introns

Data license: ODbL · Data source: Larue & Roy, 2023 · About: Minor Intron Database (WtMTA)

id
INTEGER (primary key), globally unique identifier for each intron
dinucleotide_pair
TEXT, terminal dinucleotide sequences of the intron
is_minor
INTEGER, indicates if the intron is a minor intron (1) or not (0)
score
REAL, score representing the probability (0-100%) of the intron being minor
length
INTEGER, length of the intron in base pairs
transcript_id
INTEGER (foreign key referencing transcripts(id)), parent transcript
ordinal_index
INTEGER, ordinal position of the intron within the transcript (e.g., 3 for the third intron)
start
INTEGER, start position of the intron in the genome
end
INTEGER, end position of the intron in the genome
taxonomy_id
INTEGER (foreign key referencing genomes(taxonomy_id)), NCBI taxonomy identifier for species
scored_motifs
TEXT, motifs scored for the intron
phase
INTEGER, phase of the intron in coding sequence (0, 1, or 2 or null for introns outside of coding sequence)
in_cds
INTEGER, indicates if the intron is within the coding sequence (1) or not (0; e.g., UTR introns)
relative_position
REAL, relative position of the intron within the transcript (as a percentage of coding length)

7 rows where transcript_id = 35103514

✎ View and edit SQL

This data as json, CSV (advanced)

Suggested facets: score, phase

id ▼ dinucleotide_pair is_minor score length transcript_id ordinal_index start end taxonomy_id scored_motifs phase in_cds relative_position
197657658 GT-AG 0 0.0155910056947819 1081 rna-XM_007049247.2 35103514 1 13028724 13029804 Theobroma cacao 3641 TAG|GTAGCATTCG...ATATTTTTAATA/ATATTTTTAATA...TGCAG|AAT 2 1 4.937
197657659 GT-AG 0 1.000000099473604e-05 94 rna-XM_007049247.2 35103514 2 13028505 13028598 Theobroma cacao 3641 CTG|GTCAGTGCTG...ATTCCTTTGAAA/TTCTGTCTAATA...GCCAG|CTG 1 1 8.07
197657660 GT-AG 0 0.0011890644428175 577 rna-XM_007049247.2 35103514 3 13026086 13026662 Theobroma cacao 3641 AGA|GTATGATAGT...TCATCCCTAACT/CCCTAACTTATT...GGCAG|GAC 1 1 54.236
197657661 GT-AG 0 1.000000099473604e-05 82 rna-XM_007049247.2 35103514 4 13025282 13025363 Theobroma cacao 3641 CAG|GTTAATCTTT...ACATCCTTGAAT/GAATTGTTTATC...TGCAG|GAC 0 1 72.331
197657662 GT-AG 0 0.0010035772536336 599 rna-XM_007049247.2 35103514 5 13024530 13025128 Theobroma cacao 3641 ATG|GTATGTATAT...ATAACTTTAGAT/TGTTACCTCACT...TGCAG|CAT 0 1 76.165
197657663 GT-AG 0 4.226631566724669 508 rna-XM_007049247.2 35103514 6 13023685 13024192 Theobroma cacao 3641 CAG|GTATCTATTT...TGCTCTTTGATT/TCCTTTCTGATT...ATCAG|GTA 1 1 84.612
197657664 GT-AG 0 3.660207747671852e-05 1628 rna-XM_007049247.2 35103514 7 13021989 13023616 Theobroma cacao 3641 CAG|GTTTGTTGGG...TCTGCTTTATTC/AATATATTAATC...TGCAG|GAA 0 1 86.316

Advanced export

JSON shape: default, array, newline-delimited, object

CSV options: 

CREATE TABLE "introns" (
"id" INTEGER,
  "dinucleotide_pair" TEXT,
  "is_minor" INTEGER,
  "score" REAL,
  "length" INTEGER,
  "transcript_id" INTEGER,
  "ordinal_index" INTEGER,
  "start" INTEGER,
  "end" INTEGER,
  "taxonomy_id" INTEGER,
  "scored_motifs" TEXT,
  "phase" INTEGER,
  "in_cds" INTEGER,
  "relative_position" REAL
  ,PRIMARY KEY ([id]),
   FOREIGN KEY([transcript_id]) REFERENCES [transcripts]([id]),
   FOREIGN KEY([taxonomy_id]) REFERENCES [genomes]([taxonomy_id])
);
CREATE INDEX [idx_introns_transcript_id]
    ON [introns] ([transcript_id]);
CREATE INDEX [idx_introns_taxonomy_id]
    ON [introns] ([taxonomy_id]);
CREATE INDEX [idx_introns_phase]
    ON [introns] ([phase]);
CREATE INDEX [idx_introns_is_minor]
    ON [introns] ([is_minor]);
CREATE INDEX [idx_introns_dinucleotide_pair]
    ON [introns] ([dinucleotide_pair]);
CREATE INDEX [idx_introns_score]
    ON [introns] ([score]);
CREATE INDEX [idx_introns_in_cds]
    ON [introns] ([in_cds]);