genomes

Data license: ODbL · Data source: Larue & Roy, 2023

taxonomy_id

INTEGER (primary key), NCBI taxonomy id of the species

species

TEXT, binomial species name

common_name

TEXT, vernacular common name (singularized; nearest-rank if no species-level name)

group

TEXT, high-level grouping (vertebrates, invertebrates, plants, fungi, protozoa)

phylum

TEXT, taxonomic phylum

order

TEXT, taxonomic order

family

TEXT, taxonomic family

u12_status

TEXT, genome-level minor-spliceosome verdict. U12_POSITIVE = has minor introns (snRNA + motif agree, or an overwhelming intron population); U12_NEGATIVE = no U12-type evidence on any axis (loss); MOTIF_ONLY = minor introns detected but snRNA machinery not found; SNRNA_ONLY = snRNA machinery found but no minor introns detected; UNCERTAIN = partial / mixed weak signal; NOT_ASSESSED = no scorable data. Calls from genomes with low proteome completeness (busco_score < 70) are low-confidence.

n_minor_introns

INTEGER, high-confidence (adj ≥ 90) minor introns

percent_minor_introns

REAL, percentage of introns that are minor

u12_density_percentile

REAL, genome's minor-intron density percentile within the corpus

n_u12_all

INTEGER, all U12-type calls (adj ≥ 50), including the lower-confidence 50–90 band

n_major_introns

INTEGER, U2-type (major) introns

motif_category

TEXT, genome-level U12-type motif detection verdict — DETECTED / NOT_DETECTED / INCONCLUSIVE (too few calls to decide) / UNASSESSABLE (no scorable data)

z_excess

REAL, excess of U12-type intron calls over a matched-motif null (enrichment signal)

hc_u12_cds

INTEGER, high-confidence U12-type introns within CDS

hc_u12_exon

INTEGER, high-confidence U12-type introns overlapping exons

snrna_status

TEXT, minor-snRNA cmsearch verdict. corroborated = defining (U11/U12) + corroborating (U4atac/U6atac) snRNAs detected; defining = only a defining snRNA (U11/U12) detected; ambiguous = weak / partial snRNA signal; absent = no minor snRNAs detected; not_searched = snRNA search not run

minor_snrnas

TEXT, which minor snRNAs were detected (E ≤ 0.01)

n_minor_snrna

INTEGER, count of minor spliceosomal snRNAs detected (E ≤ 0.01)

u11_E

REAL, cmsearch E-value for the U11 snRNA

u12_E

REAL, cmsearch E-value for the U12 snRNA

u4atac_E

REAL, cmsearch E-value for the U4atac snRNA

u6atac_E

REAL, cmsearch E-value for the U6atac snRNA

total_genes

INTEGER, genes in the annotation

total_introns_scored

INTEGER, introns scored by intronIC

genome_size_bp

INTEGER, assembly size (bp)

gc_content

REAL, genome-wide GC%

coding_gc_content

REAL, GC% of the coding sequence

n_contigs

INTEGER, number of contigs/scaffolds

assembly_n50

INTEGER, assembly N50

assembly_l50

INTEGER, assembly L50

busco_score

REAL, BUSCO Complete% of the annotated proteome (eukaryota_odb10, protein mode) — a joint measure of assembly + annotation completeness

accession

TEXT, assembly accession

genome_version

TEXT, assembly version

source

TEXT, data source

assembly_url

TEXT, link to the assembly

ncbi_taxonomy_url

TEXT, link to the NCBI taxonomy page

wikipedia_url

TEXT, link to the Wikipedia page

common_name_level

TEXT, taxonomic rank the common name was resolved at

taxonomy

TEXT, full NCBI lineage string

genome_path

TEXT, path to the source genome FASTA (relative to the data root)

annotation_path

TEXT, path to the source annotation GFF (relative to the data root)

2,634 rows sorted by percent_minor_introns descending

✎ View and edit SQL

This data as json, CSV (advanced)

Next page

CREATE TABLE genomes (
  -- A. identity & taxonomy
  taxonomy_id INTEGER PRIMARY KEY, species TEXT, common_name TEXT, "group" TEXT,
  phylum TEXT, "order" TEXT, family TEXT,
  -- B. minor-intron headline
  u12_status TEXT, n_minor_introns INTEGER, percent_minor_introns REAL,
  u12_density_percentile REAL, n_u12_all INTEGER, n_major_introns INTEGER,
  -- C. minor-intron detail
  motif_category TEXT, z_excess REAL, hc_u12_cds INTEGER, hc_u12_exon INTEGER,
  -- D. snRNA evidence
  snrna_status TEXT, minor_snrnas TEXT, n_minor_snrna INTEGER,
  u11_E REAL, u12_E REAL, u4atac_E REAL, u6atac_E REAL,
  -- E. assembly & pipeline stats
  total_genes INTEGER, total_introns_scored INTEGER, genome_size_bp INTEGER,
  gc_content REAL, coding_gc_content REAL, n_contigs INTEGER,
  assembly_n50 INTEGER, assembly_l50 INTEGER, busco_score REAL,
  -- F. provenance, links & paths
  accession TEXT, genome_version TEXT, source TEXT, assembly_url TEXT,
  ncbi_taxonomy_url TEXT, wikipedia_url TEXT, common_name_level TEXT,
  taxonomy TEXT, genome_path TEXT, annotation_path TEXT
);
CREATE INDEX idx_genomes_phylum ON genomes("phylum");
CREATE INDEX idx_genomes_group ON genomes("group");
CREATE INDEX idx_genomes_motif_category ON genomes("motif_category");
CREATE INDEX [idx_genomes_order]
    ON [genomes] ([order]);
CREATE INDEX [idx_genomes_family]
    ON [genomes] ([family]);
CREATE INDEX [idx_genomes_u12_status]
    ON [genomes] ([u12_status]);
CREATE INDEX [idx_genomes_snrna_status]
    ON [genomes] ([snrna_status]);