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 = 1668856
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 | 
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 9479410 | GT-AG | 0 | 0.0365299173080926 | 22474 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 1 | 1259782 | 1282255 | Anhinga anhinga 56067 | AAG|GTATCGTGCA...CAGTATTTAATC/CAGTATTTAATC...CCCAG|ACT | 0 | 1 | 9.78 | 
| 9479411 | GT-AG | 0 | 1.000000099473604e-05 | 5746 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 2 | 1253238 | 1258983 | Anhinga anhinga 56067 | AAG|GTAATGTGAC...CCTGCCTTCACT/CCTTCACTCATC...TGCAG|GTG | 0 | 1 | 46.419 | 
| 9479412 | GT-AG | 0 | 4.4422727279522544e-05 | 1766 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 3 | 1250980 | 1252745 | Anhinga anhinga 56067 | GAG|GTACGTTGTT...CCGTCTTTTTCT/TAGCAATTCACA...CCCAG|GTC | 0 | 1 | 69.008 | 
| 9479413 | GT-AG | 0 | 1.000000099473604e-05 | 2026 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 4 | 1248820 | 1250845 | Anhinga anhinga 56067 | GAG|GTGGGTTGGG...TCTTCGTTAACG/TCTTCGTTAACG...TTCAG|GAT | 2 | 1 | 75.161 | 
| 9479414 | GT-AG | 0 | 1.000000099473604e-05 | 2899 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 5 | 1245794 | 1248692 | Anhinga anhinga 56067 | AGG|GTGAGTGCCC...TTTTCTTTTTCT/GGCCATGTTATC...TTCAG|ATA | 0 | 1 | 80.992 | 
| 9479415 | GT-AG | 0 | 1.000000099473604e-05 | 2083 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 6 | 1243585 | 1245667 | Anhinga anhinga 56067 | GAG|GTGAGCACAG...CCCCCCTCACTG/ACCCCCCTCACT...TACAG|GTG | 0 | 1 | 86.777 | 
| 9479416 | GT-AG | 0 | 1.000000099473604e-05 | 659 | rna-gnl|WGS:WBMU|ANHANH_R10349_mrna 1668856 | 7 | 1242791 | 1243449 | Anhinga anhinga 56067 | AAG|GTCAGACTCC...GTGTCTTTGCCC/CCGCTCCTAACG...TGCAG|GTC | 0 | 1 | 92.975 | 
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]);