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 = 32765314
This data as json, CSV (advanced)
Suggested facets: dinucleotide_pair, score, phase
| id ▼ | dinucleotide_pair | is_minor | score | length | transcript_id | ordinal_index | start | end | taxonomy_id | scored_motifs | phase | in_cds | relative_position | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 183237624 | GT-AG | 0 | 1.000000099473604e-05 | 105 | rna-XM_004951904.2 32765314 | 1 | 8346306 | 8346410 | Setaria italica 4555 | GAG|GTAGAAATGC...ACTTCATTAACT/ACTTCATTAACT...TGCAG|TAT | 0 | 1 | 13.693 | 
| 183237625 | GT-AG | 0 | 0.0032805617686378 | 85 | rna-XM_004951904.2 32765314 | 2 | 8346095 | 8346179 | Setaria italica 4555 | CCG|GTAACTTGAA...CCTATTTTGATG/CCTATTTTGATG...TTTAG|GAA | 0 | 1 | 16.98 | 
| 183237626 | GT-AG | 0 | 9.534830713495612e-05 | 1335 | rna-XM_004951904.2 32765314 | 3 | 8344562 | 8345896 | Setaria italica 4555 | AAG|GTACATCTCT...TCCCACTTGATT/ACTTGATTCATT...TGCAG|CTG | 0 | 1 | 22.144 | 
| 183237627 | GT-AG | 0 | 0.0829160562515524 | 181 | rna-XM_004951904.2 32765314 | 4 | 8344153 | 8344333 | Setaria italica 4555 | AAG|GTATTCCTTT...ATGGTTTTGATT/ATGGTTTTGATT...TGCAG|GAA | 0 | 1 | 28.091 | 
| 183237628 | GT-AG | 0 | 1.000000099473604e-05 | 769 | rna-XM_004951904.2 32765314 | 5 | 8342244 | 8343012 | Setaria italica 4555 | GAG|GTTTGTAAAT...TCCATCTAATTT/TTCCATCTAATT...AATAG|GAA | 0 | 1 | 57.825 | 
| 183237629 | GC-AG | 0 | 1.000000099473604e-05 | 660 | rna-XM_004951904.2 32765314 | 6 | 8341224 | 8341883 | Setaria italica 4555 | CAG|GCAAGTATAC...ATTTTCTTGAAA/TAGTCATTTATT...TGCAG|GTT | 0 | 1 | 67.214 | 
| 183237630 | GT-AG | 0 | 0.0003257213302016 | 345 | rna-XM_004951904.2 32765314 | 7 | 8340392 | 8340736 | Setaria italica 4555 | CAG|GTACATTCCA...TTTCTCTTACAG/TTTATGTTCATG...TACAG|GAA | 1 | 1 | 79.917 | 
Advanced export
JSON shape: default, array, newline-delimited, object
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]);