| Previous changeset 46:5d5d01ef1d68 (2020-01-22) Next changeset 48:e4235b5231e4 (2020-02-23) |
|
Commit message:
Uploaded |
|
modified:
Marea/marea.py Marea/marea.xml Marea/ras_generator.py Marea/ras_generator.xml |
| b |
| diff -r 5d5d01ef1d68 -r 3af9d394367c Marea/marea.py --- a/Marea/marea.py Wed Jan 22 11:50:54 2020 -0500 +++ b/Marea/marea.py Wed Feb 19 10:44:52 2020 -0500 |
| [ |
| b'@@ -26,10 +26,6 @@\n parser.add_argument(\'-cr\', \'--custom\',\n type = str,\n help=\'your dataset if you want custom rules\')\n- parser.add_argument(\'-na\', \'--names\', \n- type = str,\n- nargs = \'+\', \n- help = \'input names\')\n parser.add_argument(\'-n\', \'--none\',\n type = str,\n default = \'true\',\n@@ -37,7 +33,7 @@\n help = \'compute Nan values\')\n parser.add_argument(\'-pv\' ,\'--pValue\', \n type = float, \n- default = 0.05, \n+ default = 0.1, \n help = \'P-Value threshold (default: %(default)s)\')\n parser.add_argument(\'-fc\', \'--fChange\', \n type = float, \n@@ -49,14 +45,10 @@\n help = \'your tool directory\')\n parser.add_argument(\'-op\', \'--option\', \n type = str, \n- choices = [\'datasets\', \'dataset_class\', \'datasets_rasonly\'],\n+ choices = [\'datasets\', \'dataset_class\'],\n help=\'dataset or dataset and class\')\n parser.add_argument(\'-ol\', \'--out_log\', \n help = "Output log") \n- parser.add_argument(\'-ids\', \'--input_datas\', \n- type = str,\n- nargs = \'+\', \n- help = \'input datasets\')\n parser.add_argument(\'-id\', \'--input_data\',\n type = str,\n help = \'input dataset\')\n@@ -80,15 +72,21 @@\n default = \'true\',\n choices = [\'true\', \'false\'], \n help = \'generate pdf map\')\n- parser.add_argument(\'-gr\', \'--generate_ras\',\n+ parser.add_argument(\'-on\', \'--control\',\n+ type = str)\n+ parser.add_argument(\'-co\', \'--comparison\',\n+ type = str, \n+ default = \'1vs1\',\n+ choices = [\'manyvsmany\', \'onevsrest\', \'onevsmany\'])\n+ parser.add_argument(\'-ids\', \'--input_datas\', \n type = str,\n- default = \'true\',\n- choices = [\'true\', \'false\'],\n- help = \'generate reaction activity score\')\n- parser.add_argument(\'-sr\', \'--single_ras_file\', \n- type = str, \n- help = \'file that will contain ras\')\n- \t\t\t\t\t\n+ nargs = \'+\', \n+ help = \'input datasets\')\n+ parser.add_argument(\'-na\', \'--names\', \n+ type = str,\n+ nargs = \'+\', \n+ help = \'input names\')\n+ \n args = parser.parse_args()\n return args\n \n@@ -615,7 +613,6 @@\n \n def resolve(genes, rules, ids, resolve_none, name):\n resolve_rules = {}\n- names_array = []\n not_found = []\n flag = False\n for key, value in genes.items():\n@@ -663,79 +660,157 @@\n \', the class has been disregarded\\n\')\n return class_pat\n \n-############################ create_ras #######################################\n-\n-def create_ras (resolve_rules, dataset_name, single_ras, rules, ids):\n-\n- if resolve_rules == None:\n- warning("Couldn\'t generate RAS for current dataset: " + dataset_name)\n-\n- for geni in resolve_rules.values():\n- for i, valori in enumerate(geni):\n- if valori == None:\n- geni[i] = \'None\'\n- \n- output_ras = pd.DataFrame.from_dict(resolve_rules)\n- \n- output_ras.insert(0, \'Reactions\', ids)\n- output_to_csv = pd.DataFrame.to_csv(output_ras, sep = \'\\t\', index = False)\n- \n- if (single_ras):\n- args = process_args(sys.argv)\n- text_file = open(args.single_ras_file, "w")\n- else:\n- tex'..b"name)\n+ ids = pd.Series.tolist(resolve_rules.iloc[:, 0])\n \n- if generate_ras:\n- create_ras(resolve_rules, name, False, rules, ids)\n+ resolve_rules = resolve_rules.drop(resolve_rules.columns[[0]], axis=1)\n+ resolve_rules = resolve_rules.replace({'None': None})\n+ resolve_rules = resolve_rules.to_dict('list')\n \n- if err != None and err:\n- warning('Warning: gene\\n' + str(err) + '\\nnot found in class '\n- + name + ', the expression level for this gene ' +\n- 'will be considered NaN\\n')\n+ #Converto i valori da str a float\n+ to_float = lambda x: float(x) if (x != None) else None\n+ \n+ resolve_rules_float = {}\n+ \n+ for k in resolve_rules:\n+ resolve_rules_float[k] = list(map(to_float, resolve_rules[k])); resolve_rules_float\n+ \n if resolve_rules != None:\n- class_pat[name] = list(map(list, zip(*resolve_rules.values())))\n+ class_pat[name] = list(map(list, zip(*resolve_rules_float.values())))\n+ \n num += 1\n- elif args.option == 'dataset_class':\n- name = 'RNAseq'\n- dataset = read_dataset(args.input_data, name)\n- dataset.iloc[:, 0] = (dataset.iloc[:, 0]).astype(str)\n- type_gene = gene_type(dataset.iloc[0, 0], name)\n+ \n+ if args.option == 'dataset_class':\n+ name = 'RAS'\n+ resolve_rules = read_dataset(args.input_data, name)\n+ resolve_rules.iloc[:, 0] = (resolve_rules.iloc[:, 0]).astype(str)\n+ \n+ ids = pd.Series.tolist(resolve_rules.iloc[:, 0])\n+\n+ resolve_rules = resolve_rules.drop(resolve_rules.columns[[0]], axis=1)\n+ resolve_rules = resolve_rules.replace({'None': None})\n+ resolve_rules = resolve_rules.to_dict('list')\n+ \n+ #Converto i valori da str a float\n+ to_float = lambda x: float(x) if (x != None) else None\n+ \n+ resolve_rules_float = {}\n+ \n+ for k in resolve_rules:\n+ resolve_rules_float[k] = list(map(to_float, resolve_rules[k])); resolve_rules_float\n+\n classes = read_dataset(args.input_class, 'class')\n- if not len(classes.columns) == 2:\n- warning('Warning: more than 2 columns in class file. Extra' +\n- 'columns have been disregarded\\n')\n classes = classes.astype(str)\n- if args.rules_selector != 'Custom':\n- genes = data_gene(dataset, type_gene, name, None)\n- ids, rules = load_id_rules(recon.get(type_gene))\n- elif args.rules_selector == 'Custom':\n- genes = data_gene(dataset, type_gene, name, gene_in_rule)\n- resolve_rules, err = resolve(genes, rules, ids, resolve_none, name)\n- if err != None and err:\n- warning('Warning: gene\\n'+str(err)+'\\nnot found in class '\n- + name + ', the expression level for this gene ' +\n- 'will be considered NaN\\n')\n- if resolve_rules != None:\n- class_pat = split_class(classes, resolve_rules)\n- if generate_ras:\n- create_ras(resolve_rules, name, False, rules, ids)\n- \n+ \n+ if resolve_rules_float != None:\n+ class_pat = split_class(classes, resolve_rules_float)\n \t\n if args.rules_selector == 'Custom':\n if args.yes_no == 'yes':\n@@ -857,11 +896,12 @@\n else: \n core_map = ET.parse(args.tool_dir+'/local/HMRcoreMap.svg')\n \n- maps(core_map, class_pat, ids, args.pValue, args.fChange, create_svg, create_pdf)\n+ maps(core_map, class_pat, ids, args.pValue, args.fChange, create_svg, create_pdf, args.comparison, args.control)\n \n print('Execution succeded')\n+ \n+ return None\n \n- return None\n \n ###############################################################################\n \n" |
| b |
| diff -r 5d5d01ef1d68 -r 3af9d394367c Marea/marea.xml --- a/Marea/marea.xml Wed Jan 22 11:50:54 2020 -0500 +++ b/Marea/marea.xml Wed Feb 19 10:44:52 2020 -0500 |
| [ |
| b'@@ -1,28 +1,19 @@\n-<tool id="MaREA" name="Metabolic Reaction Enrichment Analysis" version="1.0.6">\n- <description></description>\n- <macros>\n- <import>marea_macros.xml</import>\n- </macros>\n- <requirements>\n- <requirement type="package" version="0.23.0">pandas</requirement>\n- <requirement type="package" version="1.1.0">scipy</requirement>\n- <requirement type="package" version="0.10.1">cobra</requirement>\n- <requirement type="package" version="4.2.1">lxml</requirement>\n- <requirement type="package" version="0.8.1">svglib</requirement>\n- <requirement type="package" version="3.4.0">reportlab</requirement>\n- </requirements>\n- <command detect_errors="exit_code">\n- <![CDATA[\n+<tool id="MaREA" name="Metabolic Reaction Enrichment Analysis" version="1.0.7">\n+\t<macros>\n+\t\t<import>marea_macros.xml</import>\n+\t</macros>\n+\t<requirements>\n+\t\t<requirement type="package" version="0.23.0">pandas</requirement>\n+\t\t<requirement type="package" version="1.1.0">scipy</requirement>\n+\t\t<requirement type="package" version="0.10.1">cobra</requirement>\n+\t\t<requirement type="package" version="4.2.1">lxml</requirement>\n+\t\t<requirement type="package" version="0.8.1">svglib</requirement>\n+\t\t<requirement type="package" version="3.4.0">reportlab</requirement>\n+\t</requirements>\n+\t<command detect_errors="exit_code">\n+\t\t<![CDATA[\n \tpython $__tool_directory__/marea.py\n- --rules_selector $cond_rule.rules_selector\n- #if $cond_rule.rules_selector == \'Custom\':\n- --custom ${cond_rule.Custom_rules}\n- --yes_no ${cond_rule.cond_map.yes_no}\n- #if $cond_rule.cond_map.yes_no == \'yes\':\n- --custom_map $cond_rule.cond_map.Custom_map\n- #end if\n- #end if\n-\t\n+\n \t--tool_dir $__tool_directory__\n \t--option $cond.type_selector\n --out_log $log\t\t\n@@ -36,153 +27,130 @@\n #for $data in $cond.input_Datasets:\n ${data.input_name}\n #end for\n+ --comparison ${cond.comparis.comparison}\n #if $cond.advanced.choice == \'true\':\n- \t --none ${cond.advanced.None}\n- \t --pValue ${cond.advanced.pValue}\n- \t --fChange ${cond.advanced.fChange}\n-\t \t--generate_svg ${cond.advanced.generateSvg}\n-\t \t--generate_pdf ${cond.advanced.generatePdf}\n-\t --generate_ras ${cond.advanced.generateRas}\n-\t#else \n-\t --none true\n-\t --pValue 0.05\n-\t --fChange 1.5\n-\t --generate_svg false\n-\t --generate_pdf true\n-\t --generate_ras false\n-\t#end if\n+ \t --pValue ${cond.advanced.pValue}\n+ \t --fChange ${cond.advanced.fChange}\n+\t --generate_svg ${cond.advanced.generateSvg}\n+\t \t --generate_pdf ${cond.advanced.generatePdf}\n+ \t #else \n+\t --pValue 0.05\n+\t --fChange 1.5\n+\t --generate_svg false\n+\t --generate_pdf true\n+\t --generate_ras false\n+\t #end if\n #elif $cond.type_selector == \'dataset_class\':\n --input_data ${input_data}\n --input_class ${input_class}\n+ --comparison ${cond.comparis.comparison}\n+ #if $cond.comparis.comparison == \'onevsmany\'\n+ \t--control ${cond.comparis.controlgroup}\n+ #end if\n #if $cond.advanced.choice == \'true\':\n- \t --none ${cond.advanced.None}\n- \t --pValue ${cond.advanced.pValue}\n- \t --fChange ${cond.advanced.fChange}\n-\t --generate_svg ${cond.advanced.generateSvg}\n-\t --generate_pdf ${cond.advanced.generatePdf}\n-\t --generate_ras ${cond.advanced.generateRas}\n-\t#else \n-\t --none true\n-\t --pValue 0.05\n-\t --fChange 1.5\n-\t --generate_svg false\n-\t --generate_pdf true\n-\t --generate_ras false\n-\t#end if\n- #end if\n- #if $cond.type_selector == \'datasets_rasonly\':\n- --input_datas ${input_Datasets}\n- --single_ras_file $ras_single\n- --none ${cond.None}\n+ \t --'..b'\n-\t\t \t\t\t<param name="generatePdf" argument="--generatePdf" type="boolean" checked="true" label="Generate PDF map" help="should the program return a non editable (but displayble) pdf map of the processes?" />\t\n-\t\t \t\t\t<param name="generateRas" argument="--generateRas" type="boolean" checked="false" label="Generate Reaction Activity Score for each table" help="Generate Reaction Activity Score for each table" />\t\t\n+\t\t\t\t\t<when value="onevsmany">\n+\t\t\t\t\t\t<param name="controlgroup" argument="--controlgroup" type="text" label="Control group label:" value="0" help="Name of group label to be compared to others"/>\n \t\t\t\t\t</when>\n- \t</conditional>\n- </when>\n- </conditional>\n- \n- \n- \n-\t\n- </inputs>\n-\n- <outputs>\n- <data format="txt" name="log" label="MaREA - Log" />\n- <data format="tabular" name="ras_single" label="MaREA - RAS - ${cond.input_name}">\n- \t<filter>cond[\'type_selector\'] == "datasets_rasonly"</filter>\n- </data>\n- <collection name="results" type="list" label="MaREA - Results">\n- <filter>cond[\'type_selector\'] == "datasets" or cond[\'type_selector\'] == "dataset_class"</filter>\n- <discover_datasets pattern="__name_and_ext__" directory="result"/>\n- </collection>\n-\t<collection name="ras" type="list" label="MaREA - RAS list" format_source="tabular">\n-\t <filter>cond[\'type_selector\'] != "datasets_rasonly" and cond[\'advanced\'][\'choice\'] and cond[\'advanced\'][\'generateRas\']</filter>\n- \t <discover_datasets pattern="__name_and_ext__" directory="ras" format="tabular"/>\n+\t\t\t\t</conditional>\n+\t\t\t\t<conditional name="advanced">\n+\t\t\t\t<param name="choice" type="boolean" checked="false" label="Use advanced options?" help="Use this options to choose custom parameters for evaluation: pValue, Fold-Change threshold, how to solve (A and NaN) and specify output maps.">\n+\t\t\t\t\t<option value="true" selected="true">No</option>\n+\t\t\t\t\t<option value="false">Yes</option>\n+\t\t\t\t</param>\n+\t\t\t\t<when value="false"></when>\n+\t\t\t\t<when value="true">\n+\t\t\t\t\t<conditional name="cond_map">\n+\t\t\t\t\t\t<param name="choice" type="boolean" checked="false" label="Use custom map?" help="Use this option only if you have generated RAS using a custom set of rules">\n+\t\t\t\t\t\t\t<option value="false" selected="true">No</option>\n+\t\t\t\t\t\t\t<option value="true">Yes</option>\n+\t\t\t\t\t\t</param>\n+\t\t\t\t\t\t<when value="true">\t\t\t\t\t\t\t\n+\t\t\t\t\t\t\t<param name="Custom_map" argument="--custom_map" type="data" format="xml, svg" label="custom-map.svg"/>\n+\t\t\t\t\t\t</when>\n+\t\t\t\t\t</conditional>\n+\t\t\t\t\t<param name="pValue" argument="--pValue" type="float" size="20" value="0.01" max="1" min="0" label="P-value threshold:" help="min value 0" />\n+\t\t\t\t\t<param name="fChange" argument="--fChange" type="float" size="20" value="1.2" min="1" label="Fold-Change threshold:" help="min value 1" />\n+\t\t\t\t\t<param name="generateSvg" argument="--generateSvg" type="boolean" checked="false" label="Generate SVG map" help="should the program generate an editable svg map of the processes?" />\n+\t\t\t\t\t<param name="generatePdf" argument="--generatePdf" type="boolean" checked="true" label="Generate PDF map" help="should the program return a non editable (but displayble) pdf map of the processes?" />\n+\t\t\t\t</when>\n+\t\t\t</conditional>\n+\t\t</when>\n+\t</conditional>\n+</inputs>\n+<outputs>\n+\t<data format="txt" name="log" label="MaREA - Log" />\n+\t<collection name="results" type="list" label="MaREA - Results">\n+\t\t<discover_datasets pattern="__name_and_ext__" directory="result"/>\n \t</collection>\n-\t\n- </outputs>\n- <tests>\n- <test>\n- <param name="pValue" value="0.56"/>\n- <output name="log" file="log.txt"/>\n- </test>\n- </tests>\n- <help>\n-<![CDATA[\n+</outputs>\n+<help>\n+\t<![CDATA[\n \n What it does\n -------------\n@@ -268,7 +236,6 @@\n .. _MaREA cluster analysis: http://link del tool di cluster.org\n \n ]]>\n- </help>\n- <expand macro="citations" />\n-</tool>\n+</help>\n+<expand macro="citations" />undefined</tool>\n \t\n' |
| b |
| diff -r 5d5d01ef1d68 -r 3af9d394367c Marea/ras_generator.py --- a/Marea/ras_generator.py Wed Jan 22 11:50:54 2020 -0500 +++ b/Marea/ras_generator.py Wed Feb 19 10:44:52 2020 -0500 |
| [ |
| b'@@ -1,16 +1,10 @@\n from __future__ import division\n import sys\n import pandas as pd\n-import itertools as it\n-import scipy.stats as st\n import collections\n-import lxml.etree as ET\n import pickle as pk\n import math\n-import os\n import argparse\n-from svglib.svglib import svg2rlg\n-from reportlab.graphics import renderPDF\n \n ########################## argparse ##########################################\n \n@@ -26,69 +20,25 @@\n parser.add_argument(\'-cr\', \'--custom\',\n type = str,\n help=\'your dataset if you want custom rules\')\n- parser.add_argument(\'-na\', \'--names\', \n- type = str,\n- nargs = \'+\', \n- help = \'input names\')\n parser.add_argument(\'-n\', \'--none\',\n type = str,\n default = \'true\',\n choices = [\'true\', \'false\'], \n help = \'compute Nan values\')\n- parser.add_argument(\'-pv\' ,\'--pValue\', \n- type = float, \n- default = 0.05, \n- help = \'P-Value threshold (default: %(default)s)\')\n- parser.add_argument(\'-fc\', \'--fChange\', \n- type = float, \n- default = 1.5, \n- help = \'Fold-Change threshold (default: %(default)s)\')\n parser.add_argument(\'-td\', \'--tool_dir\',\n type = str,\n required = True,\n help = \'your tool directory\')\n- parser.add_argument(\'-op\', \'--option\', \n- type = str, \n- choices = [\'datasets\', \'dataset_class\', \'datasets_rasonly\'],\n- help=\'dataset or dataset and class\')\n parser.add_argument(\'-ol\', \'--out_log\', \n help = "Output log") \n- parser.add_argument(\'-ids\', \'--input_datas\', \n- type = str,\n- nargs = \'+\', \n- help = \'input datasets\')\n- parser.add_argument(\'-id\', \'--input_data\',\n+ parser.add_argument(\'-id\', \'--input\',\n type = str,\n help = \'input dataset\')\n- parser.add_argument(\'-ic\', \'--input_class\', \n- type = str, \n- help = \'sample group specification\')\n- parser.add_argument(\'-cm\', \'--custom_map\', \n- type = str, \n- help = \'custom map\')\n- parser.add_argument(\'-yn\', \'--yes_no\', \n- type = str,\n- choices = [\'yes\', \'no\'],\n- help = \'if make or not custom map\')\n- parser.add_argument(\'-gs\', \'--generate_svg\',\n+ parser.add_argument(\'-ra\', \'--ras_output\',\n type = str,\n- default = \'true\',\n- choices = [\'true\', \'false\'], \n- help = \'generate svg map\')\n- parser.add_argument(\'-gp\', \'--generate_pdf\',\n- type = str,\n- default = \'true\',\n- choices = [\'true\', \'false\'], \n- help = \'generate pdf map\')\n- parser.add_argument(\'-gr\', \'--generate_ras\',\n- type = str,\n- default = \'true\',\n- choices = [\'true\', \'false\'],\n- help = \'generate reaction activity score\')\n- parser.add_argument(\'-sr\', \'--single_ras_file\', \n- type = str, \n- help = \'file that will contain ras\')\n- \t\t\t\t\t\n+ required = True,\n+ help = \'ras output\')\n+ \n args = parser.parse_args()\n return args\n \n@@ -297,79 +247,6 @@\n return False\n return ris\n \n-############################ map_methods ######################################\n-\n-def fold_change(avg1, avg2):\n- '..b" return None\n- \n- \n- elif args.option == 'datasets':\n- num = 1\n- for i, j in zip(args.input_datas, args.names):\n-\n- name = name_dataset(j, num)\n- dataset = read_dataset(i, name)\n-\n- dataset.iloc[:, 0] = (dataset.iloc[:, 0]).astype(str)\n-\n- type_gene = gene_type(dataset.iloc[0, 0], name) \n- \n- if args.rules_selector != 'Custom':\n- genes = data_gene(dataset, type_gene, name, None)\n- ids, rules = load_id_rules(recon.get(type_gene))\n- elif args.rules_selector == 'Custom':\n- genes = data_gene(dataset, type_gene, name, gene_in_rule)\n- \n- \n- resolve_rules, err = resolve(genes, rules, ids, resolve_none, name)\n+ dataset.iloc[:, 0] = (dataset.iloc[:, 0]).astype(str)\n \n- if generate_ras:\n- create_ras(resolve_rules, name, False, rules, ids)\n- \n- if err != None and err:\n- warning('Warning: gene\\n' + str(err) + '\\nnot found in class '\n- + name + ', the expression level for this gene ' +\n- 'will be considered NaN\\n')\n- if resolve_rules != None:\n- class_pat[name] = list(map(list, zip(*resolve_rules.values())))\n- num += 1\n- elif args.option == 'dataset_class':\n- name = 'RNAseq'\n- dataset = read_dataset(args.input_data, name)\n- dataset.iloc[:, 0] = (dataset.iloc[:, 0]).astype(str)\n- type_gene = gene_type(dataset.iloc[0, 0], name)\n- classes = read_dataset(args.input_class, 'class')\n- if not len(classes.columns) == 2:\n- warning('Warning: more than 2 columns in class file. Extra' +\n- 'columns have been disregarded\\n')\n- classes = classes.astype(str)\n- if args.rules_selector != 'Custom':\n- genes = data_gene(dataset, type_gene, name, None)\n- ids, rules = load_id_rules(recon.get(type_gene))\n- elif args.rules_selector == 'Custom':\n- genes = data_gene(dataset, type_gene, name, gene_in_rule)\n- resolve_rules, err = resolve(genes, rules, ids, resolve_none, name)\n- if err != None and err:\n- warning('Warning: gene\\n'+str(err)+'\\nnot found in class '\n- + name + ', the expression level for this gene ' +\n- 'will be considered NaN\\n')\n- if resolve_rules != None:\n- class_pat = split_class(classes, resolve_rules)\n- if generate_ras:\n- create_ras(resolve_rules, name, False, rules, ids)\n+ type_gene = gene_type(dataset.iloc[0, 0], name) \n+ \n+ if args.rules_selector != 'Custom':\n+ genes = data_gene(dataset, type_gene, name, None)\n+ ids, rules = load_id_rules(recon.get(type_gene))\n+ elif args.rules_selector == 'Custom':\n+ genes = data_gene(dataset, type_gene, name, gene_in_rule)\n \n- \t\n- if args.rules_selector == 'Custom':\n- if args.yes_no == 'yes':\n- try:\n- core_map = ET.parse(args.custom_map)\n- except (ET.XMLSyntaxError, ET.XMLSchemaParseError):\n- sys.exit('Execution aborted: custom map in wrong format')\n- elif args.yes_no == 'no':\n- core_map = ET.parse(args.tool_dir + '/local/HMRcoreMap.svg')\n- else: \n- core_map = ET.parse(args.tool_dir+'/local/HMRcoreMap.svg')\n- \n- maps(core_map, class_pat, ids, args.pValue, args.fChange, create_svg, create_pdf)\n- \n+ resolve_rules, err = resolve(genes, rules, ids, resolve_none, name)\n+\n+ create_ras(resolve_rules, name, rules, ids, args.ras_output)\n+ \n+ if err != None and err:\n+ warning('Warning: gene\\n' + str(err) + '\\nnot found in class '\n+ + name + ', the expression level for this gene ' +\n+ 'will be considered NaN\\n')\n+\n+ \n print('Execution succeded')\n \n return None\n" |
| b |
| diff -r 5d5d01ef1d68 -r 3af9d394367c Marea/ras_generator.xml --- a/Marea/ras_generator.xml Wed Jan 22 11:50:54 2020 -0500 +++ b/Marea/ras_generator.xml Wed Feb 19 10:44:52 2020 -0500 |
| [ |
| @@ -1,5 +1,5 @@ -<tool id="MaREA RAS Generator" name="RAS Generator" version="1.0.0"> - <description></description> +<tool id="MaREA RAS Generator" name="Expression2RAS" version="1.0.2"> + <description>- Reaction Activity Scores computation</description> <macros> <import>marea_macros.xml</import> </macros> @@ -13,18 +13,15 @@ </requirements> <command detect_errors="exit_code"> <![CDATA[ - python $__tool_directory__/marea.py - --rules_selector $cond_rule.rules_selector - --tool_dir $__tool_directory__ - --option $cond.type_selector - --out_log $log - --input_datas ${input_Datasets} - --single_ras_file $ras_single - --none ${cond.None} - #end if + python $__tool_directory__/ras_generator.py + --rules_selector $cond_rule.rules_selector + --input $input + --none $none + --tool_dir $__tool_directory__ + --out_log $log + --ras_output $ras_output ]]> </command> - <inputs> <conditional name="cond_rule"> <expand macro="options"/> @@ -47,124 +44,21 @@ </conditional> </when> </conditional> - <conditional name="cond"> - - <param name="input_Datasets" argument="--input_datas" type="data" format="tabular, csv, tsv" label="add dataset" /> - <param name="input_name" argument="--names" type="text" label="Dataset's name:" value="Dataset" help="Default: Dataset" /> - <param name="None" argument="--none" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" /> - - - </when> - </conditional> + <param name="input" argument="--input" type="data" format="tabular, csv, tsv" label="Gene Expression dataset:" /> + <param name="name" argument="--name" type="text" label="Dataset's name:" value="Dataset" help="Default: Dataset" /> + <param name="none" argument="--none" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" /> </inputs> <outputs> - <data format="txt" name="log" label="MaREA - Log" /> - <data format="tabular" name="ras_single" label="MaREA - RAS - ${cond.input_name}"> - <filter>cond['type_selector'] == "datasets_rasonly"</filter> - </data> - <collection name="results" type="list" label="MaREA - Results"> - <filter>cond['type_selector'] == "datasets" or cond['type_selector'] == "dataset_class"</filter> - <discover_datasets pattern="__name_and_ext__" directory="result"/> - </collection> - <collection name="ras" type="list" label="MaREA - RAS list" format_source="tabular"> - <filter>cond['type_selector'] != "datasets_rasonly" and cond['advanced']['choice'] and cond['advanced']['generateRas']</filter> - <discover_datasets pattern="__name_and_ext__" directory="ras" format="tabular"/> - </collection> - + <data format="txt" name="log" label="Expression2RAS - $name - Log" /> + <data format="tabular" name="ras_output" label="$name RAS"/> </outputs> - <tests> - <test> - <param name="pValue" value="0.56"/> - <output name="log" file="log.txt"/> - </test> - </tests> + <help> <![CDATA[ What it does ------------- - -This tool analyzes RNA-seq dataset(s) as described in Graudenzi et al."`MaREA`_: Metabolic feature extraction, enrichment and visualization of RNAseq data" bioRxiv (2018): 248724. - -Accepted files are: - - option 1) two or more RNA-seq datasets, each referring to samples in a given condition/class. The user can specify a label for each class (as e.g. "*classA*" and "*classB*"); - - option 2) one RNA dataset and one class-file specifying the class/condition each sample belongs to. - -Optional files: - - custom GPR (Gene-Protein-Reaction) rules. Two accepted formats: - - * (Cobra Toolbox and CobraPy compliant) xml of metabolic model; - * .csv file specifyig for each reaction ID (column 1) the corresponding GPR rule (column 2). - - custom svg map. Graphical elements must have the same IDs of reactions. See HmrCore svg map for an example. - -The tool generates: - 1) a tab-separated file: reporting fold-change and p-values of reaction activity scores (RASs) between a pair of conditions/classes; - 2) a metabolic map file (downlodable as .svg): visualizing up- and down-regulated reactions between a pair of conditions/classes; - 3) a log file (.txt). - -RNA-seq datasets format: tab-separated text files, reporting the expression level (e.g., TPM, RPKM, ...) of each gene (row) for a given sample (column). Header: sample ID. - -Class-file format: each row of the class-file reports the sample ID (column1) and the label of the class/condition the sample belongs to (column 2). - -To calculate P-Values and Fold-Changes and to generate maps, comparisons are performed for each possible pair of classes. - -Output files will be named as classA_vs_classB. Reactions will conventionally be reported as up-regulated (down-regulated) if they are significantly more (less) active in class having label "classA". - - -Example input -------------- - -**"Custom Rules"** option: - -Custom Rules Dastaset: - -@CUSTOM_RULES_EXEMPLE@ - -**"RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N"** option: - -RNA-seq Dataset 1: - -@DATASET_EXEMPLE1@ - -RNA-seq Dataset 2: - -@DATASET_EXEMPLE2@ - -**"RNAseq of all samples + sample group specification"** option: - -RNA-seq Dataset: - -@DATASET_EXEMPLE1@ - -Class-file: - -+------------+------------+ -| Patient_ID | class | -+============+============+ -| TCGAAA3529 | MSI | -+------------+------------+ -| TCGAA62671 | MSS | -+------------+------------+ -| TCGAA62672 | MSI | -+------------+------------+ - -| - -.. class:: infomark - -**TIP**: If your data is not TAB delimited, use `Convert delimiters to TAB`_. - -.. class:: infomark - -**TIP**: If your dataset is not split into classes, use `MaREA cluster analysis`_. - -@REFERENCE@ - -.. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724 -.. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj -.. _MaREA cluster analysis: http://link del tool di cluster.org - ]]> </help> <expand macro="citations" /> |