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)
 
14 rows where transcript_id = 3395315
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 | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 16698655 | GT-AG | 0 | 1.000000099473604e-05 | 587 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 1 | 161371 | 161957 | Arenaria interpres 54971 | CAA|GTGAGTCCCG...GTCTCCCAAACC/CCGTCTCCCAAA...CCCAG|GTG | 2 | 1 | 5.003 | 
| 16698656 | GT-AG | 0 | 1.000000099473604e-05 | 487 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 2 | 160737 | 161223 | Arenaria interpres 54971 | GAG|GTGAGGACCC...CTGGCATCAGTG/CCTGGCATCAGT...CACAG|TGA | 2 | 1 | 13.266 | 
| 16698657 | GT-AG | 0 | 1.000000099473604e-05 | 109 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 3 | 160477 | 160585 | Arenaria interpres 54971 | GAG|GTGGGTCCCT...TCCATCTCACCA/CTCCATCTCACC...TCCAG|CTG | 0 | 1 | 21.754 | 
| 16698658 | GT-AG | 0 | 1.000000099473604e-05 | 157 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 4 | 160253 | 160409 | Arenaria interpres 54971 | AGG|GTGAGGAGGG...GTCCCCTGAGCC/TGTCCCCTGAGC...TGCAG|AGC | 1 | 1 | 25.52 | 
| 16698659 | GT-AG | 0 | 1.000000099473604e-05 | 388 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 5 | 159821 | 160208 | Arenaria interpres 54971 | AAG|GTAAGTGCCG...GGGTGCTCAGCC/TGGGTGCTCAGC...TCCAG|CAC | 0 | 1 | 27.993 | 
| 16698660 | GT-AG | 0 | 0.0001255336103962 | 601 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 7 | 158954 | 159554 | Arenaria interpres 54971 | AAG|GTACACACCT...GTTTCCGTCTCT/GTCTCTCCCATG...GGCAG|GTG | 0 | 1 | 34.907 | 
| 16698661 | GT-AG | 0 | 1.000000099473604e-05 | 338 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 8 | 158456 | 158793 | Arenaria interpres 54971 | TGC|GTAAGGGCCG...CCACCCTTCATC/CTGGTTTTCACC...CGCAG|CTT | 1 | 1 | 43.901 | 
| 16698662 | GT-AG | 0 | 1.000000099473604e-05 | 328 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 9 | 158015 | 158342 | Arenaria interpres 54971 | TCG|GTCAGTGCCC...GACCCCTCACCC/GGACCCCTCACC...CCCAG|TCC | 0 | 1 | 50.253 | 
| 16698663 | GT-AG | 0 | 1.000000099473604e-05 | 88 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 10 | 157688 | 157775 | Arenaria interpres 54971 | CAA|GTGAGTACCA...CTTGTTTTACCC/TCTTGTTTTACC...TGCAG|GTC | 2 | 1 | 63.687 | 
| 16698664 | GT-AG | 0 | 1.000000099473604e-05 | 203 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 11 | 157376 | 157578 | Arenaria interpres 54971 | GAG|GTGAGCGCTC...CCATCCCTGCCG/ATATCCCCCATC...TCCAG|GGA | 0 | 1 | 69.815 | 
| 16698665 | GT-AG | 0 | 1.000000099473604e-05 | 402 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 12 | 156862 | 157263 | Arenaria interpres 54971 | AAG|GTACGACACG...CAGCCCCTGCTC/GCCCCACTCAGC...CTCAG|AGC | 1 | 1 | 76.11 | 
| 16698666 | GT-AG | 0 | 1.000000099473604e-05 | 142 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 13 | 156523 | 156664 | Arenaria interpres 54971 | GAG|GTAGGAGCTG...CCTTTTTTAATT/CCTTTTTTAATT...TGCAG|TCA | 0 | 1 | 87.184 | 
| 16698667 | GT-AG | 0 | 0.0001559965028456 | 311 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 14 | 156146 | 156456 | Arenaria interpres 54971 | GAG|GTAACTGTCA...TAATCCTCACTG/CTAATCCTCACT...CGCAG|GGC | 0 | 1 | 90.894 | 
| 16698668 | GT-AG | 0 | 1.000000099473604e-05 | 1555 | rna-gnl|WGS:VXAK|AREINT_R12031_mrna 3395315 | 15 | 154542 | 156096 | Arenaria interpres 54971 | ACG|GTAAAAGGCT...ACTGCCTTAACT/ACTGCCTTAACT...TCCAG|GCC | 1 | 1 | 93.648 | 
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]);