def get_motif_list(self, pseudocounts=1.0, fpr=0.0001):
motif_list = []
# iterate over all available PWM files
for motif_dir_path in self.motif_data.pwm_list:
# iterate over all motif elements in this set
for motif_name, ma in self.motifs_map.items():
motif_file_name = os.path.join(motif_dir_path,
motif_name + ".pwm")
# if the motif annotation has a corresponding PWM file, add to return list
if os.path.isfile(motif_file_name):
# check whether ma provides the motif matching threshold for the given fpr
# recalculate (and store) it otherwise
if fpr in ma.thresholds and ma.thresholds[fpr]:
threshold = ma.thresholds[fpr]
else:
pfm = parsers.pfm(str(motif_file_name))
bg = tools.flat_bg(
len(pfm)
) # total number of "points" to add, not per-row
pssm = tools.log_odds(pfm, bg, pseudocounts, 2)
threshold = tools.threshold_from_p(pssm, bg, fpr)
ma.thresholds[fpr] = threshold
motif_list.append(
Motif(motif_file_name, pseudocounts, threshold))
return motif_list
def get_motif_list(self, pseudocounts=1.0, fpr=0.0001):
motif_list = []
# iterate over all available PWM files
for motif_dir_path in self.motif_data.pwm_list:
# iterate over all motif elements in this set
for motif_name, ma in self.motifs_map.items():
motif_file_name = os.path.join(motif_dir_path, motif_name + ".pwm")
# if the motif annotation has a corresponding PWM file, add to return list
if os.path.isfile(motif_file_name):
# check whether ma provides the motif matching threshold for the given fpr
# recalculate (and store) it otherwise
if fpr in ma.thresholds and ma.thresholds[fpr]:
threshold = ma.thresholds[fpr]
else:
pfm = parsers.pfm(str(motif_file_name))
bg = tools.flat_bg(len(pfm)) # total number of "points" to add, not per-row
pssm = tools.log_odds(pfm, bg, pseudocounts, 2)
threshold = tools.threshold_from_p(pssm, bg, fpr)
ma.thresholds[fpr] = threshold
motif_list.append(Motif(motif_file_name, pseudocounts, threshold))
return motif_list
def __init__(self, input_file_name, pseudocounts, fpr, thresholds):
"""
Initializes Motif.
Fields:
pfm -- Position Frequency Matrix.
bg -- Background frequencies.
pssm -- Position Specific Scoring Matrix.
alphabet -- A list of letters, eg ["Aa", "Cc", "Gg", "Tt"]
threshold -- Motif matching threshold.
len -- Length of the motif.
max -- Maximum PSSM score possible.
is_palindrome -- True if consensus is biologically palindromic.
"""
# Initializing name
self.name = ".".join(basename(input_file_name).split(".")[:-1])
repository = input_file_name.split("/")[-2]
# Creating PFM & PSSM
self.pfm = parsers.pfm(str(input_file_name))
self.bg = tools.flat_bg(len(
self.pfm)) # total number of "points" to add, not per-row
self.pssm = tools.log_odds(self.pfm, self.bg, pseudocounts, 2)
self.pssm_rc = tools.reverse_complement(self.pssm)
# how many bases this motif has
self.len = len(self.pfm[0])
# maximum value found in the whole PSSM
self.max = max([max(e) for e in self.pssm])
# we only support pure DNA or methylated DNA, for now.
self.alphabet = ["Aa", "Cc", "Gg", "Tt"]
if len(self.pfm) == 6:
self.alphabet += ["m", "1"]
# Evaluating threshold
try:
if pseudocounts != 1.0:
raise ValueError()
self.threshold = thresholds.dict[repository][self.name][fpr]
except Exception:
# FIXME: this requires a modified version of MOODS. Not sure if we actually need it.
# self.threshold = tools.threshold_from_p(self.pssm, self.bg, fpr, 2000.0) # 10000.0 would take too long
self.threshold = tools.threshold_from_p(self.pssm, self.bg, fpr)
print(">>> recomputing threshold for %s: %f" %
(self.name, self.threshold))
self.threshold_rc = tools.threshold_from_p(self.pssm_rc, self.bg, fpr)
self.consensus = "".join(
[self.alphabet[i][0] for i in argmax(self.pssm, axis=0)])
self.consensus_rc = "".join(
[self.alphabet[i][0] for i in argmax(self.pssm_rc, axis=0)])
# Evaluating if motif is palindromic
self.is_palindrome = self.consensus == self.consensus_rc
def __init__(self, input_file_name, pseudocounts, threshold):
"""
Initializes Motif.
Fields:
pfm -- Position Frequency Matrix.
bg -- Background frequencies.
pssm -- Position Specific Scoring Matrix.
alphabet -- A list of letters, eg ["Aa", "Cc", "Gg", "Tt"]
threshold -- Motif matching threshold.
len -- Length of the motif.
max -- Maximum PSSM score possible.
is_palindrome -- True if consensus is biologically palindromic.
"""
# Initializing name
self.name = ".".join(basename(input_file_name).split(".")[:-1])
# Creating PFM & PSSM
self.pfm = parsers.pfm(str(input_file_name))
self.bg = tools.flat_bg(len(
self.pfm)) # total number of "points" to add, not per-row
self.pssm = tools.log_odds(self.pfm, self.bg, pseudocounts, 2)
self.pssm_rc = tools.reverse_complement(self.pssm)
# how many bases this motif has
self.len = len(self.pfm[0])
# maximum value found in the whole PSSM
self.max = max([max(e) for e in self.pssm])
# we only support pure DNA or methylated DNA, for now.
self.alphabet = ["Aa", "Cc", "Gg", "Tt"]
if len(self.pfm) == 6:
self.alphabet += ["m", "1"]
self.threshold = threshold
self.consensus = "".join(
[self.alphabet[i][0] for i in argmax(self.pssm, axis=0)])
self.consensus_rc = "".join(
[self.alphabet[i][0] for i in argmax(self.pssm_rc, axis=0)])
# Evaluating if motif is palindromic
self.is_palindrome = self.consensus == self.consensus_rc
def __init__(self, input_file_name, pseudocounts, threshold):
"""
Initializes Motif.
Fields:
pfm -- Position Frequency Matrix.
bg -- Background frequencies.
pssm -- Position Specific Scoring Matrix.
alphabet -- A list of letters, eg ["Aa", "Cc", "Gg", "Tt"]
threshold -- Motif matching threshold.
len -- Length of the motif.
max -- Maximum PSSM score possible.
is_palindrome -- True if consensus is biologically palindromic.
"""
# Initializing name
self.name = ".".join(basename(input_file_name).split(".")[:-1])
# Creating PFM & PSSM
self.pfm = parsers.pfm(str(input_file_name))
self.bg = tools.flat_bg(len(self.pfm)) # total number of "points" to add, not per-row
self.pssm = tools.log_odds(self.pfm, self.bg, pseudocounts, 2)
self.pssm_rc = tools.reverse_complement(self.pssm)
# how many bases this motif has
self.len = len(self.pfm[0])
# maximum value found in the whole PSSM
self.max = max([max(e) for e in self.pssm])
# we only support pure DNA or methylated DNA, for now.
self.alphabet = ["Aa", "Cc", "Gg", "Tt"]
if len(self.pfm) == 6:
self.alphabet += ["m", "1"]
self.threshold = threshold
self.consensus = "".join([self.alphabet[i][0] for i in argmax(self.pssm, axis=0)])
self.consensus_rc = "".join([self.alphabet[i][0] for i in argmax(self.pssm_rc, axis=0)])
# Evaluating if motif is palindromic
self.is_palindrome = self.consensus == self.consensus_rc
version = ".".join(pwm_name.split(".")[2:])
gene_names = hocomoco_anno[pwm_name][0]
group = hocomoco_anno[pwm_name][1]
if not group:
group = "."
uniprot = hocomoco_anno[pwm_name][2]
data_source = hocomoco_anno[pwm_name][3]
taxGroup = "vertebrates"
species = (pwm_name.split("_")[1]).split(".")[0]
if species == "HUMAN":
species = "H**o sapiens"
elif species == "MOUSE":
species = "Mus musculus"
# Creating PSSM
pfm = parsers.pfm(inputFileName)
bg = tools.flat_bg(len(pfm)) # total number of "points" to add, not per-row
pssm = tools.log_odds(pfm, bg, pseudocounts, 2)
threshold_list = []
# Evaluating thresholds
for fpr in fprList:
# Note: this requires a modified version of MOODS. Only use it if you know what you are doing
# resVec.append(str(tools.threshold_from_p(pssm, bg, fpr, 10000.0)))
threshold = tools.threshold_from_p(pssm, bg, fpr)
threshold_list.append(str(threshold))
threshold = ",".join(threshold_list)
resultMatrix.append([matrix_id, pwm_name, version, gene_names, group, uniprot, data_source, taxGroup,
species, threshold])
version = ".".join(pwm_name.split(".")[2:])
gene_names = hocomoco_anno[pwm_name][0]
group = hocomoco_anno[pwm_name][1]
if not group:
group = "."
uniprot = hocomoco_anno[pwm_name][2]
data_source = hocomoco_anno[pwm_name][3]
taxGroup = "vertebrates"
species = (pwm_name.split("_")[1]).split(".")[0]
if species == "HUMAN":
species = "H**o sapiens"
elif species == "MOUSE":
species = "Mus musculus"
# Creating PSSM
pfm = parsers.pfm(inputFileName)
bg = tools.flat_bg(
len(pfm)) # total number of "points" to add, not per-row
pssm = tools.log_odds(pfm, bg, pseudocounts, 2)
threshold_list = []
# Evaluating thresholds
for fpr in fprList:
# Note: this requires a modified version of MOODS. Only use it if you know what you are doing
# resVec.append(str(tools.threshold_from_p(pssm, bg, fpr, 10000.0)))
threshold = tools.threshold_from_p(pssm, bg, fpr)
threshold_list.append(str(threshold))
threshold = ",".join(threshold_list)
resultMatrix.append([
matrix_id, pwm_name, version, gene_names, group, uniprot,
inFolder = sys.argv[1]
outFileName = sys.argv[2]
# Parameters
fprList = [0.005, 0.001, 0.0005, 0.0001, 0.00005, 0.00001]
pseudocounts = 1.0
outFile = open(outFileName, "w")
outFile.write("\t".join(["MOTIF"] + [str(e) for e in fprList]) + "\n")
# Iterating on all PWMs
for pwmFileName in sorted(glob(inFolder + "*.pwm")):
# Creating PSSM
name = ".".join(basename(pwmFileName).split(".")[:-1])
pfm = parsers.pfm(pwmFileName)
bg = tools.flat_bg(
len(pfm)) # total number of "points" to add, not per-row
pssm = tools.log_odds(pfm, bg, pseudocounts, 2)
# Evaluating thresholds
resVec = [name]
for fpr in fprList:
# Note: this requires a modified version of MOODS. Only use it if you know what you are doing
# resVec.append(str(tools.threshold_from_p(pssm, bg, fpr, 10000.0)))
resVec.append(str(tools.threshold_from_p(pssm, bg, fpr)))
# Writing results
outFile.write("\t".join(resVec) + "\n")
outFile.close()