def append_pfm_to_database(self, meme_db, trim_frac=0.08, freqs=[0.27, 0.23, 0.23, 0.27]):
"""write the pfm into a meme file to be used by motif search tools
"""
motif_name = "PWM_{}".format(self.short_name)
if(os.path.exists(meme_db)):
with open(meme_db, "r") as fp:
for line in fp:
if(motif_name in line):
print("{} already exists".format(motif_name))
return None
else:
with open(meme_db, "w") as fp:
fp.write("MEME version 4\n\nALPHABET= ACGT\n\nstrands: + -\n\nBackground letter frequencies\n\n")
fp.write("A {0} C {1} G {2} T {3}\n\n".format(freqs[0], freqs[1], freqs[2], freqs[3]))
i, j = trim_pssm_idx(self.get_seq_ic(), frac=trim_frac)
trimmed_pattern = self.trim(i, j)
pfm = trimmed_pattern.seq
with open(meme_db, 'a') as fp:
fp.write("MOTIF {}\n".format(motif_name))
fp.write("letter-probability matrix: alength= 4 w= {} nsites= 20 E= 0e+0\n".format(pfm.shape[0]))
for line in pfm:
fp.write('%.5f %.5f %.5f %.5f\n' % tuple(line))
fp.write("\n")
return None
def fetch_tomtom_matches(self, background=[0.27, 0.23, 0.23, 0.27],
tomtom_exec_path='tomtom',
motifs_db='HOCOMOCOv11_full_HUMAN_mono_meme_format.meme',
save_report=False,
report_dir='./',
temp_dir='./',
trim_frac=0.08):
"""Fetches top matches from a motifs database using TomTom.
Args:
background: list with ACGT background probabilities
tomtom_exec_path: path to TomTom executable
motifs_db: path to motifs database in meme format
n: number of top matches to return, ordered by p-value
temp_dir: directory for storing temp files
trim_threshold: the ppm is trimmed from left till first position for which
probability for any base pair >= trim_threshold. Similarly from right.
Returns:
list: a list of up to n results returned by tomtom, each entry is a
dictionary with keys 'Target ID', 'p-value', 'E-value', 'q-value'
"""
fname = os.path.join(temp_dir, 'query_file')
# trim and prepare meme file
i, j = trim_pssm_idx(self.get_seq_ic(), frac=trim_frac)
trimmed_pattern = self.trim(i, j)
trimmed_pattern.write_meme_file(background, fname)
# run tomtom
if(save_report):
cmd = '{0} -no-ssc -oc {1} -verbosity 1 -min-overlap 5 -mi 1 -dist pearson -evalue -thresh 10.0 {2} {3}'.format(tomtom_exec_path, report_dir, fname, motifs_db)
print(cmd)
out = subprocess.check_output(cmd, shell=True)
df = pd.read_table("{}/tomtom.tsv".format(report_dir))
df = df[['Target_ID', 'p-value', 'E-value', 'q-value']]
schema = list(df.columns)
dat = df.get_values()
else:
cmd = "{0} -no-ssc -oc . -verbosity 1 -text -min-overlap 5 -mi 1 -dist pearson -evalue -thresh 10.0 {1} {2}".format(tomtom_exec_path, fname, motifs_db)
print(cmd)
out = subprocess.check_output(cmd, shell=True)
dat = [x.split('\t') for x in out.strip().decode("utf-8").split('\n')]
schema = dat[0]
dat = dat[1:]
tget_idx, pval_idx, eval_idx, qval_idx = schema.index('Target_ID'), schema.index('p-value'), schema.index('E-value'), schema.index('q-value')
r = []
for t in dat:
if(len(t) < 4):
break
mtf = {}
mtf['Target ID'] = t[tget_idx]
mtf['p-value'] = float(t[pval_idx])
mtf['E-value'] = float(t[eval_idx])
mtf['q-value'] = float(t[qval_idx])
# if(mtf['q-value']<0.001):
# break
r.append(mtf)
os.system('rm ' + fname)
return r
def append_pwm_to_database(self, pwm_db, trim_frac=0.08):
"""write a the pwm into a database to be used by motif search tools
"""
pwm_name = "PWM_{}".format(self.short_name)
if(os.path.exists(pwm_db)): # search whether the pwm already exists in the database
with open(pwm_db, 'r') as fp:
for line in fp:
if(pwm_name in line):
print("{} already exists".format(pwm_name))
return None
i, j = trim_pssm_idx(self.get_seq_ic(), frac=trim_frac)
trimmed_pattern = self.trim(i, j)
pssm = trimmed_pattern.get_seq_ic()
with open(pwm_db, 'a') as fp:
fp.write(">{}\n".format(pwm_name))
for line in pssm:
fp.write('%.5f %.5f %.5f %.5f\n' % tuple(line))
return None
def get_trim_idx(self, pattern):
"""Return the trimming indices
"""
return trim_pssm_idx(self.mr.get_pssm(*pattern.split("/")), frac=self.trim_frac)
def _trim_seq_ic_ij(self, trim_frac=0.0):
return trim_pssm_idx(self.get_seq_ic(), frac=trim_frac)