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)
 
8 rows where transcript_id = 10007596
This data as json, CSV (advanced)
Suggested facets: phase, in_cds
| id ▼ | dinucleotide_pair | is_minor | score | length | transcript_id | ordinal_index | start | end | taxonomy_id | scored_motifs | phase | in_cds | relative_position | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 55033759 | GT-AG | 0 | 0.0003461527957671 | 314 | rna-XM_008442338.2 10007596 | 2 | 3334734 | 3335047 | Cucumis melo 3656 | AAG|GTACCAACTG...AAGATTTTACAT/CATTCATTCATC...TCCAG|AAA | 0 | 1 | 23.129 | 
| 55033760 | GT-AG | 0 | 1.108588143167714e-05 | 509 | rna-XM_008442338.2 10007596 | 3 | 3333999 | 3334507 | Cucumis melo 3656 | AAG|GTAAGCCTGT...TTTACTTTAAGT/GTTACATTTACT...TGTAG|GTG | 1 | 1 | 30.851 | 
| 55033761 | GT-AG | 0 | 0.005078383904487 | 1450 | rna-XM_008442338.2 10007596 | 4 | 3332303 | 3333752 | Cucumis melo 3656 | CAG|GTATTATTTC...ACGACCTTACTA/GTATTGCTTATG...AACAG|TTT | 1 | 1 | 39.255 | 
| 55033762 | GT-AG | 0 | 0.0002070000782061 | 117 | rna-XM_008442338.2 10007596 | 5 | 3332135 | 3332251 | Cucumis melo 3656 | GTG|GTATTGAGCT...AAAATTTTATCT/AAGTTATTTATT...TGCAG|ATG | 1 | 1 | 40.998 | 
| 55033763 | GT-AG | 0 | 0.0521587795523383 | 107 | rna-XM_008442338.2 10007596 | 6 | 3331767 | 3331873 | Cucumis melo 3656 | CAG|GTATTTTTTT...CATTTTTTATTT/TTTATTTTCATT...TTCAG|GCA | 1 | 1 | 49.915 | 
| 55033764 | GT-AG | 0 | 0.0013625961391468 | 861 | rna-XM_008442338.2 10007596 | 7 | 3330738 | 3331598 | Cucumis melo 3656 | CAG|GTTCTCTTTC...ACATTCTTGAAA/GACATGCTGATA...TGCAG|AAT | 1 | 1 | 55.654 | 
| 55033765 | GT-AG | 0 | 1.000000099473604e-05 | 643 | rna-XM_008442338.2 10007596 | 8 | 3329840 | 3330482 | Cucumis melo 3656 | ATG|GTAAGTGGCT...TAACTGTTAATG/CTTCATCTAACG...AACAG|GGA | 1 | 1 | 64.366 | 
| 55036616 | GT-AG | 0 | 0.0002634774680579 | 133 | rna-XM_008442338.2 10007596 | 1 | 3335536 | 3335668 | Cucumis melo 3656 | TAA|GTACGAATTA...TTTGCTTTATCT/TTTTGCTTTATC...TGTAG|GTG | 0 | 18.825 | 
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]);