Long short-term memory recurrent neural networks for antibacterial peptide identification

Antimicrobial peptides are short amino acid sequences with antibacterial, antifungal, and antiviral properties. Antibacterial peptides have the possibility to form a new class of antibiotics to aid in combating bacterial antibiotic resistance. Most machine learning methodologies applied to the task of identifying antimicrobial peptides have applied features representing the presence or absence of certain periodic patterns in the amino acid sequence. This requires considering different periodicities for each feature and leads to a large number of features many of which are likely irrelevant to the classification task at hand. Also as the peptides vary in length it is difficult to develop a feature vector of identical finite length representing all the sequences. An easy way to circumvent both of these problems is provided by recurrent neural networks. In this work we choose to extract a feature vector through the application of bidirectional Long Short-Term Memory (LSTM) recurrent neural networks from features representing individual amino acids within each sequence. The LSTM network recursively iterates along both directions of each amino acid sequence and extracts two finite vectors whose concatenation yields the finite length vector representation of the amino acid sequence. As this is done during the training of the network on the classification task, the representation extracted is more likely to be relevant for distinguishing between the classes. This work demonstrates the LSTM approach to classification of antibacterial peptides and compares it to a Random Forest classifier and a k-nearest neighbor classifier.