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)
 
9 rows where transcript_id = 8855885
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 | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 47813000 | GT-AG | 0 | 0.0080698296546339 | 1093 | rna-XM_027248501.1 8855885 | 1 | 38707412 | 38708504 | Coffea arabica 13443 | AAG|GTCTGCTTCT...ATTCTTTTAATG/ATTCTTTTAATG...CACAG|GTG | 1 | 1 | 4.155 | 
| 47813001 | GT-AG | 0 | 0.1652195655461292 | 406 | rna-XM_027248501.1 8855885 | 2 | 38705314 | 38705719 | Coffea arabica 13443 | CAG|GTATACTTTT...TCTTTCTTCACA/TCTTTCTTCACA...CACAG|GAG | 1 | 1 | 45.024 | 
| 47813002 | GT-AG | 0 | 1.000000099473604e-05 | 111 | rna-XM_027248501.1 8855885 | 3 | 38704943 | 38705053 | Coffea arabica 13443 | GTG|GTTAGTCCAT...TGCCCGTTAATA/ACGAGTCTCATC...TATAG|GTA | 0 | 1 | 51.304 | 
| 47813003 | GT-AG | 0 | 8.510227356526232e-05 | 124 | rna-XM_027248501.1 8855885 | 4 | 38704609 | 38704732 | Coffea arabica 13443 | GAG|GTATTGTCAA...GCTGTTGTAATT/ACCAAATTCATC...TCCAG|ATC | 0 | 1 | 56.377 | 
| 47813004 | GT-AG | 0 | 1.000000099473604e-05 | 390 | rna-XM_027248501.1 8855885 | 5 | 38704000 | 38704389 | Coffea arabica 13443 | CCT|GTGAGTATTA...GTTTCCATAGCC/CAAGAACTAACA...GTTAG|GTT | 0 | 1 | 61.667 | 
| 47813005 | GT-AG | 0 | 0.7862437083271296 | 602 | rna-XM_027248501.1 8855885 | 6 | 38702432 | 38703033 | Coffea arabica 13443 | CAG|GTATCTTTCA...CCTCTTTTCACA/ACATATTTCATT...TGTAG|GCA | 0 | 1 | 85.0 | 
| 47813006 | GT-AG | 0 | 2.043677427505433e-05 | 207 | rna-XM_027248501.1 8855885 | 7 | 38702129 | 38702335 | Coffea arabica 13443 | GAG|GTAAATTTGT...TGTTTTTTGTTT/TTTGGTCTCAGA...TGCAG|GTA | 0 | 1 | 87.319 | 
| 47813007 | GT-AG | 0 | 1.000000099473604e-05 | 185 | rna-XM_027248501.1 8855885 | 8 | 38701845 | 38702029 | Coffea arabica 13443 | CAG|GTTAGTGAGC...GAGTTCATAGCC/ACTGAGTTCATA...TACAG|ATC | 0 | 1 | 89.71 | 
| 47813008 | GT-AG | 0 | 0.1615535049560145 | 658 | rna-XM_027248501.1 8855885 | 9 | 38700997 | 38701654 | Coffea arabica 13443 | AAG|GTATCTCTGC...GATTTTTAAGCT/GGATTTTTAAGC...TGTAG|CCT | 1 | 1 | 94.3 | 
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]);