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 = 24953030
This data as json, CSV (advanced)
Suggested facets: score, 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 | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 137151309 | GT-AG | 0 | 9.565863441426773e-05 | 382 | rna-XM_041412849.1 24953030 | 2 | 1157871 | 1158252 | Onychostruthus taczanowskii 356909 | TTG|GTATGTGGCT...AGCATCTTGCTA/GCTAGGTTAACA...CTCAG|CTC | 2 | 1 | 8.659 | 
| 137151310 | GT-AG | 0 | 0.0001274618166951 | 905 | rna-XM_041412849.1 24953030 | 3 | 1158357 | 1159261 | Onychostruthus taczanowskii 356909 | GGT|GTAAGTGTCT...GTTTCCTTCACA/GTTTCCTTCACA...TGCAG|TCT | 1 | 1 | 11.421 | 
| 137151311 | GT-AG | 0 | 1.000000099473604e-05 | 790 | rna-XM_041412849.1 24953030 | 4 | 1159525 | 1160314 | Onychostruthus taczanowskii 356909 | CTG|GTGAGTGACA...CCTGCCTGGACC/AGCTGGTTGACA...CACAG|ATC | 0 | 1 | 18.406 | 
| 137151312 | GT-AG | 0 | 1.000000099473604e-05 | 14422 | rna-XM_041412849.1 24953030 | 5 | 1160383 | 1174804 | Onychostruthus taczanowskii 356909 | GAG|GTGAGTCCAG...CCTGCCTTGTCC/TTGTGCTTCACA...CTCAG|ATA | 2 | 1 | 20.212 | 
| 137151313 | GT-AG | 0 | 1.000000099473604e-05 | 3090 | rna-XM_041412849.1 24953030 | 6 | 1174993 | 1178082 | Onychostruthus taczanowskii 356909 | GTG|GTGAGTCCCT...CACCCCTCATTT/CCACCCCTCATT...TCTAG|GAG | 1 | 1 | 25.206 | 
| 137151314 | GT-AG | 0 | 6.117294468308475e-05 | 836 | rna-XM_041412849.1 24953030 | 7 | 1178734 | 1179569 | Onychostruthus taczanowskii 356909 | CAG|GTAAGCCTTG...TTTTCCTTTTTT/AACTTTGTAAAT...TACAG|CTT | 1 | 1 | 42.497 | 
| 137154329 | GT-AG | 0 | 1.000000099473604e-05 | 17086 | rna-XM_041412849.1 24953030 | 1 | 1140666 | 1157751 | Onychostruthus taczanowskii 356909 | GAG|GTGAGTCAGC...CCTTCCTTCATT/CCTTCCTTCATT...TTTAG|AAC | 0 | 5.578 | 
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]);