Merge commit '9db2c064' into develop

config.yaml

 tools:
     signalp: '/vol/biotools/bin/signalp'
     ghostx: '/vol/biotools/bin/ghostx'
+    tmhmm: '/vol/biotools/bin/tmhmm'

docs/source/installation.rst

@@ -15,6 +15,7 @@ In order to run PSOT on your machine you need:
   * hmmscan
   * signalp
   * ghostx
+  * tmhmm
 
 * the bioinformatic databases you want to use
   

modules/tmhmm.yaml

+# Module manifest for the tmhmm analysis
+
+# The name of the module. Is needed for the list-analyses option, for custom
+# configurations and custom profiles.
+name: 'tmhmm'
+
+# Short description of the analysis.
+info: 'predict transmembrane helices in proteins'
+
+# The configuration of the script for the analysis step.
+analysis:
+    # script must take a --fasta parameter
+    script: 'run_tmhmm.py'
+    # specify additional default configuration here
+    parameters:
+
+# The configuration of the script for the json conversion step.
+converter:
+    # script must take a --result parameter, which is the result from the analysis step
+    script: 'convert_tmhmm.py'
+    # specify additional default configuration here
+    parameters:

profiles/fast.yaml

@@ -4,3 +4,4 @@ modules:
   ghostx_swissprot:
   signalp:
       organism: 'euk'
+  tmhmm:

scripts/convert_tmhmm.py

+#!/usr/bin/python3
+
+import sys
+import json
+import argparse
+
+parser = argparse.ArgumentParser(description='Convert tmhmm results to json documents')
+parser.add_argument('--result', '-r', required=True, help='The tmhmm result file')
+parser.add_argument('--output', '-o', required=True, help='The converted results json file')
+args = parser.parse_args()
+
+def parse_topology(s, l):
+	elements = []
+	result = []
+	flag = False
+	num = ""
+	for c in s:
+		if c == 'i' or c == 'o' or c == '-':
+			if num != "":
+				elements.append(int(num))
+				num = ""
+			if c != '-':
+				elements.append(c)
+		else:
+			num += c
+	if num != "":
+		elements.append(int(num))
+	for i in range(len(elements)):
+		if flag:
+			flag = False
+		else:
+			if elements[i] == 'i' or elements[i] == 'o':
+				location = ""
+				if elements[i] == 'i':
+					location = "inside"
+				else:
+					location = "outside"
+				if i == 0:
+					if len(elements) == 1:
+						result.append({'start': 1, 'end': l , 'location': location})
+					else:
+						result.append({'start': 1, 'end': elements[i+1]-1 , 'location': location})
+				elif i+1 == len(elements):
+					result.append({'start': elements[i-1]+1, 'end':l , 'location': location})
+				else:
+					result.append({'start': elements[i-1]+1, 'end': elements[i+1]-1 , 'location': location})
+			else:
+				result.append({'start': elements[i], 'end': elements[i+1] , 'location': 'membrane'})
+				flag = True
+	return (result)
+
+filename = args.result
+documents = {}
+with open(filename) as f:
+	for line in f:
+		line_dic = {}
+		elements = line.rstrip().split("\t")
+		for i in range(1, len(elements)):
+			key = elements[i][:elements[i].rfind('=')]
+			value = elements[i][elements[i].rfind('=')+1:]
+			if key == 'Topology':
+				line_dic[key] = parse_topology(value, elements[i-4][elements[i-4].rfind('=')+1:])
+			else:
+				line_dic[key] = value
+		documents[elements[0]] = line_dic
+
+output_filename = args.output
+with open(output_filename, 'w') as o:
+	json.dump(documents, o)

scripts/run_tmhmm.py

+#!/usr/bin/env python3
+import env
+import argparse
+from psot import config
+from os import system
+import subprocess
+
+tmhmm_tool = config.load_config()['tools'].get('tmhmm', 'tmhmm')
+
+parser = argparse.ArgumentParser(description='Find transmembrane helices in amino acid sequences')
+parser.add_argument('--fasta', '-f', required=True, help='A fasta file with aminoacid sequences')
+#parser.add_argument('--workdir', '-workdir', help='Working directory')
+#parser.add_argument('--wwwdir', '-wwwdir', help='The place where the www server looks for files')
+#parser.add_argument('--serverhome', '-serverhome', help='') #
+#parser.add_argument('--basedir', '-basedir', help='basis directory for TMHMM package')
+#parser.add_argument('--bindir', '-bindir', help='Bin directory (defaults basedir/bin)')
+#parser.add_argument('--scrdir', '-scrdir', help='Script directory (defaults basedir/bin)')
+#parser.add_argument('--libdir', '-libdir', help='Library directory (defaults basedir/lib)')
+#parser.add_argument('--html', '-html', help='Produce HTML output')
+#parser.add_argument('--short', '-s', help='Short output format')
+#parser.add_argument('--plot', '-p', help='Produce graphics')
+#parser.add_argument('--version1', '-v1', help='Use old model (version 1)')
+#parser.add_argument('--debugging', '-d', help='') #
+parser.add_argument('--output', required=True, help='The output file')
+args = parser.parse_args()
+
+system("cat " + args.fasta + " | " + tmhmm_tool + " -short > " + args.output) #