Investigation of machine learning algorithms for taxonomic classification of marine metagenomes

Training, testing, and blind datasets used for machine learning algorithms for taxonomic classification of marine metagenomes: <strong>K12.kmers.txt</strong> - 12bp k-mer vocabulary constructed by Jellyfish v1.1.11 from 47,894 genomes in GTDB release 202 <strong>MarRef_1.6.tsv</strong> - Metadata file downloaded from MarRef v1.6 <strong>MarRef.genustrain.fasta</strong> - Training set from MarRef v1.6 (seed=808) used for genus classification <strong>MarRef.genustest.fasta</strong> - Testing set from MarRef v1.6 (seed=747) used for genus classification <strong>MarRef.speciestrain.fasta</strong> - Training set from MarRef v1.6 (seed=808) used for species classification <strong>MarRef.speciestest.fasta</strong> - Testing set from MarRef v1.6 (seed=747) used for species classification <strong>MarRef.traintest.key.tsv</strong> - Table containing MarRef accession, GenBank accession, GenBank taxonomy ID, taxonomic information, and labels used for species and genus testing and training <strong>anonymous_reads_*.fq</strong> - Blind datasets (1-10) in interleaved fastq format <strong>reads_mapping_*.tsv</strong> - Key for blind datasets 1-10. Each sequence header is mapped to its corresponding MarRef accession and NCBI taxonomic ID.