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

"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
comparison
equal deleted inserted replaced
-1:000000000000 0:c2e4127fb5bf
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