def Run(self):
self.transit_message("Starting Normalization")
start_time = time.time()
infile = self.infile
outputPath = self.outfile # output file exists, should I require -overwrite flag?
# determine ref genome from first; assume they are all the same; assume wigs have 2 header lines
line2 = "variableStep chrom=" # unknown
for line in open(infile):
if line.startswith("variableStep"): line2 = line.rstrip(); break
if self.combined_wig==True: (sites,data,files) = tnseq_tools.read_combined_wig(self.ctrldata[0])
else: (data, sites) = tnseq_tools.get_data(self.ctrldata)
(data,factors) = norm_tools.normalize_data(data,self.normalization)
print "writing",outputPath
file = open(outputPath,"w")
file.write("# %s normalization of %s\n" % (self.normalization,infile))
if self.combined_wig==True:
for f in files: file.write("#File: %s\n" % f)
for i in range(len(sites)): file.write('\t'.join([str(sites[i])]+["%0.1f" % x for x in list(data[...,i])])+"\n")
else:
file.write(line2+"\n")
for j in range(len(sites)):
file.write("%s %s\n" % (sites[j],int(data[0,j])))
file.close()
self.finish()
self.transit_message("Finished Normalization")
def convertToIGV(self, dataset_list, annotationPath, path, normchoice=None):
if not normchoice:
normchoice = "nonorm"
(fulldata, position) = tnseq_tools.get_data(dataset_list)
(fulldata, factors) = norm_tools.normalize_data(fulldata, normchoice,
dataset_list,
annotationPath)
position = position.astype(int)
output = open(path, "w")
output.write("#Converted to IGV with TRANSIT.\n")
if normchoice != "nonorm":
output.write("#Reads normalized using '%s'\n" % normchoice)
output.write("#Files:\n#%s\n" % "\n#".join(dataset_list))
output.write(
"#Chromosome\tStart\tEnd\tFeature\t%s\tTAs\n" %
("\t".join([transit_tools.fetch_name(D) for D in dataset_list])))
chrom = transit_tools.fetch_name(annotationPath)
for i, pos in enumerate(position):
output.write(
"%s\t%s\t%s\tTA%s\t%s\t1\n" %
(chrom, position[i], position[i] + 1, position[i], "\t".join(
["%1.1f" % fulldata[j][i] for j in range(len(fulldata))])))
output.close()
def test_TTR(self):
N = len(all_data_list)
data, position = tnseq_tools.get_data(all_data_list)
norm_data, factors = norm_tools.normalize_data(data, "TTR")
self.assertFalse((factors == numpy.ones(N)).all())
for k in range(N):
self.assertNotEqual(numpy.mean(norm_data[k]), raw_means[k])
def test_nonorm(self):
data, position = tnseq_tools.get_data(all_data_list)
norm_data, factors = norm_tools.normalize_data(data, "nonorm")
self.assertTrue((factors == numpy.array([1.])).all())
N = len(all_data_list)
for k in range(N):
self.assertEqual(numpy.mean(norm_data[k]), raw_means[k])
def test_nonorm(self):
data,position = tnseq_tools.get_data(all_data_list)
norm_data,factors = norm_tools.normalize_data(data, "nonorm")
self.assertTrue((factors == numpy.array([ 1.])).all())
N = len(all_data_list)
for k in range(N):
self.assertEqual(numpy.mean(norm_data[k]), raw_means[k])
def Run(self):
self.transit_message("Starting Normalization")
start_time = time.time()
infile = self.infile
outputPath = self.outfile # output file exists, should I require -overwrite flag?
# determine ref genome from first; assume they are all the same; assume wigs have 2 header lines
line2 = "variableStep chrom=" # unknown
for line in open(infile):
if line.startswith("variableStep"): line2 = line.rstrip(); break
if self.combined_wig==True: (sites,data,files) = tnseq_tools.read_combined_wig(self.ctrldata[0])
else: (data, sites) = tnseq_tools.get_data(self.ctrldata)
(data,factors) = norm_tools.normalize_data(data,self.normalization)
print "writing",outputPath
file = open(outputPath,"w")
file.write("# %s normalization of %s\n" % (self.normalization,infile))
if self.combined_wig==True:
for f in files: file.write("#File: %s\n" % f)
for i in range(len(sites)): file.write('\t'.join([str(sites[i])]+["%0.1f" % x for x in list(data[...,i])])+"\n")
else:
file.write(line2+"\n")
for j in range(len(sites)):
file.write("%s %s\n" % (sites[j],int(data[0,j])))
file.close()
self.finish()
self.transit_message("Finished Normalization")
def test_TTR(self):
N = len(all_data_list)
data,position = tnseq_tools.get_data(all_data_list)
norm_data,factors = norm_tools.normalize_data(data, "TTR")
self.assertFalse((factors == numpy.ones(N)).all())
for k in range(N):
self.assertNotEqual(numpy.mean(norm_data[k]), raw_means[k])
def __init__(self,
parent,
dataset_list=["H37Rv_Sassetti_glycerol.wig"],
annotation="H37Rv.prot_table",
gene="",
scale=None,
feature_hashes=[],
feature_data=[]):
view_trash.MainFrame.__init__(self, parent)
self.parent = parent
self.size = wx.Size(1500, 800)
self.start = 1
self.end = 10000
#self.orf2data = draw_trash.read_prot_table(annotation)
#self.hash = draw_trash.hash_prot_genes(annotation)
self.orf2data = transit_tools.get_gene_info(annotation)
self.hash = transit_tools.get_pos_hash(annotation)
self.features = []
#Data to facilitate search
self.name2id = {}
for orf, (name, desc, start, end, strand) in self.orf2data.items():
name = name.lower()
if name not in self.name2id: self.name2id[name] = []
self.name2id[name].append(orf)
self.lowerid2id = dict([(x.lower(), x) for x in self.orf2data.keys()])
self.labels = [fetch_name(d) for d in dataset_list]
(self.fulldata, self.position) = tnseq_tools.get_data(dataset_list)
#Save normalized data
(self.fulldata_norm,
self.factors) = norm_tools.normalize_data(self.fulldata,
method="nzmean")
self.wasNorm = False
#initialize parent class
self.feature_hashes = feature_hashes
self.feature_data = feature_data
if not scale:
scale = [150] * len(dataset_list)
self.scale = scale
self.globalScale = False
self.datasetChoice.SetItems(self.labels)
self.datasetChoice.SetSelection(0)
if gene:
self.searchText.SetValue(gene)
self.searchFunc(gene)
self.updateFunc(parent)
self.Fit()
def Run(self):
self.transit_message("Starting IGV Export")
start_time = time.time()
#Get orf data
self.transit_message("Getting Data")
(fulldata, position) = tnseq_tools.get_data(self.ctrldata)
(fulldata,
factors) = norm_tools.normalize_data(fulldata, self.normalization,
self.ctrldata,
self.annotation_path)
position = position.astype(int)
hash = transit_tools.get_pos_hash(self.annotation_path)
rv2info = transit_tools.get_gene_info(self.annotation_path)
self.transit_message("Normalizing")
self.output.write("#Converted to IGV with TRANSIT.\n")
if self.normalization != "nonorm":
self.output.write("#Reads normalized using '%s'\n" %
self.normalization)
if type(factors[0]) == type(0.0):
self.output.write(
"#Normalization Factors: %s\n" %
"\t".join(["%s" % f for f in factors.flatten()]))
else:
self.output.write("#Normalization Factors: %s\n" % " ".join(
[",".join(["%s" % bx for bx in b]) for b in factors]))
self.output.write("#Files:\n")
for f in self.ctrldata:
self.output.write("#%s\n" % f)
dataset_str = "\t".join(
[transit_tools.fetch_name(F) for F in self.ctrldata])
self.output.write("#Chromosome\tStart\tEnd\tFeature\t%s\tTAs\n" %
dataset_str)
chrom = transit_tools.fetch_name(self.annotation_path)
(K, N) = fulldata.shape
self.progress_range(N)
for i, pos in enumerate(position):
self.output.write(
"%s\t%s\t%s\tTA%s\t%s\t1\n" %
(chrom, position[i], position[i] + 1, position[i], "\t".join(
["%1.1f" % fulldata[j][i] for j in range(len(fulldata))])))
# Update progress
text = "Running Export Method... %5.1f%%" % (100.0 * i / N)
self.progress_update(text, i)
self.output.close()
self.transit_message("") # Printing empty line to flush stdout
self.finish()
self.transit_message("Finished Export")
def Run(self):
self.transit_message("Starting Gene Mean Counts Export")
start_time = time.time()
#Get orf data
self.transit_message("Getting Data")
(fulldata, position) = tnseq_tools.get_data(self.ctrldata)
(fulldata, factors) = norm_tools.normalize_data(fulldata, self.normalization,
self.ctrldata, self.annotation_path)
position = position.astype(int)
hash = transit_tools.get_pos_hash(self.annotation_path)
rv2info = transit_tools.get_gene_info(self.annotation_path)
self.transit_message("Normalizing")
self.output.write("#Summarized to Mean Gene Counts with TRANSIT.\n")
if self.normalization != "nonorm":
self.output.write("#Reads normalized using '%s'\n" % self.normalization)
if type(factors[0]) == type(0.0):
self.output.write("#Normalization Factors: %s\n" % "\t".join(["%s" % f for f in factors.flatten()]))
else:
self.output.write("#Normalization Factors: %s\n" % " ".join([",".join(["%s" % bx for bx in b]) for b in factors]))
self.output.write("#Files:\n")
for f in self.ctrldata:
self.output.write("#%s\n" % f)
K,Nsites = fulldata.shape
# Get Gene objects
G = tnseq_tools.Genes(self.ctrldata, self.annotation_path, norm=self.normalization)
N = len(G)
self.progress_range(N)
dataset_header = "\t".join([transit_tools.fetch_name(D) for D in self.ctrldata])
self.output.write("#Orf\tName\tNumber of TA sites\t%s\n" % dataset_header)
for i,gene in enumerate(G):
if gene.n > 0:
data_str = "\t".join(["%1.2f" % (M) for M in numpy.mean(gene.reads, 1)])
else:
data_str = "\t".join(["%1.2f" % (Z) for Z in numpy.zeros(K)])
self.output.write("%s\t%s\t%s\t%s\n" % (gene.orf, gene.name, gene.n, data_str))
# Update progress
text = "Running Export Method... %5.1f%%" % (100.0*i/N)
self.progress_update(text, i)
self.output.close()
self.transit_message("") # Printing empty line to flush stdout
self.finish()
self.transit_message("Finished Export")
def Run(self):
self.transit_message("Starting Combined Wig Export")
start_time = time.time()
#Get orf data
self.transit_message("Getting Data")
(fulldata, position) = tnseq_tools.get_data(self.ctrldata)
(fulldata,
factors) = norm_tools.normalize_data(fulldata, self.normalization,
self.ctrldata,
self.annotation_path)
position = position.astype(int)
hash = transit_tools.get_pos_hash(self.annotation_path)
rv2info = transit_tools.get_gene_info(self.annotation_path)
self.transit_message("Normalizing")
self.output.write("#Converted to CombinedWig with TRANSIT.\n")
self.output.write("#normalization method: %s\n" % self.normalization)
if self.normalization != "nonorm":
if type(factors[0]) == type(0.0):
self.output.write(
"#Normalization Factors: %s\n" %
"\t".join(["%s" % f for f in factors.flatten()]))
else:
self.output.write("#Normalization Factors: %s\n" % " ".join(
[",".join(["%s" % bx for bx in b]) for b in factors]))
(K, N) = fulldata.shape
for f in self.ctrldata:
self.output.write("#File: %s\n" % f)
self.output.write("#TAcoord\t%s\n" % ('\t'.join(self.ctrldata)))
for i, pos in enumerate(position):
#self.output.write("%d\t%s\t%s\n" % (position[i], "\t".join(["%1.1f" % c for c in fulldata[:,i]]),",".join(["%s (%s)" % (orf,rv2info.get(orf,["-"])[0]) for orf in hash.get(position[i], [])]) ))
if self.normalization != 'nonorm':
vals = "\t".join(["%1.1f" % c for c in fulldata[:, i]])
else:
vals = "\t".join(["%d" % c for c in fulldata[:, i]
]) # no decimals if raw counts
self.output.write("%d\t%s\t%s\n" % (position[i], vals, ",".join([
"%s (%s)" % (orf, rv2info.get(orf, ["-"])[0])
for orf in hash.get(position[i], [])
])))
# Update progress
text = "Running Export Method... %5.1f%%" % (100.0 * i / N)
self.progress_update(text, i)
self.output.close()
self.transit_message("") # Printing empty line to flush stdout
self.finish()
self.transit_message("Finished Export")
def convertToCombinedWig(dataset_list,
annotationPath,
outputPath,
normchoice="nonorm"):
"""Normalizes the input datasets and outputs the result in CombinedWig format.
Arguments:
dataset_list (list): List of paths to datasets in .wig format
annotationPath (str): Path to annotation in .prot_table or GFF3 format.
outputPath (str): Desired output path.
normchoice (str): Choice for normalization method.
"""
(fulldata, position) = tnseq_tools.get_data(dataset_list)
(fulldata, factors) = norm_tools.normalize_data(fulldata, normchoice,
dataset_list,
annotationPath)
position = position.astype(int)
hash = get_pos_hash(annotationPath)
rv2info = get_gene_info(annotationPath)
output = open(outputPath, "w")
output.write("#Converted to CombinedWig with TRANSIT.\n")
if normchoice != "nonorm":
output.write("#Reads normalized using '%s'\n" % normchoice)
if type(factors[0]) == type(0.0):
output.write("#Normalization Factors: %s\n" %
"\t".join(["%s" % f for f in factors.flatten()]))
else:
output.write(
"#Normalization Factors: %s\n" %
" ".join([",".join(["%s" % bx for bx in b]) for b in factors]))
(K, N) = fulldata.shape
output.write("#Files:\n")
for f in dataset_list:
output.write("#%s\n" % f)
for i, pos in enumerate(position):
#output.write("%-10d %s %s\n" % (position[i], "".join(["%7.1f" % c for c in fulldata[:,i]]),",".join(["%s (%s)" % (orf,rv2info.get(orf,["-"])[0]) for orf in hash.get(position[i], [])]) ))
output.write(
"%d\t%s\t%s\n" %
(position[i], "\t".join(["%1.1f" % c
for c in fulldata[:, i]]), ",".join([
"%s (%s)" %
(orf, rv2info.get(orf, ["-"])[0])
for orf in hash.get(position[i], [])
])))
output.close()
def convertToGeneCountSummary(dataset_list,
annotationPath,
outputPath,
normchoice="nonorm"):
"""Normalizes the input datasets and outputs the result in CombinedWig format.
Arguments:
dataset_list (list): List of paths to datasets in .wig format
annotationPath (str): Path to annotation in .prot_table or GFF3 format.
outputPath (str): Desired output path.
normchoice (str): Choice for normalization method.
"""
(fulldata, position) = tnseq_tools.get_data(dataset_list)
(fulldata, factors) = norm_tools.normalize_data(fulldata, normchoice,
dataset_list,
annotationPath)
output = open(outputPath, "w")
output.write("#Summarized to Mean Gene Counts with TRANSIT.\n")
if normchoice != "nonorm":
output.write("#Reads normalized using '%s'\n" % normchoice)
if type(factors[0]) == type(0.0):
output.write("#Normalization Factors: %s\n" %
"\t".join(["%s" % f for f in factors.flatten()]))
else:
output.write(
"#Normalization Factors: %s\n" %
" ".join([",".join(["%s" % bx for bx in b]) for b in factors]))
(K, N) = fulldata.shape
output.write("#Files:\n")
for f in dataset_list:
output.write("#%s\n" % f)
# Get Gene objects
G = tnseq_tools.Genes(dataset_list, annotationPath, norm=normchoice)
dataset_header = "\t".join([os.path.basename(D) for D in dataset_list])
output.write("#Orf\tName\tNumber of TA sites\t%s\n" % dataset_header)
for i, gene in enumerate(G):
if gene.n > 0:
data_str = "\t".join(
["%1.2f" % (M) for M in numpy.mean(gene.reads, 1)])
else:
data_str = "\t".join(["%1.2f" % (Z) for Z in numpy.zeros(K)])
output.write("%s\t%s\t%s\t%s\n" %
(gene.orf, gene.name, gene.n, data_str))
output.close()
def get_validated_data(wig_list, wxobj=None):
""" Returns a tuple of (data, position) containing a matrix of raw read-counts
, and list of coordinates.
Arguments:
wig_list (list): List of paths to wig files.
wxobj (object): wxPython GUI object for warnings
Returns:
tuple: Two lists containing data and positions of the wig files given.
:Example:
>>> import pytransit.tnseq_tools as tnseq_tools
>>> (data, position) = tnseq_tools.get_validated_data(["data/glycerol_H37Rv_rep1.wig", "data/glycerol_H37Rv_rep2.wig"])
>>> print data
array([[ 0., 0., 0., ..., 0., 0., 0.],
[ 0., 0., 0., ..., 0., 0., 0.]])
.. seealso:: :class:`get_file_types` :class:`combine_replicates` :class:`get_data_zero_fill` :class:`pytransit.norm_tools.normalize_data`
"""
(status, genome) = validate_wig_format(wig_list, wxobj=wxobj)
# Regular file with empty sites
if status == 0:
return tnseq_tools.get_data(wig_list)
# No empty sites, decided to proceed as Himar1
elif status == 1:
return tnseq_tools.get_data_w_genome(wig_list, genome)
# No empty sites, decided to proceed as Tn5
elif status == 2:
return tnseq_tools.get_data_zero_fill(wig_list)
# Didn't choose either.... what!?
else:
return tnseq_tools.get_data([])
def Run(self):
self.transit_message("Starting IGV Export")
start_time = time.time()
#Get orf data
self.transit_message("Getting Data")
(fulldata, position) = tnseq_tools.get_data(self.ctrldata)
(fulldata, factors) = norm_tools.normalize_data(fulldata, self.normalization,
self.ctrldata, self.annotation_path)
position = position.astype(int)
hash = transit_tools.get_pos_hash(self.annotation_path)
rv2info = transit_tools.get_gene_info(self.annotation_path)
self.transit_message("Normalizing")
self.output.write("#Converted to IGV with TRANSIT.\n")
if self.normalization != "nonorm":
self.output.write("#Reads normalized using '%s'\n" % self.normalization)
if type(factors[0]) == type(0.0):
self.output.write("#Normalization Factors: %s\n" % "\t".join(["%s" % f for f in factors.flatten()]))
else:
self.output.write("#Normalization Factors: %s\n" % " ".join([",".join(["%s" % bx for bx in b]) for b in factors]))
self.output.write("#Files:\n")
for f in self.ctrldata:
self.output.write("#%s\n" % f)
dataset_str = "\t".join([transit_tools.fetch_name(F) for F in self.ctrldata])
self.output.write("#Chromosome\tStart\tEnd\tFeature\t%s\tTAs\n" % dataset_str)
chrom = transit_tools.fetch_name(self.annotation_path)
(K,N) = fulldata.shape
self.progress_range(N)
for i,pos in enumerate(position):
self.output.write("%s\t%s\t%s\tTA%s\t%s\t1\n" % (chrom, position[i], position[i]+1, position[i], "\t".join(["%1.1f" % fulldata[j][i] for j in range(len(fulldata))])))
# Update progress
text = "Running Export Method... %5.1f%%" % (100.0*i/N)
self.progress_update(text, i)
self.output.close()
self.transit_message("") # Printing empty line to flush stdout
self.finish()
self.transit_message("Finished Export")
def test_genes_creation_fromdata(self):
data,position = tnseq_tools.get_data(all_data_list)
Kreps,Nsites = data.shape
G = tnseq_tools.Genes([], annotation, data=data, position=position)
N = len(G)
test_orf = "Rv0001"
test_name = "dnaA"
#Test list creation
self.assertGreater(N, 3000)
#Test dictionary lookup + data
self.assertEqual(G[test_orf].orf, test_orf)
self.assertEqual(G[test_orf].name, test_name)
#Test list lookup + data
self.assertEqual(G[0].orf, test_orf)
self.assertEqual(G[0].name, test_name)
def Run(self):
self.transit_message("Starting TnseqStats")
start_time = time.time()
datasets = self.wigs
if self.combined_wig == None:
(data, sites) = tnseq_tools.get_data(self.wigs)
else:
(sites, data,
datasets) = tnseq_tools.read_combined_wig(self.combined_wig)
# write table of stats (saturation,NZmean)
file = sys.stdout
if self.outfile != None: file = open(self.outfile, "w")
PTI = True
if PTI == True:
file.write(
"dataset\tdensity\tmean_ct\tNZmean\tNZmedian\tmax_ct\ttotal_cts\tskewness\tkurtosis\tpickands_tail_index\n"
)
else:
file.write(
"dataset\tdensity\tmean_ct\tNZmean\tNZmedian\tmax_ct\ttotal_cts\tskewness\tkurtosis\n"
)
for i in range(data.shape[0]):
density, meanrd, nzmeanrd, nzmedianrd, maxrd, totalrd, skew, kurtosis = tnseq_tools.get_data_stats(
data[i, :])
nzmedianrd = int(nzmedianrd) if numpy.isnan(
nzmedianrd) == False else 0
pti = self.pickands_tail_index(data[i, :])
vals = [
datasets[i],
"%0.3f" % density,
"%0.1f" % meanrd,
"%0.1f" % nzmeanrd,
"%d" % nzmedianrd, maxrd,
int(totalrd),
"%0.1f" % skew,
"%0.1f" % kurtosis
]
if PTI == True: vals.append("%0.3f" % pti)
file.write('\t'.join([str(x) for x in vals]) + '\n')
if self.outfile != None: file.close()
self.finish()
self.transit_message("Finished TnseqStats")
def test_genes_creation_fromdata(self):
data, position = tnseq_tools.get_data(all_data_list)
Kreps, Nsites = data.shape
G = tnseq_tools.Genes([], annotation, data=data, position=position)
N = len(G)
test_orf = "Rv0001"
test_name = "dnaA"
#Test list creation
self.assertGreater(N, 3000)
#Test dictionary lookup + data
self.assertEqual(G[test_orf].orf, test_orf)
self.assertEqual(G[test_orf].name, test_name)
#Test list lookup + data
self.assertEqual(G[0].orf, test_orf)
self.assertEqual(G[0].name, test_name)
def Run(self):
self.transit_message("Starting Combined Wig Export")
start_time = time.time()
#Get orf data
self.transit_message("Getting Data")
(fulldata, position) = tnseq_tools.get_data(self.ctrldata)
(fulldata, factors) = norm_tools.normalize_data(fulldata, self.normalization,
self.ctrldata, self.annotation_path)
position = position.astype(int)
hash = transit_tools.get_pos_hash(self.annotation_path)
rv2info = transit_tools.get_gene_info(self.annotation_path)
self.transit_message("Normalizing")
self.output.write("#Converted to CombinedWig with TRANSIT.\n")
self.output.write("#normalization method: %s\n" % self.normalization)
if self.normalization != "nonorm":
if type(factors[0]) == type(0.0):
self.output.write("#Normalization Factors: %s\n" % "\t".join(["%s" % f for f in factors.flatten()]))
else:
self.output.write("#Normalization Factors: %s\n" % " ".join([",".join(["%s" % bx for bx in b]) for b in factors]))
(K,N) = fulldata.shape
for f in self.ctrldata:
self.output.write("#File: %s\n" % f)
self.output.write("#TAcoord\t%s\n" % ('\t'.join(self.ctrldata)))
for i,pos in enumerate(position):
#self.output.write("%d\t%s\t%s\n" % (position[i], "\t".join(["%1.1f" % c for c in fulldata[:,i]]),",".join(["%s (%s)" % (orf,rv2info.get(orf,["-"])[0]) for orf in hash.get(position[i], [])]) ))
if self.normalization!='nonorm': vals = "\t".join(["%1.1f" % c for c in fulldata[:,i]])
else: vals = "\t".join(["%d" % c for c in fulldata[:,i]]) # no decimals if raw counts
self.output.write("%d\t%s\t%s\n" % (position[i],vals,",".join(["%s (%s)" % (orf,rv2info.get(orf,["-"])[0]) for orf in hash.get(position[i], [])]) ))
# Update progress
text = "Running Export Method... %5.1f%%" % (100.0*i/N)
self.progress_update(text, i)
self.output.close()
self.transit_message("") # Printing empty line to flush stdout
self.finish()
self.transit_message("Finished Export")
def test_read_data(self):
data, position = tnseq_tools.get_data(all_data_list)
K, N = data.shape
self.assertEqual(K, 5)
self.assertGreater(N, 70000)
def main(args, kwargs, quite=False, jumble=False):
missingArgs = False
if "a1" not in kwargs:
missingArgs = True
error("Missing -a1 argument")
if "a2" not in kwargs:
missingArgs = True
error("Missing -a2 argument")
if "b1" not in kwargs:
missingArgs = True
error("Missing -b1 argument")
if "b2" not in kwargs:
missingArgs = True
error("Missing -b2 argument")
if "pt" not in kwargs:
missingArgs = True
error("Missing -pt argument")
if missingArgs:
usage()
sys.exit()
A_1list = kwargs["a1"].split(",")
A_2list = kwargs["a2"].split(",")
B_1list = kwargs["b1"].split(",")
B_2list = kwargs["b2"].split(",")
annotation = kwargs["pt"]
rope = float(kwargs.get("rope", 0.5))
S = int(kwargs.get("s", 100000))
norm_method = kwargs.get("n", "TTR")
label = kwargs.get("l", "debug")
onlyNZ = kwargs.get("-nz", False)
doBFDR = kwargs.get("-bfdr", False)
doFWER = kwargs.get("-fwer", False)
DEBUG = []
if "debug" in kwargs:
DEBUG = kwargs["debug"].split(",")
wiglist = A_1list + B_1list + A_2list + B_2list
Nwig = len(wiglist)
Na1 = len(A_1list)
Nb1 = len(A_1list)
Na2 = len(B_2list)
Nb2 = len(B_2list)
(data, position) = tnseq_tools.get_data(wiglist)
######### FILTER EMTPY SITES #########
if onlyNZ:
ii_good = numpy.sum(data, 0) > 0
data = data[:, ii_good]
position = position[ii_good]
######################################
(data, factors) = norm_tools.normalize_data(data, norm_method, wiglist,
sys.argv[1])
if jumble:
numpy.random.shuffle(data.flat)
numpy.random.shuffle(data.flat)
G_A1 = tnseq_tools.Genes([],
annotation,
data=data[:Na1],
position=position)
G_B1 = tnseq_tools.Genes([],
annotation,
data=data[Na1:(Na1 + Nb1)],
position=position)
G_A2 = tnseq_tools.Genes([],
annotation,
data=data[(Na1 + Nb1):(Na1 + Nb1 + Na2)],
position=position)
G_B2 = tnseq_tools.Genes([],
annotation,
data=data[(Na1 + Nb1 + Na2):],
position=position)
means_list_a1 = []
means_list_b1 = []
means_list_a2 = []
means_list_b2 = []
var_list_a1 = []
var_list_a2 = []
var_list_b1 = []
var_list_b2 = []
# Base priors on empirical observations accross genes.
for gene in sorted(G_A1):
if gene.n > 1:
A1_data = G_A1[gene.orf].reads.flatten()
B1_data = G_B1[gene.orf].reads.flatten()
A2_data = G_A2[gene.orf].reads.flatten()
B2_data = G_B2[gene.orf].reads.flatten()
means_list_a1.append(numpy.mean(A1_data))
var_list_a1.append(numpy.var(A1_data))
means_list_b1.append(numpy.mean(B1_data))
var_list_b1.append(numpy.var(B1_data))
means_list_a2.append(numpy.mean(A2_data))
var_list_a2.append(numpy.var(A2_data))
means_list_b2.append(numpy.mean(B2_data))
var_list_b2.append(numpy.var(B2_data))
# Priors
mu0_A1 = scipy.stats.trim_mean(means_list_a1, 0.01)
mu0_B1 = scipy.stats.trim_mean(means_list_b1, 0.01)
mu0_A2 = scipy.stats.trim_mean(means_list_a2, 0.01)
mu0_B2 = scipy.stats.trim_mean(means_list_b2, 0.01)
s20_A1 = scipy.stats.trim_mean(var_list_a1, 0.01)
s20_B1 = scipy.stats.trim_mean(var_list_b1, 0.01)
s20_A2 = scipy.stats.trim_mean(var_list_a2, 0.01)
s20_B2 = scipy.stats.trim_mean(var_list_b2, 0.01)
k0 = 1.0
nu0 = 1.0
data = []
postprob = []
if not quite:
print "# Created with '%s'. Copyright 2016-2017. Michael A. DeJesus & Thomas R. Ioerger" % (
sys.argv[0])
print "# Version %1.2f; http://saclab.tamu.edu/essentiality/GI" % __version__
print "#"
print "# python %s" % " ".join(sys.argv)
print "# Samples = %d, k0=%1.1f, nu0=%1.1f" % (S, k0, nu0)
print "# Mean Prior: Variance Prior:"
print "# mu0_A1 = %1.2f s20_A1 = %1.1f" % (mu0_A1, s20_A1)
print "# mu0_B1 = %1.2f s20_B1 = %1.1f" % (mu0_B1, s20_B1)
print "# mu0_A2 = %1.2f s20_A2 = %1.1f" % (mu0_A2, s20_A2)
print "# mu0_B2 = %1.2f s20_B2 = %1.1f" % (mu0_B2, s20_B2)
print "# ROPE:", rope
print "# TTR Factors:", ", ".join(
["%1.4f" % x for x in numpy.array(factors).flatten()])
for gene in sorted(G_A1):
if len(DEBUG) > 0:
if gene.orf not in DEBUG: continue
if gene.n > 0:
A1_data = G_A1[gene.orf].reads.flatten()
B1_data = G_B1[gene.orf].reads.flatten()
A2_data = G_A2[gene.orf].reads.flatten()
B2_data = G_B2[gene.orf].reads.flatten()
# Time-1 Time-2
#
# Strain-A A C
#
# Strain-B B D
try:
muA1_post, varA1_post = sample_post(A1_data, S, mu0_A1, s20_A1,
k0, nu0)
muB1_post, varB1_post = sample_post(B1_data, S, mu0_B1, s20_B1,
k0, nu0)
muA2_post, varA2_post = sample_post(A2_data, S, mu0_A2, s20_A2,
k0, nu0)
muB2_post, varB2_post = sample_post(B2_data, S, mu0_B2, s20_B2,
k0, nu0)
except Exception as e:
muA1_post = varA1_post = numpy.ones(S)
muB1_post = varB1_post = numpy.ones(S)
muA2_post = varA2_post = numpy.ones(S)
muB2_post = varB2_post = numpy.ones(S)
logFC_A_post = numpy.log2(muA2_post / muA1_post)
logFC_B_post = numpy.log2(muB2_post / muB1_post)
delta_logFC_post = logFC_B_post - logFC_A_post
alpha = 0.05
# Get Bounds of the HDI
l_logFC_A, u_logFC_A = HDI_from_MCMC(logFC_A_post, 1 - alpha)
l_logFC_B, u_logFC_B = HDI_from_MCMC(logFC_B_post, 1 - alpha)
l_delta_logFC, u_delta_logFC = HDI_from_MCMC(
delta_logFC_post, 1 - alpha)
mean_logFC_A = numpy.mean(logFC_A_post)
mean_logFC_B = numpy.mean(logFC_B_post)
mean_delta_logFC = numpy.mean(delta_logFC_post)
# Is HDI significantly different than ROPE?
not_HDI_overlap_bit = l_delta_logFC > rope or u_delta_logFC < -rope
# Probability of posterior overlaping with ROPE
probROPE = numpy.mean(
numpy.logical_and(delta_logFC_post >= 0.0 - rope,
delta_logFC_post <= 0.0 + rope))
else:
A1_data = [0, 0]
B1_data = [0, 0]
A2_data = [0, 0]
B2_data = [0, 0]
mean_logFC_A = 0
mean_logFC_B = 0
mean_delta_logFC = 0
l_logFC_A = 0
u_logFC_A = 0
l_logFC_B = 0
u_logFC_B = 0
l_delta_logFC = 0
u_delta_logFC = 0
probROPE = 1.0
if numpy.isnan(l_logFC_A):
l_logFC_A = -10
u_logFC_A = 10
if numpy.isnan(l_logFC_B):
l_logFC_B = -10
u_logFC_B = 10
if numpy.isnan(l_delta_logFC):
l_delta_logFC = -10
u_delta_logFC = 10
if DEBUG:
out = open("%s.%s_muA1_post" % (label, gene.orf), "w")
for x in muA1_post:
print >> out, x
out = open("%s.%s_muA2_post" % (label, gene.orf), "w")
for x in muA2_post:
print >> out, x
out = open("%s.%s_logFC_A_post" % (label, gene.orf), "w")
for x in logFC_A_post:
print >> out, x
out = open("%s.%s_muB1_post" % (label, gene.orf), "w")
for x in muB1_post:
print >> out, x
out = open("%s.%s_muB2_post" % (label, gene.orf), "w")
for x in muB2_post:
print >> out, x
out = open("%s.%s_logFC_B_post" % (label, gene.orf), "w")
for x in logFC_A_post:
print >> out, x
out = open("%s.%s_delta_logFC_post" % (label, gene.orf), "w")
for x in delta_logFC_post:
print >> out, x
postprob.append(probROPE)
data.append((gene.orf, gene.name, gene.n, numpy.mean(muA1_post),
numpy.mean(muA2_post), numpy.mean(muB1_post),
numpy.mean(muB2_post), mean_logFC_A, mean_logFC_B,
mean_delta_logFC, l_delta_logFC, u_delta_logFC, probROPE,
not_HDI_overlap_bit))
if doBFDR or not doFWER:
postprob = numpy.array(postprob)
postprob.sort()
bfdr = numpy.cumsum(postprob) / numpy.arange(1, len(postprob) + 1)
adjusted_prob = bfdr
adjusted_label = "BFDR"
if doBFDR:
data.sort(key=lambda x: x[-2])
else:
data.sort(key=lambda x: x[-1], reverse=True)
elif doFWER:
fwer = FWER_Bayes(postprob)
fwer.sort()
adjusted_prob = fwer
adjusted_label = "FWER"
data.sort(key=lambda x: x[-2])
return (data, adjusted_prob, adjusted_label)
def test_normalization(self):
N = len(all_data_list)
data, position = tnseq_tools.get_data(all_data_list)
norm_data, factors = norm_tools.normalize_data(data, "TTR")
self.assertFalse((factors == numpy.ones(N)).all())
def __init__( self, parent, datasets):
try:
self.qc_prefix = "[QualityControl]"
self.index_stats = 0
self.plots_list = []
self.wigList = datasets
wx.Frame.__init__ ( self, parent, id = wx.ID_ANY, title = "Quality Control", pos = wx.DefaultPosition, size = wx.Size( 1560, 900 ), style = wx.DEFAULT_FRAME_STYLE|wx.TAB_TRAVERSAL )
#self.SetSizeHints( wx.DefaultSize, wx.DefaultSize )
bSizer9 = wx.BoxSizer( wx.VERTICAL )
self.m_scrolledWindow1 = wx.ScrolledWindow( self, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, wx.HSCROLL|wx.VSCROLL )
self.m_scrolledWindow1.SetScrollRate( 5, 5 )
bSizer10 = wx.BoxSizer( wx.VERTICAL )
self.plotsScrolledWindow = wx.ScrolledWindow( self.m_scrolledWindow1, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, wx.HSCROLL|wx.VSCROLL )
self.plotsScrolledWindow.SetScrollRate( 5, 5 )
self.plotsScrolledWindow.SetMinSize( wx.Size( -1, 515 ) )
#plotsSizer = wx.BoxSizer( wx.VERTICAL )
plotsSizer = wx.BoxSizer( wx.HORIZONTAL )
self.plotsBitmap1 = wx.StaticBitmap( self.plotsScrolledWindow, wx.ID_ANY, wx.NullBitmap, wx.DefaultPosition, wx.DefaultSize, 0 )
self.plotsBitmap2 = wx.StaticBitmap( self.plotsScrolledWindow, wx.ID_ANY, wx.NullBitmap, wx.DefaultPosition, wx.DefaultSize, 0 )
self.plotsBitmap3 = wx.StaticBitmap( self.plotsScrolledWindow, wx.ID_ANY, wx.NullBitmap, wx.DefaultPosition, wx.DefaultSize, 0 )
plotsSizer.Add( self.plotsBitmap1, 0, wx.ALL, 5 )
plotsSizer.Add( self.plotsBitmap2, 0, wx.ALL, 5 )
plotsSizer.Add( self.plotsBitmap3, 0, wx.ALL, 5 )
#self.plotsBitmap.SetMaxSize( wx.Size( 400,400 ) )
#self.plotsFigure = Figure()
#self.plotsAxes = self.plotsFigure.add_subplot(111)
#self.plotsCanvas = FigureCanvas(self, -1, self.plotsFigure)
#plotsSizer.Add( self.plotsCanvas, 0, wx.ALL, 5 )
self.plotsScrolledWindow.SetSizer( plotsSizer )
self.plotsScrolledWindow.Layout()
plotsSizer.Fit( self.plotsScrolledWindow )
bSizer10.Add( self.plotsScrolledWindow, 0, wx.EXPAND |wx.ALL, 5 )
self.statsScrolledWindow = wx.ScrolledWindow( self.m_scrolledWindow1, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, wx.HSCROLL|wx.VSCROLL )
self.statsScrolledWindow.SetScrollRate( 5, 5 )
self.statsScrolledWindow.SetMaxSize( wx.Size( -1, -1 ) )
self.statsScrolledWindow.SetMinSize( wx.Size( -1, 300 ) )
NoteText = """*Note: Plot 1 and 2 truncate the top 1% of reads for readability.
Selecting a normalization method from the drop down will normalize the data and refresh the figures and table.
This may take a long time depending on the normalization method chosen."""
#self.noticeLabel = wx.StaticText( self.statsScrolledWindow, wx.ID_ANY, u"*Note: Plot 1 and 2 truncate the top 1% of reads for readability.", wx.DefaultPosition, wx.DefaultSize, wx.ALIGN_CENTRE)
self.noticeLabel = wx.StaticText( self.statsScrolledWindow, wx.ID_ANY, NoteText, wx.DefaultPosition, wx.DefaultSize, wx.ALIGN_LEFT)
normChoices = sorted(norm_tools.methods.keys()) #[ u"nonorm", "TTR", "betageom"]
self.normChoice = wx.Choice( self.statsScrolledWindow, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, normChoices, 0 )
#self.normChoice.SetSelection( 0 )
self.normChoice.SetStringSelection("nonorm")
#noteSizer = wx.BoxSizer( wx.VERTICAL )
#noteSizer.Add(self.noticeLabel, wx.ALL|wx.EXPAND, 5 )
self.normLabel = wx.StaticText( self.statsScrolledWindow, wx.ID_ANY, u"Normalization:", wx.DefaultPosition, wx.DefaultSize, wx.ALIGN_CENTRE)
statsSizer = wx.BoxSizer( wx.VERTICAL )
normSizer = wx.BoxSizer( wx.HORIZONTAL )
self.statsListCtrl = wx.ListCtrl( self.statsScrolledWindow, wx.ID_ANY, wx.DefaultPosition, wx.Size( -1, 140 ), wx.LC_REPORT |wx.LC_SINGLE_SEL )
normSizer.Add(self.normLabel, 1, wx.ALL|wx.ALIGN_CENTER_VERTICAL, 5)
normSizer.Add(self.normChoice, 0, wx.ALL, 5)
statsSizer.Add( self.noticeLabel, 0, wx.EXPAND, 5 )
#statsSizer.Add( self.normChoice, 0, wx.ALL, 5 )
statsSizer.Add(normSizer, 0, wx.ALL, 5)
statsSizer.Add( self.statsListCtrl, 1, wx.ALL|wx.EXPAND, 5 )
self.statsScrolledWindow.SetSizer( statsSizer )
self.statsScrolledWindow.Layout()
statsSizer.Fit( self.statsScrolledWindow )
bSizer10.Add( self.statsScrolledWindow, 0, wx.EXPAND |wx.ALL, 5 )
self.m_scrolledWindow1.SetSizer( bSizer10 )
self.m_scrolledWindow1.Layout()
bSizer10.Fit( self.m_scrolledWindow1 )
bSizer9.Add( self.m_scrolledWindow1, 1, wx.EXPAND |wx.ALL, 5 )
self.SetSizer( bSizer9 )
self.Layout()
self.Centre( wx.BOTH )
########################
# Connect Events
self.statsListCtrl.Bind( wx.EVT_LIST_ITEM_SELECTED, self.onStatsItemSelect)
self.normChoice.Bind( wx.EVT_CHOICE, self.onNormSelect )
self.Bind(wx.EVT_CLOSE, self.OnClose)
#######
self.index_stats = 0
self.statsListCtrl.InsertColumn(0, 'File', width=250)
self.statsListCtrl.InsertColumn(1, 'Density', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(2, 'Mean Read', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(3, 'NZMean Read', wx.LIST_FORMAT_CENTRE, width=115)
self.statsListCtrl.InsertColumn(4, 'NZMedian Read', wx.LIST_FORMAT_CENTRE, width=125)
self.statsListCtrl.InsertColumn(5, 'Max Read', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(6, 'Total Reads', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(7, 'Skew', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(8, 'Kurtosis', wx.LIST_FORMAT_CENTRE, width=85)
############################
self.norm = "nonorm"
(self.data, self.position) = tnseq_tools.get_data(self.wigList)
self.refresh()
#self.updateFiles()
#self.addPlots()
#self.statsListCtrl.Select(0)
#self.onStatsItemSelect(None)
###########################
#self.bSizer9.Fit()
except Exception as e:
print self.qc_prefix, "Error:", e
exc_type, exc_obj, exc_tb = sys.exc_info()
fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
print(exc_type, fname, exc_tb.tb_lineno)
def __init__( self, parent, datasets):
try:
self.qc_prefix = "[QualityControl]"
self.index_stats = 0
self.plots_list = []
self.wigList = datasets
wx.Frame.__init__ ( self, parent, id = wx.ID_ANY, title = "Quality Control", pos = wx.DefaultPosition, size = wx.Size( 1560, 900 ), style = wx.DEFAULT_FRAME_STYLE|wx.TAB_TRAVERSAL )
#self.SetSizeHints( wx.DefaultSize, wx.DefaultSize )
bSizer9 = wx.BoxSizer( wx.VERTICAL )
self.m_scrolledWindow1 = wx.ScrolledWindow( self, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, wx.HSCROLL|wx.VSCROLL )
self.m_scrolledWindow1.SetScrollRate( 5, 5 )
bSizer10 = wx.BoxSizer( wx.VERTICAL )
self.plotsScrolledWindow = wx.ScrolledWindow( self.m_scrolledWindow1, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, wx.HSCROLL|wx.VSCROLL )
self.plotsScrolledWindow.SetScrollRate( 5, 5 )
self.plotsScrolledWindow.SetMinSize( wx.Size( -1, 515 ) )
#plotsSizer = wx.BoxSizer( wx.VERTICAL )
plotsSizer = wx.BoxSizer( wx.HORIZONTAL )
self.plotsBitmap1 = wx.StaticBitmap( self.plotsScrolledWindow, wx.ID_ANY, wx.NullBitmap, wx.DefaultPosition, wx.DefaultSize, 0 )
self.plotsBitmap2 = wx.StaticBitmap( self.plotsScrolledWindow, wx.ID_ANY, wx.NullBitmap, wx.DefaultPosition, wx.DefaultSize, 0 )
self.plotsBitmap3 = wx.StaticBitmap( self.plotsScrolledWindow, wx.ID_ANY, wx.NullBitmap, wx.DefaultPosition, wx.DefaultSize, 0 )
plotsSizer.Add( self.plotsBitmap1, 0, wx.ALL, 5 )
plotsSizer.Add( self.plotsBitmap2, 0, wx.ALL, 5 )
plotsSizer.Add( self.plotsBitmap3, 0, wx.ALL, 5 )
#self.plotsBitmap.SetMaxSize( wx.Size( 400,400 ) )
#self.plotsFigure = Figure()
#self.plotsAxes = self.plotsFigure.add_subplot(111)
#self.plotsCanvas = FigureCanvas(self, -1, self.plotsFigure)
#plotsSizer.Add( self.plotsCanvas, 0, wx.ALL, 5 )
self.plotsScrolledWindow.SetSizer( plotsSizer )
self.plotsScrolledWindow.Layout()
plotsSizer.Fit( self.plotsScrolledWindow )
bSizer10.Add( self.plotsScrolledWindow, 0, wx.EXPAND |wx.ALL, 5 )
self.statsScrolledWindow = wx.ScrolledWindow( self.m_scrolledWindow1, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, wx.HSCROLL|wx.VSCROLL )
self.statsScrolledWindow.SetScrollRate( 5, 5 )
self.statsScrolledWindow.SetMaxSize( wx.Size( -1, -1 ) )
self.statsScrolledWindow.SetMinSize( wx.Size( -1, 300 ) )
NoteText = """*Note: Plot 1 and 2 truncate the top 1% of reads for readability.
Selecting a normalization method from the drop down will normalize the data and refresh the figures and table.
This may take a long time depending on the normalization method chosen."""
#self.noticeLabel = wx.StaticText( self.statsScrolledWindow, wx.ID_ANY, u"*Note: Plot 1 and 2 truncate the top 1% of reads for readability.", wx.DefaultPosition, wx.DefaultSize, wx.ALIGN_CENTRE)
self.noticeLabel = wx.StaticText( self.statsScrolledWindow, wx.ID_ANY, NoteText, wx.DefaultPosition, wx.DefaultSize, wx.ALIGN_LEFT)
normChoices = sorted(norm_tools.methods.keys()) #[ u"nonorm", "TTR", "betageom"]
self.normChoice = wx.Choice( self.statsScrolledWindow, wx.ID_ANY, wx.DefaultPosition, wx.DefaultSize, normChoices, 0 )
#self.normChoice.SetSelection( 0 )
self.normChoice.SetStringSelection("nonorm")
#noteSizer = wx.BoxSizer( wx.VERTICAL )
#noteSizer.Add(self.noticeLabel, wx.ALL|wx.EXPAND, 5 )
self.normLabel = wx.StaticText( self.statsScrolledWindow, wx.ID_ANY, u"Normalization:", wx.DefaultPosition, wx.DefaultSize, wx.ALIGN_CENTRE)
statsSizer = wx.BoxSizer( wx.VERTICAL )
normSizer = wx.BoxSizer( wx.HORIZONTAL )
self.statsListCtrl = wx.ListCtrl( self.statsScrolledWindow, wx.ID_ANY, wx.DefaultPosition, wx.Size( -1, 140 ), wx.LC_REPORT |wx.LC_SINGLE_SEL )
normSizer.Add(self.normLabel, 1, wx.ALL|wx.ALIGN_CENTER_VERTICAL, 5)
normSizer.Add(self.normChoice, 0, wx.ALL, 5)
statsSizer.Add( self.noticeLabel, 0, wx.EXPAND, 5 )
#statsSizer.Add( self.normChoice, 0, wx.ALL, 5 )
statsSizer.Add(normSizer, 0, wx.ALL, 5)
statsSizer.Add( self.statsListCtrl, 1, wx.ALL|wx.EXPAND, 5 )
self.statsScrolledWindow.SetSizer( statsSizer )
self.statsScrolledWindow.Layout()
statsSizer.Fit( self.statsScrolledWindow )
bSizer10.Add( self.statsScrolledWindow, 0, wx.EXPAND |wx.ALL, 5 )
self.m_scrolledWindow1.SetSizer( bSizer10 )
self.m_scrolledWindow1.Layout()
bSizer10.Fit( self.m_scrolledWindow1 )
bSizer9.Add( self.m_scrolledWindow1, 1, wx.EXPAND |wx.ALL, 5 )
self.SetSizer( bSizer9 )
self.Layout()
self.Centre( wx.BOTH )
########################
# Connect Events
self.statsListCtrl.Bind( wx.EVT_LIST_ITEM_SELECTED, self.onStatsItemSelect)
self.normChoice.Bind( wx.EVT_CHOICE, self.onNormSelect )
self.Bind(wx.EVT_CLOSE, self.OnClose)
#######
self.index_stats = 0
self.statsListCtrl.InsertColumn(0, 'File', width=250)
self.statsListCtrl.InsertColumn(1, 'Density', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(2, 'Mean Read', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(3, 'NZMean Read', wx.LIST_FORMAT_CENTRE, width=115)
self.statsListCtrl.InsertColumn(4, 'NZMedian Read', wx.LIST_FORMAT_CENTRE, width=125)
self.statsListCtrl.InsertColumn(5, 'Max Read', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(6, 'Total Reads', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(7, 'Skew', wx.LIST_FORMAT_CENTRE, width=85)
self.statsListCtrl.InsertColumn(8, 'Kurtosis', wx.LIST_FORMAT_CENTRE, width=85)
############################
self.norm = "nonorm"
(self.data, self.position) = tnseq_tools.get_data(self.wigList)
self.refresh()
#self.updateFiles()
#self.addPlots()
#self.statsListCtrl.Select(0)
#self.onStatsItemSelect(None)
###########################
#self.bSizer9.Fit()
except Exception as e:
print(self.qc_prefix, "Error:", e)
exc_type, exc_obj, exc_tb = sys.exc_info()
fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
print(exc_type, fname, exc_tb.tb_lineno)
def test_normalization(self):
N = len(all_data_list)
data,position = tnseq_tools.get_data(all_data_list)
norm_data,factors = norm_tools.normalize_data(data, "TTR")
self.assertFalse((factors == numpy.ones(N)).all())
def test_read_data(self):
data,position = tnseq_tools.get_data(all_data_list)
K,N = data.shape
self.assertEqual(K, 5)
self.assertGreater(N, 70000)
