def readBicluster(self):
# Read in the bicluster score
summaryFile = open('cluster.summary.csv','r')
summaryFile.readline() # Skip the header
scoreDict = {}
for sumLine in summaryFile.readlines():
splitUp = sumLine.strip().split(',')
scoreDict[int(splitUp[0].strip('"'))] = splitUp[2]
self.score = scoreDict[int(self.k)]
# Read in genes
geneFile = open('biclust/'+str(self.k)+'/genes.csv','r')
geneFile.readline() # Skip header
self.genes = [line.strip().split(',')[1].strip('"') for line in geneFile.readlines()]
geneFile.close()
# Read in conditions
condFile = open('biclust/'+str(self.k)+'/conditions.csv','r')
condFile.readline() # Skip header
self.conditions = [line.strip().split(',')[1].strip('"') for line in condFile.readlines()]
condFile.close()
# Read in residuals
residFile = open('biclust/'+str(self.k)+'/resid.csv','r')
residFile.readline() # Skip header
self.resid = residFile.readline().strip().split(',')[1]
self.residNorm = residFile.readline().strip().split(',')[1]
residFile.close()
# Read in associations with clinical traits
self.cor = {}
corFile = open('biclust/'+str(self.k)+'/correlation.csv','r')
corFile.readline() # Skip header
for line in corFile.readlines():
splitUp = line.strip().split(',')
self.cor[splitUp[0].strip('"')] = {'cor':splitUp[1],'pValue':splitUp[2]}
corFile.close()
self.surv = {}
survFile = open('biclust/'+str(self.k)+'/survival.csv','r')
survFile.readline() # Skip header
for line in survFile.readlines():
splitUp = line.strip().split(',')
self.surv[splitUp[0]] = {'zScore':splitUp[1],'pValue':splitUp[2]}
survFile.close()
# Now load up the PSSMs
pssmUpFiles = os.listdir('biclust/'+str(self.k)+'/upstream')
self.pssmsUpstream = []
for pssmUpFile in pssmUpFiles:
self.pssmsUpstream.append(pssm('biclust/'+str(self.k)+'/upstream/'+pssmUpFile,self.k))
# Now read in the pssms
pssmUTRFiles = os.listdir('biclust/'+str(self.k)+'/3pUTR')
self.pssms3pUTR = []
for pssmUTRFile in pssmUTRFiles:
self.pssms3pUTR.append(pssm('biclust/'+str(self.k)+'/3pUTR/'+pssmUTRFile,self.k))
def meme(num, seqFile=None, bgFile=None, nMotifs=1, minMotifWidth=6, maxMotifWidth=12, revComp=True, seed=None):
if not os.path.exists('tmp/meme'):
os.makedirs('tmp/meme')
# Arguments for tomtom
memeArgs = str(seqFile)+' -bfile tmp/meme/bgFile.meme -nostatus -text -time 600 -dna -maxsize 9999999 -evt 1e9 -mod zoops -minw ' + str(minMotifWidth) + ' -maxw ' + str(maxMotifWidth) + ' -nmotifs ' + str(nMotifs)
if revComp==True:
memeArgs += ' -revcomp'
if not seed==None:
memeArgs += ' -cons ' + str(seed)
print memeArgs
#errOut = open('tmp/meme/stderr.out','w')
memeProc = Popen("meme " + memeArgs, shell=True,stdout=PIPE) #,stderr=errOut)
output = memeProc.communicate()[0].split('\n')
#errOut.close()
PSSMs = []
# Now iterate through output and save data
for i in range(len(output)):
splitUp1 = output[i].strip().split(' ')
if splitUp1[0]=='Motif' and splitUp1[2]=='position-specific' and splitUp1[3]=='probability':
i += 2 # Skip the separator line, go to the summary line
splitUp = output[i].strip().split(' ')
width = int(splitUp[5])
sites = splitUp[7]
eValue = splitUp[9]
matrix = []
for j in range(width):
i += 1
matrix += [[float(let) for let in output[i].strip().split(' ') if let]]
PSSMs.append(pssm(biclusterName=str(splitUp1[1]),nsites=sites,eValue=eValue,pssm=matrix,genes=[]))
clusterMemeRuns[num] = PSSMs
def merge2PSSMs(name, pssm1, pssm2, weight1, weight2, offset, overlap, orientation):
pssm1Mat = deepcopy(pssm1.getMatrix())
# Flip PSSM matrix values for nucleotides if orientation=='-'
pssm2Mat = deepcopy(pssm2.getMatrix())
if orientation=='-':
pssm2Mat = flip(pssm2Mat)
# Merge PSSM matrices
newPSSMMat = []
newWeight = []
if offset>0:
for i in range(offset):
row1 = pssm1Mat.pop(0)
w1 = weight1.pop(0)
newPSSMMat += [[row1[0]*100*w1, row1[1]*100*w1, row1[2]*100*w1, row1[3]*100*w1]]
newWeight += [w1]
elif offset<0:
for i in range(-offset):
row2 = pssm2Mat.pop(0)
w2 = weight2.pop(0)
newPSSMMat += [[row2[0]*100*w2, row2[1]*100*w2, row2[2]*100*w2, row2[3]*100*w2]]
newWeight += [w2]
maxLen = 0
if len(pssm1Mat)>=len(pssm2Mat):
maxLen = len(pssm1Mat)
else:
maxLen = len(pssm2Mat)
for i in range(maxLen):
if len(pssm1Mat)>0:
row1 = pssm1Mat.pop(0)
w1 = weight1.pop(0)
else:
row1 = [0, 0, 0, 0]
w1 = 0
if len(pssm2Mat)>0:
row2 = pssm2Mat.pop(0)
w2 = weight2.pop(0)
else:
row2 = [0, 0, 0, 0]
w2 = 0
newPSSMMat += [[row1[0]*100*w1+row2[0]*100*w2, row1[1]*100*w1+row2[1]*100*w2, row1[2]*100*w1+row2[2]*100*w2, row1[3]*100*w1+row2[3]*100*w2]]
newWeight += [w1+w2]
# Normalize matrix
for i in range(len(newPSSMMat)):
total = newPSSMMat[i][0]+newPSSMMat[i][1]+newPSSMMat[i][2]+newPSSMMat[i][3]
newPSSMMat[i][0] = newPSSMMat[i][0]/total
newPSSMMat[i][1] = newPSSMMat[i][1]/total
newPSSMMat[i][2] = newPSSMMat[i][2]/total
newPSSMMat[i][3] = newPSSMMat[i][3]/total
# Now build the new PSSM object
newPSSM = pssm(biclusterName=name, nsites='30', eValue='0', pssm=newPSSMMat, genes=[])
print name, newPSSM.getConsensusMotif(), pssm1.getName(), pssm1.getConsensusMotif(), pssm2.getName(), pssm2.getConsensusMotif(), offset, overlap, orientation
return [newPSSM, newWeight]
def weeder(config, seqFile=None, percTargets=50, revComp=False, bgModel='HS'):
weeder_dir = os.path.join(config.get('General', 'tmp_dir'), 'weeder')
if not os.path.exists(weeder_dir):
os.makedirs(weeder_dir)
# Note that we use a slightly hacked version of weeder. Weederlauncher has
# hard-coded paths to the other executables, and weederlauncher and
# weederTFBS have hard-coded paths to the FreqFiles directory. We hacked
# those to point to our directories.
# First run weederTFBS for 6bp motifs
weederArgs = ' '+str(seqFile)+' '+str(bgModel)+' small T50'
if revComp==True:
weederArgs += ' -S'
errOut = open(os.path.join(weeder_dir, 'stderr.out'), 'w')
weederProc = Popen("weederlauncher " + weederArgs, shell=True, stdout=PIPE, stderr=errOut)
output = weederProc.communicate()
# Now parse output from weeder
PSSMs = []
output = open(str(seqFile)+'.wee','r')
outLines = [line for line in output.readlines() if line.strip()]
hitBp = {}
# Get top hit of 6bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[6] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Searching for motifs of length 8') == -1:
break
# Get top hit of 8bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[8] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Your sequences:') == -1:
break
# Get into the highest ranking motifs
seqDict = {}
while 1:
outLine = outLines.pop(0)
if not outLine.find('**** MY ADVICE ****') == -1:
break
splitUp = outLine.strip().split(' ')
seqDict[splitUp[1]] = splitUp[3].lstrip('>')
# Get into the highest ranking motifs
while 1:
outLine = outLines.pop(0)
if not outLine.find('Interesting motifs (highest-ranking)') == -1:
break
while 1:
name = outLines.pop(0).strip() # Get match
if not name.find('(not highest-ranking)') == -1:
break
# Get redundant motifs
outLines.pop(0)
redMotifs = [i for i in outLines.pop(0).strip().split(' ') if not i=='-']
outLines.pop(0)
outLines.pop(0)
line = outLines.pop(0)
instances = []
matches = []
while line.find('Frequency Matrix') == -1:
splitUp = [i for i in line.strip().split(' ') if i]
instances.append({'gene':seqDict[splitUp[0]],
'strand':splitUp[1],
'site':splitUp[2],
'start':splitUp[3],
'match':splitUp[4].lstrip('(').rstrip(')'),
'mfe':rnaDuplex(config, name,[splitUp[2]])[0] })
line = outLines.pop(0)
# Read in Frequency Matrix
outLines.pop(0)
outLines.pop(0)
matrix = []
col = outLines.pop(0)
while col.find('======') == -1:
nums = [i for i in col.strip().split('\t')[1].split(' ') if i]
colSum = 0
for i in nums:
colSum += int(i.strip())
matrix += [[ float(nums[0])/float(colSum), float(nums[1])/float(colSum), float(nums[2])/float(colSum), float(nums[3])/float(colSum)]]
col = outLines.pop(0)
PSSMs += [pssm(biclusterName=name,nsites=instances,eValue=hitBp[len(matrix)][1],pssm=matrix,genes=redMotifs)]
return PSSMs
def readBicluster(self,
de_novo_method_upstream=None,
de_novo_method_3pUTR=None):
# Attach to the database
con = lite.connect(self.sqliteDb)
con.row_factory = lite.Row
cur = con.cursor()
# Get the number of biclusters in run
q1 = 'SELECT name FROM row_members, row_names WHERE row_members.cluster=' + str(
self.k) + ' and row_members.iteration=' + str(
self.maxIter
) + ' and row_members.order_num=row_names.order_num'
cur.execute(q1)
data = cur.fetchall()
self.genes = [str(i['name']) for i in data]
# Read in conditions
q1 = 'SELECT name FROM column_members, column_names WHERE column_members.cluster=' + str(
self.k) + ' and column_members.iteration=' + str(
self.maxIter
) + ' and column_members.order_num=column_names.order_num'
cur.execute(q1)
data = cur.fetchall()
self.conditions = [i['name'] for i in data]
# Read in residuals
q1 = 'SELECT residual FROM cluster_stats WHERE cluster=' + str(
self.k) + ' and iteration=' + str(self.maxIter)
cur.execute(q1)
data = cur.fetchall()
self.residNorm = float(data[0]['residual'])
# At some point might be nice to figure out how to include this
"""# Read in associations with clinical traits
self.cor = {}
corFile = open('biclust/'+str(self.k)+'/correlation.csv','r')
corFile.readline() # Skip header
for line in corFile.readlines():
splitUp = line.strip().split(',')
self.cor[splitUp[0].strip('"')] = {'cor':splitUp[1],'pValue':splitUp[2]}
corFile.close()
self.surv = {}
survFile = open('biclust/'+str(self.k)+'/survival.csv','r')
survFile.readline() # Skip header
for line in survFile.readlines():
splitUp = line.strip().split(',')
self.surv[splitUp[0]] = {'zScore':splitUp[1],'pValue':splitUp[2]}
survFile.close()
"""
# Now load up the PSSMs
q1 = 'SELECT rowid, seqtype, motif_num, evalue FROM motif_infos WHERE cluster=' + str(
self.k) + ' and iteration=2001'
cur.execute(q1)
motifs = cur.fetchall()
# Set the de novo method
if not de_novo_method_upstream == None:
de_novo_method = de_novo_method_upstream
else:
de_novo_method = de_novo_method_3pUTR
self.pssmsUpstream = []
self.pssms3pUTR = []
for motif in motifs:
name = str(self.k) + '_motif' + str(
motif['motif_num']) + '_' + de_novo_method
q1 = 'SELECT row_names.name, motif_annotations.position, motif_annotations.reverse, motif_annotations.pvalue FROM motif_annotations, row_names WHERE motif_annotations.motif_info_id=' + str(
motif['rowid']
) + ' and motif_annotations.gene_num=row_names.order_num'
cur.execute(q1)
sites = [[
str(i['name']), i['position'], i['reverse'], i['pvalue']
] for i in cur.fetchall()]
nsites = sites
eValue = motif['evalue']
q1 = 'SELECT a, c, g, t FROM motif_pssm_rows WHERE motif_info_id=' + str(
motif['rowid']) #+' and iteration='+str(self.maxIter)
cur.execute(q1)
matrix = [[i['a'], i['c'], i['g'], i['t']] for i in cur.fetchall()]
genes = list(set([i[0] for i in sites]))
if motif['seqtype'] == 'upstream':
self.pssmsUpstream.append(
pssm(pssmFileName=None,
biclusterName=name,
nsites=nsites,
eValue=eValue,
pssm=matrix,
genes=genes,
de_novo_method=de_novo_method))
else:
self.pssms3pUTR.append(
pssm(pssmFileName=None,
biclusterName=name,
nsites=nsites,
eValue=eValue,
pssm=matrix,
genes=genes,
de_novo_method=de_novo_method))
con.close()
else:
genes[gene] = [gene+'.1']
gene = gene+'.1'
# Get rid of the header crap
for i in range(len(inLines)-4):
crap = inLines.pop(0)
tmpPssm = []
for line in inLines:
splitUp = [i for i in line.strip().split('\t') if i]
catchMe = splitUp.pop(0)
for j in range(len(splitUp)):
if catchMe=='A:':
tmpPssm.append([float(splitUp[j])])
else:
tmpPssm[j].append(float(splitUp[j]))
uniprobePSSMs[gene] = pssm(biclusterName=gene, pssm=deepcopy(tmpPssm), nsites=str(100), eValue=str(0.01))
print 'PSSMs recovered:', len(uniprobePSSMs)
print 'Genes recovered:',len(genes)
red1 = 0
for gene in genes:
if len(genes[gene])>1:
red1 += 1
print 'Redundant genes:',red1
# Test to show that the information content produces the expected values
# The code for this funciton was obtained from the Biopyhton Bio.motif.ic funciton
#tmpPssm = [[0.05, 0.05, 0.85, 0.05],
# [0.85, 0.05, 0.05, 0.05],
# [0.05, 0.05, 0.85, 0.05],
# [0.65, 0.05, 0.25, 0.05],
# [0.85, 0.05, 0.05, 0.05]]
def weeder(seqFile=None, revComp=False):
if not os.path.exists('tmp/weeder'):
os.makedirs('tmp/weeder')
# First run weederTFBS
weederArgs = str(seqFile) + ' HS3P small T50'
if revComp == True:
weederArgs += ' S'
#weederArgs += '&> /dev/null'
errOut = open('tmp/weeder/stderr.out', 'w')
weederProc = Popen("progs/weederlauncher " + weederArgs,
shell=True,
stdout=PIPE,
stderr=errOut)
errOut.close()
output = weederProc.communicate()
# Now parse output from weeder
PSSMs = []
output = open(str(seqFile) + '.wee', 'r')
outLines = [line for line in output.readlines() if line.strip()]
hitBp = {}
# Get top hit of 6bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[6] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Searching for motifs of length 8') == -1:
break
# Get top hit of 8bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[8] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Your sequences:') == -1:
break
# Get into the highest ranking motifs
seqDict = {}
while 1:
outLine = outLines.pop(0)
if not outLine.find('**** MY ADVICE ****') == -1:
break
splitUp = outLine.strip().split(' ')
seqDict[splitUp[1]] = splitUp[3].lstrip('>')
# Get into the highest ranking motifs
while 1:
outLine = outLines.pop(0)
if not outLine.find('Interesting motifs (highest-ranking)') == -1:
break
while 1:
name = outLines.pop(0).strip() # Get match
if not name.find('(not highest-ranking)') == -1:
break
# Get redundant motifs
outLines.pop(0)
redMotifs = [
i for i in outLines.pop(0).strip().split(' ') if not i == '-'
]
outLines.pop(0)
outLines.pop(0)
line = outLines.pop(0)
instances = []
while line.find('Frequency Matrix') == -1:
splitUp = [i for i in line.strip().split(' ') if i]
instances.append({
'gene': seqDict[splitUp[0]],
'strand': splitUp[1],
'site': splitUp[2],
'start': splitUp[3],
'match': splitUp[4].lstrip('(').rstrip(')')
})
line = outLines.pop(0)
# Read in Frequency Matrix
outLines.pop(0)
outLines.pop(0)
matrix = []
col = outLines.pop(0)
while col.find('======') == -1:
nums = [i for i in col.strip().split('\t')[1].split(' ') if i]
colSum = 0
for i in nums:
colSum += int(i.strip())
matrix += [[
float(nums[0]) / float(colSum),
float(nums[1]) / float(colSum),
float(nums[2]) / float(colSum),
float(nums[3]) / float(colSum)
]]
col = outLines.pop(0)
PSSMs += [
pssm(biclusterName=name,
nsites=instances,
eValue=hitBp[len(matrix)][1],
pssm=matrix,
genes=redMotifs)
]
return PSSMs
def weeder(i=None, percTargets=50, revComp=False):
seqFile = fastaFiles[i]
print seqFile
if not os.path.exists('tmp/weeder'):
os.makedirs('tmp/weeder')
# First run weederTFBS for 6bp motifs
weederArgs = ' '+str(seqFile)+' HS3P small T50'
if revComp==True:
weederArgs += ' -S'
errOut = open('tmp/weeder/stderr.out','w')
weederProc = Popen("weederlauncher " + weederArgs, shell=True,stdout=PIPE,stderr=errOut)
output = weederProc.communicate()
# Now parse output from weeder
PSSMs = []
output = open(str(seqFile)+'.wee','r')
outLines = [line for line in output.readlines() if line.strip()]
hitBp = {}
# Get top hit of 6bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[6] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Searching for motifs of length 8') == -1:
break
# Get top hit of 8bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[8] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Your sequences:') == -1:
break
# Get into the highest ranking motifs
seqDict = {}
while 1:
outLine = outLines.pop(0)
if not outLine.find('**** MY ADVICE ****') == -1:
break
splitUp = outLine.strip().split(' ')
seqDict[splitUp[1]] = splitUp[3].lstrip('>')
# Get into the highest ranking motifs
while 1:
outLine = outLines.pop(0)
if not outLine.find('Interesting motifs (highest-ranking)') == -1:
break
while 1:
name = seqFile.split('/')[-1].split('.')[0] +'_'+ outLines.pop(0).strip() # Get match
if not name.find('(not highest-ranking)') == -1:
break
# Get redundant motifs
outLines.pop(0)
redMotifs = [i for i in outLines.pop(0).strip().split(' ') if not i=='-']
outLines.pop(0)
outLines.pop(0)
line = outLines.pop(0)
instances = []
while line.find('Frequency Matrix') == -1:
splitUp = [i for i in line.strip().split(' ') if i]
instances.append({'gene':seqDict[splitUp[0]], 'strand':splitUp[1], 'site':splitUp[2], 'start':splitUp[3], 'match':splitUp[4].lstrip('(').rstrip(')') })
line = outLines.pop(0)
# Read in Frequency Matrix
outLines.pop(0)
outLines.pop(0)
matrix = []
col = outLines.pop(0)
while col.find('======') == -1:
nums = [i for i in col.strip().split('\t')[1].split(' ') if i]
colSum = 0
for i in nums:
colSum += int(i.strip())
matrix += [[ float(nums[0])/float(colSum), float(nums[1])/float(colSum), float(nums[2])/float(colSum), float(nums[3])/float(colSum)]]
col = outLines.pop(0)
weederPSSMs1.append(pssm(biclusterName=name,nsites=instances,eValue=hitBp[len(matrix)][1],pssm=matrix,genes=redMotifs))
for cur in ['A','C','G','T']:
line = inFile.readline()
splitUp = [i for i in line.strip().split(',') if i]
catchMe = splitUp.pop(0)
for j in range(len(splitUp)):
if cur=='A':
tmpPssm.append([splitUp[j]])
else:
tmpPssm[j].append(splitUp[j])
# Convert counts to frequencies
for i in range(len(tmpPssm)):
tmpSum = float(tmpPssm[i][0])+float(tmpPssm[i][1])+float(tmpPssm[i][2])+float(tmpPssm[i][3])
for j in [0,1,2,3]:
tmpPssm[i][j] = float(tmpPssm[i][j])/tmpSum
# Instantiate PSSM object
selexPSSMs[name] = pssm(biclusterName=name, pssm=deepcopy(tmpPssm), nsites=str(100), eValue=str(0.01))
inFile.close()
print 'PSSMs recovered:',len(selexPSSMs)
# Test to show that the information content produces the expected values
# The code for this funciton was obtained from the Biopyhton Bio.motif.ic funciton
#tmpPssm = [[0.05, 0.05, 0.85, 0.05],
# [0.85, 0.05, 0.05, 0.05],
# [0.05, 0.05, 0.85, 0.05],
# [0.65, 0.05, 0.25, 0.05],
# [0.85, 0.05, 0.05, 0.05]]
#testPssm = pssm(biclusterName='test', pssm=deepcopy(tmpPssm), nsites=str(100), eValue=str(0.01))
#print 'ic.norm = ',ic(testPssm,norm=True)
#print 'ic = ', ic(testPssm,norm=False) # Biopython Bio.moitf.ic gives 5.27 as the IC
# 3. Write out pickle of the PSSMs for the systematic SELEX experiemnts
def weeder(seqFile=None, percTargets=50, revComp=False, bgModel='HS'):
if not os.path.exists(conf.tmp_dir+'/weeder'):
os.makedirs(conf.tmp_dir+'/weeder')
# Note that we use a slightly hacked version of weeder. Weederlauncher has
# hard-coded paths to the other executables, and weederlauncher and
# weederTFBS have hard-coded paths to the FreqFiles directory. We hacked
# those to point to our directories.
# First run weederTFBS for 6bp motifs
weederArgs = ' '+str(seqFile)+' '+str(bgModel)+' small T50'
if revComp==True:
weederArgs += ' -S'
errOut = open(conf.tmp_dir+'/weeder/stderr.out','w')
weederProc = Popen("weederlauncher " + weederArgs, shell=True,stdout=PIPE,stderr=errOut)
output = weederProc.communicate()
"""# First run weederTFBS for 6bp motifs
weederArgs = '-f '+str(seqFile)+' -W 6 -e 1 -O HS -R '+str(percTargets)
if revComp==True:
weederArgs += ' -S'
errOut = open(conf.tmp_dir+'/weeder/stderr.out','w')
weederProc = Popen("weeder " + weederArgs, shell=True,stdout=PIPE,stderr=errOut)
output = weederProc.communicate()
# Second run weederTFBS for 8bp motifs
weederArgs = '-f '+str(seqFile)+' -W 8 -e 2 -O HS -R '+str(percTargets)
if revComp==True:
weederArgs += ' -S'
weederProc = Popen("weeder " + weederArgs, shell=True,stdout=PIPE,stderr=errOut)
output = weederProc.communicate()
# Finally run adviser
weederArgs = str(seqFile)
weederProc = Popen("adviser " + weederArgs, shell=True,stdout=PIPE,stderr=errOut)
output = weederProc.communicate()
errOut.close()
"""
# Now parse output from weeder
PSSMs = []
output = open(str(seqFile)+'.wee','r')
outLines = [line for line in output.readlines() if line.strip()]
hitBp = {}
# Get top hit of 6bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[6] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Searching for motifs of length 8') == -1:
break
# Get top hit of 8bp look for "1)"
while 1:
outLine = outLines.pop(0)
if not outLine.find('1) ') == -1:
break
hitBp[8] = outLine.strip().split(' ')[1:]
# Scroll to where the 8bp reads wll be
while 1:
outLine = outLines.pop(0)
if not outLine.find('Your sequences:') == -1:
break
# Get into the highest ranking motifs
seqDict = {}
while 1:
outLine = outLines.pop(0)
if not outLine.find('**** MY ADVICE ****') == -1:
break
splitUp = outLine.strip().split(' ')
seqDict[splitUp[1]] = splitUp[3].lstrip('>')
# Get into the highest ranking motifs
while 1:
outLine = outLines.pop(0)
if not outLine.find('Interesting motifs (highest-ranking)') == -1:
break
while 1:
name = outLines.pop(0).strip() # Get match
if not name.find('(not highest-ranking)') == -1:
break
# Get redundant motifs
outLines.pop(0)
redMotifs = [i for i in outLines.pop(0).strip().split(' ') if not i=='-']
outLines.pop(0)
outLines.pop(0)
line = outLines.pop(0)
instances = []
matches = []
while line.find('Frequency Matrix') == -1:
splitUp = [i for i in line.strip().split(' ') if i]
instances.append({'gene':seqDict[splitUp[0]], 'strand':splitUp[1], 'site':splitUp[2], 'start':splitUp[3], 'match':splitUp[4].lstrip('(').rstrip(')'), 'mfe':rnaDuplex(name,[splitUp[2]])[0] })
line = outLines.pop(0)
# Read in Frequency Matrix
outLines.pop(0)
outLines.pop(0)
matrix = []
col = outLines.pop(0)
while col.find('======') == -1:
nums = [i for i in col.strip().split('\t')[1].split(' ') if i]
colSum = 0
for i in nums:
colSum += int(i.strip())
matrix += [[ float(nums[0])/float(colSum), float(nums[1])/float(colSum), float(nums[2])/float(colSum), float(nums[3])/float(colSum)]]
col = outLines.pop(0)
PSSMs += [pssm(biclusterName=name,nsites=instances,eValue=hitBp[len(matrix)][1],pssm=matrix,genes=redMotifs)]
return PSSMs
from Bio import SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from pssm import pssm
from malign import malign
# multiple alignment on clusters
# for i in range(3):
# # malign("neg/PR_neg_%d.fasta" % (i))
# pssm
centroids = []
for i in range(3):
records = list(SeqIO.parse("neg/PR_neg_%d.clustal" % (i), "clustal"))
centroids.append(pssm([ record.seq for record in records ]))
SeqIO.write([SeqRecord(Seq(c), id=str(i)) for i, c in enumerate(centroids)], "neg/centroids.fasta", "fasta")
# comparison
malign("neg/centroids.fasta")
