| Next changeset 1:9e63d5f02d62 (2018-11-07) |
|
Commit message:
Uploaded |
|
added:
Marea/local/HMRcoreMap.svg Marea/local/HMRcore_genes.p Marea/local/HMRcore_rules.p Marea/local/Recon_genes.p Marea/local/Recon_rules.p Marea/marea.py Marea/marea.xml Marea/marea_cluster.py Marea/marea_cluster.xml |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/local/HMRcoreMap.svg --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Marea/local/HMRcoreMap.svg Tue Nov 06 03:16:21 2018 -0500 |
| b |
| b'@@ -0,0 +1,7702 @@\n+<?xml version="1.0" encoding="UTF-8" standalone="no"?>\n+<!-- Generator: Adobe Illustrator 22.0.1, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->\n+\n+<svg\n+ xmlns:dc="http://purl.org/dc/elements/1.1/"\n+ xmlns:cc="http://creativecommons.org/ns#"\n+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"\n+ xmlns:svg="http://www.w3.org/2000/svg"\n+ xmlns="http://www.w3.org/2000/svg"\n+ xmlns:xlink="http://www.w3.org/1999/xlink"\n+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"\n+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"\n+ version="1.1"\n+ x="0px"\n+ y="0px"\n+ viewBox="0 0 1904.8016 1511.2752"\n+ xml:space="preserve"\n+ id="svg2"\n+ inkscape:version="0.91 r13725"\n+ sodipodi:docname="HMRcoreMap.svg"\n+ width="1904.8015"\n+ height="1511.2753"><metadata\n+ id="metadata2021"><rdf:RDF><cc:Work\n+ rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type\n+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" /><dc:title /></cc:Work></rdf:RDF></metadata><defs\n+ id="defs2019"><sodipodi:namedview\n+ showguides="true"\n+ showgrid="true"\n+ pagecolor="#ffffff"\n+ inkscape:zoom="1.4702451"\n+ inkscape:window-y="-8"\n+ inkscape:window-x="-8"\n+ inkscape:window-width="1920"\n+ inkscape:window-maximized="1"\n+ inkscape:window-height="1017"\n+ inkscape:snap-page="false"\n+ inkscape:snap-grids="true"\n+ inkscape:pageshadow="2"\n+ inkscape:pageopacity="0.0"\n+ inkscape:document-units="px"\n+ inkscape:cy="338.10986"\n+ inkscape:cx="1343.7768"\n+ inkscape:current-layer="layer1"\n+ id="base"\n+ fit-margin-top="0"\n+ fit-margin-right="0"\n+ fit-margin-left="0"\n+ fit-margin-bottom="0"\n+ borderopacity="1.0"\n+ bordercolor="#666666"><inkscape:grid\n+ type="xygrid"\n+ originy="72.926308"\n+ originx="-97.409688"\n+ id="grid3434"\n+ dotted="true" /></sodipodi:namedview></defs><sodipodi:namedview\n+ pagecolor="#ffffff"\n+ bordercolor="#666666"\n+ borderopacity="1"\n+ objecttolerance="10"\n+ gridtolerance="10"\n+ guidetolerance="10"\n+ inkscape:pageopacity="0"\n+ inkscape:pageshadow="2"\n+ inkscape:window-width="1920"\n+ inkscape:window-height="1017"\n+ id="namedview2017"\n+ showgrid="false"\n+ inkscape:zoom="0.44727204"\n+ inkscape:cx="497.63252"\n+ inkscape:cy="796.80241"\n+ inkscape:window-x="-8"\n+ inkscape:window-y="-8"\n+ inkscape:window-maximized="1"\n+ inkscape:current-layer="svg2"\n+ fit-margin-top="0"\n+ fit-margin-left="0"\n+ fit-margin-right="0"\n+ fit-margin-bottom="0" /><style\n+ type="text/css"\n+ id="style4">\n+\t.st0{display:none;}\n+\t.st1{display:inline;}\n+\t.st2{fill:none;stroke:#5AB6E7;stroke-width:7;stroke-linejoin:round;}\n+\t.st3{fill:none;stroke:#5AB6E7;stroke-width:7;stroke-linejoin:round;stroke-dasharray:11.9422,11.9422;}\n+\t.st4{fill:none;stroke:#5AB6E7;stroke-width:7;stroke-linejoin:round;stroke-dasharray:12.1815,12.1815;}\n+\t.st5{font-family:\'Helvetica\';}\n+\t.st6{font-size:30px;}\n+\t.st7{font-size:39.262px;}\n+\t.st8{fill:none;stroke:#0000FF;stroke-width:30;}\n+\t.st9{fill:none;stroke:#E41A1C;stroke-width:30;}\n+\t.st10{fill:none;stroke:#BEBEBE;stroke-width:30;}\n+\t.st11{stroke:#000000;stroke-width:30;}\n+\t.st12{fill:none;stroke:#BEBEBE;stroke-width:30;stroke-dasharray:30,30;stroke-dashoffset:6;}\n+\t.st13{fill:none;stroke:#000000;stroke-width:1.8444;}\n+\t.st14{fill:none;stroke:#000000;stroke-width:2.1821;}\n+\t.st15{font-family:\'Calibri-Bold\';}\n+\t.st16{font-size:16px;}\n+\t.st17{font-family:\'Calibri\';}\n+\t.st18{font-size:10px;}\n+\t.st19{fill:none;stroke:#000000;stroke-width:1.8856;}\n+\t.st20{fill:none;stroke:#000000;stroke-width:1.9459;}\n+\t.st21{fill:none;stroke:#000000;stroke-width:2.2892;}\n+\t.st22{fill:none;stroke:#000000;stroke-width:2.5;}\n+\t.st23{fill:none;stroke:#000000;stroke-width:1.9412;}\n+\t.st24{fill:none;str'..b'31.89,1231.8186 2.2,-7.3 2.2,7.3 -2.2,-1.8 -2.2,1.8 z"\n+ class="st14"\n+ inkscape:label="Glutamine_DM_COOP b"\n+ inkscape:connector-curvature="0"\n+ id="B_Glutamine_DM_COOP" /><path\n+ style="fill:none;stroke:#000000;stroke-width:2.18210006"\n+ d="m 1233.89,1279.4186 0,-48"\n+ class="st14"\n+ inkscape:label="Glutamine_DM_COOP"\n+ inkscape:connector-curvature="0"\n+ id="R_Glutamine_DM_COOP" /><flowRoot\n+ xml:space="preserve"\n+ id="flowRoot5366"\n+ style="font-style:normal;font-weight:normal;font-size:35px;line-height:125%;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"\n+ transform="translate(-20.6,18.418554)"><flowRegion\n+ id="flowRegion5368"><rect\n+ id="rect5370"\n+ width="1165.1471"\n+ height="77.465683"\n+ x="306.70087"\n+ y="-39.523308" /></flowRegion><flowPara\n+ id="flowPara5372" /></flowRoot><flowRoot\n+ xml:space="preserve"\n+ id="TitoloConfronto"\n+ style="font-style:normal;font-weight:normal;font-size:35px;line-height:125%;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"\n+ inkscape:label="TitoloConfronto"\n+ transform="translate(-18.364224,56.426743)"><flowRegion\n+ id="flowRegion5376"><rect\n+ id="rect5378"\n+ width="1869.6877"\n+ height="68.569115"\n+ x="301.95807"\n+ y="-69.56102" /></flowRegion><flowPara\n+ id="TitleText"\n+ style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:45px;font-family:sans-serif;-inkscape-font-specification:sans-serif">TITOLO: TITOLOTITOLO </flowPara></flowRoot><flowRoot\n+ xml:space="preserve"\n+ id="flowRoot5382"\n+ style="font-style:normal;font-weight:normal;font-size:35px;line-height:125%;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"\n+ transform="translate(-16.64767,38.180207)"><flowRegion\n+ id="flowRegion5384"><rect\n+ id="rect5386"\n+ width="275.00043"\n+ height="149.79698"\n+ x="1681.3033"\n+ y="204.59315" /></flowRegion><flowPara\n+ id="flowPara5390"\n+ style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-family:sans-serif;-inkscape-font-specification:\'sans-serif Bold\'">Fold Change</flowPara></flowRoot><flowRoot\n+ xml:space="preserve"\n+ id="FC_min"\n+ style="font-style:normal;font-weight:normal;font-size:35px;line-height:125%;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"\n+ transform="translate(-8.622366,131.05768)"\n+ inkscape:label="FC_min"><flowRegion\n+ id="flowRegion5384-2"><rect\n+ id="rect5386-9"\n+ width="275.00043"\n+ height="149.79698"\n+ x="1681.3033"\n+ y="204.59315" /></flowRegion><flowPara\n+ id="Val_FC_min">min: </flowPara></flowRoot><flowRoot\n+ xml:space="preserve"\n+ id="FC_max"\n+ style="font-style:normal;font-weight:normal;font-size:35px;line-height:125%;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"\n+ transform="translate(-17.492772,95.648076)"\n+ inkscape:label="FC_max"><flowRegion\n+ id="flowRegion5384-2-2"><rect\n+ id="rect5386-9-9"\n+ width="275.00043"\n+ height="149.79698"\n+ x="1681.3033"\n+ y="204.59315" /></flowRegion><flowPara\n+ id="Val_FC_max">max:</flowPara></flowRoot></svg>\n\\ No newline at end of file\n' |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/local/HMRcore_genes.p |
| b |
| Binary file Marea/local/HMRcore_genes.p has changed |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/local/HMRcore_rules.p |
| b |
| Binary file Marea/local/HMRcore_rules.p has changed |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/local/Recon_genes.p |
| b |
| Binary file Marea/local/Recon_genes.p has changed |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/local/Recon_rules.p |
| b |
| Binary file Marea/local/Recon_rules.p has changed |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/marea.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Marea/marea.py Tue Nov 06 03:16:21 2018 -0500 |
| [ |
| b'@@ -0,0 +1,760 @@\n+\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+def process_args(args):\n+ parser = argparse.ArgumentParser(usage = \'%(prog)s [options]\',\n+ description = \'process some value\\\'s\'+\n+ \' genes to create a comparison\\\'s map.\')\n+ parser.add_argument(\'-rs\', \'--rules_selector\', \n+ type = str,\n+ default = \'HMRcore\',\n+ choices = [\'HMRcore\', \'Recon\', \'Custom\'], \n+ help = \'chose which type of dataset you want use\')\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\'],\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+ 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+ args = parser.parse_args()\n+ return args\n+\n+########################### warning ###########################################\n+\n+def warning(s):\n+ args = process_args(sys.argv)\n+ with open(args.out_log, \'a\') as log:\n+ log.write(s)\n+ \n+############################ dataset input ####################################\n+\n+def read_dataset(data, name):\n+ try:\n+ dataset = pd.read_csv(data, sep = \'\\t\', header = 0)\n+ except pd.errors.EmptyDataError:\n+ sys.exit(\'Execution aborted: wrong format of \' + name + \'\\n\')\n+ if len(dataset.columns) < 2:\n+ sys.exit(\'Execution aborted: wrong format of \' + name + \'\\n\')\n+ return dataset\n+\n+############################ dataset name #####################################\n+\n+def name_dataset(name_data, count):\n+ if str(name_data) '..b'method=\'xml\'))\n+ file_pdf = \'map_pdf/\' + i + \'_vs_\' + j + \'.pdf\'\n+ renderPDF.drawToFile(svg2rlg(file_svg), file_pdf)\n+ return None\n+\n+############################ MAIN #############################################\n+\n+def main():\n+ args = process_args(sys.argv)\n+ os.makedirs(\'table_out\')\n+ if args.rules_selector == \'HMRcore\':\n+ os.makedirs(\'map_svg\')\n+ os.makedirs(\'map_pdf\')\n+ recon = pk.load(open(args.tool_dir + \'/local/HMRcore_rules.p\', \'rb\'))\n+ elif args.rules_selector == \'Recon\':\n+ recon = pk.load(open(args.tool_dir + \'/local/Recon_rules.p\', \'rb\'))\n+ elif args.rules_selector == \'Custom\':\n+ ids, rules, gene_in_rule = make_recon(args.custom)\n+ resolve_none = check_bool(args.none)\n+ class_pat = {}\n+ if args.option == \'datasets\':\n+ num = 1\n+ #if len(args.names) != len(set(args.names)):\n+ # sys.exit(\'Execution aborted: datasets name duplicated\')\n+ for i, j in zip(args.input_datas, args.names):\n+ name = name_dataset(j, num)\n+ dataset = read_dataset(i, name)\n+ dataset.iloc[:, 0] = (dataset.iloc[:, 0]).astype(str)\n+ type_gene = gene_type(dataset.iloc[0, 0], name)\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[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 args.rules_selector == \'Custom\':\n+ if args.yes_no == \'yes\':\n+ os.makedirs(\'map_svg\')\n+ os.makedirs(\'map_pdf\')\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+ maps(core_map, class_pat, ids, args.pValue, args.fChange)\n+ warning(\'Execution succeeded\')\n+ return None\n+\n+###############################################################################\n+\n+if __name__ == "__main__":\n+ main()\n' |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/marea.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Marea/marea.xml Tue Nov 06 03:16:21 2018 -0500 |
| [ |
| b'@@ -0,0 +1,240 @@\n+<tool id="MaREA" name="Metabolic Enrichment Analysis">\r\n+ <description>for Galaxy</description>\r\n+ <requirements>\r\n+ <requirement type="package">pandas</requirement>\r\n+ <requirement type="package">scipy</requirement>\r\n+ <requirement type="package">lxml</requirement>\r\n+ <requirement type="package">svglib</requirement>\r\n+ <requirement type="package">reportlab</requirement>\r\n+ <requirement type="package">cobrapy</requirement>\r\n+ <requirement type="package">python-libsbml</requirement>\r\n+ </requirements>\r\n+ <command>\r\n+ <![CDATA[\r\n+ \tpython $__tool_directory__/marea.py\r\n+ --rules_selector $cond_rule.rules_selector\r\n+ #if $cond_rule.rules_selector == \'Custom\':\r\n+ --custom ${cond_rule.Custom_rules}\r\n+ --yes_no ${cond_rule.cond_map.yes_no}\r\n+ #if $cond_rule.cond_map.yes_no == \'yes\':\r\n+ --custom_map $cond_rule.cond_map.Custom_map\r\n+ #end if\r\n+ #end if\r\n+ \t--none $None\r\n+ \t--pValue $pValue\r\n+ \t--fChange $fChange\r\n+ \t--tool_dir $__tool_directory__\r\n+ \t--option $cond.type_selector\r\n+ --out_log $log\r\n+ #if $cond.type_selector == \'datasets\':\r\n+ --input_datas\r\n+ #for $data in $cond.input_Datasets:\r\n+ ${data.input}\r\n+ #end for\r\n+ --names\r\n+ #for $data in $cond.input_Datasets:\r\n+ ${data.input_name}\r\n+ #end for\r\n+ #elif $cond.type_selector == \'dataset_class\':\r\n+ --input_data ${input_data}\r\n+ --input_class ${input_class}\r\n+ #end if\r\n+ ]]>\r\n+ </command>\r\n+ <inputs>\r\n+ <conditional name="cond_rule">\r\n+ <param name="rules_selector" type="select" label="Gene-Protein-Reaction rules:">\r\n+ <option value="HMRcore" selected="true">HMRcore rules</option>\r\n+ <option value="Recon">Recon 2.2 rules</option>\r\n+ <option value="Custom">Custom rules</option>\r\n+ </param>\r\n+ <when value="Custom">\r\n+ <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules"/>\r\n+ <conditional name="cond_map">\r\n+ <param name="yes_no" type="select" label="Custom map? (optional)">\r\n+ <option value="no" selected="true">no</option>\r\n+ <option value="yes">yes</option>\r\n+ </param>\r\n+ <when value="yes">\r\n+ <param name="Custom_map" type="data" format="xml, svg" label="custom-map.svg"/>\r\n+ </when>\r\n+ </conditional>\r\n+ </when>\r\n+ </conditional>\r\n+ <conditional name="cond">\r\n+ <param name="type_selector" type="select" label="Input format:">\r\n+ <option value="datasets" selected="true">RNAseq of group 1 + RNAseq of group 2 + \xe2\x80\xa6 + RNAseq of group N</option>\r\n+ <option value="dataset_class">RNAseq of all samples + sample group specification</option>\r\n+ </param>\r\n+ <when value="datasets">\r\n+ <repeat name="input_Datasets" title="RNAseq" type="data" min="2">\r\n+ <param name="input" type="data" format="tabular, csv, tsv" label="add dataset"/>\t\r\n+ <param name="input_name" type="text" label="Dataset\'s name:" value="Dataset" help="Defalut: Dataset"/>\r\n+\t </repeat>\r\n+ </when>\r\n+ <when value="dataset_class">\r\n+ <param name="input_data" type="data" format="tabular, csv, tsv" label="RNAseq of all samples"/>\r\n+ <param name="input_class" type="data" format="tabular, csv, tsv" label="Sample group specification"/>\r\n+ </when>\r\n+ </conditional>\r\n+ <param name="None" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A '..b'A_vs_classB. Reactions will conventionally be reported as up-regulated (down-regulated) if they are significantly more (less) active in class having label \xe2\x80\x9cclassA\xe2\x80\x9d.\r\n+\r\n+.. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724\r\n+\r\n+\r\n+Example input\r\n+-------------\r\n+\r\n+**"RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N" exemple input"** option:\r\n+\r\n+Dataset 1:\t\t\t\t\t\t\r\n+\r\n++------------+------------+------------+------------+ \r\n+| Hugo_ID | TCGAA62670 | TCGAA62671 | TCGAA62672 | \r\n++============+============+============+============+ \r\n+| HGNC:24086 | 0.523167 | 0.371355 | 0.925661 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:24086 | 0.568765 | 0.765567 | 0.456789 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:9876 | 0.876545 | 0.768933 | 0.987654 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:9 | 0.456788 | 0.876543 | 0.876542 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:23 | 0.876543 | 0.786543 | 0.897654 | \r\n++------------+------------+------------+------------+ \r\n+ \r\n+|\r\n+\r\n+Dataset 2:\r\n+\r\n++-------------+------------+------------+------------+\r\n+| Hugo_Symbol | TCGAA62670 | TCGAA62671 | TCGAA62672 |\r\n++=============+============+============+============+\r\n+| A1BG | 0.523167 | 0.371355 | 0.925661 |\r\n++-------------+------------+------------+------------+\r\n+| A1CF | 0.568765 | 0.765567 | 0.456789 |\r\n++-------------+------------+------------+------------+\r\n+| A2M | 0.876545 | 0.768933 | 0.987654 |\r\n++-------------+------------+------------+------------+\r\n+| A4GALT | 0.456788 | 0.876543 | 0.876542 |\r\n++-------------+------------+------------+------------+\r\n+| M664Y65 | 0.876543 | 0.786543 | 0.897654 |\r\n++-------------+------------+------------+------------+\r\n+\r\n+|\r\n+\r\n+**"RNAseq of all samples + sample group specification"** option:\r\n+\r\n+Dataset:\r\n+\r\n++------------+------------+------------+------------+ \r\n+| Hugo_ID | TCGAA62670 | TCGAA62671 | TCGAA62672 | \r\n++============+============+============+============+ \r\n+| HGNC:24086 | 0.523167 | 0.371355 | 0.925661 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:24086 | 0.568765 | 0.765567 | 0.456789 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:9876 | 0.876545 | 0.768933 | 0.987654 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:9 | 0.456788 | 0.876543 | 0.876542 | \r\n++------------+------------+------------+------------+ \r\n+| HGNC:23 | 0.876543 | 0.786543 | 0.897654 | \r\n++------------+------------+------------+------------+ \r\n+\r\n+|\r\n+\r\n+Class-file:\r\n+\r\n++------------+------------+ \r\n+| Patient_ID | class | \r\n++============+============+ \r\n+| TCGAAA3529 | MSI | \r\n++------------+------------+ \r\n+| TCGAA62671 | MSS | \r\n++------------+------------+ \r\n+| TCGAA62672 | MSI | \r\n++------------+------------+\r\n+\r\n+|\r\n+\r\n+\r\n+\r\n+.. class:: warningmark\r\n+\r\n+This tool expects input datasets consisting of tab-delimited columns.\r\n+\r\n+\r\n+.. class:: infomark\r\n+\r\n+TIP: If your data is not TAB delimited, use `Convert delimiters to TAB`_.\r\n+\r\n+.. class:: infomark\r\n+\r\n+TIP: If your dataset is not split into classes, use `Cluster for MaREA`_.\r\n+\r\n+This tool is developed by the `nome del gruppo di bioinformatica`_ at the `dipartimento di informatica disco`_.\r\n+\r\n+\r\n+.. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj\r\n+.. _Cluster for MaREA: http://link del tool di cluster.org/\r\n+.. _nome del gruppo di bioinformatica: http://sito di bio.org\r\n+.. _dipartimento di informatica disco : http://www.disco.unimib.it/go/Home/English\r\n+\r\n+]]>\r\n+ </help>\r\n+</tool>\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n+\t\r\n' |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/marea_cluster.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Marea/marea_cluster.py Tue Nov 06 03:16:21 2018 -0500 |
| [ |
| b'@@ -0,0 +1,608 @@\n+\n+from __future__ import division\n+import os\n+import sys\n+import pandas as pd\n+import collections\n+import pickle as pk\n+import argparse\n+from sklearn.cluster import KMeans\n+import matplotlib.pyplot as plt\n+\n+########################## argparse ###########################################\n+\n+def process_args(args):\n+ parser = argparse.ArgumentParser(usage = \'%(prog)s [options]\',\n+ description = \'process some value\\\'s\' +\n+ \' genes to create class.\')\n+ parser.add_argument(\'-rs\', \'--rules_selector\', \n+ type = str,\n+ default = \'HMRcore\',\n+ choices = [\'HMRcore\', \'Recon\', \'Custom\'], \n+ help = \'chose which type of dataset you want use\')\n+ parser.add_argument(\'-cr\', \'--custom\',\n+ type = str,\n+ help=\'your dataset if you want custom rules\')\n+ parser.add_argument(\'-ch\', \'--cond_hier\', \n+ type = str,\n+ default = \'no\',\n+ choices = [\'no\', \'yes\'], \n+ help = \'chose if you wanna hierical dendrogram\')\n+ parser.add_argument(\'-lk\', \'--k_min\', \n+ type = int,\n+ help = \'min number of cluster\')\n+ parser.add_argument(\'-uk\', \'--k_max\', \n+ type = int,\n+ help = \'max number of cluster\')\n+ parser.add_argument(\'-li\', \'--linkage\', \n+ type = str, \n+ choices = [\'single\', \'complete\', \'average\'], \n+ help=\'linkage hierarchical cluster\')\n+ parser.add_argument(\'-d\', \'--data\',\n+ type = str,\n+ required = True,\n+ help = \'input dataset\')\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(\'-td\', \'--tool_dir\',\n+ type = str,\n+ required = True,\n+ help = \'your tool directory\')\n+ parser.add_argument(\'-na\', \'--name\',\n+ type = str,\n+ help = \'name of dataset\')\n+ parser.add_argument(\'-de\', \'--dendro\', \n+ help = "Dendrogram out")\n+ parser.add_argument(\'-ol\', \'--out_log\', \n+ help = "Output log")\n+ parser.add_argument(\'-el\', \'--elbow\', \n+ help = "Out elbow")\n+ args = parser.parse_args()\n+ return args\n+\n+########################### warning ###########################################\n+\n+def warning(s):\n+ args = process_args(sys.argv)\n+ with open(args.out_log, \'a\') as log:\n+ log.write(s)\n+ \n+############################ dataset input ####################################\n+\n+def read_dataset(data, name):\n+ try:\n+ dataset = pd.read_csv(data, sep = \'\\t\', header = 0)\n+ except pd.errors.EmptyDataError:\n+ sys.exit(\'Execution aborted: wrong format of \'+name+\'\\n\')\n+ if len(dataset.columns) < 2:\n+ sys.exit(\'Execution aborted: wrong format of \'+name+\'\\n\')\n+ return dataset\n+\n+############################ dataset name #####################################\n+\n+def name_dataset(name_data, count):\n+ if str(name_data) == \'Dataset\':\n+ return str(name_data) + \'_\' + str(count)\n+ else:\n+ return str(name_data)\n+ \n+############################ load id e rules ##################################\n+\n+def load_id_rules(reactions):\n+ ids, rules = [], []\n+ for key, value in reactions.items():\n+ ids.append(key)\n+ rules.append(value)\n+ return (ids, rules)\n+\n+############################ check_methods ####################################\n+\n+def'..b' if tmp:\n+ tmp, err = replace_gene_value(tmp, value)\n+ if err:\n+ not_found.extend(err)\n+ ris = control(None, tmp, resolve_none)\n+ if ris is False or ris == None:\n+ tmp_resolve.append(None)\n+ else:\n+ tmp_resolve.append(ris)\n+ flag = True\n+ else:\n+ tmp_resolve.append(None) \n+ resolve_rules[key] = tmp_resolve\n+ if flag is False:\n+ sys.exit(\'Execution aborted: no computable score\' +\n+ \' (due to missing gene values) for class \'\n+ + name + \', the class has been disregarded\\n\')\n+ return (resolve_rules, list(set(not_found)))\n+\n+################################# clustering ##################################\n+\n+def f_cluster(resolve_rules):\n+ os.makedirs(\'cluster_out\')\n+ args = process_args(sys.argv)\n+ cluster_data = pd.DataFrame.from_dict(resolve_rules, orient = \'index\')\n+ for i in cluster_data.columns:\n+ tmp = cluster_data[i][0]\n+ if tmp == None:\n+ cluster_data = cluster_data.drop(columns=[i])\n+ distorsion = []\n+ for i in range(args.k_min, args.k_max+1):\n+ tmp_kmeans = KMeans(n_clusters = i,\n+ n_init = 100, \n+ max_iter = 300,\n+ random_state = 0).fit(cluster_data)\n+ distorsion.append(tmp_kmeans.inertia_)\n+ predict = tmp_kmeans.predict(cluster_data)\n+ predict = [x+1 for x in predict]\n+ classe = (pd.DataFrame(zip(cluster_data.index, predict))).astype(str)\n+ dest = \'cluster_out/K=\' + str(i) + \'_\' + args.name+\'.tsv\'\n+ classe.to_csv(dest, sep = \'\\t\', index = False,\n+ header = [\'Patient_ID\', \'Class\'])\n+ plt.figure(0)\n+ plt.plot(range(args.k_min, args.k_max+1), distorsion, marker = \'o\')\n+ plt.xlabel(\'Number of cluster\')\n+ plt.ylabel(\'Distorsion\')\n+ plt.savefig(args.elbow, dpi = 240, format = \'pdf\')\n+ if args.cond_hier == \'yes\':\n+ import scipy.cluster.hierarchy as hier\n+ lin = hier.linkage(cluster_data, args.linkage)\n+ plt.figure(1)\n+ plt.figure(figsize=(10, 5))\n+ hier.dendrogram(lin, leaf_font_size = 2, labels = cluster_data.index)\n+ plt.savefig(args.dendro, dpi = 480, format = \'pdf\')\n+ return None\n+\n+################################# main ########################################\n+\n+def main():\n+ args = process_args(sys.argv)\n+ if args.k_min > args.k_max:\n+ sys.exit(\'Execution aborted: max cluster > min cluster\')\n+ if args.rules_selector == \'HMRcore\':\n+ recon = pk.load(open(args.tool_dir + \'/local/HMRcore_rules.p\', \'rb\'))\n+ elif args.rules_selector == \'Recon\':\n+ recon = pk.load(open(args.tool_dir + \'/local/Recon_rules.p\', \'rb\'))\n+ elif args.rules_selector == \'Custom\':\n+ ids, rules, gene_in_rule = make_recon(args.custom)\n+ resolve_none = check_bool(args.none)\n+ dataset = read_dataset(args.data, args.name)\n+ dataset.iloc[:, 0] = (dataset.iloc[:, 0]).astype(str)\n+ type_gene = gene_type(dataset.iloc[0, 0], args.name)\n+ if args.rules_selector != \'Custom\':\n+ genes = data_gene(dataset, type_gene, args.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, args.name, gene_in_rule)\n+ resolve_rules, err = resolve(genes, rules, ids, resolve_none, args.name)\n+ if err:\n+ warning(\'WARNING: gene\\n\' + str(err) + \'\\nnot found in class \' \n+ + args.name + \', the expression level for this gene \' +\n+ \'will be considered NaN\\n\')\n+ f_cluster(resolve_rules)\n+ warning(\'Execution succeeded\')\n+ return None\n+\n+###############################################################################\n+\n+if __name__ == "__main__":\n+ main()\n\\ No newline at end of file\n' |
| b |
| diff -r 000000000000 -r 23ac9cf12788 Marea/marea_cluster.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Marea/marea_cluster.xml Tue Nov 06 03:16:21 2018 -0500 |
| [ |
| @@ -0,0 +1,97 @@ +<tool id="MaREA_cluester" name="MaREA cluster analysis"> + <description>of Reaction Activity Scores</description> + <requirements> + <requirement type="package">pandas</requirement> + <requirement type="package">scikit-learn</requirement> + <requirement type="package">scipy</requirement> + <requirement type="package">matplotlib</requirement> + <requirement type="package">cobrapy</requirement> + <requirement type="package">python-libsbml</requirement> + </requirements> + <command> + <![CDATA[ + python $__tool_directory__/marea_cluster.py + --rules_selector $cond_rule.rules_selector + #if $cond_rule.rules_selector == 'Custom': + --custom ${cond_rule.Custom_rules} + #end if + --cond_hier $cond_hier.hier + #if $cond_hier.hier == 'yes': + --linkage ${cond_hier.linkage} + --dendro $dendrogram + #end if + --k_max $k_max + --k_min $k_min + --data $input + --name $name + --none $None + --tool_dir $__tool_directory__ + --out_log $log + --elbow $elbow + ]]> + </command> + <inputs> + <conditional name="cond_rule"> + <param name="rules_selector" type="select" label="Gene-Protein-Reaction rules:"> + <option value="HMRcore" selected="true">HMRcore rules</option> + <option value="Recon">Recon 2.2 rules</option> + <option value="Custom">Custom rules</option> + </param> + <when value="Custom"> + <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules"/> + </when> + </conditional> + <param name="input" type="data" format="tabular, csv, tsv" label="RNAseq of all samples"/> + <param name="name" type="text" label="Output name prefix" value = "dataset"/> + <param name="k_min" type="integer" size="20" value="3" min="2" max="30" label="min number of clusters (k) to be tested (k-means)"/> + <param name="k_max" type="integer" size="20" value="3" min="2" max="30" label="max number of clusters (k) to be tested (k-means)"/> + <param name="None" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" help="if NO is selected (A and NaN) is solved as (NaN)"/> + <conditional name="cond_hier"> + <param name="hier" type="select" label="Produce dendrogram (hierarchical clustering):"> + <option value="no" selected="true">no</option> + <option value="yes">yes</option> + </param> + <when value="yes"> + <param name="linkage" type="select" label="Linkage type:"> + <option value="single" selected="true">Single: minimum distance between all observations of two sets</option> + <option value="complete">Complete: maximum distance between all observations of two sets</option> + <option value="average">Average: average distance between all observations of two sets</option> + </param> + </when> + </conditional> + </inputs> + <outputs> + <data format="txt" name="log" label="Log"/> + <data format="pdf" name="dendrogram" label="$name dendrogram"> + <filter>cond_hier['hier'] == 'yes'</filter> + </data> + <data format="pdf" name="elbow" label="$name elbow evaluation method"/> + <collection name="cluster_out" type="list" label="Clusters $k_min - $k_max"> + <discover_datasets pattern="__name_and_ext__" directory="cluster_out"/> + </collection> + </outputs> + <help> + +.. class:: warningmark + +This tool expects input datasets consisting of tab-delimited columns. + +.. class:: infomark + +**TIP:** If your data is not TAB delimited, use *Text Manipulation > Convert delimiters to TAB* + + </help> +</tool> + + + + + + + + + + + + + |
