Abstract
BackgroundDetection of highly divergent or yet unknown viruses from metagenomics sequencing datasets is a major bioinformatics challenge. When human samples are sequenced, a large proportion of assembled contigs are classified as “unknown”, as conventional methods find no similarity to known sequences. We wished to explore whether machine learning algorithms using Relative Synonymous Codon Usage frequency (RSCU) could improve the detection of viral sequences in metagenomic sequencing data.ResultsWe trained Random Forest and Artificial Neural Network using metagenomic sequences taxonomically classified into virus and non-virus classes. The algorithms achieved accuracies well beyond chance level, with area under ROC curve 0.79. Two codons (TCG and CGC) were found to have a particularly strong discriminative capacity.ConclusionRSCU-based machine learning techniques applied to metagenomic sequencing data can help identify a large number of putative viral sequences and provide an addition to conventional methods for taxonomic classification.
Highlights
Detection of highly divergent or yet unknown viruses from metagenomics sequencing datasets is a major bioinformatics challenge
We show that models trained using Relative Synonymous Codon Usage frequency (RSCU) values from contigs from a set of metagenomics experiments generalizes to other metagenomics experiments
To test whether the relative synonymous codon usage frequency can predict the viral nature of a sequence we firstly trained a model on sequences originating from NCBI GenBank
Summary
Detection of highly divergent or yet unknown viruses from metagenomics sequencing datasets is a major bioinformatics challenge. When human samples are sequenced, a large proportion of assembled contigs are classified as “unknown”, as conventional methods find no similarity to known sequences. We wished to explore whether machine learning algorithms using Relative Synonymous Codon Usage frequency (RSCU) could improve the detection of viral sequences in metagenomic sequencing data. Conclusion: RSCU-based machine learning techniques applied to metagenomic sequencing data can help identify a large number of putative viral sequences and provide an addition to conventional methods for taxonomic classification. In order to detect potential viral sequences in metagenomic datasets, conventional alignment-based classification is performed by BLAST, which compares sequences to known genomes and calculates how much similarity they share.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
