Mercurial > repos > bgruening > data_manager_semibin

changeset 0:1e4dd26db773 draft default tip

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_semibin commit aa9bfb2fb62547ee8bac34f0de5b3beaa0bfd1a4"
author bgruening
date Fri, 14 Oct 2022 21:29:47 +0000
parents
children
files data_manager/data_manager_semibin.py data_manager/data_manager_semibin.xml data_manager_conf.xml test-data/gtdb.loc tool-data/gtdb.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test
diffstat 7 files changed, 230 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/data_manager_semibin.py	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,153 @@
+#!/usr/bin/env python
+#
+# Data manager for reference data for the MetaPhlAn Galaxy tools
+import argparse
+import json
+import subprocess
+from datetime import date
+from pathlib import Path
+
+
+# Utility functions for interacting with Galaxy JSON
+def read_input_json(json_fp):
+    """Read the JSON supplied from the data manager tool
+
+    Returns a tuple (param_dict,extra_files_path)
+
+    'param_dict' is an arbitrary dictionary of parameters
+    input into the tool; 'extra_files_path' is the path
+    to a directory where output files must be put for the
+    receiving data manager to pick them up.
+
+    NB the directory pointed to by 'extra_files_path'
+    doesn't exist initially, it is the job of the script
+    to create it if necessary.
+
+    """
+    with open(json_fp) as fh:
+        params = json.load(fh)
+    return (params['param_dict'],
+            Path(params['output_data'][0]['extra_files_path']))
+
+
+# Utility functions for creating data table dictionaries
+#
+# Example usage:
+# >>> d = create_data_tables_dict()
+# >>> add_data_table(d,'my_data')
+# >>> add_data_table_entry(dict(dbkey='hg19',value='human'))
+# >>> add_data_table_entry(dict(dbkey='mm9',value='mouse'))
+# >>> print(json.dumps(d))
+def create_data_tables_dict():
+    """Return a dictionary for storing data table information
+
+    Returns a dictionary that can be used with 'add_data_table'
+    and 'add_data_table_entry' to store information about a
+    data table. It can be converted to JSON to be sent back to
+    the data manager.
+
+    """
+    d = {
+        'data_tables': {}
+    }
+    return d
+
+
+def add_data_table(d, table):
+    """Add a data table to the data tables dictionary
+
+    Creates a placeholder for a data table called 'table'.
+
+    """
+    d['data_tables'][table] = []
+
+
+def add_data_table_entry(d, table, entry):
+    """Add an entry to a data table
+
+    Appends an entry to the data table 'table'. 'entry'
+    should be a dictionary where the keys are the names of
+    columns in the data table.
+
+    Raises an exception if the named data table doesn't
+    exist.
+
+    """
+    try:
+        d['data_tables'][table].append(entry)
+    except KeyError:
+        raise Exception("add_data_table_entry: no table '%s'" % table)
+
+
+def download_gtdb(data_tables, table_name, target_dp, test=False):
+    """Download GTDB
+
+    Creates references to the specified file(s) on the Galaxy
+    server in the appropriate data table (determined from the
+    file extension).
+
+    The 'data_tables' dictionary should have been created using
+    the 'create_data_tables_dict' and 'add_data_table' functions.
+
+    Arguments:
+      data_tables: a dictionary containing the data table info
+      table_name: name of the table
+      target_dp: directory to put copy or link to the data file
+
+    """
+    db_dp = target_dp
+    if not test:
+        cmd = "SemiBin download_GTDB --reference-db-data-dir %s" % (db_dp)
+        subprocess.check_call(cmd, shell=True)
+        dbkey = 'gtdb'
+        name = "GTDB reference genome generated by MMseqs2 used in SemiBin"
+    else:
+        dbkey = 'test'
+        name = "Test"
+        empty_fp = db_dp / Path("empty")
+        empty_fp.touch()
+    add_data_table_entry(
+        data_tables,
+        table_name,
+        dict(
+            dbkey=dbkey,
+            value='%s' % (date.today().strftime("%d%m%Y")),
+            name=name,
+            path=str(db_dp)))
+
+
+if __name__ == "__main__":
+    print("Starting...")
+
+    # Read command line
+    parser = argparse.ArgumentParser(description='Download reference genomes (GTDB)')
+    parser.add_argument('--json', help="Path to JSON file")
+    parser.add_argument('--test', action='store_true', help="Test")
+    args = parser.parse_args()
+    print("args   : %s" % args)
+
+    # Read the input JSON
+    json_fp = Path(args.json)
+    params, target_dp = read_input_json(json_fp)
+
+    # Make the target directory
+    print("Making %s" % target_dp)
+    target_dp.mkdir(parents=True, exist_ok=True)
+
+    # Set up data tables dictionary
+    data_tables = create_data_tables_dict()
+    add_data_table(data_tables, "gtdb")
+
+    # Fetch data from specified data sources
+    print("Download and build database")
+    download_gtdb(
+        data_tables,
+        "gtdb",
+        target_dp,
+        args.test)
+
+    # Write output JSON
+    print("Outputting JSON")
+    with open(json_fp, 'w') as fh:
+        json.dump(data_tables, fh, sort_keys=True)
+    print("Done.")
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/data_manager_semibin.xml	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,39 @@
+<tool id="data_manager_semibin" name="Download reference genomes (GTDB) for SemiBin" tool_type="manage_data" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description></description>
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">semibin</requirement>
+    </requirements>
+    <macros>
+        <token name="@TOOL_VERSION@">1.1.1</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@PROFILE@">21.01</token>
+    </macros>
+    <command detect_errors="exit_code"><![CDATA[
+python '$__tool_directory__/data_manager_semibin.py'
+    --json '$out_file'
+    $type
+    ]]></command>
+    <inputs>
+        <param name="type" type="hidden" value="" />
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json"/>
+    </outputs>
+    <tests>
+    <test expect_num_outputs="1">
+        <param name="type" value="--test" />
+        <output name="out_file">
+            <assert_contents>
+                <has_text text="test"/>
+                <has_text text="Test"/>
+            </assert_contents>
+        </output>
+    </test>
+    </tests>
+    <help><![CDATA[
+This tool downloads reference genomes (GTDB) for SemiBin
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1038/s41467-022-29843-y</citation>
+    </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,21 @@
+<?xml version="1.0"?>
+<data_managers>
+    <data_manager tool_file="data_manager/data_manager_semibin.xml" id="data_manager_semibin" >
+        <data_table name="gtdb">  <!-- Defines a Data Table to be modified. -->
+            <output> <!-- Handle the output of the Data Manager Tool -->
+                <column name="value" />  <!-- columns that are going to be specified by the Data Manager Tool -->
+                <column name="name" />  <!-- columns that are going to be specified by the Data Manager Tool -->
+                <column name="dbkey" /> <!-- columns that are going to be specified by the Data Manager Tool -->
+                <column name="path" output_ref="out_file" >
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">semibin/data/${dbkey}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/semibin/data/${dbkey}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gtdb.loc	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,3 @@
+#file has this format (white space characters are TAB characters)
+#dbkey	description	name	/path/to/data
+test-date	description	test	/path/to/data
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/gtdb.loc.sample	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,2 @@
+#file has this format (white space characters are TAB characters)
+#dbkey	description	name	/path/to/data
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,6 @@
+<tables>
+    <table name="gtdb" comment_char="#">
+        <columns>value, name, dbkey, path</columns>
+        <file path="tool-data/gtdb.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.test	Fri Oct 14 21:29:47 2022 +0000
@@ -0,0 +1,6 @@
+<tables>
+    <table name="gtdb" comment_char="#">
+        <columns>value, name, dbkey, path</columns>
+        <file path="${__HERE__}/test-data/gtdb.loc" />
+    </table>
+</tables>
\ No newline at end of file