struct
let major_contigs_b37 =
List.init 22 (fun i -> sprintf "%d" (i + 1))
@ ["X"; "Y"; "MT";]
let major_contigs_hg_family =
List.init 22 (fun i -> sprintf "chr%d" (i + 1))
@ [
"chrX";
"chrY";
"chrM";
]
let major_contigs_mm10 =
List.init 19 (fun i -> sprintf "%d" (i + 1))
@ [ "X"; "Y" ]
module Name = struct
let b37 = "b37"
let b37decoy = "b37decoy"
let b38 = "b38"
let hg38 = "hg38"
let hg18 = "hg18"
let hg19 = "hg19"
let mm10 = "mm10"
end
let b37_dbsnp_url =
"https://storage.googleapis.com/hammerlab-biokepi-data/raw_data/dbsnp_138.b37.vcf.gz"
let b37_cosmic_url =
"http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/mutect/b37_cosmic_v54_120711.vcf"
let b37_exome_gtf_url =
"http://ftp.ensembl.org/pub/release-75/gtf/homo_sapiens/Homo_sapiens.GRCh37.75.gtf.gz"
let b37_cdna_url =
"http://ftp.ensembl.org/pub/release-75/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh37.75.cdna.all.fa.gz"
let b37_whess_url =
"ftp://genetics.bwh.harvard.edu/pph2/whess/polyphen-2.2.2-whess-2011_12.sqlite.bz2"
let b37_known_indels_url =
"https://storage.googleapis.com/hammerlab-biokepi-data/raw_data/Mills_and_1000G_gold_standard.indels.b37.vcf.gz"
let human = "homo sapiens"
let mouse = "mus musculus"
let b37 =
create Name.b37
~species:human
~ensembl:75
~metadata:"Provided by the Biokepi library"
~major_contigs:major_contigs_b37
~fasta:Location.(
url "ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/2.8/b37/human_g1k_v37.fasta.gz"
|> gunzip)
~dbsnp:Location.(url b37_dbsnp_url |> gunzip)
~known_indels:Location.(url b37_known_indels_url |> gunzip)
~cosmic:Location.(url b37_cosmic_url)
~exome_gtf:Location.(url b37_exome_gtf_url |> gunzip)
~cdna:Location.(url b37_cdna_url |> gunzip)
~whess:Location.(url b37_whess_url |> bunzip2)
~snpeff_name:"GRCh37.75"
let b37decoy =
create Name.b37decoy
~species:human
~ensembl:75
~metadata:"Provided by the Biokepi library"
~major_contigs:major_contigs_b37
~fasta:Location.(
url
"ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/phase2_reference_assembly_sequence/hs37d5.fa.gz"
|> gunzip)
~dbsnp:Location.(url b37_dbsnp_url |> gunzip)
~known_indels:Location.(url b37_known_indels_url |> gunzip)
~exome_gtf:Location.(url b37_exome_gtf_url |> gunzip)
~cosmic:Location.(url b37_cosmic_url)
~cdna:Location.(url b37_cdna_url |> gunzip)
~whess:Location.(url b37_whess_url |> bunzip2)
~snpeff_name:"GRCh37.75"
let hg38 =
let hg38_url =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/hg38/hg38bundle/Homo_sapiens_assembly38.fasta.gz" in
let dbsnp_hg38 =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/hg38/hg38bundle/Homo_sapiens_assembly38.dbsnp.vcf.gz" in
let known_indels_hg38 =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/hg38/hg38bundle/Homo_sapiens_assembly38.known_indels.vcf.gz" in
create Name.hg38
~species:human
~ensembl:87
~metadata:"Provided by the Biokepi library"
~major_contigs:major_contigs_hg_family
~fasta:Location.(url hg38_url|> gunzip)
~dbsnp:Location.(url dbsnp_hg38 |> gunzip)
~known_indels:Location.(url known_indels_hg38 |> gunzip)
~snpeff_name:"GRCh38.86"
let b38 =
let b38_url =
"http://ftp.ensembl.org/pub/release-87/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz" in
let gtf_b38_url =
"http://ftp.ensembl.org/pub/release-87/gtf/homo_sapiens/Homo_sapiens.GRCh38.87.gtf.gz" in
let cdna_b38_url =
"http://ftp.ensembl.org/pub/release-87/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh38.cdna.all.fa.gz" in
let dbsnp_url =
"http://ftp.ncbi.nlm.nih.gov/snp/organisms/human_9606_b150_GRCh38p7/VCF/common_all_20170710.vcf.gz" in
create Name.b38
~species:human
~ensembl:87
~metadata:"Provided by the Biokepi library"
~major_contigs:major_contigs_b37
~fasta:Location.(url b38_url |> gunzip)
~exome_gtf:Location.(url gtf_b38_url |> gunzip)
~dbsnp:Location.(url dbsnp_url |> gunzip)
~cdna:Location.(url cdna_b38_url |> gunzip)
~snpeff_name:"GRCh38.86"
let hg18 =
let hg18_url =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/2.8/hg18/Homo_sapiens_assembly18.fasta.gz" in
let dbsnp_hg18_url =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/2.8/hg18/dbsnp_138.hg18.vcf.gz" in
create Name.hg18
~ensembl:54
~species:human
~metadata:"Provided by the Biokepi library"
~major_contigs:major_contigs_hg_family
~fasta:Location.(url hg18_url|> gunzip)
~dbsnp:Location.(url dbsnp_hg18_url |> gunzip)
let hg19 =
let hg19_url =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/2.8/hg19/ucsc.hg19.fasta.gz" in
let dbsnp_hg19_url =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/2.8/hg19/dbsnp_138.hg19.vcf.gz" in
let known_indels_hg19_url =
"ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/2.8/hg19/Mills_and_1000G_gold_standard.indels.hg19.sites.vcf.gz" in
create Name.hg19
~ensembl:75
~species:human
~metadata:"Provided by the Biokepi library"
~major_contigs:major_contigs_hg_family
~fasta:Location.(url hg19_url|> gunzip)
~dbsnp:Location.(url dbsnp_hg19_url |> gunzip)
~known_indels:Location.(url known_indels_hg19_url |> gunzip)
~whess:Location.(url b37_whess_url |> bunzip2)
~snpeff_name:"hg19"
let mm10 =
let mm10_url =
"https://storage.googleapis.com/hammerlab-biokepi-data/raw_data/mm10.GRCm38.dna_sm.fa" in
let dbsnp_mm10_snps_url =
"ftp://ftp-mouse.sanger.ac.uk/REL-1303-SNPs_Indels-GRCm38/mgp.v3.snps.rsIDdbSNPv137.vcf.gz" in
let dbsnp_mm10_indels_url =
"ftp://ftp-mouse.sanger.ac.uk/REL-1303-SNPs_Indels-GRCm38/mgp.v3.indels.rsIDdbSNPv137.vcf.gz" in
let gene_annotations_gtf =
"ftp://ftp.ensembl.org/pub/release-84/gtf/mus_musculus/Mus_musculus.GRCm38.84.gtf.gz" in
let cdna_mm10_url =
"ftp://ftp.ensembl.org/pub/release-84/fasta/mus_musculus/cdna/Mus_musculus.GRCm38.cdna.all.fa.gz" in
create Name.mm10
~ensembl:87
~species:mouse
~metadata:"Provided by the Biokepi Library"
~major_contigs:major_contigs_mm10
~fasta:Location.(url mm10_url |> gunzip)
~dbsnp:Location.(
vcf_concat ["db_snps.vcf", url dbsnp_mm10_snps_url |> gunzip;
"db_indels.vcf", url dbsnp_mm10_indels_url |> gunzip]
)
~exome_gtf:Location.(url gene_annotations_gtf |> gunzip)
~cdna:Location.(url cdna_mm10_url |> gunzip)
~snpeff_name:"mm10"
end