def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### ~ Basics ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.strlist = ['DomFile', 'DMIFile', 'OccFile', 'PPIFile']
self.boollist = []
self.intlist = []
self.numlist = []
self.filelist = []
self.listlist = []
self.dictlist = []
self.objlist = []
### ~ Defaults ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setDefaults(str='None',
bool=False,
int=0,
num=0.0,
obj=None,
setlist=True,
setdict=True,
setfile=True)
self.setStr({})
self.setBool({})
self.setInt({})
self.setNum({})
### ~ Other Attributes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
self.obj['SLiMList'] = rje_slimlist.SLiMList(self.log, self.cmd_list)
def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### ~ Basics ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.strlist = ['Candidates', 'SeqIn']
self.boollist = []
self.intlist = []
self.numlist = []
self.filelist = []
self.listlist = []
self.dictlist = []
self.objlist = []
### ~ Defaults ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setDefaults(str='None',
bool=False,
int=0,
num=0.0,
obj=None,
setlist=True,
setdict=True,
setfile=True)
self.setStr({})
self.setBool({})
self.setInt({})
self.setNum({})
### ~ Other Attributes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setForkAttributes() # Delete if no forking
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
self.obj['HTML'] = rje_html.HTML(self.log, self.cmd_list)
def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### Basics ###
self.infolist = ['Pillars', 'PPIFile', 'XRef']
self.optlist = ['SGD2SP', 'Gopher']
self.statlist = []
self.listlist = ['Pillars', 'YeastSeq']
self.dictlist = ['PPI', 'Rename']
self.objlist = ['SeqList']
### Defaults ###
self._setDefaults(info='None',
opt=False,
stat=0.0,
obj=None,
setlist=True,
setdict=True)
self.setInfo({
'Pillars': 'Pillars.tab',
'PPIFile': 'Y2H_union.txt',
'XRef': 'yeast_xref.20101222.tdt'
})
### Other Attributes ###
self.obj['SeqList'] = rje_seq.SeqList(
self.log,
['accnr=F', 'seqnr=F', 'autoload=T', 'seqin=Proteins.fsa'] +
self.cmd_list)
self.dict['SeqDict'] = self.obj['SeqList'].seqNameDic(
proglog=self.stat['Verbose'] > 0)
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try:### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log,self.cmd_list+['tuplekeys=T'])
if self.baseFile().lower() in ['','none']: self.baseFile('%s.vs.%s.Q%d' % (rje.baseFile(self.getStr('MutPileup'),True),rje.baseFile(self.getStr('WTPileup'),True),self.getInt('QCut')))
if not self.force() and os.path.exists('%s.fdr.tdt' % self.baseFile()): return
### ~ [2] Look for/process WT Data ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
if self.force() or not os.path.exists('%s.WT.tdt' % self.baseFile()): self.parsePileup('WT',self.getStr('WTPileup'))
### ~ [3] Generate Reference sequences and Major Alleles (by locus) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
refseq = {}; rx = 0
majors = {}
locus = None
WTDATA = open('%s.WT.tdt' % self.baseFile(),'r'); wx = 0
for line in WTDATA:
self.progLog('\r#WT','Reading WT data: Reference seq length = %s nt' % (rje.iStr(rx)),rand=0.01)
data = rje.readDelimit(line); wx += 1
if data[0] == 'Locus': continue
else:
if data[0] != locus: locus = data[0]; refseq[locus] = ''; majors[locus] = []
pos = int(data[1])
while (pos - 1) > len(refseq[locus]): refseq[locus] += '?'; rx += 1
while (pos - 1) > len(majors[locus]): majors[locus].append('-')
refseq[locus] += data[2]; majors[locus].append(data[5]); rx += len(data[2])
WTDATA.close()
self.printLog('\r#WT','%s lines read from WT data: Reference seq length = %s nt' % (rje.iStr(wx),rje.iStr(rx)))
for locus in rje.sortKeys(majors):
if len(majors[locus]) != len(refseq[locus]): self.errorLog('%s WTMajor versus RefSeq length mismatch!' % locus,printerror=False); raise ValueError
self.dict['WTMajor'] = majors
self.dict['RefSeq'] = refseq
### ~ [3] Look for/process Mutant Data ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
if self.force() or not os.path.exists('%s.Mut.tdt' % self.baseFile()): self.parsePileup('Mut',self.getStr('MutPileup'),True)
return True # Setup successful
except: self.errorLog('Problem during %s setup.' % self); return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try:### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
db = self.obj['DB'] = rje_db.Database(self.log,self.cmd_list+['delimit=,'])
self.splitMascot()
if self.getBool('iTRAQ') and self.dict['Samples']: self.iTRAQSamples()
return True # Setup successful
except: self.errorLog('Problem during %s setup.' % self); return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try:### ~ [1] Setup Database ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log,self.cmd_list)
db = self.db().addEmptyTable('ProDigIS',['AccNum','Protease','PepCount'],['AccNum','Protease'])
if self.getInt('MinPepLen') > 0: db.addField('MinPepLen')
if self.getBool('NRPep'): db.addField('NRPep')
if rje.exists(self.getStr('Source')):
fdb = self.db().addTable(self.getStr('Source'),mainkeys=['AccNum'],name='Source')
fdb.addField('File')
fdb.addField('ProtMWt')
else: fdb = self.db().addEmptyTable('Source',['AccNum','File','ProtMWt'],['AccNum'])
for i in range(1,self.getInt('MaxPepLen')+1): db.addField(i)
if self.getBool('PepMWt'):
for i in range(1,self.getInt('MaxPepLen')+1): db.addField(i*100.0)
### ~ [2] Load Sequences ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['SeqList'] = rje_seq.SeqList(self.log,self.cmd_list+['seqin=None','autoload=F'])
self.obj['SeqList'].seq = fullseq = []
for seqfile in self.list['SeqFiles']:
file = rje.baseFile(seqfile,True)
seqlist = rje_seq.SeqList(self.log,['autofilter=T','gnspacc=T','seqnr=F']+self.cmd_list+['seqin=%s' % seqfile,'autoload=T'])
fullseq += seqlist.seqs()
for seq in seqlist.seqs():
accnum = seq.getStr('AccNum')
try:
entry = fdb.data()[accnum]
if 'File' in entry and entry['File']: self.errorLog('%s found in %s AND %s!' % (accnum,entry['File'],file),printerror=False)
entry['File'] = file
entry['ProtMWt'] = seq.MWt()
except:
entry = {'AccNum':accnum,'File':file,'ProtMWt':seq.MWt()}
fdb.addEntry(entry)
self.deBug(fdb.dict['Data'][seq.getStr('AccNum')])
self.printLog('#SEQ','%s sequences to analyse in total' % rje.iLen(fullseq))
fdb.fillBlanks()
### ~ [3] Setup Peptide Probabilities ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
if self._peptideProbabilities():
db.addField('LenExp','PepCount');
if self.getBool('PepMWt'): db.addField('MWtExp','LenExp'); db.addField('Len7Exp','MWtExp')
else: db.addField('Len7Exp','LenExp')
db.addField('Len37','Len7Exp')
if self.getBool('PepMWt'):
db.addField('Len5','MWtExp'); db.addField('MWt5','Len5')
db.addField('Len3','MWtExp'); db.addField('MWt3','Len3')
else: db.addField('Len5','LenExp'); db.addField('Len3','LenExp')
return
### ~ [4] Temp GABLAM Data ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
gdb = self.db().addTable('Chlam_Pos.vs.embl_bacteria.hitsum.tdt',['Qry'],name='GABLAM')
ndb = self.db().addTable('Chlam_Neg.vs.embl_bacteria.hitsum.tdt',['Qry'],name='GNeg')
self.db().mergeTables(gdb,ndb,overwrite=True,matchfields=True)
gdb.renameField('Qry','AccNum')
tmp = self.db().joinTables(name='blast',join=[('Source','AccNum'),('GABLAM','AccNum')],newkey=['AccNum','File'],keeptable=False)
tmp.saveToFile()
tmp.compress(['File'],default='mean')
tmp.dropFields(['AccNum'])
tmp.info['Name'] = 'blastsum'
tmp.saveToFile()
except: self.errorLog('Problem during %s setup.' % self); return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log,
self.cmd_list + ['tuplekeys=T'])
if not self.baseFile(return_none=''): self.baseFile('diploidocus')
self.printLog('#BASE',
'Output file basename: %s' % self.baseFile())
return True # Setup successful
except:
self.errorLog('Problem during %s setup.' % self.prog())
return False # Setup failed
def batchSummarise(
self
): ### Batch run seqlist summarise on batchrun=LIST files and output table of results
'''
Batch run seqlist summarise on batchrun=LIST files and output table of results
'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
if not self.list['BatchRun']:
raise ValueError(
'Need to provide batchrun=LIST files for summarise mode.')
db = rje_db.Database(self.log, self.cmd_list)
self.printLog('#BASE', db.baseFile())
sdb = None
if not self.force():
sdb = db.addTable(mainkeys=['File'],
name='summarise',
expect=False)
if not sdb: sdb = db.addEmptyTable('summarise', ['File'], ['File'])
### ~ [2] Run Summarise ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.printLog(
'#BATCH', 'Batch summarising %s input files' %
rje.iLen(self.list['BatchRun']))
for file in self.list['BatchRun']:
seqdata = rje_seqlist.SeqList(
self.log, self.cmd_list +
['seqin=%s' % file, 'autoload=T', 'summarise=F'
]).summarise()
if seqdata:
if 'GC' in seqdata:
seqdata.pop('GC')
seqdata['GCPC'] = '%.2f' % seqdata['GCPC']
if 'GapLength' in seqdata:
seqdata['GapPC'] = '%.2f' % (100.0 *
seqdata['GapLength'] /
seqdata['TotLength'])
seqdata['MeanLength'] = '%.1f' % seqdata['MeanLength']
for field in string.split(
'SeqNum, TotLength, MinLength, MaxLength, MeanLength, MedLength, N50Length, L50Count, GapLength, GapPC, GCPC',
', '):
if field in seqdata and field not in sdb.fields():
sdb.addField(field)
for field in seqdata.keys():
if field not in sdb.fields(): sdb.addField(field)
sdb.addEntry(seqdata)
else:
self.errorLog('Summarise failed for %s' % file,
printerror=False)
### ~ [3] Output Summarise ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
sdb.saveToFile()
return True
except:
self.errorLog('%s.batchSummarise error' % self)
return False
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = db = rje_db.Database(self.log, self.cmd_list)
db.addEmptyTable('TimePoints', [
'TimePoint Name', 'TimePoint Description', 'Source URL',
'Year', 'yearUnit', 'month', 'day', 'keyword1', 'keyword2',
'keyword3', 'keyword4', 'keyword5'
],
keys=['TimePoint Name'])
return True # Setup successful
except:
self.errorLog('Problem during %s setup.' % self)
return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log,
self.cmd_list + ['tuplekeys=T'])
if not self.baseFile(return_none=''):
if self.getStrLC('SeqIn'):
self.baseFile(
rje.baseFile(self.getStr('SeqIn'), strip_path=True))
self.printLog('#BASE',
'Output file basename: %s' % self.baseFile())
except:
self.errorLog('Problem during %s setup.' % self.prog())
return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
fixfields = ['Location', 'Name', 'Artist', 'Composer', 'Album']
db = self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
#self.deBug(self.list['iTunes'])
for ifile in self.list['iTunes']:
#self.deBug(string.split(open(ifile,'r').readline(),'\t'))
idb = db.addTable(ifile,
mainkeys=['Location'],
name=rje.baseFile(ifile, True))
for field in iformat:
if iformat[field] == 'del' and field in idb.fields():
idb.dropField(field)
idb.dataFormat(iformat)
idb.addField('Album_Artist', 'Album')
idb.addField('Tracks', evalue=1)
if self.getBool('AddScore'): idb.addField('Score', evalue=0)
for entry in idb.entries():
for field in fixfields:
newval = ''
for x in entry[field]:
if x.isalnum() or x in '\\/: -_()[].~$':
newval += x
entry[field] = newval
entry['Album_Artist'] = entry['Artist']
try:
for divider in ['\\\\', '\\', ':', '/']:
if len(string.split(entry['Location'],
divider)) > 2:
entry['Album_Artist'] = string.split(
entry['Location'], divider)[-3]
break
except:
self.errorLog('!')
self.deBug(entry['Location'])
if not entry['Plays']: entry['Plays'] = 0
if not entry['Skips']: entry['Skips'] = 0
if self.getBool('AddScore'):
if entry['My Rating']:
entry['Score'] = (entry['My Rating'] - 60) / 20.0
idb.remakeKeys()
return True # Setup successful
except:
self.errorLog('Problem during %s setup.' % self)
return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
self.db().addTable(self.getStr('GeneMap'),
mainkeys=['Gene'],
datakeys='All',
name='GeneMap')
self.db().addTable(self.getStr('Pairwise'),
mainkeys=['Hub', 'Spoke'],
datakeys='All',
name='PPI')
self.loadHHPID()
return True # Setup successful
except:
self.errorLog('Problem during %s setup.' % self)
return False # Setup failed
def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### ~ Basics ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.strlist = ['ProtDesc', 'TaxBase']
self.boollist = ['BootWeight', 'Monophyly']
self.intlist = []
self.numlist = [
'BootFilter', 'MinBoot', 'MinScore', 'MinClass', 'MinSum',
'NoneBoot'
]
self.filelist = []
self.listlist = ['Classify', 'NwkList', 'TaxFilter']
self.dictlist = []
self.objlist = []
### ~ Defaults ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setDefaults(str='None',
bool=False,
int=0,
num=0.0,
obj=None,
setlist=True,
setdict=True,
setfile=True)
self.setStr({})
self.setBool({'BootWeight': True, 'Monophyly': False})
self.setInt({})
self.setNum({
'BootFilter': 0.0,
'MinBoot': 0.5,
'MinClass': 1.0,
'MinScore': 1.0,
'MinSum': 10.0,
'NoneBoot': 1.0
})
self.obj['DB'] = rje_db.Database(
self.log, ['tuplekeys=T', 'basefile=taxmap'] + self.cmd_list)
self.baseFile(self.obj['DB'].baseFile())
self.list['Classify'] = glob.glob(
'*.class') # List of files using wildcards and glob
self.list['NwkList'] = glob.glob(
'*.nwk') # List of files using wildcards and glob
### ~ Other Attributes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setForkAttributes() # Delete if no forking
def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### ~ Basics ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.strlist = []
self.boollist = []
self.intlist = []
self.numlist = []
self.listlist = []
self.dictlist = []
self.objlist = []
### ~ Defaults ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setDefaults(str='None',bool=False,int=0,num=0.0,obj=None,setlist=True,setdict=True)
#self.setInfo({})
#self.setBool({})
#self.setInt({})
#self.setNum({})
### ~ Other Attributes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setForkAttributes() # Delete if no forking
self.obj['DB'] = rje_db.Database(self.log,self.cmd_list)
self.obj['SeqList'] = rje_seq.SeqList(self.log,['autoload=T','dna=T']+self.cmd_list)
def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### ~ Basics ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.strlist = ['ExOpt']
self.boollist = ['MemSaver','Cleanup','GZip']
self.intlist = []
self.numlist = []
self.filelist = []
self.listlist = []
self.dictlist = []
self.objlist = []
### ~ Defaults ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setDefaults(str='None',bool=False,int=0,num=0.0,obj=None,setlist=True,setdict=True,setfile=True)
self.setStr({})
self.setBool({'MemSaver':False,'Cleanup':False,'GZip':True})
self.setInt({})
self.setNum({})
### ~ Other Attributes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setForkAttributes() # Delete if no forking
self.obj['DB'] = rje_db.Database(self.log,self.cmd_list+['tuplekeys=T'])
def setup(self): ### Main class setup method.
'''
Main class setup method. This will load sequences into a SeqList object, gaps into a 'gaps' database table, and
check or generate a PAF file from the mapped long reads.
'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
if not self.getStrLC('SeqIn'):
raise ValueError('seqin=FILE must be set')
if not rje.exists(self.getStr('SeqIn')):
raise IOError('Unable to read seqin=FILE: "{0}"'.format(
self.getStr('SeqIn')))
seqbase = rje.baseFile(self.getStr('SeqIn'), strip_path=True)
if not self.getStrLC('Basefile'): self.baseFile(seqbase)
if rje.checkForFiles(filelist=['.gaps.tdt'],
basename=seqbase,
log=self.log) and not self.force():
self.cmd_list.append('gapstats=F')
else:
self.cmd_list.append('gapstats=T')
seqin = self.seqinObj()
gapdb = self.db().addTable('%s.gaps.tdt' % seqbase,
mainkeys=['seqname', 'start', 'end'],
name='gaps',
ignore=[],
expect=True)
gapdb.dataFormat({'start': 'int', 'end': 'int'})
### ~ [2] PAF File ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
if not self.getStrLC('PAF'):
self.setStr({'PAF': self.baseFile() + '.paf'})
pfile = self.getStr('PAF')
if self.force() or not rje.exists(pfile):
paf = rje_paf.PAF(self.log, self.cmd_list)
paf.longreadMinimapPAF(pfile)
if not rje.exists(self.getStr('PAF')):
raise IOError(
'Unable to read or create PAF file: {0}'.format(pfile))
return True
except:
self.errorLog('Problem during %s setup.' % self.prog())
return False # Setup failed
def _setAttributes(self): ### Sets Attributes of Object
'''Sets Attributes of Object.'''
### ~ Basics ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.strlist = [
'BegField', 'EndField', 'QueryField', 'Reformat', 'TargetField',
'TDTFile'
]
self.boollist = []
self.intlist = []
self.numlist = []
self.filelist = []
self.listlist = ['TDTKeys']
self.dictlist = []
self.objlist = []
### ~ Defaults ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self._setDefaults(str='None',
bool=False,
int=0,
num=0.0,
obj=None,
setlist=True,
setdict=True,
setfile=True)
self.setStr({
'BegField': 'QryStart',
'EndField': 'HitStart',
'QueryField': 'Qry',
'Reformat': 'GFF3',
'TargetField': 'Hit'
})
self.setBool({})
self.setInt({})
self.setNum({})
self.list['TDTKeys'] = ['Qry', 'Hit', 'AlnNum']
### ~ Other Attributes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
self._setForkAttributes() # Delete if no forking
def setup(
self
): ### Main class setup method. |0.0|
'''Main class setup method.'''
try: ### ~ [1] Load tables ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
db = self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
self.baseFile('ingolia')
names = {
's1a': 'synthesis',
's1c': 'efficiency', # Not sure what Table S1 data is!
's2a': 'genes',
's2b': 'pauses',
's2c': 'stops',
's3': 'starts',
's4': 'lincRNA'
}
for tab in [
's1a', 's1b', 's1c', 's1d', 's2a', 's2b', 's2c', 's3', 's4'
]:
if tab in names: name = names[tab]
else: name = tab
dfile = '%s.%s.csv' % (self.baseFile(), tab)
if name == 'pauses':
self.db().addTable(dfile,
mainkeys=['UCSC ID', 'Codon'],
name=name)
elif name == 'starts':
self.db().addTable(
dfile,
mainkeys=['knownGene', 'Init Codon [nt]'],
name=name)
else:
self.db().addTable(dfile, name=name)
return True # Setup successful
except:
self.errorLog('Problem during %s setup.' % self)
return False # Setup failed
def setup(self): ### Main class setup method.
'''Main class setup method.'''
try: ### ~ [1] Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
self.obj['DB'] = rje_db.Database(self.log, self.cmd_list)
self.db().basefile(self.basefile())
self.list['Accuracy'] = [0, 1.0 - self.getNum('ErrPerBase')]
## ~ [1a] SMRTReads ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
while self.getStrLC('SMRTUnits') not in ['reads', 'gb', 'mb']:
txt = 'SMRTUnits "%s" not recognised'
if self.getNum('SMRTReads') < 10: smrtunits = 'Gb'
elif self.getNum('SMRTReads') > 10000: smrtunits = 'reads'
else: smrtunits = 'Mb'
if self.i() < 0 or rje.yesNo(
'%s: switch to (%s) %s?' %
(txt, self.getNum('SMRTReads'), smrtunits)):
self.setStr({'SMRTUnits': smrtunits})
elif self.i() > 0:
self.setStr(
{'SMRTUnits': rje.choice('SMRTUnits (reads/Gb/Mb)?')})
self.printLog('#UNITS',
'%s => %s' % (txt, self.getStr('SMRTUnits')))
if self.getStrLC('SMRTUnits') in ['gb', 'mb']:
smrttotal = self.getNum('SMRTReads') * {
'gb': 1e9,
'mb': 1e6
}[self.getStrLC('SMRTUnits')]
txt = '%s %s @ %.3f kb/read' % (self.getNum('SMRTReads'),
self.getStr('SMRTUnits'),
self.getNum('AvRead') / 1000.0)
self.setNum({'SMRTReads': smrttotal / self.getNum('AvRead')})
txt += ' => %s reads' % rje.iStr(int(self.getNum('SMRTReads')))
self.printLog('#READS', txt)
## ~ [1b] XnList ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
xnlist = []
for xn in self.list['XnList']:
if xn == '': continue
try:
ixn = int(xn)
if xn not in [ixn, '%d' % ixn]:
self.printLog('#XN', '"%s" -> %dX' % (xn, ixn))
if ixn == 0:
self.printLog(
'#XN', 'No point in 0X output: use 1-%Coverage.')
elif ixn == 1:
self.printLog('#XN',
'No point in 1X output: use %Coverage.')
else:
xnlist.append(ixn)
except:
self.errorLog(
'Could not process %s as part of XnList. (Integers only.)'
% xn)
xnlist.sort()
if xnlist:
self.printLog(
'#XN', 'XnList: %sX.' %
string.join(string.split('%s' % xnlist, ','), 'X, ')[1:-1])
self.list['XnList'] = xnlist
return True # Setup successful
except:
self.errorLog('Problem during %s setup.' % self.prog())
return False # Setup failed
def run(self): ### Main run method
'''Main run method.'''
try: ### ~ [1] ~ Setup ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
infile = self.getStr('InFile')
while not rje.exists(infile):
infile = rje.choice(
'File "%s" not found. Input file name? (Blank to quit):' %
infile)
if not infile:
return self.printLog('#QUIT', 'Execution terminated!')
db = rje_db.Database(self.log, self.cmd_list)
db.basefile(rje.baseFile(infile))
sdb = db.addTable(infile,
mainkeys='#',
delimit='\t',
name='SPF.Mod')
levels = {
'Level_1': 'k',
'Level_2': 'p',
'Level_3': 'c',
'Level_4': 'o',
'Level_5': 'f',
'Level_6': 'g',
'Level_7': 's'
}
# k__Bacteria p__Proteobacteria c__Alphaproteobacteria o__Rhodospirillales f__Rhodospirillaceae g__ s__ denovo44
# Unassigned unclassified unclassified unclassified unclassified unclassified unclassified denovo49
### ~ [1] Modify Text ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
dupnames = []
parents = {} # Parent for each term
renamed = []
ex = 0.0
etot = sdb.entryNum()
for entry in sdb.entries():
self.progLog('\r#SPF',
'Modifying SPF content: %.1f%%' % (ex / etot))
ex += 100.0
taxon = ''
parent = ''
#self.debug(entry)
for lvl in [
'Level_1', 'Level_2', 'Level_3', 'Level_4', 'Level_5',
'Level_6', 'Level_7'
]:
entry[lvl] = string.replace(entry[lvl], 'unidentified',
'unclassified')
#entry[lvl] = string.replace(entry[lvl],'Incertae_sedis','Incertae_sedis-%s' % levels[lvl])
null = '%s__' % levels[lvl]
#self.bugPrint(null)
#self.bugPrint(entry[lvl])
if entry[lvl] in [
null, 'Unassigned', 'unclassified',
'%sunclassified' % null,
'%sunidentified' % null,
'%sunculturedfungus' % null,
'%sIncertae_sedis' % null,
'%sunclassified_sp.' % null
]:
if not taxon or taxon.endswith('unclassified'):
entry[lvl] = '%sunclassified' % null
#elif taxon.endswith('unassigned)'): entry[lvl] = '%s%s' % (null,taxon[3:])
#elif taxon.endswith('unassigned)'): entry[lvl] = '%s(%s;%s-unassigned)' % (null,string.split(taxon,'(')[1][:-1],levels[lvl])
elif taxon.endswith('unassigned)'):
entry[lvl] = '%s%s;%s-unassigned)' % (
null, taxon[3:][:-1], levels[lvl])
else:
entry[lvl] = '%s%s(%s-unassigned)' % (
null, taxon[3:], levels[lvl])
if entry[lvl] in parents:
#self.debug(parents[entry[lvl]])
if parent in parents[entry[lvl]]:
entry[lvl] = parents[entry[lvl]][parent]
else:
self.bugPrint(entry[lvl])
self.bugPrint(parents[entry[lvl]])
renamed.append(entry[lvl])
newtax = '%s%d' % (entry[lvl],
renamed.count(entry[lvl]))
self.warnLog(
'%s had multiple parents (%s & %s) -> %s' %
(entry[lvl],
string.join(parents[entry[lvl]],
'|'), parent, newtax))
parents[newtax] = {parent: newtax}
parents[entry[lvl]][parent] = newtax
entry[lvl] = newtax
self.deBug(parents[entry[lvl]])
elif parent:
parents[entry[lvl]] = {parent: entry[lvl]}
parent = entry[lvl]
if entry[lvl][3:] == taxon[3:]:
if (entry[lvl], taxon) not in dupnames:
dupnames.append((entry[lvl], taxon))
#self.bugPrint(entry[lvl])
taxon = entry[lvl]
#self.debug(entry)
#self.debug(parents)
self.printLog('\r#SPF', 'Modifying SPF content complete.')
dupnames.sort()
for (dupA, dupB) in dupnames:
self.warnLog('Duplicate taxa names: %s & %s' % (dupA, dupB))
### ~ [2] Save to file ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
sdb.saveToFile(savefields=sdb.list['Fields'][1:])
### ~ [3] Compress to different taxonomic levels ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
compress = [
'Level_1', 'Level_2', 'Level_3', 'Level_4', 'Level_5',
'Level_6', 'Level_7', '#'
]
dump = compress.pop(-1)
rules = {'Observation Ids': 'list', dump: 'str'}
sdb.dropField('Observation Ids')
while compress:
sdb.compress(compress,
rules=rules,
default='sum',
best=[],
joinchar='|')
#if dump == '#':
sdb.dropField(dump)
sdb.saveToFile(
'%s.SPF.%s.%s.spf' %
(rje.baseFile(infile), compress[-1], levels[compress[-1]]))
dump = compress.pop(-1)
rules[dump] = 'list'
return
except:
self.errorLog(self.zen())
raise # Delete this if method error not terrible
