Effects of sequence features on machine-learned enzyme classification fidelity

• Published in: Biochemical engineering journal Vol. 187; p. 108612
• Main Authors: Ferdous, Sakib, Shihab, Ibne Farabi, Reuel, Nigel F.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.11.2022
• Subjects: Benchmarking; Deep learning; Enzyme classification; Hidden markov model; Machine learning; Sequence feature; Deep learning; Benchmarking; Sequence feature; Enzyme classification; Hidden markov model; Machine learning
• ISSN: 1369-703X; 1873-295X
• DOI: 10.1016/j.bej.2022.108612

Assigning enzyme commission (EC) numbers using sequence information alone has been the subject of recent classification algorithms where statistics, homology and machine-learning based methods are used. This work benchmarks performance of a few of these algorithms as a function of sequence features such as chain length and amino acid composition (AAC). This enables determination of optimal classification windows for de novo sequence generation and enzyme design. Parallelization and visualization workflows are developed to observe the performance of the classifier over changing enzyme length, main EC class and AAC. We applied these workflows to the entire SwissProt database to date (n = 565928) using two, locally installable classifiers, ECpred and DeepEC, and collecting results from two other webserver-based tools, Deepre and BENZ-ws. All the classifiers exhibit peak performance in the range of 300–450 amino acids in length. Classifiers were most accurate at predicting translocases (EC-6) and were least accurate in determining hydrolases (EC-3) and oxidoreductases (EC-1). We also identified AAC ranges that are most common in the annotated enzymes and found that all classifiers work best in this common range. Among the four classifiers, ECpred showed the best consistency in changing feature space. These workflows can be used to benchmark new algorithms as they are developed and find optimum design spaces for the generation of new, synthetic enzymes. •EC number annotation tools are benchmarked with sequences from entire SwissProt database.•All the classifiers exhibit peak performance in the range of 300–450 amino acids in length.•Classifiers were most accurate at predicting EC-6 and were least accurate in determining EC-3 and EC-1.•All classifiers work best in the AAC range which are most common in the annotated enzymes.•ECpred showed the best consistency in changing feature space.