genome_attribs-GTDB.yml

columns:
   - key: coll
     type: string
     filter_strategy: identity
     non_visible: true

   - key: load_ver
     type: string
     filter_strategy: identity
     non_visible: true

   - key: _mtchsel
     type: string
     filter_strategy: identity
     non_visible: true
     no_cast: true

   - key: kbase_id
     type: string
     filter_strategy: identity
     display_name: KBase ID
     category: Identifiers
     description:

   - key: kbase_display_name
     type: string
     filter_strategy: ngram
     display_name: KBase Name
     category: Identifiers
     description:

   - key: accession
     type: string
     filter_strategy: identity  # this seems like a good candidate for substring
     display_name: Accession
     category: Identifiers
     description:

   - key: checkm_completeness
     type: float
     display_name: CheckM Completeness
     category: Quality
     description:

   - key: checkm_contamination
     type: float
     display_name: CheckM Contamination
     category: Quality
     description:

   - key: checkm_marker_count
     type: int
     display_name: Number of CheckM Markers
     category: Other
     description:

   - key: checkm_marker_lineage  # GTDB node, might need better tokenizing or substring search
     type: string
     filter_strategy: fulltext
     display_name: CheckM Marker Lineage
     category: Other
     description:

   - key: checkm_marker_set_count
     type: int
     display_name: Number of CheckM Marker Sets
     category: Other
     description:

   - key: contig_count
     type: int
     display_name: Number of Contigs
     category: Other
     description:

   - key: gc_count
     type: int
     display_name: GC Count
     category: Other
     description:

   - key: gc_percentage
     type: float
     display_name: GC Content
     category: Statistics
     description:

   - key: genome_size
     type: int
     display_name: Genome Size
     category: Statistics
     description:

   - key: classification  # GTDB classification, might need better tokenizing
     type: string
     filter_strategy: ngram
     display_name: Classification
     category: Taxonomy
     description:

   - key: longest_contig
     type: int
     display_name: Longest Contig
     category: Other
     description:

   - key: longest_scaffold
     type: int
     display_name: Longest Scaffold
     category: Other
     description:

   - key: mean_contig_length
     type: float
     display_name: Mean Contig Length
     category: Other
     description:

   - key: mean_scaffold_length
     type: float
     display_name: Mean Scaffold Length
     category: Other
     description:

   - key: mimag_high_quality  # is this a boolean? do we need a bool type & convert?
     type: string
     filter_strategy: identity
     display_name: Mimag High Quality
     category: Quality
     description:

   - key: mimag_low_quality  # is this a boolean? do we need a bool type & convert?
     type: string
     filter_strategy: identity
     display_name: Mimag Low Quality
     category: Quality
     description:

   - key: mimag_medium_quality  # is this a boolean? do we need a bool type & convert?
     type: string
     filter_strategy: identity
     display_name: Mimag Medium Quality
     category: Quality
     description:

   - key: n50_contigs
     type: int
     display_name: N50 Contigs
     category: Other
     description:

   - key: n50_scaffolds
     type: int
     display_name: N50 Scaffolds
     category: Other
     description:

   - key: ncbi_assembly_level
     type: string
     filter_strategy: fulltext
     display_name: NCBI Assembly Level
     category: Source
     description:

   - key: ncbi_assembly_name
     type: string
     filter_strategy: identity  # this seems like a good candidate for substring
     display_name: NCBI Assembly Name
     category: Other
     description:

   - key: ncbi_bioproject
     type: string
     filter_strategy: identity  # this seems like a good candidate for substring
     display_name: NCBI BioProject
     category: Source
     description:

   - key: ncbi_biosample
     type: string
     filter_strategy: identity  # this seems like a good candidate for substring
     display_name: NCBI BioSample
     category: Source
     description:

   - key: ncbi_country
     type: string
     filter_strategy: fulltext
     display_name: NCBI Country
     category: Other
     description:

   - key: ncbi_date  # should put all dates into ISO8601 format, but not add significance
     type: date
     display_name: NCBI Date
     category: Source
     description:

   - key: ncbi_genbank_assembly_accession
     type: string
     filter_strategy: identity  # this seems like a good candidate for substring
     display_name: NCBI GenBank Assembly Accession
     category: Other
     description:

   - key: ncbi_genome_category
     type: string
     filter_strategy: fulltext
     display_name: NCBI Genome Category
     category: Other
     description:

   - key: ncbi_isolate
     type: string
     filter_strategy: fulltext
     display_name: NCBI Isolate
     category: Other
     description:

   - key: ncbi_isolation_source
     type: string
     filter_strategy: fulltext
     display_name: NCBI Isolation Source
     category: Other
     description:

   - key: ncbi_lat_lon  # might want to do specialized processing here
     type: string
     filter_strategy: fulltext
     display_name: NCBI Latitude/Longitude
     category: Other
     description:

   - key: ncbi_organism_name
     type: string
     filter_strategy: fulltext
     display_name: NCBI Organism Name
     category: Taxonomy
     description:

   - key: ncbi_seq_rel_date  # should put all dates into ISO8601 format, but not add significance
     type: date
     display_name: NCBI Sequence Release Date
     category: Other
     description:

   - key: ncbi_species_taxid
     type: int
     display_name: NCBI Species Taxon ID
     category: Other
     description:

   - key: ncbi_strain_identifiers
     type: string
     filter_strategy: fulltext
     display_name: NCBI Strain Identifiers
     category: Other
     description:

   - key: ncbi_submitter
     type: string
     filter_strategy: fulltext
     display_name: NCBI Submitter
     category: Other
     description:

   - key: ncbi_taxid
     type: int
     display_name: NCBI Taxon ID
     category: Other
     description:

   - key: ncbi_taxonomy_unfiltered  # might need better tokenizing
     type: string
     filter_strategy: fulltext
     display_name: NCBI Taxonomy (Unfiltered)
     category: Other
     description:

   - key: protein_count
     type: int
     display_name: Number of Protein Encoding Genes
     category: Statistics
     description:

   - key: scaffold_count
     type: int
     display_name: Number of Scaffolds
     category: Other
     description:

   - key: ssu_count
     type: int
     display_name: SSU Count
     category: Other
     description:

   - key: ssu_length  # this looks like an int that's a string in the DB. Should we coerce?
     type: string
     filter_strategy: fulltext
     display_name: SSU Length
     category: Other
     description:

   - key: trna_aa_count
     type: int
     display_name: tRNA AA Count
     category: Other
     description:

   - key: trna_count
     type: int
     display_name: Number of tRNA Genes
     category: Statistics
     description:

   - key: trna_selenocysteine_count
     type: int
     display_name: tRNA Selenocysteine Count
     category: Other
     description: