ABLE: Attention based learning for enzyme classification. (October 2021)

• Record Type: Journal Article
• Authors: Nallapareddy, Mohan Vamsi; Dwivedula, Rohit
• Is Part Of: Computational biology and chemistry. Volume 94(2021)
• Publication Date: 2021-10
• Subjects: Attention -- Bidirectional LSTM -- Deep learning -- Enzyme classification; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2021.107558
• Languages: English
• ISSNs: 1476-9271

Abstract

Abstract: Classifying proteins into their respective enzyme class is an interesting question for researchers for a variety of reasons. The open source Protein Data Bank (PDB) contains more than 1, 60, 000 structures, with more being added everyday. This paper proposes an attention-based bidirectional-LSTM model (ABLE) trained on over sampled data generated by SMOTE to analyse and classify a protein into one of the six enzyme classes or a negative class using only the primary structure of the protein described as a string by the FASTA sequence as an input. We achieve the highest F1-score of 0.834 using our proposed model on a dataset of proteins from the PDB. We baseline our model against eighteen other machine learning and deep learning networks, including CNN, LSTM, Bi-LSTM, GRU, and the state-of-the-art DeepEC model. We conduct experiments with two different oversampling techniques, SMOTE and ADASYN. To corroborate the obtained results, we perform extensive experimentation and statistical testing. Graphical Abstract: ga1 Highlights: The proposed attention-BiLSTM model for classifying enzymes outperforms vanilla deep learning and machine learning models. Extensive experimentation was conducted through 10-fold cross-validation and comparison against a wide range of baselines. Class imbalance problem in the enzyme dataset was tackled with two data oversampling techniques, SMOTE and ADASYN. Statistical testing was performed to validate our results, instead of relying only on increases in performance metrics.