def assemble_genomes(self):
"""
Use skesa to assemble genomes
"""
assembly = skesa.Skesa(inputobject=self)
assembly.main()
metadataprinter.MetadataPrinter(inputobject=self)
def evaluate_assemblies(self):
"""
Evaluate assemblies with Quast
"""
qual = evaluate.AssemblyEvaluation(inputobject=self)
qual.main()
metadataprinter.MetadataPrinter(inputobject=self)
def quality_features(self, analysis):
"""
Extract features from assemblies such as total genome size, longest contig, and N50
"""
features = quality.QualityFeatures(inputobject=self, analysis=analysis)
features.main()
metadataprinter.MetadataPrinter(self)
def contamination_detection(self):
"""
Calculate the levels of contamination in the reads
"""
self.qualityobject.contamination_finder(report_path=self.reportpath,
debug=self.debug)
metadataprinter.MetadataPrinter(inputobject=self)
def quality(self):
"""
Creates quality objects and runs quality assessments and quality processes on the
supplied sequences
"""
# Validate that the FASTQ files are in the proper format, and that there are no issues e.g. different numbers
# of forward and reverse reads, read length longer than quality score length, proper extension
if not self.debug:
self.fastq_validate()
# Run FastQC on the unprocessed fastq files
self.fastqc_raw()
# Perform quality trimming and FastQC on the trimmed files
self.quality_trim()
# Run FastQC on the trimmed files
self.fastqc_trimmed()
# Perform error correcting on the reads
self.error_correct()
# Detect contamination in the reads
self.contamination_detection()
# Run FastQC on the processed fastq files
self.fastqc_trimmedcorrected()
# Exit if only pre-processing of data is requested
metadataprinter.MetadataPrinter(inputobject=self)
if self.preprocess:
logging.info('Pre-processing complete')
quit()
def sixteens(self):
"""
Run the 16S analyses
"""
sixteen_s = BLAST(args=self, analysistype='sixteens_full', cutoff=95)
sixteen_s.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def virulence(self):
"""
Virulence gene detection
"""
virulence = BLAST(args=self, analysistype='virulence')
virulence.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def resfinder(self):
"""
Resistance finding - assemblies
"""
resfinder = BLAST(args=self, analysistype='resfinder_assembled')
resfinder.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def seqsero(self):
"""
Run SeqSero2 on Salmonella samples
"""
seqsero = SeqSero(self)
seqsero.main()
metadataprinter.MetadataPrinter(inputobject=self)
def sistr(self):
"""
Sistr
"""
sistr_obj = sistr.Sistr(inputobject=self, analysistype='sistr')
sistr_obj.main()
metadataprinter.MetadataPrinter(inputobject=self)
def geneseekr(self):
"""
Find genes of interest
"""
geneseekr = BLAST(args=self, analysistype='genesippr', cutoff=95)
geneseekr.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def helper(self):
"""Helper function for file creation (if desired), manipulation, quality assessment,
and trimming as well as the assembly"""
# Simple assembly without requiring accessory files (SampleSheet.csv, etc).
if self.basicassembly:
self.runmetadata = Basic(inputobject=self)
else:
# Populate the runmetadata object by parsing the SampleSheet.csv, GenerateFASTQRunStatistics.xml, and
# RunInfo.xml files
self.runinfo = os.path.join(self.path, 'RunInfo.xml')
self.runmetadata = runMetadata.Metadata(passed=self)
# Extract the flowcell ID and the instrument name if the RunInfo.xml file was provided
self.runmetadata.parseruninfo()
# Extract PhiX mapping information from the run
phi = phix.PhiX(inputobject=self)
phi.main()
# Populate the lack of bclcall and nohup call into the metadata sheet
for sample in self.runmetadata.samples:
sample.commands = GenObject()
sample.commands.nohupcall = 'NA'
sample.commands.bclcall = 'NA'
# Move/link the FASTQ files to strain-specific working directories
fastqmover.FastqMover(inputobject=self)
# Print the metadata to file
metadataprinter.MetadataPrinter(inputobject=self)
def mash(self):
"""
Run mash to determine closest refseq genome
"""
logging.info('Running MASH analyses')
mash.Mash(inputobject=self, analysistype='mash')
metadataprinter.MetadataPrinter(inputobject=self)
def run_gdcs(self):
"""
Determine the presence of genomically-dispersed conserved sequences (genes from MLST, rMLST, and cgMLST
analyses)
"""
# Run the GDCS analysis
gdcs = GDCS(inputobject=self)
gdcs.main()
metadataprinter.MetadataPrinter(inputobject=self)
def legacy_vtyper(self):
"""
Legacy vtyper - uses ePCR
"""
legacy_vtyper = LegacyVtyper(inputobject=self,
analysistype='legacy_vtyper',
mismatches=2)
legacy_vtyper.vtyper()
metadataprinter.MetadataPrinter(inputobject=self)
def prophages(self):
"""
Prophage detection
"""
prophages = Prophages(args=self,
analysistype='prophages',
cutoff=90,
unique=True)
prophages.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def univec(self):
"""
Univec contamination search
"""
univec = Univec(args=self,
analysistype='univec',
cutoff=80,
unique=True)
univec.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def coregenome(self):
"""
Core genome calculation
"""
coregen = core.CoreGenome(args=self,
analysistype='coregenome',
genus_specific=True)
coregen.seekr()
core.AnnotatedCore(inputobject=self)
metadataprinter.MetadataPrinter(inputobject=self)
def rmlst_assembled(self):
"""
Run rMLST analyses on assemblies
"""
if not os.path.isfile(os.path.join(self.reportpath, 'rmlst.csv')):
rmlst = BLAST(args=self, analysistype='rmlst', cutoff=100)
rmlst.seekr()
else:
parse = ReportParse(args=self, analysistype='rmlst')
parse.report_parse()
metadataprinter.MetadataPrinter(inputobject=self)
def ec_typer(self):
"""
Assembly-based serotyping
"""
ec = ECTyper(metadata=self.runmetadata,
report_path=self.reportpath,
assembly_path=os.path.join(self.path, 'raw_assemblies'),
threads=self.cpus,
logfile=self.logfile)
ec.main()
metadataprinter.MetadataPrinter(inputobject=self)
def univec(self):
"""
Univec contamination search
"""
if not os.path.isfile(os.path.join(self.reportpath, 'univec.csv')):
univec = Univec(args=self,
analysistype='univec',
cutoff=80,
unique=True)
univec.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def assembly_stats(self):
"""
Perform some basic quality analyses on the assemblies
"""
# Calculate assembly metrics on raw assemblies
self.quality_features(analysis='polished')
# ORF detection
self.prodigal()
# CLARK analyses
self.clark()
metadataprinter.MetadataPrinter(inputobject=self)
def sixteens(self):
"""
Run the 16S analyses
"""
SixteensFull(args=self,
pipelinecommit=self.commit,
startingtime=self.starttime,
scriptpath=self.homepath,
analysistype='sixteens_full',
cutoff=0.95)
metadataprinter.MetadataPrinter(inputobject=self)
def serosippr(self):
"""
Serotyping analyses
"""
Serotype(args=self,
pipelinecommit=self.commit,
startingtime=self.starttime,
scriptpath=self.homepath,
analysistype='serosippr',
cutoff=0.90,
pipeline=True)
metadataprinter.MetadataPrinter(inputobject=self)
def prophages(self, cutoff=90):
"""
Prophage detection
:param cutoff: cutoff value to be used in the analyses
"""
prophages = Prophages(args=self,
analysistype='prophages',
cutoff=cutoff,
unique=True)
if not os.path.isfile(os.path.join(self.reportpath, 'prophages.csv')):
prophages.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def serosippr(self):
"""
Serotyping analyses
"""
# pipeline=True)
sero = BLAST(args=self,
analysistype='serosippr',
cutoff=90,
genus_specific=True,
unique=True)
sero.seekr()
metadataprinter.MetadataPrinter(inputobject=self)
def mob_suite(self):
"""
"""
mob = MobRecon(metadata=self.runmetadata.samples,
analysistype='mobrecon',
databasepath=self.reffilepath,
threads=self.cpus,
logfile=self.logfile,
reportpath=self.reportpath)
mob.mob_recon()
metadataprinter.MetadataPrinter(inputobject=self)
def genesippr(self):
"""
Find genes of interest
"""
GeneSippr(args=self,
pipelinecommit=self.commit,
startingtime=self.starttime,
scriptpath=self.homepath,
analysistype='genesippr',
cutoff=0.95,
pipeline=False,
revbait=False)
metadataprinter.MetadataPrinter(inputobject=self)
def objectprep(self):
# Only find the data files if a datapath is provided
if self.datapath:
self.runmetadata = createobject.ObjectCreation(self)
else:
for sample in self.runmetadata.samples:
sample.general.abundancefile = sample.general.abundance
sample.general.assignmentfile = sample.general.classification
sample.general.fastqfiles = [sample.general.combined]
# Print the metadata to file
metadataprinter.MetadataPrinter(self)
# Load the results in the csv files into dictionaries
self.taxids()
def ressippr(self):
"""
Resistance finding - raw reads
"""
res = Resistance(args=self,
pipelinecommit=self.commit,
startingtime=self.starttime,
scriptpath=self.homepath,
analysistype='resfinder',
cutoff=0.7,
pipeline=False,
revbait=True)
res.main()
metadataprinter.MetadataPrinter(inputobject=self)
