60 (3) , 1833-1843
Abstract
Un-annotated gene sequences in databases are increasing due to sequencing advances. Therefore, computational methods to predict functions of un-annotated genes are needed. Moreover, novel enzyme discovery for metabolic engineering applications further encourages annotation of sequences. Here, enzyme functions are predicted using two general approaches, each including several machine learning algorithms. First, Enzyme-models (E-models) predict Enzyme Commission (EC) numbers from amino acid sequence information. Second, Substrate-Enzyme models (SE-models) are built to predict substrates of enzymatic reactions together with EC numbers, and Substrate-Enzyme-Product models (SEP-models) are built to predict substrates, products and EC numbers. While accuracy of E-models is not optimal, SE-models and SEP-models predict EC numbers and reactions with high accuracy using all tested machine learning-based methods. For example, a single Random Forests-based SEP-model predicts EC first digits with an Average AUC score of over 0.94. Various metrics indicate that the current strategy of combining sequence and chemical structure information is effective at improving enzyme reaction prediction.Keywords
Funding Information
- Takeda Science Foundation
- New Energy and Industrial Technology Development Organization (NEDO) (P16009)
This publication has 47 references indexed in Scilit:
- UniProt: the universal protein knowledgebaseNucleic Acids Research, 2016
- KEGG: new perspectives on genomes, pathways, diseases and drugsNucleic Acids Research, 2016
- BRENDA in 2017: new perspectives and new tools in BRENDANucleic Acids Research, 2016
- Machine learning applications in genetics and genomicsNature Reviews Genetics, 2015
- Ten years of next-generation sequencing technologyTrends in Genetics, 2014
- Current IUBMB recommendations on enzyme nomenclature and kineticsPerspectives in Science, 2014
- An overview of in silico protein function predictionArchives of Microbiology, 2010
- The impact of next-generation sequencing technology on geneticsTrends in Genetics, 2008
- Automated protein function prediction--the genomic challengeBriefings in Bioinformatics, 2006
- History of the enzyme nomenclature systemBioinformatics, 2000