def getGoodDivergenceAlignedTrimmedSeqPair(seqId, seq, hitSeqId, hitSeq, workPath):
'''
aligns seq to hit. trims aligned seq and hit seq.
returns: pairs of pairs of id and aligned trimmed sequences for sequences in hits,
and a predicate function that, given a divergence threshold, says if the divergence of the sequences exceeds the threshold.
e.g. ((seqId, alignedTrimmedSeq), (hitSeqId, alignedTrimmedHitSeq), divergencePredicateFunc)
'''
# ALIGN SEQ and HIT
# need to align the sequences so we'z can study the rate of evolution per site
inputFasta = '>%s\n%s\n>%s\n%s\n'%(seqId, seq, hitSeqId, hitSeq)
if USE_CLUSTALW:
alignedFasta = alignFastaClustalw(inputFasta, workPath)
else:
alignedFasta = alignFastaKalign(inputFasta)
# try to recover from rare, intermittent failure of fasta alignment
if not alignedFasta:
logging.error('fasta alignment failed.\ninputFasta=%s\n' +
'alignedFasta=%s\nSleep and retry alignment.',
inputFasta, alignedFasta)
time.sleep(0.1)
alignedFasta = alignFastaKalign(inputFasta)
try:
# parse the aligned fasta into sequence ids and sequences
namelinesAndSeqs = list(fasta.readFasta(cStringIO.StringIO(alignedFasta)))
idAndSeqs = [(fasta.idFromName(seqNameline), seq) for seqNameline, seq in namelinesAndSeqs]
alignedIdAndSeq, alignedHitIdAndSeq = idAndSeqs
except Exception as e:
e.args += (inputFasta, alignedFasta)
raise
# CHECK FOR EXCESSIVE DIVERGENCE AND TRIMMING
# find most diverged sequence
# sort sequences by dash count. why?
divIdSeqs = []
for id, seq in (alignedIdAndSeq, alignedHitIdAndSeq):
dashCount = seq.count('-')
div = dashCount / float(len(seq))
g = (dashCount, div, id, seq)
divIdSeqs.append(g)
divIdSeqs.sort()
# check for excessive divergence
leastDivergedDashCount, leastDivergedDiv, leastDivergedId, leastDivergedSeq = divIdSeqs[0]
# check for excessive divergence and generate dashtrim.
mostDivergedDashCount, mostDivergedDiv, mostDivergedId, mostDivergedSeq = divIdSeqs[1]
# dashtrim = dashlen_check(mostDivergedSeq, divergence)
startTrim, endTrim, trimDivergence = dashlen_check(mostDivergedSeq)
# logging.debug('dashtrim='+str(dashtrim))
# trim and add seqs to output
def divergencePredicate(divergenceThreshold):
'''Why this logic? Ask Dennis. Function closed over local variables that returns whether or not the alignment of the sequences is too diverged.'''
if leastDivergedSeq and leastDivergedDiv > divergenceThreshold:
return True
if (startTrim or endTrim) and trimDivergence >= divergenceThreshold:
return True
return False
alignedTrimmedIdAndSeq, alignedTrimmedHitIdAndSeq = [(id, seq[startTrim:(len(seq)-endTrim)]) for id, seq in (alignedIdAndSeq, alignedHitIdAndSeq)]
return alignedTrimmedIdAndSeq, alignedTrimmedHitIdAndSeq, divergencePredicate
def makeGetSeqForId(genomeFastaPath):
'''
genomeFastaPath: location of fasta file. also location/name of blast formatted indexes of the fasta file.
'''
# suck fasta file into memory, converting it into a map from id to sequence
# in memory dict performs much better than on-disk retrieval with xdget or fastacmd.
# and genome fasta files do not take much space (on a modern computer).
fastaMap = {}
for (seqNameline, seq) in fasta.readFasta(genomeFastaPath):
seqId = fasta.idFromName(seqNameline)
fastaMap[seqId] = seq
def getSeqForIdInMemory(seqId):
return fastaMap[seqId]
return getSeqForIdInMemory
def makeGetSeqForId(genomeFastaPath):
'''
genomeFastaPath: location of fasta file. also location/name of blast formatted indexes of the fasta file.
'''
# suck fasta file into memory, converting it into a map from id to sequence
# in memory dict performs much better than on-disk retrieval with xdget or fastacmd.
# and genome fasta files do not take much space (on a modern computer).
fastaMap = {}
for (seqNameline, seq) in fasta.readFasta(genomeFastaPath):
seqId = fasta.idFromName(seqNameline)
fastaMap[seqId] = seq
def getSeqForIdInMemory(seqId):
return fastaMap[seqId]
return getSeqForIdInMemory
def create_fv_files():
filename_fasta = inputFile
filename_profile = profile
filename_fv = outputFile
fasta_dict = readFasta(filename_fasta)
profile_dict = read_profiles(filename_profile)
pool = mp.Pool(processes=8)
results = [
pool.apply_async(form_feature_vector,
args=(prot_id, fasta_dict[prot_id], profile_dict))
for prot_id in fasta_dict
]
fv_dict_raw = dict()
for p in results:
(prot_id, fv) = p.get()
fv_dict_raw[prot_id] = fv
write_feature_vector(filename_fv, fv_dict_raw)
return
count[posdict[c]] += 1
return ranks
#Gather arguments from the user
if (len(sys.argv) < 4):
#If in the incorrect form, return an error message
print("Arguments must be of the form : referencefile, readsfile, k, dmax.")
exit(0)
#referencefile and readsfile must be file names, k and dmax integers.
referencefile, readsfile, kmerLength, dmax = sys.argv[1], sys.argv[2], int(
sys.argv[3]), int(sys.argv[4])
#Initialization of the reference file
#readFasta only take the sequence of bases, and the $ is for the BWT, to mark the end of the string.
reference = (fasta.readFasta(referencefile)).lower() + "$"
#Initialization of reads and readsInv, its reverse complementary
reads, readsBioPalind = [], []
for line in open(readsfile, "r"):
if line[0] != ">": #lines with > do not contain sequences, but merely comments about the sequences.
reads.append(
line[:-1].lower()
) #-1 to remove \n. To lower case for practical reasons when calling posdict.
readsBioPalind.append(biologicalPalyndrome(
line[:-1].lower())) #We also stock the biological palyndromes
#We create SA, BWT, Rank and F from reference
print("generating SA")
def getGoodDivergenceAlignedTrimmedSeqPair(seqId, seq, hitSeqId, hitSeq,
workPath):
'''
aligns seq to hit. trims aligned seq and hit seq.
returns: pairs of pairs of id and aligned trimmed sequences for sequences in hits,
and a predicate function that, given a divergence threshold, says if the divergence of the sequences exceeds the threshold.
e.g. ((seqId, alignedTrimmedSeq), (hitSeqId, alignedTrimmedHitSeq), divergencePredicateFunc)
'''
# ALIGN SEQ and HIT
# need to align the sequences so we'z can study the rate of evolution per site
inputFasta = '>%s\n%s\n>%s\n%s\n' % (seqId, seq, hitSeqId, hitSeq)
if USE_CLUSTALW:
alignedFasta = alignFastaClustalw(inputFasta, workPath)
else:
alignedFasta = alignFastaKalign(inputFasta)
# try to recover from rare, intermittent failure of fasta alignment
if not alignedFasta:
logging.error(
'fasta alignment failed.\ninputFasta=%s\n' +
'alignedFasta=%s\nSleep and retry alignment.', inputFasta,
alignedFasta)
time.sleep(0.1)
alignedFasta = alignFastaKalign(inputFasta)
try:
# parse the aligned fasta into sequence ids and sequences
namelinesAndSeqs = list(
fasta.readFasta(cStringIO.StringIO(alignedFasta)))
idAndSeqs = [(fasta.idFromName(seqNameline), seq)
for seqNameline, seq in namelinesAndSeqs]
alignedIdAndSeq, alignedHitIdAndSeq = idAndSeqs
except Exception as e:
e.args += (inputFasta, alignedFasta)
raise
# CHECK FOR EXCESSIVE DIVERGENCE AND TRIMMING
# find most diverged sequence
# sort sequences by dash count. why?
divIdSeqs = []
for id, seq in (alignedIdAndSeq, alignedHitIdAndSeq):
dashCount = seq.count('-')
div = dashCount / float(len(seq))
g = (dashCount, div, id, seq)
divIdSeqs.append(g)
divIdSeqs.sort()
# check for excessive divergence
leastDivergedDashCount, leastDivergedDiv, leastDivergedId, leastDivergedSeq = divIdSeqs[
0]
# check for excessive divergence and generate dashtrim.
mostDivergedDashCount, mostDivergedDiv, mostDivergedId, mostDivergedSeq = divIdSeqs[
1]
# dashtrim = dashlen_check(mostDivergedSeq, divergence)
startTrim, endTrim, trimDivergence = dashlen_check(mostDivergedSeq)
# logging.debug('dashtrim='+str(dashtrim))
# trim and add seqs to output
def divergencePredicate(divergenceThreshold):
'''Why this logic? Ask Dennis. Function closed over local variables that returns whether or not the alignment of the sequences is too diverged.'''
if leastDivergedSeq and leastDivergedDiv > divergenceThreshold:
return True
if (startTrim or endTrim) and trimDivergence >= divergenceThreshold:
return True
return False
alignedTrimmedIdAndSeq, alignedTrimmedHitIdAndSeq = [
(id, seq[startTrim:(len(seq) - endTrim)])
for id, seq in (alignedIdAndSeq, alignedHitIdAndSeq)
]
return alignedTrimmedIdAndSeq, alignedTrimmedHitIdAndSeq, divergencePredicate
