Application of machine learning in bacteriophage research

Abstract

Phages are one of the key components in the structure, dynamics, and interactions of microbial communities in different bins. It has a clear impact on human health and the food industry. Bacteriophage characterization using in vitro approaches are time/cost consuming and laborious tasks. On the other hand, with the advent of new high-throughput sequencing technology, the development of a powerful computational framework to characterize the newly identified bacteriophages is inevitable for future research. Machine learning includes powerful techniques that enable the analysis of complex datasets for knowledge discovery and pattern recognition. In this study, we have conducted a comprehensive review of machine learning methods application using different types of features were applied in various aspects of bacteriophage research including, automated curation, identification, classification, host species recognition, virion protein identification, and life cycle prediction. Moreover, potential limitations and advantages of the developed frameworks were discussed.

Combination of MALDI-TOF Mass Spectrometry and Machine Learning for Rapid Antimicrobial Resistance Screening: The Case of Campylobacter spp.

“…Over the last 5 years, machine learning (ML), a subset of artificial intelligence, has gained interest in many areas of research pertaining to an improved diagnosis of diseases (e.g., cancer detection, infectious diseases, etc.) (Caballé et al, 2020;Goodswen et al, 2021;Nami et al, 2021). This popularity is greatly explained by the current era, where large daily amounts of data are being collected digitally, known as big data, which are requiring new approaches to investigate it.…”

Probiotic potential characterization and clustering using unsupervised algorithms of lactic acid bacteria from saltwater fish samples

“…Identified and characterized strains with desired probiotic features such as acid and bile tolerance, cell surface hydrophobicity, auto-aggregation and co-aggregation were subjected to cluster analysis based on unsupervised methods. Unsupervised methods are types of learning algorithm used to knowledge discovery from datasets that are neither classified nor labeled 35 – 37 . As depicted in Fig.…”

Computational Prediction of Bacteriophage Host Ranges

“…In addition to alignment-based and alignment-free methods, machine-learning (ML) approaches have found a home in bacteriophage research in general [40] and in the prediction of bacteriophage-host interactions specifically [41]. In order to infer virus-host relationships, ML approaches utilize 'features', i.e., measurable properties of the object being analyzed such as the nucleotide and amino acid content of the viral genome, amino acid properties, and protein domains (see [42] for a comparison of feature representations).…”