Mercurial > repos > iuc > data_manager_build_bracken_database

view test-data/reproduce_test_dataset.sh @ 0:c2e4127fb5bf draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_build_bracken_database/ commit 74e81c69c8806d98beb15a889741bcd702866ce3"
author iuc
date Sun, 20 Oct 2019 09:37:21 -0400
parents
children
line wrap: on
line source

#!/bin/bash

# This script produces a small kraken2 database containing only a ~1kb portion each of a salmonella and ecoli genome
# It requires kraken2, and entrez-direct (available on bioconda)
kraken2-build --db test_db --download_taxonomy
mv test_db/taxonomy/nucl_gb.accession2taxid test_db/taxonomy/nucl_gb.accession2taxid_full
grep -e 'NC_003198.1' -e 'NC_011750.1' test_db/taxonomy/nucl_gb.accession2taxid_full > test_db/taxonomy/nucl_gb.accession2taxid
mv test_db/taxonomy/nodes.dmp test_db/taxonomy/nodes.dmp_full
grep -f node_patterns.txt test_db/taxonomy/nodes.dmp_full > test_db/taxonomy/nodes.dmp
mv test_db/taxonomy/names.dmp test_db/taxonomy/names.dmp_full
grep -e '^220341\s' -e '^585057\s' test_db/taxonomy/names.dmp_full > test_db/taxonomy/names.dmp
esearch -db nucleotide -query "NC_003198.1" | efetch -format fasta > NC_003198.1.fasta
esearch -db nucleotide -query "NC_011750.1" | efetch -format fasta > NC_011750.1.fasta
head -n 14 NC_003198.1.fasta > NC_003198.1_1kb.fasta
head -n 14 NC_011750.1.fasta > NC_011750.1_1kb.fasta
kraken2-build --db test_db --add-to-library NC_003198.1_1kb.fasta
kraken2-build --db test_db --add-to-library NC_011750.1_1kb.fasta
kraken2-build --db test_db --build