def convert(self,filelist=[],outfile=None): ### Converts scansite output files in FileList to Outfile
'''
Converts scansite output files in FileList to Outfile.
'''
try:
### Setup ###
_stage = 'Setup'
if len(filelist) < 1:
filelist = self.list['FileList']
if not outfile:
outfile = self.info['Name']
if len(filelist) < 1:
self.log.errorLog('No scansite files to convert! %s unchanged/not made.' % outfile,printerror=False)
return False
delimit = rje.getDelimit(self.cmd_list)
ext = rje.delimitExt(delimit)
if ext != outfile[-3:]:
newfile = outfile[:-3] + ext
if rje.yesNo('Change file name from %s to %s?' % (outfile, newfile)):
outfile = newfile
self.log.printLog('#OUT','Converting %d file(s), output to %s.' % (len(filelist),outfile))
### Output File ###
_stage = 'Output File'
if not self.opt['Append'] or not os.path.exists(outfile): # Create with header
OUTFILE = open(outfile,'w')
headers = ['seq_id','enzyme','enz_group','aa','pos','score','percentile','matchseq','sa']
rje.writeDelimit(OUTFILE,headers,delimit)
else:
OUTFILE = open(outfile,'a')
### Conversion ###
_stage = 'Conversion'
sx = 0
for infile in filelist:
if not os.path.exists(infile):
self.log.errorLog('Input file %s does not exist! :o(' % infile,False,False)
continue
fx = 0
INFILE = open(infile,'r')
inline = rje.nextLine(INFILE)
while inline != None:
if rje.matchExp(re_scansite,inline):
scanlist = rje.matchExp(re_scansite,inline)
rje.writeDelimit(OUTFILE,scanlist,delimit)
sx += 1
fx += 1
rje.progressPrint(self,sx)
inline = rje.nextLine(INFILE)
self.log.printLog('#OUT','%s scansite results from %s. (%s Total.)' % (rje.integerString(fx),infile,rje.integerString(sx)))
INFILE.close()
### End ###
_stage = 'End'
OUTFILE.close()
self.log.printLog('#OUT','%s scansite results output to %s.' % (rje.integerString(sx),outfile))
return True
except:
self.log.errorLog('Error in convert(%s)' % _stage,printerror=True,quitchoice=False)
raise
def convert(self,
filelist=[],
outfile=None
): ### Converts scansite output files in FileList to Outfile
'''
Converts scansite output files in FileList to Outfile.
'''
try:
### Setup ###
_stage = 'Setup'
if len(filelist) < 1:
filelist = self.list['FileList']
if not outfile:
outfile = self.info['Name']
if len(filelist) < 1:
self.log.errorLog(
'No scansite files to convert! %s unchanged/not made.' %
outfile,
printerror=False)
return False
delimit = rje.getDelimit(self.cmd_list)
ext = rje.delimitExt(delimit)
if ext != outfile[-3:]:
newfile = outfile[:-3] + ext
if rje.yesNo('Change file name from %s to %s?' %
(outfile, newfile)):
outfile = newfile
self.log.printLog(
'#OUT', 'Converting %d file(s), output to %s.' %
(len(filelist), outfile))
### Output File ###
_stage = 'Output File'
if not self.opt['Append'] or not os.path.exists(
outfile): # Create with header
OUTFILE = open(outfile, 'w')
headers = [
'seq_id', 'enzyme', 'enz_group', 'aa', 'pos', 'score',
'percentile', 'matchseq', 'sa'
]
rje.writeDelimit(OUTFILE, headers, delimit)
else:
OUTFILE = open(outfile, 'a')
### Conversion ###
_stage = 'Conversion'
sx = 0
for infile in filelist:
if not os.path.exists(infile):
self.log.errorLog(
'Input file %s does not exist! :o(' % infile, False,
False)
continue
fx = 0
INFILE = open(infile, 'r')
inline = rje.nextLine(INFILE)
while inline != None:
if rje.matchExp(re_scansite, inline):
scanlist = rje.matchExp(re_scansite, inline)
rje.writeDelimit(OUTFILE, scanlist, delimit)
sx += 1
fx += 1
rje.progressPrint(self, sx)
inline = rje.nextLine(INFILE)
self.log.printLog(
'#OUT', '%s scansite results from %s. (%s Total.)' %
(rje.integerString(fx), infile, rje.integerString(sx)))
INFILE.close()
### End ###
_stage = 'End'
OUTFILE.close()
self.log.printLog(
'#OUT', '%s scansite results output to %s.' %
(rje.integerString(sx), outfile))
return True
except:
self.log.errorLog('Error in convert(%s)' % _stage,
printerror=True,
quitchoice=False)
raise
def run(self): ### Main Run method
'''
Main Run method.
'''
try:
### SLiMDisc Run ###
if self.opt['SLiMDisc']:
return self.slimDisc()
### TEIRESIAS ###
if self.opt['Teiresias']:
## Setup ##
seqlist = rje_seq.SeqList(self.log,self.cmd_list)
infile = '%s.teiresias.fas' % rje.baseFile(seqlist.info['Name'],True)
outfile = '%s.teiresias.out' % rje.baseFile(seqlist.info['Name'],True)
run_teiresias = True
if rje.isYounger(outfile,infile) == outfile:
if self.stat['Interactive'] < 1 or not rje.yesNo('%s and %s exist already. Regenerate?' % (infile,outfile),'N'):
run_teiresias = False
## Run TEIRESIAS ##
if run_teiresias:
seqlist.saveFasta(seqfile=infile,name='Teiresias') ### Saves sequences in fasta format
command = rje.makePath(self.info['TeiresiasPath'],True)
command += ' -i%s -o%s %s' % (infile,outfile,self.info['TeiresiasOpt'])
self.log.printLog('#CMD',command)
os.system(command)
## Read Results ##
self.verbose(0,2,'Reading TEIRESIAS output from %s...' % outfile,1)
self.list['Pattern'] = []
RESULTS = open(outfile,'r')
line = RESULTS.readline()
while line:
if rje.matchExp('^(\d+)\s+(\d+)\s+(\S+)\s+(\d.+\d)$',line): # New pattern
self.addTeiresiasPattern(rje.matchExp('^(\d+)\s+(\d+)\s+(\S+)\s+(\d.+\d)$',line))
elif len(line) > 3 and line[0] != '#':
self.log.errorLog('Did not recognise line: %s' % line,False,False)
line = RESULTS.readline()
RESULTS.close()
patx = len(self.list['Pattern'])
self.log.printLog('#PAT','%s TEIRESIAS patterns read from %s.' % (rje.integerString(patx),outfile))
## Calculate Information Content ##
aafreq = seqlist.aaFreq()
self.verbose(0,3,'Calculating Information Content & Length stats...',0)
occx = 0
for pattern in self.list['Pattern']:
pattern.stat['Info'] = self.calculateScore(pattern.info['Pattern'],aafreq)
pattern._makeLength()
occx += 1
rje.progressPrint(self,occx,patx/100,patx/10)
self.verbose(0,1,'...Done!',2)
## Prepare Results ##
delimit = rje.getDelimit(self.cmd_list)
if self.info['Name'] == 'None':
self.info['Name'] = '%s.teiresias.%s' % (rje.baseFile(seqlist.info['Name'],True),rje.delimitExt(delimit))
if self.opt['MySQL']: # Two tables
patfile = os.path.splitext(self.info['Name'])
occfile = '%s.occ%s' % (patfile[0],patfile[1])
patfile = '%s.patterns%s' % (patfile[0],patfile[1])
if self.opt['Append']:
PATFILE = open(patfile,'a')
OCCFILE = open(occfile,'a')
else:
PATFILE = open(patfile,'w')
rje.writeDelimit(PATFILE,['pattern','tot_occ','seq_occ','info','len','fix','wild'],delimit)
OCCFILE = open(occfile,'a')
rje.writeDelimit(OCCFILE,['seq_id','pos','pattern','pat_match'],delimit)
else:
if self.opt['Append']:
RESFILE = open(self.info['Name'],'a')
else:
RESFILE = open(patfile,'w')
rje.writeDelimit(RESFILE,['Sequence Name','Position','Pattern','Match','Total Occurrences','Num Sequences','Information Content','Length','Fixed','Wildcard'],delimit)
## Save Results ##
occx = 0
for pattern in self.list['Pattern']:
patstats = []
for stat in ['OccCount','SeqCount','Info','Length','Fixed','Wildcards']:
patstats.append('%d' % pattern.stat[stat])
patstats[2] = '%.3f' % pattern.stat['Info']
if self.opt['MySQL']: # Two tables
rje.writeDelimit(PATFILE,[pattern.info['Pattern']] + patstats,delimit)
for occ in rje.sortKeys(pattern.occ):
seq = seqlist.seq[occ]
for pos in pattern.occ[occ]:
match = seq.info['Sequence'][pos:(pos+pattern.stat['Length'])]
outlist = [seq.shortName(),'%d' % pos,pattern.info['Pattern'],match]
if self.opt['MySQL']: # Two tables
rje.writeDelimit(OCCFILE,outlist,delimit)
else:
rje.writeDelimit(RESFILE,outlist+patstats,delimit)
occx += 1
if self.opt['MySQL']: # Two tables
PATFILE.close()
OCCFILE.close()
self.log.printLog('#OUT','%s patterns output to %s.' % (rje.integerString(patx),patfile))
self.log.printLog('#OUT','%s pattern occurrences output to %s.' % (rje.integerString(occx),occfile))
else:
RESFILE.close()
self.log.printLog('#OUT','%s occurrences of %s patterns output to %s.' %
(rje.integerString(occx),rje.integerString(patx),self.info['Name']))
### InfoContent ###
elif self.info['Info'] != 'None':
## Setup ##
alphabet = rje_seq.alph_protx
if not os.path.exists(self.info['Info']):
self.log.errorLog('Input file %s missing!' % self.info['Info'],False,False)
return False
else:
mypresto = presto.Presto(self.log,self.cmd_list)
mypresto.loadMotifs(file=self.info['Info'],clear=True)
seqlist = rje_seq.SeqList(self.log,self.cmd_list+['autoload=T'])
if seqlist.seqNum() > 0:
aafreq = seqlist.aaFreq(alphabet=None,fromfile=None,loadfile=None,total=False) ### Returns dictionary of AA (& gap etc.) frequencies
else:
aafreq = {}
for aa in alphabet:
aafreq[aa] = 1.0 / len(alphabet)
alphabet = aafreq.keys()
maxinfo = 0
for aa in alphabet:
maxinfo += (aafreq[aa] * math.log(aafreq[aa],2))
## Output ##
delimit = rje.getDelimit(self.cmd_list)
ext = rje.delimitExt(delimit)
outfile = '%s.info.%s' % (rje.baseFile(self.info['Info'],True,['.txt','.%s' % ext]),ext)
if self.opt['Append']:
OUTFILE = open(outfile,'a')
else:
OUTFILE = open(outfile,'w')
rje.writeDelimit(OUTFILE,['motif','pattern','info'],delimit)
## Calculate Information Scores ##
for motif in mypresto.motif:
self.verbose(2,4,motif.info['Sequence'],0)
pattern = string.replace(motif.info['Sequence'],'X','.')
elements = string.split(pattern,'-')
pattern = ''
for el in elements:
if el.find('.{') == 0: # Ambiguous spacer length - compress
pattern += '.'
else:
pattern += el
self.verbose(2,2,'=> %s' % pattern,1)
motif.stat['Info'] = self.calculateInformationContent(pattern,aafreq,maxinfo,self.stat['InfoGapPen'])
self.verbose(0,3,'%s (%s) = %.2f' % (motif.info['Name'],pattern,motif.stat['Info']),1)
## Output ##
rje.writeDelimit(OUTFILE,[motif.info['Name'],pattern,'%.2f' % motif.stat['Info']],delimit)
## Finish ##
OUTFILE.close()
except:
self.log.errorLog('Error in run().',printerror=True,quitchoice=False)
raise # Delete this if method error not terrible