Auxiliary Data Import

Importing a New Human Reference Genome

$ URI='ftp://ftp.ncbi.nih.gov/genbank/genomes/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh37/special_requests/GRCh37-lite.fa.gz'

$ genome taxon create                                         \
  --domain=Eukaryota                                          \
  --name=human                                                \
  --ncbi-taxon-id=9606                                        \
  --species-latin-name='Homo sapiens'

$ genome processing-profile create imported-reference-sequence --name=chromosome-fastas

$ wget $URI

$ gunzip GRCh37-list.fa.gz

$ genome model define imported-reference-sequence             \
  --fasta-file=$PWD/GRCh37-lite.fa                            \
  --processing-profile-id=2dc430f34746455b87b3dd179b3a193e    \
  --species-name=human                                        \
  --version=37-lite-test                                      \
  --prefix=GRC                                                \
  --assembly-name=GRCh37-lite                                 \
  --build-name=GRCh37-lite-build37                            \
  --sequence-uri=$URI

Creating a Modified Reference from a Previously Imported Reference Genome

$ genome model define imported-reference-sequence
  --append-to=106942997
  --fasta-file=/ERCC/ERCC92.fa
  --use-default-sequence-uri
  --species-name=human
  --version=37_ERCC

Importing a New Version of dbSNP

$ genome model imported-variation-list import-dbsnp-build
  --vcf-file-url ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b141_GRCh37p13/VCF/00-All.vcf.gz
  --version 141
  --reference-sequence-build 106942997
  --flat-file-pattern ds_flat_chX.flat.gz
  --contig-names-translation-file /reference/scaffold_names
  --from-names-column 2
  --to-names-column 3

Importing a New Version of Ensembl