Mercurial > repos > dfornika > data_manager_build_bracken_database
comparison test-data/reproduce_test_dataset.sh @ 0:911bb6c95bf8 draft default tip
"planemo upload for repository https://github.com/dfornika/galaxytools/tree/master/data_managers/data_manager_build_bracken_database/ commit d0b060e7d9cc9fd89926dbc07fc93c8a1471b3fe-dirty"
| author | dfornika |
|---|---|
| date | Thu, 24 Oct 2019 17:44:45 -0400 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:911bb6c95bf8 |
|---|---|
| 1 #!/bin/bash | |
| 2 | |
| 3 # This script produces a small kraken2 database containing only a ~1kb portion each of a salmonella and ecoli genome | |
| 4 # It requires kraken2, and entrez-direct (available on bioconda) | |
| 5 kraken2-build --db test_db --download_taxonomy | |
| 6 mv test_db/taxonomy/nucl_gb.accession2taxid test_db/taxonomy/nucl_gb.accession2taxid_full | |
| 7 grep -e 'NC_003198.1' -e 'NC_011750.1' test_db/taxonomy/nucl_gb.accession2taxid_full > test_db/taxonomy/nucl_gb.accession2taxid | |
| 8 mv test_db/taxonomy/nodes.dmp test_db/taxonomy/nodes.dmp_full | |
| 9 grep -f node_patterns.txt test_db/taxonomy/nodes.dmp_full > test_db/taxonomy/nodes.dmp | |
| 10 mv test_db/taxonomy/names.dmp test_db/taxonomy/names.dmp_full | |
| 11 grep -e '^220341\s' -e '^585057\s' test_db/taxonomy/names.dmp_full > test_db/taxonomy/names.dmp | |
| 12 esearch -db nucleotide -query "NC_003198.1" | efetch -format fasta > NC_003198.1.fasta | |
| 13 esearch -db nucleotide -query "NC_011750.1" | efetch -format fasta > NC_011750.1.fasta | |
| 14 head -n 14 NC_003198.1.fasta > NC_003198.1_1kb.fasta | |
| 15 head -n 14 NC_011750.1.fasta > NC_011750.1_1kb.fasta | |
| 16 kraken2-build --db test_db --add-to-library NC_003198.1_1kb.fasta | |
| 17 kraken2-build --db test_db --add-to-library NC_011750.1_1kb.fasta | |
| 18 kraken2-build --db test_db --build |