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)
 
12 rows where transcript_id = 8205956
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 | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 43958600 | GT-AG | 0 | 1.000000099473604e-05 | 54647 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 1 | 2714368 | 2769014 | Chloropsis hardwickii 667144 | GTG|GTAAGTGACT...ATGTCTTGGACA/TTTGAACTGATT...TTCAG|ACA | 0 | 1 | 16.25 | 
| 43958601 | GT-AG | 0 | 1.000000099473604e-05 | 3164 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 2 | 2769129 | 2772292 | Chloropsis hardwickii 667144 | ATT|GTAAGTGCCA...TTTGCTTTTTTT/GATTATCTAATT...CCTAG|GGG | 0 | 1 | 22.188 | 
| 43958602 | GT-AG | 0 | 1.000000099473604e-05 | 8030 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 3 | 2772449 | 2780478 | Chloropsis hardwickii 667144 | GAG|GTTGGTTATC...CGCTCTATAACT/TTCTGTTTCATT...AAAAG|AAA | 0 | 1 | 30.312 | 
| 43958603 | GT-AG | 0 | 0.0001304966491264 | 4137 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 4 | 2780590 | 2784726 | Chloropsis hardwickii 667144 | ATG|GTAAGTTTCC...TTCTCTTTATTT/GTTCTCTTTATT...TGTAG|GTT | 0 | 1 | 36.094 | 
| 43958604 | GT-AG | 0 | 1.000000099473604e-05 | 25129 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 5 | 2784990 | 2810118 | Chloropsis hardwickii 667144 | AAG|GTAGGATGGT...AACCACTTGAAT/ACTTGAATTATT...TGCAG|ACG | 2 | 1 | 49.792 | 
| 43958605 | GT-AG | 0 | 1.000000099473604e-05 | 5381 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 6 | 2810306 | 2815686 | Chloropsis hardwickii 667144 | ATG|GTGAGTTTAA...TCTGATTTAATT/ATTTAATTTATT...TATAG|GAA | 0 | 1 | 59.531 | 
| 43958606 | GT-AG | 0 | 1.000000099473604e-05 | 6204 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 7 | 2815772 | 2821975 | Chloropsis hardwickii 667144 | CAA|GTAAGTGAGC...GTTTTCTTATTA/GGTTTTCTTATT...CTTAG|ATC | 1 | 1 | 63.958 | 
| 43958607 | GT-AG | 0 | 1.000000099473604e-05 | 2110 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 8 | 2822056 | 2824165 | Chloropsis hardwickii 667144 | AGG|GTAAGTAAAT...ATGAATTTAAAG/CATGAATTTAAA...ACTAG|GGA | 0 | 1 | 68.125 | 
| 43958608 | GT-AG | 0 | 1.000000099473604e-05 | 6218 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 9 | 2824304 | 2830521 | Chloropsis hardwickii 667144 | GAG|GTATGACAAC...ACTCTGTTGATG/CCAGGATTCACT...TCCAG|AAA | 0 | 1 | 75.312 | 
| 43958609 | GT-AG | 0 | 1.000000099473604e-05 | 1137 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 10 | 2830633 | 2831769 | Chloropsis hardwickii 667144 | AAG|GTAATAATCT...AAAATCTTTGTG/CAATTGTTCATG...TTCAG|CAA | 0 | 1 | 81.094 | 
| 43958610 | GT-AG | 0 | 1.6397021098339885e-05 | 1999 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 11 | 2831928 | 2833926 | Chloropsis hardwickii 667144 | CAG|GTAATTAGCC...AATTCCTTGATC/GTGAACTTCATT...TTCAG|TGC | 2 | 1 | 89.323 | 
| 43958611 | GT-AG | 0 | 1.000000099473604e-05 | 6275 | rna-gnl|WGS:WEIW|CHLHAR_R11550_mrna 8205956 | 12 | 2834041 | 2840315 | Chloropsis hardwickii 667144 | TCG|GTGAGTTCCA...GCAGTCTAGAAA/TAAGATTTCAGT...TCCAG|GGG | 2 | 1 | 95.26 | 
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]);