{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "JSON Schema for GTDB metadata files.",
"description": "Inferred JSON Schema with `qsv schema /Users/gwg/code/kbase/cdm-data-loaders/src/cdm_data_loaders/parsers/gtdb/files/ar53_metadata.tsv`",
"type": "object",
"properties": {
"accession": {
"description": "Unique genome identifier. Data from NCBI or GTDB.",
"minLength": 18,
"maxLength": 18,
"type": [
"string"
],
"pattern": "^(RS_GCF|GB_GCA)_[0-9]{9,}\\.[0-9]+$$"
},
"ambiguous_bases": {
"description": "Number of ambiguous bases. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"checkm2_completeness": {
"description": "Estimated completeness of genome using CheckM v2. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"checkm2_contamination": {
"description": "Estimated contamination of genome using CheckM v2. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"checkm2_model": {
"description": "Model used by CheckM v2 to estimate completeness and contamination. Data from CheckM.",
"minLength": 7,
"maxLength": 8,
"type": [
"string"
],
"enum": [
"General",
"Specific"
]
},
"checkm_completeness": {
"description": "Estimated completeness of genome. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"checkm_contamination": {
"description": "Estimated contamination of genome. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"checkm_marker_count": {
"description": "Number of marker genes used to estimate genome quality. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"checkm_marker_lineage": {
"description": "Lineage of marker genes used to estimate genome quality. Data from CheckM.",
"minLength": 7,
"type": [
"string"
],
"pattern": "^[a-z]__\\S+ \\(UID[0-9]+\\)$"
},
"checkm_marker_set_count": {
"description": "Number of marker sets used to estimate genome quality. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"checkm_strain_heterogeneity": {
"description": "Estimated strain heterogeneity of genome. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"coding_bases": {
"description": "Number of coding bases. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"coding_density": {
"description": "Coding density of genome. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"contig_count": {
"description": "Number of contigs. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"gc_count": {
"description": "Number of GC bases. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"gc_percentage": {
"description": "GC-content of genome. Data from CheckM.",
"minimum": 0.0,
"maximum": 100.0,
"type": [
"number"
]
},
"genome_size": {
"description": "Size of genome. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"gtdb_genome_representative": {
"description": "Indicates the representative genome of the GTDB species cluster to which this genome is assigned. Data from GTDB.",
"minLength": 18,
"maxLength": 18,
"type": [
"string"
],
"pattern": "^(RS_GCF|GB_GCA)_[0-9]{9,}\\.[0-9]+$$"
},
"gtdb_representative": {
"description": "Indicates if a genome is the representative of a GTDB species cluster. Data from GTDB.",
"minLength": 1,
"maxLength": 1,
"type": [
"string"
],
"enum": [
"f",
"t"
]
},
"gtdb_taxonomy": {
"description": "GTDB taxonomy string. Data from GTDB.",
"minLength": 20,
"type": [
"string"
]
},
"gtdb_type_designation_ncbi_taxa": {
"description": "Indicates if genome is assembled from the type strain of a species or subspecies according to its NCBI classification. Data from GTDB.",
"minLength": 1,
"maxLength": 50,
"type": [
"string"
],
"enum": [
"not type material",
"not used as type",
"type strain of subspecies",
"type strain of heterotypic synonym",
"type strain of species"
]
},
"gtdb_type_designation_ncbi_taxa_sources": {
"description": "Authoritative sources supporting type designation in gtdb_type_designation_ncbi_taxa. Data from GTDB.",
"minLength": 4,
"maxLength": 12,
"type": [
"string"
],
"enum": [
"LPSN",
"Seqcode",
"Seqcode;LPSN",
"none"
]
},
"gtdb_type_species_of_genus": {
"description": "Indicates if genome is assembled from the type species of the genus. Data from GTDB.",
"minLength": 1,
"maxLength": 1,
"type": [
"string"
],
"enum": [
"f",
"t"
]
},
"l50_contigs": {
"description": "L50 of contigs. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"l50_scaffolds": {
"description": "L50 of scaffolds. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"longest_contig": {
"description": "Longest contig. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"longest_scaffold": {
"description": "Longest scaffold. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"lsu_23s_contig_len": {
"description": "Length of contig containing selected 23S rRNA gene. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|\\d+)$"
},
"lsu_23s_count": {
"description": "Number of 23S rRNA genes. Data from HMMER w/ Barrnap HMMs.",
"type": [
"string"
],
"pattern": "^(none|\\d+)$"
},
"lsu_23s_length": {
"description": "Length of single 23S rRNA gene selected from genome. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"lsu_23s_query_id": {
"description": "Identifier of contig containing selected 23S rRNA gene. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"lsu_5s_contig_len": {
"description": "Length of contig containing selected 5S rRNA gene. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|\\d+)$"
},
"lsu_5s_count": {
"description": "Number of 5S rRNA genes. Data from HMMER w/ Barrnap HMMs.",
"minimum": 0,
"type": [
"integer"
]
},
"lsu_5s_length": {
"description": "Length of single 5S rRNA gene selected from genome. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|\\d+)$"
},
"lsu_5s_query_id": {
"description": "Identifier of contig containing selected 5S rRNA gene. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"lsu_silva_23s_blast_align_len": {
"description": "Alignment length of top BLAST hit in SILVA LSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|\\d+)$"
},
"lsu_silva_23s_blast_bitscore": {
"description": "Bitscore of top BLAST hit in SILVA LSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+(\\.[0-9]+)?|none)$"
},
"lsu_silva_23s_blast_evalue": {
"description": "E-value of top BLAST hit in SILVA LSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"lsu_silva_23s_blast_perc_identity": {
"description": "Percent identity of top BLAST hit in SILVA LSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+(\\.[0-9]+)?|none)$"
},
"lsu_silva_23s_blast_subject_id": {
"description": "Identifier of top BLAST hit in SILVA LSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"lsu_silva_23s_taxonomy": {
"description": "SILVA taxonomy of top BLAST hit for selected 23S rRNA gene. Data from SILVA.",
"minLength": 1,
"type": [
"string"
]
},
"mean_contig_length": {
"description": "Average length of contigs. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"mean_scaffold_length": {
"description": "Average length of scaffolds. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"mimag_high_quality": {
"description": "Indicates if genome meets the high-quality MIMAG criteria. Data from GTDB.",
"minLength": 1,
"maxLength": 1,
"type": [
"string"
],
"enum": [
"f",
"t"
]
},
"mimag_low_quality": {
"description": "Indicates if genome meets the low-quality MIMAG criteria. Data from GTDB.",
"minLength": 1,
"maxLength": 1,
"type": [
"string"
],
"enum": [
"f",
"t"
]
},
"mimag_medium_quality": {
"description": "Indicates if genome meets the medium-quality MIMAG criteria. Data from GTDB.",
"minLength": 1,
"maxLength": 1,
"type": [
"string"
],
"enum": [
"f",
"t"
]
},
"n50_contigs": {
"description": "N50 of contigs. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"n50_scaffolds": {
"description": "N50 of scaffolds. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_assembly_level": {
"description": "NCBI assembly level. Data from NCBI.",
"minLength": 6,
"maxLength": 15,
"type": [
"string"
],
"enum": [
"Chromosome",
"Complete Genome",
"Contig",
"Scaffold"
]
},
"ncbi_assembly_name": {
"description": "Assembly name. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_assembly_type": {
"description": "NCBI assembly type. Data from NCBI.",
"minLength": 2,
"maxLength": 2,
"type": [
"string"
]
},
"ncbi_bioproject": {
"description": "NCBI BioProject for genome. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^PRJ[DEN][A-Z][0-9]+$"
},
"ncbi_biosample": {
"description": "NCBI BioSample for genome. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|SAM[NED][A-Za-z0-9_]?[0-9]+)$"
},
"ncbi_contig_count": {
"description": "Number of contigs. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+|none)$"
},
"ncbi_contig_n50": {
"description": "N50 of contigs. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_country": {
"description": "Country. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_date": {
"description": "Data submitted to NCBI. Data from NCBI.",
"minLength": 10,
"maxLength": 10,
"type": [
"string"
],
"pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$"
},
"ncbi_genbank_assembly_accession": {
"description": "GenBank assembly accession.. Data from NCBI.",
"minLength": 15,
"maxLength": 15,
"type": [
"string"
],
"pattern": "^GCA_\\d{9,}\\.\\d+$$"
},
"ncbi_genome_category": {
"description": "Genome is assembled from a single cell, metagenome, or environmental sample. Data from NCBI/GTDB.",
"minLength": 4,
"maxLength": 33,
"type": [
"string"
],
"enum": [
"derived from environmental sample",
"derived from metagenome",
"derived from single cell",
"none"
]
},
"ncbi_genome_representation": {
"description": "Indicates if genome is full or partial. Data from NCBI.",
"minLength": 4,
"maxLength": 7,
"type": [
"string"
],
"enum": [
"full",
"partial"
]
},
"ncbi_isolate": {
"description": "Isolate name at NCBI. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_isolation_source": {
"description": "Isolation source. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_lat_lon": {
"description": "Latitude and longitude. Data from NCBI.",
"minLength": 4,
"maxLength": 39,
"type": [
"string"
]
},
"ncbi_molecule_count": {
"description": "Molecule count. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_ncrna_count": {
"description": "Non-coding RNA count. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|[0-9]+)$"
},
"ncbi_organism_name": {
"description": "Organism name at NCBI. Data from NCBI.",
"minLength": 8,
"type": [
"string"
]
},
"ncbi_protein_count": {
"description": "Protein count. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|[0-9]+)$"
},
"ncbi_refseq_category": {
"description": "NCBI RefSeq genome category. Data from NCBI.",
"minLength": 2,
"maxLength": 16,
"type": [
"string"
],
"enum": [
"na",
"reference genome"
]
},
"ncbi_rrna_count": {
"description": "rRNA count. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+|none)$"
},
"ncbi_scaffold_count": {
"description": "Number of scaffolds. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|[0-9]+)$"
},
"ncbi_scaffold_l50": {
"description": "L50 of scaffolds. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|[0-9]+)$"
},
"ncbi_scaffold_n50": {
"description": "N50 of scaffolds. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_scaffold_n75": {
"description": "N75 of scaffolds. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_scaffold_n90": {
"description": "N90 of scaffolds. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_seq_rel_date": {
"description": "NCBI sequence release date. Data from NCBI.",
"minLength": 10,
"maxLength": 10,
"type": [
"string"
],
"pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$"
},
"ncbi_spanned_gaps": {
"description": "Number of spanned gaps. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_species_taxid": {
"description": "NCBI species taxonomy identifier. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_ssu_count": {
"description": "Number of 16S rRNA genes. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+|none)$"
},
"ncbi_strain_identifiers": {
"description": "NCBI strain information from the assembly report. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_submitter": {
"description": "Submitter at NCBI. Data from NCBI.",
"minLength": 1,
"type": [
"string"
]
},
"ncbi_taxid": {
"description": "NCBI taxonomy identifier. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_taxonomy": {
"description": "NCBI taxonomy string. Data from NCBI.",
"minLength": 4,
"type": [
"string"
]
},
"ncbi_taxonomy_unfiltered": {
"description": "Full NCBI taxonomy string, including non-standard or unspecified ranks. Data from NCBI.",
"minLength": 4,
"type": [
"string"
]
},
"ncbi_total_gap_length": {
"description": "Length of all gaps. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_total_length": {
"description": "Size of genome. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_translation_table": {
"description": "Translation table. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+|none)$"
},
"ncbi_trna_count": {
"description": "tRNA count. Data from NCBI.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+|none)$"
},
"ncbi_type_material_designation": {
"description": "Indicates if genome is assembled from type material. Data from NCBI.",
"minLength": 2,
"maxLength": 47,
"type": [
"string"
],
"enum": [
"assembly designated as clade exemplar",
"assembly designated as neotype",
"assembly designated as reftype",
"assembly from heterotypic synonym type material",
"assembly from pathotype material",
"assembly from type material",
"na"
]
},
"ncbi_ungapped_length": {
"description": "Number of ungapped bases. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_unspanned_gaps": {
"description": "Number of unspanned gaps. Data from NCBI.",
"minimum": 0,
"type": [
"integer"
]
},
"ncbi_wgs_master": {
"description": "NCBI WGS accession. Data from NCBI.",
"minLength": 2,
"maxLength": 17,
"type": [
"string"
],
"pattern": "^(na|[A-Z]{4,6}[0-9]+(\\.\\d+)?)$"
},
"protein_count": {
"description": "Number of proteins. Data from Prodigal.",
"minimum": 0,
"type": [
"integer"
]
},
"scaffold_count": {
"description": "Number of scaffolds. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"ssu_contig_len": {
"description": "Length of contig containing selected 16S rRNA gene. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_count": {
"description": "Number of 16S rRNA genes. Data from HMMER w/ Barrnap HMMs.",
"minimum": 0,
"type": [
"integer"
]
},
"ssu_gg_blast_align_len": {
"description": "Alignment length of top BLAST hit in Greengenes. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_gg_blast_bitscore": {
"description": "Bitscore of top BLAST hit in Greengenes. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+(\\.[0-9]+)?|none)$"
},
"ssu_gg_blast_evalue": {
"description": "E-value of top BLAST hit in Greengenes. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_gg_blast_perc_identity": {
"description": "Percent identity of top BLAST hit in Greengenes. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+(\\.[0-9]+)?|none)$"
},
"ssu_gg_blast_subject_id": {
"description": "Identifier of top BLAST hit in Greengenes. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_gg_taxonomy": {
"description": "Greengenes taxonomy. Data from Greengenes.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_length": {
"description": "Length of single 16S rRNA gene selected from genome. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^(none|\\d+)$"
},
"ssu_query_id": {
"description": "Identifier of contig containing selected 16S rRNA gene. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_silva_blast_align_len": {
"description": "Alignment length of top BLAST hit in SILVA SSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_silva_blast_bitscore": {
"description": "Bitscore of top BLAST hit in SILVA SSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
],
"pattern": "^([0-9]+(\\.[0-9]+)?|none)$"
},
"ssu_silva_blast_evalue": {
"description": "E-value of top BLAST hit in SILVA SSU database. Data from GTDB.",
"minLength": 1,
"type": [
"string"
]
},
"ssu_silva_blast_perc_identity": {
"description": "Percent identity of top BLAST hit in SILVA SSU database. Data from GTDB.",
"type": [
"string"
],
"pattern": "^([0-9]+(\\.[0-9]+)?|none)$"
},
"ssu_silva_blast_subject_id": {
"description": "Identifier of top BLAST hit in SILVA SSU database. Data from GTDB.",
"minLength": 4,
"type": [
"string"
]
},
"ssu_silva_taxonomy": {
"description": "SILVA taxonomy of top BLAST hit for selected 16S rRNA gene. Data from SILVA.",
"minLength": 4,
"type": [
"string"
]
},
"total_gap_length": {
"description": "Length of all gaps. Data from CheckM.",
"minimum": 0,
"type": [
"integer"
]
},
"trna_aa_count": {
"description": "Number of standard amino acids with a tRNA. Data from tRNAscan-SE.",
"minimum": 0,
"type": [
"integer"
]
},
"trna_count": {
"description": "Total number of identified tRNAs. Data from tRNAscan-SE.",
"minimum": 0,
"type": [
"integer"
]
},
"trna_selenocysteine_count": {
"description": "Number of tRNAs for selenocysteine. Data from tRNAscan-SE.",
"minimum": 0,
"type": [
"integer"
]
}
},
"required": [
"accession",
"ambiguous_bases",
"checkm2_completeness",
"checkm2_contamination",
"checkm2_model",
"checkm_completeness",
"checkm_contamination",
"checkm_marker_count",
"checkm_marker_lineage",
"checkm_marker_set_count",
"checkm_strain_heterogeneity",
"coding_bases",
"coding_density",
"contig_count",
"gc_count",
"gc_percentage",
"genome_size",
"gtdb_genome_representative",
"gtdb_representative",
"gtdb_taxonomy",
"gtdb_type_designation_ncbi_taxa",
"gtdb_type_designation_ncbi_taxa_sources",
"gtdb_type_species_of_genus",
"l50_contigs",
"l50_scaffolds",
"longest_contig",
"longest_scaffold",
"lsu_23s_contig_len",
"lsu_23s_count",
"lsu_23s_length",
"lsu_23s_query_id",
"lsu_5s_contig_len",
"lsu_5s_count",
"lsu_5s_length",
"lsu_5s_query_id",
"lsu_silva_23s_blast_align_len",
"lsu_silva_23s_blast_bitscore",
"lsu_silva_23s_blast_evalue",
"lsu_silva_23s_blast_perc_identity",
"lsu_silva_23s_blast_subject_id",
"lsu_silva_23s_taxonomy",
"mean_contig_length",
"mean_scaffold_length",
"mimag_high_quality",
"mimag_low_quality",
"mimag_medium_quality",
"n50_contigs",
"n50_scaffolds",
"ncbi_assembly_level",
"ncbi_assembly_name",
"ncbi_assembly_type",
"ncbi_bioproject",
"ncbi_biosample",
"ncbi_contig_count",
"ncbi_contig_n50",
"ncbi_country",
"ncbi_date",
"ncbi_genbank_assembly_accession",
"ncbi_genome_category",
"ncbi_genome_representation",
"ncbi_isolate",
"ncbi_isolation_source",
"ncbi_lat_lon",
"ncbi_molecule_count",
"ncbi_ncrna_count",
"ncbi_organism_name",
"ncbi_protein_count",
"ncbi_refseq_category",
"ncbi_rrna_count",
"ncbi_scaffold_count",
"ncbi_scaffold_l50",
"ncbi_scaffold_n50",
"ncbi_scaffold_n75",
"ncbi_scaffold_n90",
"ncbi_seq_rel_date",
"ncbi_spanned_gaps",
"ncbi_species_taxid",
"ncbi_ssu_count",
"ncbi_strain_identifiers",
"ncbi_submitter",
"ncbi_taxid",
"ncbi_taxonomy",
"ncbi_taxonomy_unfiltered",
"ncbi_total_gap_length",
"ncbi_total_length",
"ncbi_translation_table",
"ncbi_trna_count",
"ncbi_type_material_designation",
"ncbi_ungapped_length",
"ncbi_unspanned_gaps",
"ncbi_wgs_master",
"protein_count",
"scaffold_count",
"ssu_contig_len",
"ssu_count",
"ssu_gg_blast_align_len",
"ssu_gg_blast_bitscore",
"ssu_gg_blast_evalue",
"ssu_gg_blast_perc_identity",
"ssu_gg_blast_subject_id",
"ssu_gg_taxonomy",
"ssu_length",
"ssu_query_id",
"ssu_silva_blast_align_len",
"ssu_silva_blast_bitscore",
"ssu_silva_blast_evalue",
"ssu_silva_blast_perc_identity",
"ssu_silva_blast_subject_id",
"ssu_silva_taxonomy",
"total_gap_length",
"trna_aa_count",
"trna_count",
"trna_selenocysteine_count"
]
}