def snv_pattern(self, iFileList, xLabel):
import numpy as np
N = len(iFileList)
dict1 = dict()
for i, item in enumerate(iFileList):
inFile = open(item)
for line in inFile:
line = line.strip()
fields = line.split('\t')
type = fields[4] + fields[5]
dict1.setdefault(type, [0] * N)
dict1[type][i] += 1
inFile.close()
dict1['T>G/A>C'] = list(np.array(dict1['TG']) + np.array(dict1['AC']))
dict1['T>C/A>G'] = list(np.array(dict1['TC']) + np.array(dict1['AG']))
dict1['T>A/A>T'] = list(np.array(dict1['TA']) + np.array(dict1['AT']))
dict1['C>A/G>T'] = list(np.array(dict1['CA']) + np.array(dict1['GT']))
dict1['C>G/G>C'] = list(np.array(dict1['CG']) + np.array(dict1['GC']))
dict1['C>T/G>A'] = list(np.array(dict1['CT']) + np.array(dict1['GA']))
dict1['SNV'] = list(
np.array(dict1['T>G/A>C']) + np.array(dict1['T>C/A>G']) +
np.array(dict1['T>A/A>T']) + np.array(dict1['C>A/G>T']) +
np.array(dict1['C>G/G>C']) + np.array(dict1['C>T/G>A']))
pp = PyPlot()
pp.single_bar_multi_bar_vertical_proportion(dict1['SNV'], [
dict1['T>G/A>C'], dict1['T>C/A>G'], dict1['T>A/A>T'],
dict1['C>A/G>T'], dict1['C>G/G>C'], dict1['C>T/G>A']
], xLabel)
def venn_diagram(self, iFile1, iFile2, iFile3=0, setname1="A", setname2="B", setname3="C", filename="test.pdf"):
pp = PyPlot(filename)
A = []
B = []
C = []
inFile1 = open(iFile1)
inFile2 = open(iFile2)
for line in inFile1:
line = line.strip()
# fields=line.split('\t')
A.append(line)
for line in inFile2:
line = line.strip()
# fields=line.split('\t')
B.append(line)
inFile1.close()
inFile2.close()
if iFile3 == 0:
pp.venn_diagram([set(A), set(B)], setname1, setname2)
else:
inFile3 = open(iFile3)
for line in inFile3:
line = line.strip()
# fields=line.split('\t')
C.append(line)
inFile3.close()
pp.venn_diagram([set(A), set(B), set(C)], setname1, setname2, setname3)
def box_plot(self, iFile, xLabel):
pp = PyPlot()
inFile = open(iFile)
head = inFile.readline()
for line in inFile:
line = line.strip()
fields = line.split("\t")
pp.filename = iFile + "." + fields[0] + ".pdf"
group1 = [int(x) for x in fields[-8:-4]]
group2 = [int(x) for x in fields[-4:]]
pp.box_plot([group1, group2], [xLabel[0] + ":" + fields[0], xLabel[1] + ":" + fields[0]])
inFile.close()
def __legacy_box_plot(self, iFileList, filename, xLabel=0, yLabel=0):
pp = PyPlot(filename)
aList = []
for item in iFileList:
L = list()
for it in item:
row = 0
inFile = open(it)
for line in inFile:
row += 1
inFile.close()
L.append(row)
aList.append(L)
pp.box_plot(aList, xLabel)
def __legacy_box_plot(self, iFileList, filename, xLabel=0, yLabel=0):
pp = PyPlot(filename)
aList = []
for item in iFileList:
L = list()
for it in item:
row = 0
inFile = open(it)
for line in inFile:
row += 1
inFile.close()
L.append(row)
aList.append(L)
pp.box_plot(aList, xLabel)
def gene_two_group_ranksum_test_matshow(self, iFile, geneNum, sampleNameList):
geneList = list()
list1 = list()
row = 0
inFile = open(iFile)
for line in inFile:
row += 1
if row <= geneNum:
line = line.strip()
fields = line.split()
geneList.append(fields[0])
list1.append([int(x) for x in fields[1:]])
inFile.close()
pp = PyPlot()
pp.heatmap_matshow(list1, sampleNameList, geneList)
def snv_region_based_annotation(self, iFile):
inFile = open(iFile)
dict1 = dict()
head = inFile.readline()
for line in inFile:
line = line.strip()
fields = line.split('\t')
dict1[fields[0]] = [int(x) for x in fields[1:]]
inFile.close()
pp = PyPlot()
pp.multi_bar([
dict1['Coding'][0:4], dict1['Intronic'][0:4],
dict1['NonCoding'][0:4], dict1['Intergenic'][0:4],
dict1['Genomic'][0:4]
])
def box_plot(self, iFile, xLabel):
pp = PyPlot()
inFile = open(iFile)
head = inFile.readline()
for line in inFile:
line = line.strip()
fields = line.split('\t')
pp.filename = iFile + '.' + fields[0] + '.pdf'
group1 = [int(x) for x in fields[-8:-4]]
group2 = [int(x) for x in fields[-4:]]
pp.box_plot(
[group1, group2],
[xLabel[0] + ':' + fields[0], xLabel[1] + ':' + fields[0]])
inFile.close()
def gene_two_group_ranksum_test_matshow(self, iFile, geneNum,
sampleNameList):
geneList = list()
list1 = list()
row = 0
inFile = open(iFile)
for line in inFile:
row += 1
if row <= geneNum:
line = line.strip()
fields = line.split()
geneList.append(fields[0])
list1.append([int(x) for x in fields[1:]])
inFile.close()
pp = PyPlot()
pp.heatmap_matshow(list1, sampleNameList, geneList)
def snv_pattern(self, iFileList, xLabel):
import numpy as np
N = len(iFileList)
dict1 = dict()
for i, item in enumerate(iFileList):
inFile = open(item)
for line in inFile:
line = line.strip()
fields = line.split("\t")
type = fields[4] + fields[5]
dict1.setdefault(type, [0] * N)
dict1[type][i] += 1
inFile.close()
dict1["T>G/A>C"] = list(np.array(dict1["TG"]) + np.array(dict1["AC"]))
dict1["T>C/A>G"] = list(np.array(dict1["TC"]) + np.array(dict1["AG"]))
dict1["T>A/A>T"] = list(np.array(dict1["TA"]) + np.array(dict1["AT"]))
dict1["C>A/G>T"] = list(np.array(dict1["CA"]) + np.array(dict1["GT"]))
dict1["C>G/G>C"] = list(np.array(dict1["CG"]) + np.array(dict1["GC"]))
dict1["C>T/G>A"] = list(np.array(dict1["CT"]) + np.array(dict1["GA"]))
dict1["SNV"] = list(
np.array(dict1["T>G/A>C"])
+ np.array(dict1["T>C/A>G"])
+ np.array(dict1["T>A/A>T"])
+ np.array(dict1["C>A/G>T"])
+ np.array(dict1["C>G/G>C"])
+ np.array(dict1["C>T/G>A"])
)
pp = PyPlot()
pp.single_bar_multi_bar_vertical_proportion(
dict1["SNV"],
[
dict1["T>G/A>C"],
dict1["T>C/A>G"],
dict1["T>A/A>T"],
dict1["C>A/G>T"],
dict1["C>G/G>C"],
dict1["C>T/G>A"],
],
xLabel,
)
def snv_region_based_annotation(self, iFile):
inFile = open(iFile)
dict1 = dict()
head = inFile.readline()
for line in inFile:
line = line.strip()
fields = line.split("\t")
dict1[fields[0]] = [int(x) for x in fields[1:]]
inFile.close()
pp = PyPlot()
pp.multi_bar(
[
dict1["Coding"][0:4],
dict1["Intronic"][0:4],
dict1["NonCoding"][0:4],
dict1["Intergenic"][0:4],
dict1["Genomic"][0:4],
]
)
def venn_diagram(self,
iFile1,
iFile2,
iFile3=0,
setname1='A',
setname2='B',
setname3='C',
filename='test.pdf'):
pp = PyPlot(filename)
A = []
B = []
C = []
inFile1 = open(iFile1)
inFile2 = open(iFile2)
for line in inFile1:
line = line.strip()
#fields=line.split('\t')
A.append(line)
for line in inFile2:
line = line.strip()
#fields=line.split('\t')
B.append(line)
inFile1.close()
inFile2.close()
if iFile3 == 0:
pp.venn_diagram([set(A), set(B)], setname1, setname2)
else:
inFile3 = open(iFile3)
for line in inFile3:
line = line.strip()
#fields=line.split('\t')
C.append(line)
inFile3.close()
pp.venn_diagram([set(A), set(B), set(C)], setname1, setname2,
setname3)
def _plot_snv_number(self, yList):
pp = PyPlot()
pp.single_bar(yList)
def _plot_snv_number(self, yList):
pp = PyPlot()
pp.single_bar(yList)
