From 88705fab86660ef797d8261c80a7ad77d182dc81 Mon Sep 17 00:00:00 2001
From: Yohan Jarosz <yohanjarosz@yahoo.fr>
Date: Tue, 21 Jul 2015 15:46:44 +0200
Subject: [PATCH] rm download db from main rule
---
init.rule | 22 ++++++++-
rules/Util.rules | 123 -----------------------------------------------
2 files changed, 21 insertions(+), 124 deletions(-)
diff --git a/init.rule b/init.rule
index 1aab328..86eb8f5 100644
--- a/init.rule
+++ b/init.rule
@@ -13,7 +13,9 @@ rule ALL:
"{path}/idx/{files}.{ext}",
files=config["sortmerna"]["files"],
path=DBPATH + "/sortmerna",
- ext=['bursttrie_0.dat', 'kmer_0.dat', 'pos_0.dat', 'stats'])
+ ext=['bursttrie_0.dat', 'kmer_0.dat', 'pos_0.dat', 'stats']),
+ "%s/ec2pathway.txt" % DBPATH,
+ "%s/pathway2hierarchy.txt" % DBPATH
rule _DOWNLOAD_HUMAN_DB:
output:
@@ -118,3 +120,21 @@ rule _DOWNLOAD_TRIMMOMATIC_ADAPTERS:
rm Trimmomatic-Src-0.32.zip && rm -rf trimmomatic-0.32
touch {output}
"""
+
+
+rule _DOWNLOAD_KEGG_INFORMATION:
+ log:
+ U_LOG
+ benchmark:
+ "%s/benchmarks/DOWNLOAD_KEGG_INFORMATION.json" % U_OUT
+ output:
+ "%s/ec2pathway.txt" % DBPATH,
+ "%s/pathway2hierarchy.txt" % DBPATH
+ shell:
+ """
+ wget --no-check-certificate {config[kegg][db_ec2pthy]} -O {DBPATH}/ec2pathway.txt.tmp
+ grep "path:ec" {DBPATH}/ec2pathway.txt.tmp | sed -e 's/path:ec//g' | sed -e 's/ec://g' > {output[0]}
+ rm {DBPATH}/ec2pathway.txt.tmp
+
+ python src/make.pwy.hierarchy.kegg.py > {output[1]}
+ """
diff --git a/rules/Util.rules b/rules/Util.rules
index 82ffbbd..df1da6f 100644
--- a/rules/Util.rules
+++ b/rules/Util.rules
@@ -1,60 +1,6 @@
# output directory and log
U_OUT, U_LOG = prepare_environment('Util')
-rule _DOWNLOAD_HUMAN_DB:
- output:
- expand("{path}/{filter}.{ext}", path=DBPATH + "/human", filter=config["human_filtering"]["filter"], ext=['fa'])
- params:
- filter = config["human_filtering"]["filter"], outdir = DBPATH + "/human"
- shell:
- """
- TMPD=$(mktemp -d -t --tmpdir={TMPDIR} "XXXXXX")
- wget {config[human_filtering][url]} -O $TMPD/{params.filter}.fa.gz
- gunzip $TMPD/{params.filter}.fa.gz
- mkdir -p {params.outdir}
- mv $TMPD/{params.filter}.fa {params.outdir}
- rm -rf $TMPD
- """
-
-
-rule _DOWNLOAD_SORTMERNA_DATABASES:
- output:
- expand("{path}/{files}.fasta", files=config["sortmerna"]["files"], path=DBPATH + "/sortmerna")
- shell:
- """
- TMPD=$(mktemp -d -t --tmpdir={tmp} "XXXXXX")
- wget {pkg_url} -O $TMPD/sortmerna.tgz
- tar -xzf $TMPD/sortmerna.tgz --strip-components=1 -C $TMPD
- mkdir -p {path}
- mv $TMPD/rRNA_databases/*.fasta {path}/.
- rm -rf $TMPD
- """.format(pkg_url=config["sortmerna"]["pkg_url"], path=DBPATH + "/sortmerna", tmp=TMPDIR)
-
-rule _DOWNLOAD_PROKKA_DATABASES:
- output:
- expand("{path}/{db}", path=DBPATH, db=config["prokka"]["databases"])
- shell:
- """
- ### prokka by default will look databases where is located the binary.
- ### we have to softlink to put the binary somewhere and the databases somewhere else.
- if [[ "{DBPATH}" = /* ]]
- then
- PP={DBPATH};
- else
- PP=$PWD/{DBPATH};
- fi
- cd $(dirname $(which prokka))/.. && ln -s $PP db
- echo "Softlinking $(dirname $(which prokka))/../db to $PP"
- TMPDIR=$(mktemp -d -t "XXXXXX")
- wget {config[prokka][pkg_url]} --no-check-certificate -O $TMPDIR/prokka.tgz
- tar -xzf $TMPDIR/prokka.tgz --strip-components=1 -C $TMPDIR
- mkdir -p {DBPATH}
- cp -r $TMPDIR/db/* {DBPATH}/.
- rm -rf $TMPDIR
- prokka --setupdb
- """
-
-
rule _DOWNLOAD_LIBRARY_FILES:
output:
"lib/d3.min.js", "lib/d3pie.min.js", "lib/jquery-2.1.1.min.js"
@@ -65,29 +11,6 @@ rule _DOWNLOAD_LIBRARY_FILES:
wget http://code.jquery.com/jquery-2.1.1.min.js -O lib/jquery-2.1.1.min.js
"""
-rule INDEX_SORTMERNA_DB:
- log:
- U_LOG
- benchmark:
- "%s/benchmarks/INDEX_SORTMERNA_DB.json" % U_OUT
- input:
- expand("{path}/{files}.fasta", files=config["sortmerna"]["files"], path=DBPATH + "/sortmerna")
- output:
- expand(
- "{path}/idx/{files}.{ext}",
- files=config["sortmerna"]["files"],
- path=DBPATH + "/sortmerna",
- ext=['bursttrie_0.dat', 'kmer_0.dat', 'pos_0.dat', 'stats'])
- run:
- fastaindexed = expand(
- "{path}/idx/{files}",
- files=config["sortmerna"]["files"],
- path=DBPATH + "/sortmerna")
- ref = ':'.join('%s,%s' % (a, b) for a, b in zip(input, fastaindexed))
- shell("mkdir -p {DBPATH}/sortmerna")
- shell("indexdb_rna --ref {ref} > {log} 2>&1")
-
-
rule DIAGRAMMS:
message:
"Creating diagramms."
@@ -198,49 +121,3 @@ rule CHECK_TOOL_VERSION:
echo "# KronaTools" >> {output}
"""
-#
-# rule _DOWNLOAD_KEGG_INFORMATION:
-# log:
-# U_LOG
-# benchmark:
-# "%s/benchmarks/DOWNLOAD_KEGG_INFORMATION.json" % U_OUT
-# output:
-# "%s/ec2pwy.txt" % U_OUT,
-# "%s/pwy2hierarchy.txt" % U_OUT
-# shell:
-# """
-# echo "[x] DOWNLOAD_KEGG_INFORMATION `date +"%Y/%m/%d %H:%M:%S"`" >> {log}
-# echo "Preparing EC to KEGG ID mappings"
-# python {SRCDIR}/make.ec.to.pwy.kegg.py -o {output[0]}
-# echo "Preparing KEGG ID to pathway mappings"
-# python {SRCDIR}/make.pwy.hierarchy.kegg.py -o {output[1]}
-# """
-
-rule _DOWNLOAD_TRIMMOMATIC_ADAPTERS:
- output:
- "{DBPATH}/adapters/adapters.done"
- shell:
- """
- wget http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-Src-0.32.zip
- unzip Trimmomatic-Src-0.32.zip
- cp -r trimmomatic-0.32/adapters {DBPATH}
- rm Trimmomatic-Src-0.32.zip && rm -rf trimmomatic-0.32
- touch {output}
- """
-
-rule _DOWNLOAD_KEGG_INFORMATION:
- log:
- U_LOG
- benchmark:
- "%s/benchmarks/DOWNLOAD_KEGG_INFORMATION.json" % U_OUT
- output:
- "%s/ec2pathway.txt" % DBPATH,
- "%s/pathway2hierarchy.txt" % DBPATH
- shell:
- """
- wget --no-check-certificate {config[kegg][db_ec2pthy]} -O {DBPATH}/ec2pathway.txt.tmp
- grep "path:ec" {DBPATH}/ec2pathway.txt.tmp | sed -e 's/path:ec//g' | sed -e 's/ec://g' > {output[0]}
- rm {DBPATH}/ec2pathway.txt.tmp
-
- python src/make.pwy.hierarchy.kegg.py > {output[1]}
- """
--
GitLab