Mercurial > repos > matthias > data_manager_dada2

changeset 0:419037fe1150 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/master/data_managers/data_manager_dada2 commit 42eb67646e47bef13eed672ff6b9d06b1d82ae3d-dirty
author matthias
date Thu, 07 Mar 2019 09:33:43 -0500
parents
children 1c50cfb0c0ab
files data_manager/.dada_fetcher.xml.swp data_manager/.data_manager.py.swp data_manager/.megan_tools_fetcher.xml.swp data_manager/dada_fetcher.xml data_manager/data_manager.py data_manager_conf.xml test-data/SSURef_Nr99_132_tax_silva_to_NCBI_synonyms_json tool-data/.dada2_species.loc.sample.swp tool-data/.dada2_taxonomy.loc.sample.swp tool-data/dada2_species.loc.sample tool-data/dada2_taxonomy.loc.sample tool_data_table_conf.xml.sample
diffstat 11 files changed, 208 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
Binary file data_manager/.dada_fetcher.xml.swp has changed
Binary file data_manager/.data_manager.py.swp has changed
Binary file data_manager/.megan_tools_fetcher.xml.swp has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/dada_fetcher.xml	Thu Mar 07 09:33:43 2019 -0500
@@ -0,0 +1,39 @@
+<?xml version="1.0"?>
+<tool id="dada_fetcher" name="dada2 dada manager" tool_type="manage_data" version="0.0.1">
+    <description>Download reference data sets</description>
+    <command detect_errors="exit_code">
+    <![CDATA[
+    python '$__tool_directory__/data_manager.py' 
+    --out '${out_file}'
+    --file '$type_cond.database_name'
+    ]]>
+    </command>
+    <inputs>
+        <param name="database_name" type="select" label="mapping data">
+            <option value="silva132">Silva version 132</option>
+            <option value="silva128">Silva version 128</option>
+            <option value="rdp16">RDP trainset 16 + RDP database release 11.5</option>
+            <option value="rdp14">RDP trainset 14</option>
+            <option value="gg13.84">GreenGenes version 13.8</option>
+<!--            <option value="unite8.0">UNITE: General Fasta release 8.0 </option>
+            <option value="RefSeq_RDP">NCBI RefSeq 16S rRNA database supplemented by RDP</option>
+            <option value="gtdb">GTDB: Genome Taxonomy Database (More info: http://gtdb.ecogenomic.org/)</option>
+            <option value="hitdb1">HitDB version 1 (Human InTestinal 16S rRNA)</option>
+            <option value="silva132_euk">Silva Eukaryotic 18S, v132 &amp; v128</option>
+            <option value="PR2v4.11.0">Protist Ribosomal Reference database 2 version 4.11.0</option>-->
+        </param>
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="database_name" value="silva132"/>
+            <output name="out_file" file="silva132_json"/>
+        </test>
+    </tests>
+    <help>
+http://www.arb-silva.de/silva-license-information
+    </help>
+</tool>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/data_manager.py	Thu Mar 07 09:33:43 2019 -0500
@@ -0,0 +1,106 @@
+import argparse
+import json
+import os
+import shutil
+import sys
+import zipfile
+try:
+    # For Python 3.0 and later
+    from urllib.request import Request, urlopen
+except ImportError:
+    # Fall back to Python 2 imports
+    from urllib2 import Request, urlopen
+
+DEFAULT_TAXLEVELS="Kingdom,Phylum,Class,Order,Family,Genus,Species"
+
+FILE2NAME = {
+    "silva132":"Silva version 132",
+    "silva128":"Silva version 128",
+    "rdp16":"RDP trainset 16",
+    "rdp14":"RDP trainset 14",
+    "gg13.84":"GreenGenes version 13.8",
+}
+
+FILE2TAXURL = {
+    "silva132":"https://zenodo.org/record/1172783/files/silva_nr_v132_train_set.fa.gz?download=1",
+    "silva128":"https://zenodo.org/record/824551/files/silva_nr_v128_train_set.fa.gz?download=1",
+    "rdp16":"https://zenodo.org/record/801828/files/rdp_train_set_16.fa.gz?download=1",
+    "rdp14":"https://zenodo.org/record/158955/files/rdp_train_set_14.fa.gz?download=1",
+    "gg13.84":"https://zenodo.org/record/158955/files/gg_13_8_train_set_97.fa.gz?download=1",
+}
+
+FILE2SPECIESURL = {
+    "silva132":"https://zenodo.org/record/1172783/files/silva_species_assignment_v132.fa.gz?download=1",
+    "silva128":"https://zenodo.org/record/824551/files/silva_species_assignment_v128.fa.gz?download=1",
+    "rdp16":"https://zenodo.org/record/801828/files/rdp_species_assignment_16.fa.gz?download=1",
+    "rdp14":"https://zenodo.org/record/158955/files/rdp_species_assignment_14.fa.gz?download=1"
+}
+
+FILE2TAXLEVELS = {
+}
+
+def url_download(url, fname, workdir):
+    """
+    download url to workdir/fname
+    
+    return the path to the resulting file 
+    """
+    file_path = os.path.join(workdir, fname)
+    if not os.path.exists(workdir):
+        os.makedirs(workdir)
+    src = None
+    dst = None
+    try:
+        req = Request(url)
+        src = urlopen(req)
+        with open(file_path, 'wb') as dst:
+            while True:
+                chunk = src.read(2**10)
+                if chunk:
+                    dst.write(chunk)
+                else:
+                    break
+    finally:
+        if src:
+            src.close()
+    return os.path.join(workdir, fname)
+
+def main(dataset, outjson):
+
+    params = json.loads(open(outjson).read())
+    target_directory = params['output_data'][0]['extra_files_path']
+    os.mkdir(target_directory)
+    output_path = os.path.abspath(os.path.join(os.getcwd(), 'dada2'))
+
+    workdir = os.path.join(os.getcwd(), 'dada2') 
+    path = url_download( FILE2TAXURL[dataset], taxdataset+".taxonomy", workdir)
+
+    data_manager_json = {"data_tables":{}}
+    data_manager_entry = {}
+    data_manager_entry['value'] = dataset
+    data_manager_entry['name'] = FILE2NAME[dataset]
+    data_manager_entry['path'] = path
+    data_manager_entry['taxlevels'] = FILE2TAXLEVELS.get(dataset, DEFAULT_TAXLEVELS)
+    data_manager_json["data_tables"]["dada2_taxonomy"] = data_manager_entry
+
+
+    if FILE2SPECIES.get(dataset, False ):
+        path = url_download( FILE2SPECIES[dataset], taxdataset+".species", workdir)
+    
+        data_manager_entry = {}
+        data_manager_entry['value'] = dataset
+        data_manager_entry['name'] = FILE2NAME[dataset]
+        data_manager_entry['path'] = path
+        data_manager_json["data_tables"]["dada2_species"] = data_manager_entry
+    
+    for filename in os.listdir(workdir):
+        shutil.move(os.path.join(output_path, filename), target_directory)
+    file(outjson, 'w').write(json.dumps(data_manager_json))
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='Create data manager json.')
+    parser.add_argument('--out', action='store', help='JSON filename')
+    parser.add_argument('--dataset', action='store', help='Download data set name')
+    args = parser.parse_args()
+
+    main(args.dataset, args.out)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml	Thu Mar 07 09:33:43 2019 -0500
@@ -0,0 +1,34 @@
+<?xml version="1.0"?>
+<data_managers>
+    <data_manager tool_file="data_manager/dada2_fetcher.xml" id="dada2_fetcher" version="0.0.1">
+        <data_table name="dada2_taxonomy">
+            <output>
+                <column name="value" />
+                <column name="name" />
+                <column name="path" output_ref="out_file">
+                    <move type="file" relativize_symlinks="True">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">dada2/${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/dada2/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="taxlevels" />
+            </output>
+        </data_table>
+        <data_table name="dada2_species">
+            <output>
+                <column name="value" />
+                <column name="name" />
+                <column name="path" output_ref="out_file">
+                    <move type="file" relativize_symlinks="True">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">dada2/${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/dada2/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>
Binary file tool-data/.dada2_species.loc.sample.swp has changed
Binary file tool-data/.dada2_taxonomy.loc.sample.swp has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/dada2_species.loc.sample	Thu Mar 07 09:33:43 2019 -0500
@@ -0,0 +1,9 @@
+# This is a sample file distributed with Galaxy that is used to define a
+# list of dada2 reference data sets for species assignment, using three
+# tab separated columns:
+#
+# <unique_build_id>	<display_name>	<fasta_file_path>
+#
+# Datasets can be retrieved from http://busco.ezlab.org/frame_wget.html
+#
+# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/dada2_taxonomy.loc.sample	Thu Mar 07 09:33:43 2019 -0500
@@ -0,0 +1,9 @@
+# This is a sample file distributed with Galaxy that is used to define a
+# list of dada2 reference data sets for taxonomy assignment, using three
+# tab separated columns:
+#
+# <unique_build_id>	<display_name>	<fasta_file_path>	<taxlevels>
+#
+# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html
+# 
+# taxlevels is a comma separated list of taxonomy levels
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Thu Mar 07 09:33:43 2019 -0500
@@ -0,0 +1,11 @@
+<?xml version="1.0"?>
+<tables>
+    <table name="dada2_species" comment_char="#">
+        <columns>value, name, path</columns>
+        <file path="tool-data/dada2_species.loc" />
+    </table>
+    <table name="dada2_taxonomy" comment_char="#">
+        <columns>value, name, path, taxlevels</columns>
+        <file path="tool-data/dada2_taxonomy.loc" />
+    </table>
+</tables>