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 = 35103495

✎ 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
197657420 GT-AG 0 0.0228260976551079 596 rna-XM_007046817.2 35103495 1 1429293 1429888 Theobroma cacao 3641 TTG|GTATGCTCAT...ATAATTTTGATG/ATAATTTTGATG...CATAG|GAT 2 1 9.618
197657421 GT-AG 0 1.000000099473604e-05 76 rna-XM_007046817.2 35103495 2 1425739 1425814 Theobroma cacao 3641 TCT|GTGAGTGTGT...TGGATCTTAATT/TTTTTTATGACT...GGCAG|GAT 0 1 88.323
197657422 GT-AG 0 1.000000099473604e-05 136 rna-XM_007046817.2 35103495 3 1425527 1425662 Theobroma cacao 3641 ATG|GTAGGTTATT...AGTTTCTTTCTG/AAAAATCTAATT...TGAAG|GAG 1 1 90.043
197657423 GT-AG 0 7.689413980738194e-05 86 rna-XM_007046817.2 35103495 4 1425370 1425455 Theobroma cacao 3641 GCG|GTATGATATT...GAATGTTTATTC/TGTTTATTCATC...TGCAG|GCA 0 1 91.65
197657424 GT-AG 0 0.0096342312442003 94 rna-XM_007046817.2 35103495 5 1425210 1425303 Theobroma cacao 3641 AAT|GTAATCTGTC...TTTTCCCTGACC/TTTTCCCTGACC...TGCAG|AGA 0 1 93.143
197657425 GT-AG 0 0.013761531588728 348 rna-XM_007046817.2 35103495 6 1424772 1425119 Theobroma cacao 3641 TAT|GTATGTTATA...AAGCTCTTGAGG/CTTTTTCTCATT...GGCAG|ATC 0 1 95.18
197657426 GT-AG 0 1.000000099473604e-05 123 rna-XM_007046817.2 35103495 7 1424472 1424594 Theobroma cacao 3641 AAG|GTCAGTTACT...ACATTTTTGTTG/TCTACACTAACA...CTCAG|GAA 0 1 99.185

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]);