Data used for Benchmarking Cenote-Taker 3

data |____discovery | |____ERR10905741 | | |____ERR10905741_myloasm_1a.circ.fna | | |____genomad | | | |____genomad_only_contigs.txt | | | |____ERR10905741_myloasm_1a.circ_with_dtr_virus_genes.tsv | | | |____ERR10905741_myloasm_1a.circ_with_dtr_virus_summary.tsv | | |____phold_annotations | | | |____phold_ERR10905741_gnmd | | | | |____phold_all_cds_functions.tsv | | | | |____phold_per_cds_predictions.tsv | | | |____phold_ERR10905741_ct3 | | | | |____phold_all_cds_functions.tsv | | | | |____phold_per_cds_predictions.tsv | | | | |____fails.tsv | | |____ct3 | | | |____ct3_ERR10905741_1b_virus_summary.tsv | | | |____ct3_only_contigs.txt | | | |____ct3_ERR10905741_1b_prune_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____contigs | | | |____ERR10905741_unique_calls.genomad.fna | | | |____ERR10905741_unique_calls.ct3.fna | |____short_read_assemblies | | |____VLP_samples | | | |____ERR8081307.ct3_only_contigs.txt | | | |____ERR8081362.gnmd_only_contigs.txt | | | |____ERR8081362.ct3_only_contigs.txt | | | |____ERR8081370.ct3_only_contigs.txt | | | |____genomad | | | | |____ERR8081307.contigs_virus_summary.tsv | | | | |____ERR8081370.contigs_virus_summary.tsv | | | | |____ERR8081362.contigs_virus_summary.tsv | | | |____ERR8081370.contigs.fa | | | |____ERR8081370.gnmd_only_contigs.txt | | | |____ERR8081307.gnmd_only_contigs.txt | | | |____ERR8081362.contigs.fa | | | |____ct3 | | | | |____ERR8081307_ct3_virus_summary.tsv | | | | |____ERR8081307_ct3_prune_summary.tsv | | | | |____ERR8081362_ct3_virus_summary.tsv | | | | |____ERR8081370_ct3_prune_summary.tsv | | | | |____ERR8081362_ct3_prune_summary.tsv | | | | |____ERR8081370_ct3_virus_summary.tsv | | | |____ERR8081307.contigs.fa | | |____bulk_wgs_samples | | | |____SRR36807671.contigs.fa | | | |____ERR13455686.ct3_only_contigs.txt | | | |____SRR36807671.ct3_only_contigs.txt | | | |____genomad | | | | |____ERR13455686.contigs_virus_summary.tsv | | | | |____SRR36807671.contigs_virus_summary.tsv | | | | |____SRR36931851.contigs_virus_summary.tsv | | | |____SRR36807671.gnmd_only_contigs.txt | | | |____SRR36931851.gnmd_only_contigs.txt | | | |____ERR13455686.gnmd_only_contigs.txt | | | |____ERR13455686.contigs.fa | | | |____SRR36931851.contigs.fa | | | |____SRR36931851.ct3_only_contigs.txt | | | |____ct3 | | | | |____ERR13455686_ct3_virus_summary.tsv | | | | |____SRR36931851_ct3_virus_summary.tsv | | | | |____ERR13455686_ct3_prune_summary.tsv | | | | |____SRR36931851_ct3_prune_summary.tsv | | | | |____SRR36807671_ct3_prune_summary.tsv | | | | |____SRR36807671_ct3_virus_summary.tsv | |____DRR290133 | | |____genomad | | | |____DRR290133_myloasm_1a.circ_with_dtr_virus_genes.tsv | | | |____DRR290133_myloasm_1a.circ_with_dtr_virus_summary.tsv | | | |____genomad_only_contigs.txt | | |____phold_annotations | | | |____unique_calls_genomad | | | | |____phold_run_1751497002.788138.log | | | | |____phold_aa.fasta | | | |____ct3_DRR290133_1b_294_phold1 | | | | |____phold_all_cds_functions.tsv | | | | |____phold_per_cds_predictions.tsv | | | |____phold_DRR290133_genomad1 | | | | |____phold_all_cds_functions.tsv | | | | |____phold_per_cds_predictions.tsv | | | |____phold_DRR290133_ct3_1 | | | | |____phold_all_cds_functions.tsv | | | | |____phold_per_cds_predictions.tsv | | |____ct3 | | | |____ct3_only_contigs.txt | | | |____ct3_DRR290133_1b_prune_summary.tsv | | | |____ct3_DRR290133_1b_virus_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____contigs | | | |____DRR290133_unique_calls.genomad.fna | | | |____genomad_only_contigs.txt | | | |____ct3_only_contigs.txt | | | |____DRR290133_myloasm_1a.circ.fna | | | |____DRR290133_unique_calls.ct3.fna | |____refseq | | |____refseq_virus_AA_20260107.fasta | | |____refseq_virus_genomes_20260107.fasta | | |____blastDBs | | | |____refseq_AA.pdb | | | |____refseq_AA.phr | | | |____refseq_AA.pot | | | |____refseq_AA.pto | | | |____refseq_AA.ptf | | | |____refseq_AA.psq | | | |____refseq_AA.pin | | | |____refseq_AA.pjs | | |____refseq_virus_metadata_20260107.tsv | |____large_metagenome | | |____large_meta_resource_testing_metrics.xlsx |____annotation | |____hmms | | |____pharokka_phrogs_consensus.names.tsv | | |____metc_pgap_consensus.faa | | |____ct3_v311_virion_consensus.faa | | |____metc_cog_consensus.faa | | |____metc_phrog_consensus.faa | | |____metc_vog_consensus.faa | | |____ct2_all_consensus.faa | | |____metc_GVDB_consensus.faa | | |____all_metc_consensus.faa | | |____ct2_specific_consensus.faa | | |____ct3_v311_useful_models_consensus.faa | | |____ct2_rna_consensus.faa | | |____all_ct3_consensus.names.tsv | | |____ct3_v311_dnarep_consensus.faa | | |____metc_PVOG_consensus.faa | | |____all_ct3_consensus.VS.ct2_all.mmseqs1.tsv | | |____all_ct3_consensus.VS.metc.tsv | | |____all_ct3_consensus.VS.pharokka.tsv | | |____ct3_v311_rdrp_consensus.faa | | |____pharokka_phrogs_consensus.faa | | |____metc_tigr_consensus.faa | | |____ct3_v311_phrogs_consensus.faa | | |____ct2_useful_consensus.faa | | |____all_metc_consensus.names.tsv | | |____genomad_consensus.faa | | |____all_ct3_consensus.faa | | |____all_ct3_consensus.VS.genomad.mmseqs1.tsv | | |____metc_kofam_consensus.faa | | |____metc_pfam_consensus.faa | |____seawater_rna_virome | | |____phold | | | |____phold_per_cds_predictions.tsv | | |____genomad | | | |____hq_complete_genomes.PRJNA605028_genes.tsv | | |____AAs | | | |____PRJNA605028.AA.lengths.tsv | | | |____PRJNA605028.AA.VS.refseq_virus_AA_20260107.tsv | | | |____PRJNA605028.AA.faa | | |____pharokka | | | |____pharokka_cds_final_merged_output.tsv | | |____ct3 | | | |____ct3_PRJNA605028_a_virus_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____contigs | | | |____hq_complete_genomes.PRJNA605028.fna | | |____metc | | | |____final_annotation_summary.tsv | |____gut_dtrs | | |____gut_dtr_pairwise_fisher.csv | | |____phold | | | |____phold_per_cds_predictions.tsv | | |____genomad | | | |____gut_dtr_head_tail_contigs1_genes.tsv | | | |____gut_dtr_head_tail_contigs1_taxonomy.tsv | | |____AAs | | | |____gut_dtr_head_tail_AA.faa | | | |____gut_dtr_head_tail_AA.VS.refseq_virus_AA_20260107.tsv | | | |____gut_dtr_head_tail_AA.lengths.tsv | | |____gut_dtr_perfect_stats.csv | | |____gut_dtr_per_gene_stats.csv | | |____pharokka | | | |____pharokka_cds_final_merged_output.tsv | | |____gut_ct3_vs_genomad | | | |____gut_ct3_vs_genomad.nb.html | | | |____ct3_genomad_virion_disagree1.tsv | | | |____gut_ct3_vs_genomad.Rmd | | | |____ct3_genomad_annotation_compare.tsv | | | |____gut_dtr_ct3_virion_contigs_genes.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____ct3 | | | |____ct3_g_dtr_ht_1b_virus_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____contigs | | | |____gut_dtr_head_tail_contigs.txt | | | |____gut_dtr_head_tail_contigs1.fna | | |____metc | | | |____final_annotation_summary.tsv | |____uhgv | | |____phold | | | |____phold_per_cds_predictions.tsv | | |____genomad | | | |____first_100_uhgv_votus_taxonomy.tsv | | | |____first_100_uhgv_votus_genes.tsv | | |____pipeline_time_data1.xlsx | | |____pharokka | | | |____pharokka_cds_final_merged_output.tsv | | |____ct3 | | | |____ct3_uhgv100_1a_virus_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____contigs | | | |____first_100_uhgv_votus.fna | | | |____first_1000_uhgv_votus.fna | | |____metc | | | |____final_annotation_summary.tsv | |____seawater_dtrs | | |____seawater_dtr_per_gene_stats.csv | | |____phold | | | |____phold_per_cds_predictions.tsv | | |____seawater_dtr_perfect_stats.csv | | |____genomad | | | |____seawater_dtr_headtail_contigs_genes.tsv | | | |____seawater_dtr_headtail_contigs_taxonomy.tsv | | |____AAs | | | |____seawater_dtr_headtail_AA.VS.refseq_virus_AA_20260107.tsv | | | |____seawater_dtr_headtail_AA.faa | | | |____seawater_dtr_headtail_AA.lengths.tsv | | |____seawater_dtr_pairwise_fisher.csv | | |____pharokka | | | |____pharokka_cds_final_merged_output.tsv | | |____ct3 | | | |____ct3_s_dtr_ht_1a_virus_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____contigs | | | |____seawater_dtr_headtail_contigs.fna | | | |____seawater_dtr_headtail_contigs.txt | | |____sea_ct3_vs_genomad | | | |____sea_ct3_vs_genomad1.nb.html | | | |____sea_ct3_vs_genomad1.Rmd | | | |____ct3_genomad_virion_disagree1.tsv | | | |____seawater_dtr_ct3_virion_contigs.fasta | | | |____seawater_dtr_ct3_virion_contigs_genes.tsv | | | |____ct3_genomad_annotation_compare.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____metc | | | |____final_annotation_summary.tsv | |____refseq | | |____genomad | | | |____refseq_virus_genomes_20260107_genes.tsv | | |____pharokka | | | |____pharokka_cds_final_merged_output.tsv | | |____ct3 | | | |____ct3_refseq_an2_virus_summary.tsv | | | |____final_genes_to_contigs_annotation_summary.tsv | | |____metc | | | |____final_annotation_summary.tsv | |____genbank | | |____random_4000_gb_clean.1k.taxonomy.tsv | | |____gb_clean_an1_virus_summary.tsv | | |____random_4000_gb_clean.1k.fasta