def dMutAdd(project, mutID, mutparent,kind, name='', descr='', color=None):
'''
Check and add a mutant
'''
org = Organism(project)
if org.isOrg(mutID):
logger.warning('Organism %s is already present'%mutID)
logger.warning('Remove it before addition')
return False
if not org.isOrg(mutparent):
logger.error('Parent organism %s not present!'%mutparent)
return False
elif org.isMutant(mutparent):
logger.error('Parent organism %s cannot be a mutant!'%mutparent)
return False
parents = len(org) - org.howManyMutants()
if parents != 1:
logger.error('Only one parent is allowed!')
return False
if not color:
org.addOrg(mutID, name=name, description=descr,
mutant=True, reference=mutparent, mkind=kind)
else:
org.addOrg(mutID, name=name, description=descr,
mutant=True, reference=mutparent, mkind=kind, color=color)
logger.info('Mutant %s (%s) added'
%(mutID, org.getOrg(mutID).mkind))
return True
def dGenomeRemove(project, organisms):
'''
Remove all the genomic data about specific organism ID(s)
'''
gen = Genome(project)
oCheck = Organism(project)
for org in organisms:
if not oCheck.isOrg(org):
logger.warning('Genome %s is not present: skipping'%org)
continue
gen.delProteome(org)
logger.info('Successfully removed genome %s'%org)
return True
def dPhenomeRemove(project, organisms):
'''
Remove all the phenomic data about specific organism ID(s)
'''
biolog = Biolog(project)
oCheck = Organism(project)
for org in organisms:
if not oCheck.isOrg(org):
logger.warning('Phenome %s is not present: skipping'%org)
continue
biolog.delOrg(org)
logger.info('Successfully removed phenome %s'%org)
if biolog.atLeastOneParameter():
logger.warning('The activity must be recalculated')
return True
def dRemove(project, organisms):
'''
Remove all the organism info regarding a particular organism ID(s)
'''
org = Organism(project)
for orgID in organisms:
if not org.isOrg(orgID):
logger.warning('Organism %s is not present: skipping'%orgID)
continue
muts = [mutID for mutID in org.getOrgMutants(orgID)]
org.delOrg(orgID, True)
logger.info('Successfully removed organism %s'%orgID)
if len(muts) > 0:
logger.info('Removed also %d %s mutant(s)'%(len(muts),orgID))
return True
def dGenomeMutAdd(project, mutID, mutfasta):
'''
Check and add a mutant
'''
if not os.path.exists(mutfasta):
logger.error('Fasta file %s may not be present'%(mutfasta))
return False
org = Organism(project)
if not org.isOrg(mutID):
logger.warning('Organism %s is not present yet!'%mutID)
return False
gen = Genome(project)
gen.addProteome(mutID, mutfasta)
logger.info('Mutant %s (%s) added, having %d mutated genes'
%(mutID, org.getOrg(mutID).mkind,gen.howMany(mutID)))
return True
def dGenomeAdd(project, orgID, filename):
'''
Add a single genome
'''
if not os.path.exists(filename):
logger.error('Fasta file %s may not be present'%(filename))
return False
filename = os.path.abspath(filename)
org = Organism(project)
if not org.isOrg(orgID):
logger.warning('Organism %s is not present yet!'%orgID)
return False
gen = Genome(project)
gen.addProteome(orgID, filename)
logger.info('Added genome %s, having %d proteins'%
(orgID, gen.howMany(orgID)))
return True
def dAdd(project, orgID, name='', descr='', color=None):
'''
Add a single organism
'''
org = Organism(project)
# If trying to override a present organism, throw an error
if org.isOrg(orgID):
logger.warning('Organism %s is already present'%orgID)
logger.warning('Remove it before addition')
return False
if not color:
org.addOrg(orgID, name=name, description=descr)
else:
org.addOrg(orgID, name=name, description=descr, color=color)
logger.info('Added organism %s'%orgID)
return True
def dGenomeDirAdd(project, folder, extension):
'''
Add a series of genomes contained in a directory
'''
if not os.path.exists(folder):
logger.error('Fasta folder %s may not be present'%(folder))
return False
logger.info('Looking for files with extension %s'%extension)
org = Organism(project)
added = 0
for infile in os.listdir(folder):
if infile.split('.')[-1] != extension:
logger.debug('Skipping file %s'%infile)
continue
orgID = infile.split('.')[0]
filename = os.path.join(folder, infile)
if os.path.isdir(filename):
continue
if not org.isOrg(orgID):
logger.warning('Organism %s is not present yet! Skipping...'%orgID)
continue
if not org.isMutant(orgID):
if not dGenomeAdd(project, orgID, filename):
logger.error('Could not add genome %s'%infile)
return False
else:
if not dGenomeMutAdd(project, orgID, filename):
logger.error('Could not add genome %s'%infile)
return False
added += 1
if added > 0:
logger.info('Added %d genomes from %s'%
(added, folder))
else:
logger.warning('No genomes were added from %s'%folder)
return True
def dPhenomeAdd(project, orgID, filename):
'''
Add a single phenome
'''
if not os.path.exists(filename):
logger.error('Phenomic file %s may not be present'%(filename))
return False
org = Organism(project)
if not org.isOrg(orgID):
logger.warning('Organism %s is not present yet!'%orgID)
return False
filename = os.path.abspath(filename)
bparser = BiologParser(filename)
bparser.parse()
if len(bparser.plates) == 0:
logger.warning('No biolog data was found!')
return False
# Check the organisms id inside the biolog files
strainNumbers = set([plate.strainNumber for plate in bparser.plates])
strainNames = set([plate.strainName for plate in bparser.plates])
samples = set([plate.sample for plate in bparser.plates])
if orgID not in samples:
logger.debug('No sign of %s in sample field'%orgID)
if orgID not in strainNames:
logger.debug('No sign of %s in strainName field'%orgID)
if orgID not in strainNumbers:
logger.debug('No sign of %s in strainNumber field'%orgID)
# TODO: regular expression search
if orgID in samples:
if len(samples) > 1:
logger.warning('''More than one organism ID may be present in this phenomic data file!''')
logger.warning('''%s'''%' '.join(samples))
return False
for plate in bparser.plates:
plate.strain = plate.sample
elif orgID in strainNames:
if len(strainNames) > 1:
logger.warning('''More than one organism ID may be present in this phenomic data file!''')
logger.warning('''%s'''%' '.join(strainNames))
return False
for plate in bparser.plates:
plate.strain = plate.strainName
elif orgID in strainNumbers:
if len(strainNumbers) > 1:
logger.warning('''More than one organism ID may be present in this phenomic data file!''')
logger.warning('''%s'''%' '.join(strainNumbers))
return False
for plate in bparser.plates:
plate.strain = plate.strainNumber
else:
logger.warning('''The organism ID you provided was not found inside the phenomic data file''')
logger.info('''Using it anyway to add this data''')
# Prepare a series of Plate objects to catch the replicas
dPlates={}
for plate in bparser.plates:
if plate.plate_id not in dPlates:
dPlates[plate.plate_id] = Plate(plate.plate_id)
dPlates[plate.plate_id].addData(plate.strain, plate)
# Grep the wells
wells = [w for plate in dPlates.itervalues() for w in plate.getWells()]
# Add to the project
biolog = Biolog(project)
biolog.addWells(wells, clustered=False)
logger.info('Added phenome %s, having %d biolog plates (%d wells)'%
(orgID, len(dPlates), len(wells)))
return True
def dPhenomeMultiAdd(project, filename):
'''
Add a single phenomic file with multiple organisms in it
'''
if not os.path.exists(filename):
logger.error('Phenomic file %s may not be present'%(filename))
return False
filename = os.path.abspath(filename)
bparser = BiologParser(filename)
bparser.parse()
if len(bparser.plates) == 0:
logger.warning('No biolog data was found!')
return False
# Check the organism ids inside the biolog files
# Assuming the names are correct AND stored inside the strainName field
logger.debug('Assuming organism IDs are correct and inside the field strainName')
strainNames = set([plate.strainName for plate in bparser.plates])
strainNames.discard(None)
strainNames.discard('')
if len(strainNames) == 0:
logger.warning('''Field strainName doesn't contain any value (%s)'''%filename)
return False
logger.info('Found the following organism IDs: %s'%' '.join(strainNames))
for plate in bparser.plates:
plate.strain = plate.strainName
# TODO: regular expressions verification
orgs = strainNames
for orgID in orgs:
org = Organism(project)
if not org.isOrg(orgID):
logger.warning('Organism %s is not present yet! Skipping...'%orgID)
continue
# Prepare a series of Plate objects to catch the replicas
dPlates={}
for plate in bparser.plates:
if plate.strain == orgID:
if plate.plate_id not in dPlates:
dPlates[plate.plate_id] = Plate(plate.plate_id)
dPlates[plate.plate_id].addData(plate.strain, plate)
# Grep the wells
wells = [w for plate in dPlates.itervalues()
for w in plate.getWells()]
# Add to the project
biolog = Biolog(project)
biolog.addWells(wells, clustered=False)
logger.info('Added phenome %s, having %d biolog plates (%d wells)'%
(orgID, len(dPlates), len(wells)))
return True