Tree-based machine learning reveals hidden human viral sequences in plasma metagenomic dark matter

This zip file contains: The CSV file of the metadata of the sequences used to build the Random Forest and XGBoost models to classify into 34 viral families (Final_df.csv); The FASTA file of all sequences used to extract GC% content, Tetranucleotide Frequency and protein profiles (All_sequences.fasta); HMMER3 results of the refered FASTA (HMMER_results.txt); ORF1 CDS used to bulid Anelloviruses phylogeny (ORF1_CDS_aln_trim.fasta); FASTA file of the assembled aligned Anelloviruses contigs, already trimmed (AVs_contigs.fasta) This dataset can be used to sucsessfully reproduct the findings of the entitled study: "Tree-based machine learning reveals hidden human viral sequences in plasma metagenomic dark matter".