def run():
file_step1 = './02-pipeline/step6.fna'
"""Retrieve known sequences"""
knownseqfile = known()
"""Check if a BLAST DB of step7_knownseq already exists; Make BLAST DB if it doesn't"""
blastdb = blast.check(knownseqfile)
"""BLAST unique mature peptides against known sequences"""
blastoutfile = './02-pipeline/step7_blastp.csv'
blast.blastp(blastdb, file_step1, blastoutfile)
"""Parse the BLASTp output file"""
print 'Parsing BLASTp output...\n'
blastout = []
for b in blast.parse(
blastoutfile): #[cds_id, known sequence, %ID, length, evalue]
blastout.append([str(b[0]), b[1], b[2], b[3], b[4]])
"""Populate the SQLite Annotated table with BLASTp results"""
print 'Populating the Annotated table in the SQLite DB.'
count = 0
for b in blastout:
c = mysqlpop.annotated(b)
count += c
print '{} hits have been entered in the SQLite annotated table.'.format(
count)
print 'DATA ENTRY INTO MYSQL ANNOTATED TABLE IS COMPLETE'
filename = './02-pipeline/step7.csv'
header = ['cds_id', 'knownNP id', 'PID', 'length', 'evalue']
output.csv(filename, header, blastout)
print 'The BLASTp results have were written to {}.\n'.format(filename)
def run():
file_step1 = './02-pipeline/step1.csv'
"""Retrieve seqreads table entries from the SQLite DB"""
seqreads = []
for l in mysqlout.seqreads():
seqreads.append([str(l[0]), str(l[1]), str(l[2])])
"""Output to csv file"""
filename = './02-pipeline/step2.csv'
header = ['seqreads id', 'sequence', 'profile-HMM name']
output.csv(filename, header, seqreads)
print 'The hits (MySQL id and sequence) have been written to the file {}.\n'.format(
filename)
def run():
file_step3 = './02-pipeline/step3.csv'
print 'Running SignalP...\n'
"""Retrieve sequences from Step3 output and run SignalP"""
nosignalpep = []
for c in CDS(file_step3):
s = signal(c, config.C['sp_cutoff'], config.C['sp_min_length'])[0]
nosignalpep.append(s)
"""Output to csv file"""
filename = './02-pipeline/step4.csv'
header = ['cds_id', 'signal peptide position', 'nosignalpeptide']
output.csv(filename, header, nosignalpep)
print '\nSignalP results have been written to the file {}.\n'.format(
filename)
def output_data(stuff):
"Dump the data appropriately."
# pickle is always output as a backup
session_id = str(datetime.datetime.now()).replace(" ",".")
dump(tweets, open("OUTPUT_TWEETS_%s.pkl"%session_id,"wb"))
if config["output"] == "json":
output.json(tweets, session_id)
elif config["output"] == "csv":
output.csv(tweets, session_id)
elif config["output"] == "pickle":
pass
else:
print "Probably should have told you this before, but your output"
print "format is unrecognized. Nevertheless, a serialized python pickle"
print "has been dumped in its stead."
print
def run(evaluecutoff):
file_step4 = './02-pipeline/step4.csv'
matseq = []
"""Find mature sequences"""
for s in sp(file_step4):
mat = mature.findmat(s, path_fasta(), float(evaluecutoff),
config.C['mature_min_length'],
config.C['mature_max_length'])
if mat is not None:
matseq.append(mat)
"""Output to csv file """
filename = './02-pipeline/step5.csv'
header = ['cdsid_mature#', 'mature sequence']
out = []
for m in matseq:
for mm in m:
out.append(mm)
output.csv(filename, header, out)
print 'The mature peptides were written to the file {}.\n'.format(filename)
def run():
filename = './02-pipeline/step8.csv'
fields = mysqlout.final(config.C['neuropeptide_family'])
output.csv(filename, fields[0], fields[1:])
analysis()
print 'The output files have been written.'