Resolving indel fixes.

charite · May 3, 2019 · 57c6bd9 · 57c6bd9
1 parent 01ad62a
commit 57c6bd9
Show file tree

Hide file tree

Showing 2 changed files with 69 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,7 @@
 * Adding support for rn6 RefSeq transcripts.
   Adding `allowNonCodingNm` directive for data source INI file to disable check that RefSeq NM transcript has CDS.
 * Adding versions to ENST accessions for ENSEMBL.
+* Resolving indel problem for RefSeq transcripts (see issue #447).
 
 ## v0.28
 

diff --git a/jannovar-cli/src/main/resources/default_sources.ini b/jannovar-cli/src/main/resources/default_sources.ini
@@ -169,6 +169,51 @@ chrToAccessions.format=chr_accessions
 gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GRCh37.p13_interim_annotation/interim_GRCh37.p13_top_level_2017-01-13.gff3.gz
 rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GRCh37.p13_interim_annotation/interim_GRCh37.p13_rna.fa.gz
 
+; HG19 from RefSeq
+[hg19/refseq_fixindels]
+type=refseq
+alias=MT,M,chrM
+chromInfo=http://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/chromInfo.txt.gz
+chrToAccessions=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/Assembled_chromosomes/chr_accessions_GRCh37.p13
+chrToAccessions.format=chr_accessions
+gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/GFF/ref_GRCh37.p13_top_level.gff3.gz
+rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/RNA/rna.fa.gz
+
+; HG19 from RefSeq (only curated data sets)
+[hg19/refseq_curated_fixindels]
+type=refseq
+alias=MT,M,chrM
+onlyCurated=true
+fixIndels=true
+chromInfo=http://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/chromInfo.txt.gz
+chrToAccessions=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/Assembled_chromosomes/chr_accessions_GRCh37.p13
+chrToAccessions.format=chr_accessions
+gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/GFF/ref_GRCh37.p13_top_level.gff3.gz
+rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/RNA/rna.fa.gz
+
+; HG19 from RefSeq interim alignment (see https://www.ncbi.nlm.nih.gov/books/NBK430989/#_news_02-14-2017-interim-annotation-update-human_)
+[hg19/refseq_interim_fixindels]
+type=refseq
+alias=MT,M,chrM
+fixIndels=true
+chromInfo=http://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/chromInfo.txt.gz
+chrToAccessions=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/Assembled_chromosomes/chr_accessions_GRCh37.p13
+chrToAccessions.format=chr_accessions
+gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GRCh37.p13_interim_annotation/interim_GRCh37.p13_top_level_2017-01-13.gff3.gz
+rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GRCh37.p13_interim_annotation/interim_GRCh37.p13_rna.fa.gz
+
+; HG19 from RefSeq interim alignment, only curated (see https://www.ncbi.nlm.nih.gov/books/NBK430989/#_news_02-14-2017-interim-annotation-update-human_)
+[hg19/refseq_interim_curated_fixindels]
+type=refseq
+alias=MT,M,chrM
+onlyCurated=true
+fixIndels=true
+chromInfo=http://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/chromInfo.txt.gz
+chrToAccessions=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/ARCHIVE/ANNOTATION_RELEASE.105/Assembled_chromosomes/chr_accessions_GRCh37.p13
+chrToAccessions.format=chr_accessions
+gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GRCh37.p13_interim_annotation/interim_GRCh37.p13_top_level_2017-01-13.gff3.gz
+rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GRCh37.p13_interim_annotation/interim_GRCh37.p13_rna.fa.gz
+
 ; ---------------------------------------------------------------------------
 ; hg38/GRCh38
 ; ---------------------------------------------------------------------------
@@ -220,6 +265,29 @@ chrToAccessions.format=chr_accessions
 gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GFF/ref_GRCh38.p12_top_level.gff3.gz
 rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/RNA/rna.fa.gz
 
+; HG38 from RefSeq (fixed indels)
+[hg38/refseq_fixindel]
+type=refseq
+alias=MT,M,chrM
+fixIndels=true
+chromInfo=http://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/chromInfo.txt.gz
+chrToAccessions=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/Assembled_chromosomes/chr_accessions_GRCh38.p12
+chrToAccessions.format=chr_accessions
+gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GFF/ref_GRCh38.p12_top_level.gff3.gz
+rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/RNA/rna.fa.gz
+
+; HG38 from RefSeq (only curated data sets; fixed indels)
+[hg38/refseq_curated_fixindel]
+type=refseq
+alias=MT,M,chrM
+onlyCurated=true
+fixIndels=true
+chromInfo=http://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/chromInfo.txt.gz
+chrToAccessions=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/Assembled_chromosomes/chr_accessions_GRCh38.p12
+chrToAccessions.format=chr_accessions
+gff=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/GFF/ref_GRCh38.p12_top_level.gff3.gz
+rna=ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/RNA/rna.fa.gz
+
 ; ---------------------------------------------------------------------------
 ; mm9
 ; ---------------------------------------------------------------------------