def predictSequence(args, hpoGraph, uni2hpoDict, name="Sequence", seq=""):
# ok, do the whole thing
try:
# debug msg
out.writeLog('Predict function for protein: id: "' + str(name) + '" sequence: "' + str(seq) + '"')
# lookup resulst if available
foundInLookUp, hits = False, []
if args.lookupdb:
out.writeLog("Checking for precalculated results!")
# ok, load them
f = open(args.lookupdb, "r")
for line in f:
if line.strip() == name.strip():
# oh, cool, its precalculated
foundInLookUp = True
elif foundInLookUp and line.startswith("\t"):
# ok, this belongs to result, load it
m = re.search("\t([^\t]*)\t([^\t]*)\t([^\t]*)\t([^\t]*)\t([^\t]*)\t([^\t]*)", line)
hits.append(
{
"method": m.group(1),
"hit_id": m.group(2),
"hit_value": float(m.group(3)),
"hit_from": int(m.group(4)),
"hit_to": int(m.group(5)),
"hit_order": bool(m.group(6)),
}
)
elif foundInLookUp:
break
f.close()
# ok, first of all, get similar sequences!
if not foundInLookUp:
out.writeLog("Check blast and hhblits for sequence orthologs!")
blastResults = blast.Blast.localBlast(seq=seq, database=args.blastDbFile, minEVal=args.blastMinEVal)
for hit in blastResults.hits:
out.writeDebug("Blast: found hit: " + str(hit))
hhblitsResults = hhblits.HHBLITS.localHHBLITS(seq=str(seq), database=args.hhblitsDbFile)
for hit in hhblitsResults.hits:
out.writeDebug("hhblits: found hit: " + str(hit))
hits.extend(blastResults.hits)
hits.extend(hhblitsResults.hits)
# reduce hits if fast prediction
if args.fast:
out.writeLog("Reduce hits for faster prediction!")
hitsTmp = sorted(hits, key=lambda t: t["hit_value"])
hits = hitsTmp[:6]
# now get the hpo-Identifiers for each similar sequence
out.writeLog("uniprot ids ({}) 2 HPO Terms".format(len(hits)))
for hit in hits:
try:
# Do not output this, it might be some GB output
# out.writeDebug("found hpoTerms for " + str( hit[ "hit_id" ] ) + ": " + str( uni2hpoDict[ hit[ "hit_id" ] ] ) )
hit.update({"hpoTerms": uni2hpoDict[hit["hit_id"]]})
except KeyError:
out.writeWarning("MISSING HPO TERMS FOR HIT: " + str(hit))
# build and merge trees
out.writeLog("Build and merge tree for similar sequences!")
graph, hit_id = hpoGraph.getHpoSubGraph(hpoGraph.getRoot()), 0
for hit in hits:
# out.writeDebug("@blast merging: {}".format(hit))
subtree = hpoGraph.getHpoSubGraph(hit["hpoTerms"], {hit_id: hit})
hit_id += 1
graph += subtree
# do the prediciton
out.writeLog("Run main prediction!")
# init the predictor
p = predictor.Predictor(args.neuronalNet)
p.runprediction(seq, graph)
# always accept the root
for root in hpoGraph.getRoot():
graph.getHpoTermById(root).accepted = 1
# do the output
out.writeLog("writing output")
for node in graph.getAcceptedNodes(args.minimalConfidence):
out.writeOutput("{}\t{}\t{}".format(name, node.id, "%.*f" % (2, (node.accepted + 2) / 4)))
# svg image desired?
if args.createSvgImage:
out.writeLog("Create a svg image showing all results!")
if graph != None:
graph.writeSvgImage(fileName=str(name) + ".svg")
else:
out.writeWarning("Can't create a svg image from an empty tree!")
# clear attrs from all tree nodes, so that these don't interfere with later predictions
# out.writeLog("Clear memory for next prediction")
# hpoGraph.clearAttr()
except Exception as err:
exc_type, exc_obj, exc_tb = sys.exc_info()
out.writeError("Predicting Error: " + str(err) + " on line: " + str(exc_tb.tb_lineno))
exit(1)
pass
def __init__(self, hpoFile="../data/hp.obo"):
""" initalize an hpo graph by an hpo file """
# debug message
if hpoFile != None:
out.writeDebug( "parsing hpo file " + str( hpoFile ) )
# init main class varibale
self.hpoTermsDict = {}
self.isSubTree = hpoFile == None
# if the file to parse is None, an empty HpoGraph will be returned
if hpoFile == None:
return
# helper function to analyse the lines
def _analyseLines(self, lines):
""" Analyse the parsed lines (helper function) """
# file descriptor or hp term?
if lines[0].startswith( "[Term]" ):
# add a hpoterm by the hpoterms description
for line in lines:
# do nothing, if HpoTerm is_obsolete
if line.startswith('is_obsolete:'):
return
term = HpoTerm( lines[1:] )
self.hpoTermsDict.update( { term.id.split(" ")[0] : term } )
else:
for line in lines:
# ok, get the position of the :
attrName = line[:line.find(":")].strip()
attrVal = line[line.find(":")+1:].strip()
# now add this as attribute
if hasattr(self, attrName):
if isinstance(getattr(self, attrName), list):
getattr(self, attrName).append( attrVal )
else:
setattr(self, attrName, [ getattr(self, attrName), attrVal ])
else:
setattr(self, attrName, attrVal)
# ok, parse the lines in the file
try:
f = file( hpoFile, "r" )
lines = []
for line in f:
# skip empty lines
if line.strip() == "":
continue
# do something for non empty lines
if line.startswith( "[Term]" ):
_analyseLines(self, lines)
lines = [ line ]
else:
lines.append(line)
_analyseLines(self, lines)
f.close()
except Exception as e:
out.writeError("Error parsing hpo file " + str( e.message ) + " " + str( e.args) )
# good and now create the relation ship childrens
for key in self.hpoTermsDict:
node = self.hpoTermsDict[key]
if hasattr(node, "is_a"):
if isinstance(node.is_a, list):
for element in node.is_a:
self.hpoTermsDict[ element.split(" ")[0] ].childrens.append(key)
else:
self.hpoTermsDict[ node.is_a.split(" ")[0] ].childrens.append(key)
exc_type, exc_obj, exc_tb = sys.exc_info()
out.writeError("Predicting Error: " + str(err) + " on line: " + str(exc_tb.tb_lineno))
exit(1)
pass
# printheader output
out.writeOutput("AUTHOR TEAM_NAME")
out.writeOutput("MODEL\t1")
out.writeOutput("KEYWORDS clinical data, synteny.")
# ok, do the whole thing
if args.sequence != None:
predictSequence(args, hpoGraph, uni2hpoDict, seq=args.sequence)
elif os.path.isfile(args.fastaFile):
f = open(args.fastaFile, "rU")
for record in SeqIO.parse(f, "fasta"):
predictSequence(args, hpoGraph, uni2hpoDict, name=record.id, seq=str(record.seq))
f.close()
else:
out.writeError("Error: no sequence to predict given! (wrong path?)")
out.writeOutput("END")
# quit without error code
exit(0)
except Exception as err:
# main routine exception handler
out.writeError("Unexpected Error: " + str(err))
exit(1)