human metagenome Genome sequencing. human metagenome

The main purpose of the study was to use Machine Learning algorithms to predict viral sequences in NGS data. This data is the training data which includes viral as well as non-viral sequences from different samples. Our bioinformatics analysis starts with removal of reads that are highly identical to human, phage, bacterial and vector DNA. For the rest of the reads, genome assembly is applied and then taxonomic classification using BLAST and HMMER3. These sequences in the training data are identified by these two algorithms. This data is a combination of studies with different samples. Sample types include Serum, Skin, Cervix tissue, Pancreas, etc.