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"