Skip to content

Commit

Permalink
Initial example file upload
Browse files Browse the repository at this point in the history
  • Loading branch information
@ossmith
ossmith authored Nov 14, 2022
1 parent 8835492 commit c1f1e18
Show file tree
Hide file tree
Showing 7 changed files with 3,642 additions and 0 deletions.
123 changes: 123 additions & 0 deletions example_files/example.annotation
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,123 @@
## ENSEMBL VARIANT EFFECT PREDICTOR v108.1
## Output produced at 2022-11-13 22:57:45
## Using cache in ./homo_sapiens/105_GRCh37
## Using API version 108, DB version ?
## ensembl-variation version 108.a885ada
## ensembl version 108.d8a9c80
## ensembl-io version 108.58d13c1
## ensembl-funcgen version 108.56bb136
## gnomAD version r2.1
## dbSNP version 154
## COSMIC version 92
## ClinVar version 202012
## polyphen version 2.2.2
## sift version sift5.2.2
## genebuild version 2011-04
## HGMD-PUBLIC version 20204
## 1000genomes version phase3
## assembly version GRCh37.p13
## regbuild version 1.0
## gencode version GENCODE 19
## Column descriptions:
## Uploaded_variation : Identifier of uploaded variant
## Location : Location of variant in standard coordinate format (chr:start or chr:start-end)
## Allele : The variant allele used to calculate the consequence
## Gene : Stable ID of affected gene
## Feature : Stable ID of feature
## Feature_type : Type of feature - Transcript, RegulatoryFeature or MotifFeature
## Consequence : Consequence type
## cDNA_position : Relative position of base pair in cDNA sequence
## CDS_position : Relative position of base pair in coding sequence
## Protein_position : Relative position of amino acid in protein
## Amino_acids : Reference and variant amino acids
## Codons : Reference and variant codon sequence
## Existing_variation : Identifier(s) of co-located known variants
## Extra column keys:
## IMPACT : Subjective impact classification of consequence type
## DISTANCE : Shortest distance from variant to transcript
## STRAND : Strand of the feature (1/-1)
## FLAGS : Transcript quality flags
## BIOTYPE : Biotype of transcript or regulatory feature
## NEAREST : Identifier(s) of nearest transcription start site
## VEP command-line: vep --offline --cache --dir_cache . -i HARE_results/example.snps -o HARE_results/example.annotation --nearest gene --cache_version 105 --distance 5000 --biotype --force_overwrite
#Uploaded_variation Location Allele Gene Feature Feature_type Consequence cDNA_position CDS_position Protein_position Amino_acids Codons Existing_variation Extra
rs4908936 1:5963669 C ENSG00000131697 ENST00000378156 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000069424
rs4908936 1:5963669 C ENSG00000131697 ENST00000378169 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000069424
rs4908936 1:5963669 C ENSG00000131697 ENST00000466897 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;FLAGS=cds_start_NF;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000069424
rs4908936 1:5963669 C ENSG00000131697 ENST00000478423 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=processed_transcript;NEAREST=ENSG00000069424
rs4908936 1:5963669 C ENSG00000131697 ENST00000489180 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000069424
rs4411131 1:116164626 C ENSG00000207502 ENST00000384771 Transcript non_coding_transcript_exon_variant 1 - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=snoRNA;NEAREST=ENSG00000173218
rs10800714 1:200562117 A ENSG00000118193 ENST00000367350 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000118193
rs189606623 3:46432609 C ENSG00000223552 ENST00000451485 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000121797
rs6548981 3:68148825 T ENSG00000183662 ENST00000478136 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000183662
rs6548981 3:68148825 T ENSG00000183662 ENST00000496687 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000183662
rs4600819 3:163285923 A - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000090402
rs74505207 4:759883 A ENSG00000185619 ENST00000362003 Transcript 3_prime_UTR_variant 1140 - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000185619 ENST00000430644 Transcript 3_prime_UTR_variant,NMD_transcript_variant 2117 - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000185619 ENST00000440452 Transcript 3_prime_UTR_variant,NMD_transcript_variant 2108 - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000233799 ENST00000454037 Transcript upstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=1021;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000185619 ENST00000470161 Transcript 3_prime_UTR_variant 1139 - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000185619 ENST00000488032 Transcript downstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=4731;STRAND=1;BIOTYPE=processed_transcript;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000249592 ENST00000503571 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000185619 ENST00000505655 Transcript 3_prime_UTR_variant 789 - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000249592 ENST00000507446 Transcript downstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=1046;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000185619
rs74505207 4:759883 A ENSG00000185619 ENST00000521023 Transcript 3_prime_UTR_variant 2108 - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000185619
rs374109 5:10012518 G - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000150756
rs6892991 5:25609505 G - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000040731
rs356561 5:63328721 C - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000178394
rs10037878 5:100529927 A - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000113532
rs35765330 5:128579817 C - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000066583
rs114006078 6:31211473 A - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000204525
rs2931085 6:120662994 C - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000111885
rs17867623 7:89979275 A ENSG00000105793 ENST00000222511 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000257659 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000380058 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000417207 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;FLAGS=cds_end_NF;BIOTYPE=protein_coding;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000421719 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000426366 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;FLAGS=cds_end_NF;BIOTYPE=protein_coding;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000439832 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000450619 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;FLAGS=cds_end_NF;BIOTYPE=protein_coding;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000453512 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000474503 Transcript upstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=4567;STRAND=1;BIOTYPE=processed_transcript;NEAREST=ENSG00000105793
rs17867623 7:89979275 A ENSG00000105793 ENST00000477972 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=retained_intron;NEAREST=ENSG00000105793
rs10827956 10:20365362 T ENSG00000120594 ENST00000377238 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=processed_transcript;NEAREST=ENSG00000120594
rs10827956 10:20365362 T ENSG00000120594 ENST00000377242 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000120594
rs10827956 10:20365362 T ENSG00000120594 ENST00000377252 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000120594
rs10827956 10:20365362 T ENSG00000238246 ENST00000451584 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000120594
rs7932988 11:10094476 C ENSG00000133812 ENST00000256190 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000133812
rs7932988 11:10094476 C ENSG00000133812 ENST00000533770 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=retained_intron;NEAREST=ENSG00000133812
rs118067598 12:42810387 T ENSG00000134283 ENST00000256678 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000317560 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000337898 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000358314 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000395568 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000395580 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000432191 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000449194 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000549190 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs118067598 12:42810387 T ENSG00000134283 ENST00000552761 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000139174
rs34193955 13:94042801 A ENSG00000183098 ENST00000377047 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000183098
rs34193955 13:94042801 A ENSG00000235784 ENST00000426409 Transcript downstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=4429;STRAND=-1;BIOTYPE=processed_pseudogene;NEAREST=ENSG00000183098
rs2543388 14:76629268 G ENSG00000089916 ENST00000261530 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000089916
rs2543388 14:76629268 G ENSG00000089916 ENST00000312858 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000089916
rs2543388 14:76629268 G ENSG00000089916 ENST00000554125 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=retained_intron;NEAREST=ENSG00000089916
rs2543388 14:76629268 G ENSG00000089916 ENST00000554375 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000089916
rs2543388 14:76629268 G ENSG00000089916 ENST00000556663 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000089916
rs2543388 14:76629268 G ENSG00000089916 ENST00000557263 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000089916
rs117034934 15:96760479 G ENSG00000247809 ENST00000559505 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000205148
rs117034934 15:96760479 G ENSG00000247809 ENST00000560800 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=antisense;NEAREST=ENSG00000205148
rs77508211 16:54447249 A - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000177508
rs9906524 17:4111727 A ENSG00000185722 ENST00000341657 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000185722
rs9906524 17:4111727 A ENSG00000185722 ENST00000433651 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000185722
rs9906524 17:4111727 A ENSG00000185722 ENST00000570535 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000185722
rs9906524 17:4111727 A ENSG00000185722 ENST00000570934 Transcript intron_variant,non_coding_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=retained_intron;NEAREST=ENSG00000185722
rs9906524 17:4111727 A ENSG00000185722 ENST00000572412 Transcript intron_variant,NMD_transcript_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=nonsense_mediated_decay;NEAREST=ENSG00000185722
rs9906524 17:4111727 A ENSG00000185722 ENST00000573250 Transcript upstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=300;STRAND=-1;BIOTYPE=retained_intron;NEAREST=ENSG00000185722
rs9906524 17:4111727 A ENSG00000185722 ENST00000574367 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=-1;BIOTYPE=protein_coding;NEAREST=ENSG00000185722
rs78148126 18:63872801 G - - - intergenic_variant - - - - - - IMPACT=MODIFIER;NEAREST=ENSG00000071991
rs722568 20:11285245 T ENSG00000230990 ENST00000444792 Transcript upstream_gene_variant - - - - - - IMPACT=MODIFIER;DISTANCE=3072;STRAND=-1;BIOTYPE=lincRNA;NEAREST=ENSG00000125899
rs11089810 22:37323638 T ENSG00000100368 ENST00000262825 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000100368
rs11089810 22:37323638 T ENSG00000100368 ENST00000403662 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000100368
rs11089810 22:37323638 T ENSG00000100368 ENST00000406230 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000100368
rs11089810 22:37323638 T ENSG00000100368 ENST00000421539 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;FLAGS=cds_end_NF;BIOTYPE=protein_coding;NEAREST=ENSG00000100368
rs11089810 22:37323638 T ENSG00000100368 ENST00000536485 Transcript intron_variant - - - - - - IMPACT=MODIFIER;STRAND=1;BIOTYPE=protein_coding;NEAREST=ENSG00000100368
13 changes: 13 additions & 0 deletions example_files/example.biomart
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
ENSEMBL_ID START END CHR GENE_NAME STRAND
ENSG00000069424 6051526 6161253 1 KCNAB2 1
ENSG00000089916 76618259 76720685 14 GPATCH2L 1
ENSG00000100368 37309670 37336491 22 CSF2RB 1
ENSG00000105793 89964537 90020769 7 GTPBP10 1
ENSG00000118193 200520628 200589862 1 KIF14 -1
ENSG00000120594 20105168 20578785 10 PLXDC2 1
ENSG00000133812 9800214 10315754 11 SBF2 -1
ENSG00000139174 42852140 42984157 12 PRICKLE1 -1
ENSG00000183098 93879095 95059655 13 GPC6 1
ENSG00000183662 68053359 68594776 3 FAM19A1 1
ENSG00000185619 699537 764428 4 PCGF3 1
ENSG00000185722 4067201 4167274 17 ANKFY1 -1
Loading

0 comments on commit c1f1e18

Please sign in to comment.