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 = 35103487

✎ View and edit SQL

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
197657292 GT-AG 0 7.017891050618612e-05 663 rna-XM_007050511.2 35103487 2 29525042 29525704 Theobroma cacao 3641 AAA|GTAAATATTT...TTTTTCTCATTT/TTTTTTCTCATT...CTCAG|GCA 0 1 59.886
197657293 GT-AG 0 0.0059888975764272 144 rna-XM_007050511.2 35103487 3 29524762 29524905 Theobroma cacao 3641 AAT|GTATTTGTCT...ATTCATTTGACA/ATGCTATTCATT...TGTAG|ATC 1 1 62.666
197657294 GT-AG 0 0.0905370289998343 472 rna-XM_007050511.2 35103487 4 29524207 29524678 Theobroma cacao 3641 GAG|GTATATTTTT...TTGATCTTGAAG/TTGAAGTTGATC...TGCAG|TTG 0 1 64.363
197657295 GT-AG 0 1.000000099473604e-05 745 rna-XM_007050511.2 35103487 5 29523223 29523967 Theobroma cacao 3641 TGG|GTAAGTGCGC...GAATTATTAATC/GAATTATTAATC...TTCAG|GTC 2 1 69.25
197657296 GT-AG 0 1.3068425450992742e-05 524 rna-XM_007050511.2 35103487 6 29522612 29523135 Theobroma cacao 3641 CAG|GTAAATTTAC...TTTGCCTAAATG/CAGTTATTTACT...AATAG|GGT 2 1 71.028
197657297 GT-AG 0 0.4213969867341272 361 rna-XM_007050511.2 35103487 7 29522151 29522511 Theobroma cacao 3641 TCT|GTATGTCTGA...TTTTCCTTATTT/TTTTTCCTTATT...TTCAG|GCT 0 1 73.073
197671365 GT-AG 0 1.000000099473604e-05 203 rna-XM_007050511.2 35103487 1 29528609 29528811 Theobroma cacao 3641 AAG|GTTTGTGATC...GCTTCTTTACTT/GGCTTCTTTACT...TCCAG|TTA   0 1.922

Advanced export

JSON shape: default, array, newline-delimited, object

CSV options: 

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]);