def worx(platform):
bogus = os.listdir(r'.\Gene Expressions\CurrentCel')
names = []
for bug in bogus:
if bug[-7:] == '.CEL.gz':
names.append(bug)
platPath = ''
try:
pforms = os.listdir(r'.\Gene Expressions\GPL')
i = 0
while i < len(pforms):
if pforms[i][:-4] == platform:
platPath = r'.\Gene Expressions\GPL/' + pforms[i]
i = len(pforms)
i += 1
except:
errno
cdfP = cdfParser.cdfParse()
print 'Reading .CDF file:', platform, r'...'
cdfP.parse(platPath)
print 'Done'
PMLoc = cdfP.getPMLocs()
Catche.spickle(r'.\Gene Expressions\CurrentCel/PMLoc.pickle', PMLoc)
Catche.spickle(r'.\Gene Expressions\CurrentCel/ProbeSets.pickle',
cdfP.getProbeSets())
def adjust(iters):
Xes = os.listdir(r'.\Gene Expressions\CurrentCel')
names = []
for x in Xes:
if x[-7:] == r'.CEL.gz':
names.append(x[:-7])
geoMat = Catche.opickle(r'.\Gene Expressions\CurrentCel\PMIntense' +
names[iters] + r'.pickle')
sigma = 0
alpha = 0
a = []
y = []
vector = []
for row in geoMat:
vector.append(row)
#print vector[1]
#print i
m1 = mode(vector)
m2 = mode(leftOf(vector, m1))
#estimate sigma?
#find elements in dataO less than mu. group in leftz
leftZ = leftOf(vector, m2)
n = len(leftZ)
zSum = 0
for lZ in leftZ:
zSum += (lZ - m2)**2
if n > 1:
sigma = math.sqrt(zSum / (n - 1)) * math.sqrt(2.0)
else:
sigma = math.sqrt(zSum) * math.sqrt(2.0)
#estimate alpha
#find elements in dataO greater than mu. store in rightz. rightz - mu for all
#find mode of rightz
alpha = 1 / mode(rightOf(vector, m2))
for j, val in enumerate(vector):
a.append(val - m2 - alpha * (sigma**2))
print 'pass 1'
for val in a:
if sigma == 0:
y.append(1)
elif normcdf(val / sigma) == 0:
y.append(2)
else:
y.append(val + sigma * normpdf(val / sigma) / normcdf(val / sigma))
print 'pass 2'
for i, col in enumerate(y):
geoMat[i] = col
print 'pass 3'
Catche.spickle(
r'.\Gene Expressions\CurrentCel/BAIntense' + names[iters] + r'.pickle',
geoMat)
def adjust(iters):
Xes = os.listdir(r'.\Gene Expressions\CurrentCel')
names = []
for x in Xes:
if x[-7:] == r'.CEL.gz':
names.append(x[:-7])
geoMat = Catche.opickle(r'.\Gene Expressions\CurrentCel\PMIntense'+names[iters]+r'.pickle')
sigma = 0
alpha = 0
a = []
y = []
vector = []
for row in geoMat:
vector.append(row)
#print vector[1]
#print i
m1 = mode(vector)
m2 = mode(leftOf(vector,m1))
#estimate sigma?
#find elements in dataO less than mu. group in leftz
leftZ = leftOf(vector,m2)
n = len(leftZ)
zSum = 0
for lZ in leftZ:
zSum += (lZ - m2) ** 2
if n > 1:
sigma = math.sqrt( zSum / (n - 1)) * math.sqrt(2.0)
else:
sigma = math.sqrt(zSum) * math.sqrt(2.0)
#estimate alpha
#find elements in dataO greater than mu. store in rightz. rightz - mu for all
#find mode of rightz
alpha = 1 / mode(rightOf(vector,m2))
for j,val in enumerate(vector):
a.append(val - m2 - alpha * (sigma ** 2))
print 'pass 1'
for val in a:
if sigma == 0:
y.append(1)
elif normcdf(val / sigma) == 0:
y.append(2)
else:
y.append(val + sigma * normpdf(val / sigma) / normcdf(val / sigma))
print 'pass 2'
for i,col in enumerate(y):
geoMat[i] = col
print 'pass 3'
Catche.spickle(r'.\Gene Expressions\CurrentCel/BAIntense'+names[iters]+r'.pickle',geoMat)
def GetExec():
Recs = os.listdir(os.getcwd())
newList = []
j = 0
listdata = dict()
ftime = open('lastChecked.txt', 'r')
prevTime = float(ftime.readline())
ftime.close()
f = open('lastChecked.txt', 'w')
f.write(str(time.time()))
f.close()
k = 0
while k < len(Recs):
(name, ext) = os.path.splitext(Recs[k])
if len(ext) > 2 and not ext == '.pickle':
ListFile = name + ".pickle"
if not os.path.isfile(ListFile) or float(fmt.filemtime(
Recs[k])) > prevTime:
if ext[:3] == ".fa":
if name != "my_seq":
seqIORec = list(SeqIO.parse(Recs[k], 'fasta'))
for i, v in enumerate(seqIORec):
newList.append([v, v.id])
listdata[j] = str(v.id), len(
v.seq), str(name) + str(ext)
rHoward = [
str(v.id),
len(v.seq),
str(name) + str(ext), v
]
mP.spickle(ListFile, rHoward)
j += 1
elif ext[:3] == ".gb":
seqIORec = list(SeqIO.parse(Recs[k], 'genbank'))
for i, v in enumerate(seqIORec):
newList.append([v, v.id])
listdata[j] = str(v.id), len(
v.seq), str(name) + str(ext)
rHoward = [
str(v.id),
len(v.seq),
str(name) + str(ext), v
]
mP.spickle(ListFile, rHoward)
j += 1
else:
if ext[:3] in [".gb", ".fa"]:
rHoward = mP.opickle(ListFile)
listdata[j] = str(rHoward[0]), rHoward[1], rHoward[2]
newList.append([rHoward[3], rHoward[0]])
j += 1
k += 1
return [newList, listdata]
def GetExec():
Recs = os.listdir(os.getcwd())
newList=[]
j = 0
listdata=dict()
ftime = open('lastChecked.txt','r')
prevTime = float(ftime.readline())
ftime.close()
f = open('lastChecked.txt','w')
f.write(str(time.time()))
f.close()
k = 0
while k < len(Recs):
(name, ext) = os.path.splitext(Recs[k])
if len(ext) > 2 and not ext == '.pickle':
ListFile = name + ".pickle"
if not os.path.isfile(ListFile) or float(fmt.filemtime(Recs[k])) > prevTime:
if ext[:3] == ".fa":
if name != "my_seq":
seqIORec = list(SeqIO.parse(Recs[k],'fasta'))
for i,v in enumerate(seqIORec):
newList.append([v,v.id])
listdata[j] = str(v.id),len(v.seq),str(name)+str(ext)
rHoward = [str(v.id),len(v.seq),str(name)+str(ext),v]
mP.spickle(ListFile,rHoward)
j+=1
elif ext[:3] == ".gb":
seqIORec = list(SeqIO.parse(Recs[k],'genbank'))
for i,v in enumerate(seqIORec):
newList.append([v,v.id])
listdata[j] = str(v.id),len(v.seq),str(name)+str(ext)
rHoward = [str(v.id),len(v.seq),str(name)+str(ext),v]
mP.spickle(ListFile,rHoward)
j+=1
else:
if ext[:3] in [".gb",".fa"]:
rHoward = mP.opickle(ListFile)
listdata[j] = str(rHoward[0]),rHoward[1],rHoward[2]
newList.append([rHoward[3],rHoward[0]])
j+=1
k += 1
return [newList,listdata]
def funccall(x):
bogus = os.listdir(r'.\Gene Expressions\CurrentCel')
names = []
for bug in bogus:
if bug[-7:] == '.CEL.gz':
names.append(bug)
h = gzip.GzipFile(r'.\Gene Expressions\CurrentCel/' + names[x])
b = CelFileReader.read(h)
g = b.intensities
PMIntense = []
PMLoc = Catche.opickle(r'.\Gene Expressions\CurrentCel/PMLoc.pickle')
for loc in PMLoc:
PMIntense.append(g[loc[1]][loc[0]])
Catche.spickle(
r'.\Gene Expressions\CurrentCel/PMIntense' + names[x][:-7] +
r'.pickle', PMIntense)
return x
def countSort(xe):
names = []
Xes = os.listdir(r'.\Gene Expressions\CurrentCel')
out = [[0]]
for x in Xes:
if x[-7:] == r'.CEL.gz':
names.append(x[:-7])
arrayX = Catche.opickle(r'.\Gene Expressions\CurrentCel/BAIntense'+names[xe]+r'.pickle')
counter = []
final = []
ranker = []
finRank = []
i = 0
while i < len(arrayX):
counter.append(0)
final.append(0)
ranker.append([])
finRank.append(0)
i += 1
for j,val in enumerate(arrayX):
counter[int(val)] += 1
ranker[int(val)].append(j)
preSum = []
preSum.append(0)
i = 0
while i < len(arrayX) - 1:
preSum.append(preSum[i] + counter[i])
i += 1
i = len(counter) - 1
while i >= 0:
while counter[i] > 0:
final[preSum[i]] = i
finRank[preSum[i]] = ranker[i][-1]
preSum[i] += 1
del ranker[i][-1]
counter[i] -= 1
i -= 1
Catche.spickle(r'.\GeneExpressions\CurrentCel/SortAndRank'+names[xe]+r'.pickle',[final,finRank])
def GetExec():
Recs = os.listdir(os.getcwd())
newList = []
j = 0
listdata=dict()
k = 0
p = PDBParser(PERMISSIVE=1)
ftime = open('lastChecked.txt','r')
pT = float(ftime.readline())
ftime.close()
f = open('lastChecked.txt','w')
f.write(str(time.time()))
f.close()
while k < len(Recs):
try:
(name, ext) = os.path.splitext(Recs[k])
if ext=='':
2+2
elif ext==".pdb":
f = name + ".pickle"
newList.append([Recs[k],os.getcwd()])
if not os.path.isfile(f) or float(fmt.filemtime(Recs[k])) > pT:
with warnings.catch_warnings():
warnings.simplefilter("ignore")
pdbRec = p.get_structure(name, Recs[k])
models = pdbRec.get_list()
listdata[j] = str(name), len(models), os.getcwd()+'/'+str(name) + str(ext)
rHoward = [str(name), len(models), str(name) + str(ext)]
mP.spickle(f, rHoward)
else:
rHoward = mP.opickle(f)
listdata[j] = str(rHoward[0]), rHoward[1], rHoward[2]
j += 1
except IOError, e:
print e
k += 1
def GetExec():
Recs = os.listdir(os.getcwd())
newList = []
j = 0
listdata = dict()
k = 0
p = PDBParser(PERMISSIVE=1)
ftime = open('lastChecked.txt', 'r')
pT = float(ftime.readline())
ftime.close()
f = open('lastChecked.txt', 'w')
f.write(str(time.time()))
f.close()
while k < len(Recs):
try:
(name, ext) = os.path.splitext(Recs[k])
if ext == '':
2 + 2
elif ext == ".pdb":
f = name + ".pickle"
newList.append([Recs[k], os.getcwd()])
if not os.path.isfile(f) or float(fmt.filemtime(Recs[k])) > pT:
with warnings.catch_warnings():
warnings.simplefilter("ignore")
pdbRec = p.get_structure(name, Recs[k])
models = pdbRec.get_list()
listdata[j] = str(name), len(
models), os.getcwd() + '/' + str(name) + str(ext)
rHoward = [str(name), len(models), str(name) + str(ext)]
mP.spickle(f, rHoward)
else:
rHoward = mP.opickle(f)
listdata[j] = str(rHoward[0]), rHoward[1], rHoward[2]
j += 1
except IOError, e:
print e
k += 1
def GetExec():
try:
for names in os.listdir(r'.\CurrentCel/'):
os.remove(r'.\CurrentCel/'+names)
os.removedirs(r'.\CurrentCel')
except:
errno
Recs = os.listdir(os.getcwd())
newList=[]
j = 0
PForm = ""
listdata=dict()
GeoUntar = []
k = 0
ftime = open('lastChecked.txt','r')
prevTime = float(ftime.readline())
ftime.close()
f = open('lastChecked.txt','w')
f.write(str(time.time()))
f.close()
for i in Recs:
(nameLeft, ext) = os.path.splitext(i)
if ext == '.tgz':
newList.append([i])
geoListFile = nameLeft + ".pickle"
if not os.path.isfile(geoListFile) or float(fmt.filemtime(i)) > prevTime:
filelib = tarfile.TarFile.gzopen(i)
#Istar = i
GeoUntar.append(filelib)
#print Istar
nameHolder = filelib.getnames()
''''for k,itsgo in enumerate(nameHolder):
try:
if itsgo[-4:] =='.txt' :
if itsgo[0:3] != r"GPL":
newList.append(itsgo)
elif itsgo[0:3] == r"GPL":
PForm = itsgo[:-10]
elif itsgo[-4:] == ".xml":
f = filelib.extractfile(itsgo)
minimal = minidom.parse(f).childNodes[0]
titleText = minimal.childNodes[-2].childNodes[3].childNodes[0].toxml()
except IOError, e:
print e'''
#print nameHolder[:5]
PForm = nameHolder[1][:-10]
#i = nameHolder[0]
#print i
f = filelib.extractfile(nameHolder[0])
minimal = minidom.parse(f).childNodes[0]
titleText = minimal.childNodes[-2].childNodes[3].childNodes[0].toxml()
#print len(minimal.childNodes)
listdata[j] = str(nameLeft[:-4]),titleText, PForm, len(nameHolder)-2
rHoward = [nameLeft,titleText,PForm,len(nameHolder)-2]
mP.spickle(geoListFile,rHoward)
j += 1
else:
rHoward = mP.opickle(geoListFile)
listdata[j] = str(rHoward[0][:-4]),rHoward[1],rHoward[2],rHoward[3]
j += 1
elif ext == r'.tar':
filelib = tarfile.TarFile.taropen(i)
nameHolder = filelib.getnames()
cels = 0
for n in nameHolder:
if n[-7:] == r'.CEL.gz':
cels += 1
"""
sys.path.append(r'..\plugins\Tools\ETOOLSPlugins')
exTool = __import__('ESearch').GetExec('gds',str(nameLeft[:-4]))
esTool = __import__('ESummary').GetExec('gds',str(exTool['IdList'][0]))
titleText = ''
PForm = ''
for line in esTool.split('\n'):
if len(line) > 32:
if line[:34] == '\t<Item Name="title" Type="String">':
titleText = line[34:-8]
elif line[:32] == '\t<Item Name="GPL" Type="String">':
PForm = 'GPL' + str(line[32:-7])
listdata[j] = str(nameLeft[:-4]),titleText, PForm, cels
newList.append([i,PForm])"""
return [newList,listdata]
import Catche as mP
na = [
'A', 'C', 'G', 'T', 'R', 'Y', 'S', 'W', 'K', 'M', 'B', 'D', 'H', 'V', 'N',
'.'
]
a = dict()
alpha = 1
for i in na:
for j in na:
a[i + j] = alpha
alpha += 1
seqIORec = SeqIO.read(
r'C:\Users\francis\Documents\Monguis\BioGui\Nucleic Acids\NC_003074.gbk',
'genbank')
trace = 0
outcome = []
while trace < len(seqIORec.seq) - 1:
temp = str(seqIORec.seq[trace:trace + 2])
outcome.append(a[temp])
trace += 2
if len(seqIORec.seq) % 2 == 1:
temp = str(seqIORec.seq[trace] + '.')
outcome.append(a[temp])
trace += 2
mP.spickle('plainseq.pickle', seqIORec.seq)
mP.spickle('modseq.pickle', outcome)
diff -= 1
pool.map(cS.countSort,baggage)
i = 0
while i < lenX:
sorts = Catche.opickle(r'.\GeneExpressions\CurrentCel/SortAndRank' + names[i] + r'.pickle')
sortedVals.append(sorts[0])
rankerVals.append(sorts[1])
print 'ranked and sorted'
i += 1
sortedVals = nP.array(sortedVals)
meanVals = nP.mean(sortedVals, axis=0)
for i,n in enumerate(names):
out.append([])
for mV in meanVals:
out[i+1].append(0)
for j,mV in enumerate(meanVals):
out[i+1][rankerVals[i][j]] = mV
print 'done qn'
i = 0
while i < lenX:
Catche.spickle(r'.\GeneExpressions\CurrentCel/RMAPreSum' + names[i] + r'.pickle',out[i + 1])
i += 1
#print out[0][:5]
#print out[1][:5]
#print out[2][:5]
#print out[-1][:5]
#print out[0][:20]
#return out
i = 0
while i < lenX:
sorts = Catche.opickle(r'.\GeneExpressions\CurrentCel/SortAndRank' +
names[i] + r'.pickle')
sortedVals.append(sorts[0])
rankerVals.append(sorts[1])
print 'ranked and sorted'
i += 1
sortedVals = nP.array(sortedVals)
meanVals = nP.mean(sortedVals, axis=0)
for i, n in enumerate(names):
out.append([])
for mV in meanVals:
out[i + 1].append(0)
for j, mV in enumerate(meanVals):
out[i + 1][rankerVals[i][j]] = mV
print 'done qn'
i = 0
while i < lenX:
Catche.spickle(
r'.\GeneExpressions\CurrentCel/RMAPreSum' + names[i] + r'.pickle',
out[i + 1])
i += 1
#print out[0][:5]
#print out[1][:5]
#print out[2][:5]
#print out[-1][:5]
#print out[0][:20]
#return out
rollingSum = 0
valMat = []
for n in names:
valMat.append(
Catche.opickle(r'.\Gene Expressions\CurrentCel\RMAPreSum' + n +
r'.pickle'))
print 'begin sum'
while i < len(ProbeSet):
print i
rHoMat = []
for n, na in enumerate(names):
k = rollingSum
rHoMat.append([])
while k < ProbeSet[i][1]:
rHoMat[-1].append(valMat[n][k])
k += 1
temp = getMedPol(rHoMat)
for n, na in enumerate(names):
if na == geoMat[n][0]:
geoMat[n].append(temp[n])
else:
print '??????????????????????????????'
rollingSum = ProbeSet[i][1]
i += 1
print 'done rmaSum'
geoMat.append([])
for pname in ProbeSet:
geoMat[-1].append(pname[0])
Catche.spickle(r'.\Gene Expressions\CurrentCel/RMAFinal.pickle', geoMat)
rollingSum = 0
valMat = []
for n in names:
valMat.append(Catche.opickle(r'.\Gene Expressions\CurrentCel\RMAPreSum' + n + r'.pickle'))
print 'begin sum'
while i < len(ProbeSet):
print i
rHoMat = []
for n,na in enumerate(names):
k = rollingSum
rHoMat.append([])
while k < ProbeSet[i][1]:
rHoMat[-1].append(valMat[n][k])
k += 1
temp = getMedPol(rHoMat)
for n,na in enumerate(names):
if na == geoMat[n][0]:
geoMat[n].append(temp[n])
else:
print '??????????????????????????????'
rollingSum = ProbeSet[i][1]
i += 1
print 'done rmaSum'
geoMat.append([])
for pname in ProbeSet:
geoMat[-1].append(pname[0])
Catche.spickle(r'.\Gene Expressions\CurrentCel/RMAFinal.pickle',geoMat)
from Bio import SeqIO
import Catche as mP
na = ["A", "C", "G", "T", "R", "Y", "S", "W", "K", "M", "B", "D", "H", "V", "N", "."]
a = dict()
alpha = 1
for i in na:
for j in na:
a[i + j] = alpha
alpha += 1
seqIORec = SeqIO.read(r"C:\Users\francis\Documents\Monguis\BioGui\Nucleic Acids\NC_003074.gbk", "genbank")
trace = 0
outcome = []
while trace < len(seqIORec.seq) - 1:
temp = str(seqIORec.seq[trace : trace + 2])
outcome.append(a[temp])
trace += 2
if len(seqIORec.seq) % 2 == 1:
temp = str(seqIORec.seq[trace] + ".")
outcome.append(a[temp])
trace += 2
mP.spickle("plainseq.pickle", seqIORec.seq)
mP.spickle("modseq.pickle", outcome)
