def command_scan(inputfile, pwmfile, nreport=1, fpr=0.01, cutoff=None,
bed=False, scan_rc=True, table=False, score_table=False, moods=False,
pvalue=None, bgfile=None, genome=None, ncpus=None, normalize=False):
motifs = read_motifs(pwmfile)
fa = as_fasta(inputfile, genome)
# initialize scanner
s = Scanner(ncpus=ncpus)
s.set_motifs(pwmfile)
if genome:
s.set_genome(genome=genome)
if genome or bgfile:
s.set_background(genome=genome, fname=bgfile, length=fa.median_length())
if not score_table:
s.set_threshold(fpr=fpr, threshold=cutoff)
if table:
it = scan_table(s, inputfile, fa, motifs, cutoff, bgfile, nreport, scan_rc, pvalue, moods)
elif score_table:
it = scan_score_table(s, fa, motifs, scan_rc, normalize=normalize)
else:
it = scan_normal(s, inputfile, fa, motifs, cutoff, bgfile, nreport, scan_rc, pvalue, moods, bed, normalize=normalize)
for row in it:
yield row
def get_PWMScore(self, fin_regions_fa):
""" Scan motif in every peak.
Arguments:
fin_regions_fa {[type]} -- [input fasta file]
Returns:
[type] -- [pfmscorefile]
"""
pfmscorefile = NamedTemporaryFile(mode="w", dir=mytmpdir(), delete=False)
seqs = [s.split(" ")[0] for s in as_fasta(fin_regions_fa, genome=self.genome).ids]
s = Scanner(ncpus=self.ncore)
s.set_motifs(self.pfmfile)
s.set_threshold(threshold=0.0)
s.set_genome(self.genome)
with open(self.pfmfile) as f:
motifs = read_motifs(f)
chunksize = 10000
# Run 10k peaks one time.
with tqdm(total=len(seqs)) as pbar:
for chunk in range(0, len(seqs), chunksize):
chunk_seqs = seqs[chunk : chunk + chunksize]
# print(chunk, "-", chunk + chunksize, "enhancers")
pfm_score = []
it = s.best_score(chunk_seqs, zscore=True, gc=True)
# We are using GC-normalization for motif scan because many sequence is GC-enriched.
# GimmeMotif develop branch already include GC-normalization option now.
for seq, scores in zip(chunk_seqs, it):
for motif, score in zip(motifs, scores):
pfm_score.append([motif.id, seq, score])
pbar.update(1)
pfm_score = pd.DataFrame(pfm_score, columns=["motif", "enhancer", "zscore"])
pfm_score = pfm_score.set_index("motif")
# print("\tCombine")
pfm_score["zscoreRank"] = minmax_scale(rankdata(pfm_score["zscore"]))
# When we built model, rank and minmax normalization was used.
cols = ["enhancer", "zscore", "zscoreRank"]
write_header = False
if chunk == 0:
write_header = True
pfm_score[cols].to_csv(pfmscorefile, sep="\t", header=write_header)
# pbar.update(chunk + chunksize)
return pfmscorefile.name
def scan_to_table(input_table,
genome,
data_dir,
scoring,
pwmfile=None,
ncpus=None):
config = MotifConfig()
if pwmfile is None:
pwmfile = config.get_default_params().get("motif_db", None)
if pwmfile is not None:
pwmfile = os.path.join(config.get_motif_dir(), pwmfile)
if pwmfile is None:
raise ValueError("no pwmfile given and no default database specified")
logger.info("reading table")
if input_table.endswith("feather"):
df = pd.read_feather(input_table)
idx = df.iloc[:, 0].values
else:
df = pd.read_table(input_table, index_col=0, comment="#")
idx = df.index
regions = list(idx)
s = Scanner(ncpus=ncpus)
s.set_motifs(pwmfile)
s.set_genome(genome)
nregions = len(regions)
scores = []
if scoring == "count":
logger.info("setting threshold")
s.set_threshold(fpr=FPR, genome=genome)
logger.info("creating count table")
for row in s.count(regions):
scores.append(row)
logger.info("done")
else:
s.set_threshold(threshold=0.0)
logger.info("creating score table")
for row in s.best_score(regions):
scores.append(row)
logger.info("done")
motif_names = [m.id for m in read_motifs(open(pwmfile))]
logger.info("creating dataframe")
return pd.DataFrame(scores, index=idx, columns=motif_names)
def get_motif_scores(fa, motifs):
s = Scanner()
s.set_motifs(motifs)
s.set_threshold(threshold=0.0)
seqs = Fasta(fa.seqfn)
for i, result in enumerate(s.scan(seqs, nreport=1)):
intron_id = seqs.ids[i]
for m, matches in enumerate(result):
motif = motifs[m]
for score, pos, strand in matches:
if score < 0:
score_rescaled = rescale(score,
orig_range=[motif.min_score, 0],
new_range=[0, 50])
else:
score_rescaled = rescale(score,
orig_range=[0, motif.max_score],
new_range=[50, 100])
yield (intron_id, motif.id, score_rescaled)
def threshold(args):
"""Calculate motif score threshold for a given FPR."""
if args.fpr < 0 or args.fpr > 1:
print("Please specify a FPR between 0 and 1")
sys.exit(1)
motifs = read_motifs(args.pwmfile)
s = Scanner()
s.set_motifs(args.pwmfile)
s.set_threshold(args.fpr, filename=args.inputfile)
print("Motif\tScore\tCutoff")
for motif in motifs:
min_score = motif.pwm_min_score()
max_score = motif.pwm_max_score()
opt_score = s.threshold[motif.id]
if opt_score is None:
opt_score = motif.pwm_max_score()
threshold = (opt_score - min_score) / (max_score - min_score)
print("{0}\t{1}\t{2}".format(motif.id, opt_score, threshold))
def threshold(args):
"""Calculate motif score threshold for a given FPR."""
if args.fpr < 0 or args.fpr > 1:
print("Please specify a FPR between 0 and 1")
sys.exit(1)
motifs = read_motifs(args.pwmfile)
s = Scanner()
s.set_motifs(args.pwmfile)
s.set_threshold(args.fpr, filename=args.inputfile)
print("Motif\tScore\tCutoff")
for motif in motifs:
min_score = motif.pwm_min_score()
max_score = motif.pwm_max_score()
opt_score = s.threshold[motif.id]
if opt_score is None:
opt_score = motif.pwm_max_score()
threshold = (opt_score - min_score) / (max_score - min_score)
print("{0}\t{1}\t{2}".format(
motif.id, opt_score, threshold))
def scan(self, background_length=200, fpr=0.02, n_cpus=-1, verbose=True):
"""
Scan DNA sequences searching for TF binding motifs.
Args:
background_length (int): background length. This is used for the calculation of the binding score.
fpr (float): False positive rate for motif identification.
n_cpus (int): number of CPUs for parallel calculation.
verbose (bool): Whether to show a progress bar.
"""
self.fpr = fpr
self.background_length = background_length
print("initiating scanner ...")
## 1. initialilze scanner ##
# load motif
motifs = default_motifs()
# initialize scanner
s = Scanner(ncpus=n_cpus)
# set parameters
s.set_motifs(motifs)
s.set_background(genome=self.ref_genome, length=background_length)
#s.set_background(genome="mm9", length=400)
s.set_threshold(fpr=fpr)
## 2. motif scan ##
print("getting DNA sequences ...")
target_sequences = peak2fasta(self.all_peaks, self.ref_genome)
print("scanning motifs ...")
self.scanned_df = scan_dna_for_motifs(s, motifs, target_sequences,
verbose)
self.__addLog("scanMotifs")
def scan_to_table(
input_table, genome, scoring, pfmfile=None, ncpus=None, zscore=True, gc=True
):
"""Scan regions in input table with motifs.
Parameters
----------
input_table : str
Filename of input table. Can be either a text-separated tab file or a
feather file.
genome : str
Genome name. Can be either the name of a FASTA-formatted file or a
genomepy genome name.
scoring : str
"count" or "score"
pfmfile : str, optional
Specify a PFM file for scanning.
ncpus : int, optional
If defined this specifies the number of cores to use.
Returns
-------
table : pandas.DataFrame
DataFrame with motif ids as column names and regions as index. Values
are either counts or scores depending on the 'scoring' parameter.s
"""
config = MotifConfig()
if pfmfile is None:
pfmfile = config.get_default_params().get("motif_db", None)
if pfmfile is not None:
pfmfile = os.path.join(config.get_motif_dir(), pfmfile)
if pfmfile is None:
raise ValueError("no pfmfile given and no default database specified")
logger.info("reading table")
if input_table.endswith("feather"):
df = pd.read_feather(input_table)
idx = df.iloc[:, 0].values
else:
df = pd.read_table(input_table, index_col=0, comment="#")
idx = df.index
regions = list(idx)
if len(regions) >= 1000:
check_regions = np.random.choice(regions, size=1000, replace=False)
else:
check_regions = regions
size = int(
np.median([len(seq) for seq in as_fasta(check_regions, genome=genome).seqs])
)
s = Scanner(ncpus=ncpus)
s.set_motifs(pfmfile)
s.set_genome(genome)
s.set_background(genome=genome, gc=gc, size=size)
scores = []
if scoring == "count":
logger.info("setting threshold")
s.set_threshold(fpr=FPR)
logger.info("creating count table")
for row in s.count(regions):
scores.append(row)
logger.info("done")
else:
s.set_threshold(threshold=0.0)
msg = "creating score table"
if zscore:
msg += " (z-score"
if gc:
msg += ", GC%"
msg += ")"
else:
msg += " (logodds)"
logger.info(msg)
for row in s.best_score(regions, zscore=zscore, gc=gc):
scores.append(row)
logger.info("done")
motif_names = [m.id for m in read_motifs(pfmfile)]
logger.info("creating dataframe")
return pd.DataFrame(scores, index=idx, columns=motif_names)
def diff(args):
infiles = args.inputfiles.split(",")
bgfile = args.bgfile
outfile = args.outputfile
pwmfile = args.pwmfile
cutoff = args.cutoff
genome = args.genome
minenr = float(args.minenr)
minfreq = float(args.minfreq)
tmpdir = mkdtemp()
# Retrieve FASTA clusters from BED file
if len(infiles) == 1 and infiles[0].endswith("bed"):
if not args.genome:
sys.stderr.write("Can't convert BED file without genome!\n")
sys.exit(1)
clusters = {}
for line in open(infiles[0]):
vals = line.strip().split("\t")
clusters.setdefault(vals[4], []).append(vals[:3])
infiles = []
for cluster, regions in clusters.items():
sys.stderr.write("Creating FASTA file for {0}\n".format(cluster))
inbed = os.path.join(tmpdir, "{0}.bed".format(cluster))
outfa = os.path.join(tmpdir, "{0}.fa".format(cluster))
with open(inbed, "w") as f:
for vals in regions:
f.write("{0}\t{1}\t{2}\n".format(*vals))
Genome(genome).track2fasta(inbed, outfa)
infiles.append(outfa)
pwms = dict([(m.id, m) for m in pwmfile_to_motifs(pwmfile)])
motifs = [m for m in pwms.keys()]
names = [os.path.basename(os.path.splitext(fname)[0]) for fname in infiles]
s = Scanner()
s.set_motifs(pwmfile)
s.set_threshold(threshold=cutoff)
# Get background frequencies
nbg = float(len(Fasta(bgfile).seqs))
bgcounts = s.total_count(bgfile, nreport=1)
bgfreq = [(c + 0.01) / nbg for c in bgcounts]
# Get frequences in input files
freq = {}
counts = {}
for fname in infiles:
mcounts = s.total_count(fname, nreport=1)
n = float(len(Fasta(fname).seqs))
counts[fname] = mcounts
freq[fname] = [(c + 0.01) / n for c in mcounts]
freq = np.array([freq[fname] for fname in infiles]).transpose()
counts = np.array([counts[fname] for fname in infiles]).transpose()
#for row in freq:
# print freq
diff_plot(motifs,
pwms,
names,
freq,
counts,
bgfreq,
bgcounts,
outfile,
minenr=minenr,
minfreq=minfreq)
shutil.rmtree(tmpdir)
def diff(args):
infiles = args.inputfiles.split(",")
bgfile = args.bgfile
outfile = args.outputfile
pwmfile = args.pwmfile
cutoff = args.cutoff
genome = args.genome
minenr = float(args.minenr)
minfreq = float(args.minfreq)
tmpdir = mkdtemp()
# Retrieve FASTA clusters from BED file
if len(infiles) == 1 and infiles[0].endswith("bed"):
if not args.genome:
sys.stderr.write("Can't convert BED file without genome!\n")
sys.exit(1)
clusters = {}
for line in open(infiles[0]):
vals = line.strip().split("\t")
clusters.setdefault(vals[4], []).append(vals[:3])
infiles = []
for cluster,regions in clusters.items():
sys.stderr.write("Creating FASTA file for {0}\n".format(cluster))
inbed = os.path.join(tmpdir, "{0}.bed".format(cluster))
outfa = os.path.join(tmpdir, "{0}.fa".format(cluster))
with open(inbed, "w") as f:
for vals in regions:
f.write("{0}\t{1}\t{2}\n".format(*vals))
Genome(genome).track2fasta(inbed, outfa)
infiles.append(outfa)
pwms = dict([(m.id, m) for m in pwmfile_to_motifs(pwmfile)])
motifs = [m for m in pwms.keys()]
names = [os.path.basename(os.path.splitext(fname)[0]) for fname in infiles]
s = Scanner()
s.set_motifs(pwmfile)
s.set_threshold(threshold=cutoff)
# Get background frequencies
nbg = float(len(Fasta(bgfile).seqs))
bgcounts = s.total_count(bgfile, nreport=1)
bgfreq = [(c + 0.01) / nbg for c in bgcounts]
# Get frequences in input files
freq = {}
counts = {}
for fname in infiles:
mcounts = s.total_count(fname, nreport=1)
n = float(len(Fasta(fname).seqs))
counts[fname] = mcounts
freq[fname] = [(c + 0.01) / n for c in mcounts]
freq = np.array([freq[fname] for fname in infiles]).transpose()
counts = np.array([counts[fname] for fname in infiles]).transpose()
#for row in freq:
# print freq
diff_plot(motifs, pwms, names, freq, counts, bgfreq, bgcounts, outfile, minenr=minenr, minfreq=minfreq)
shutil.rmtree(tmpdir)
def moap(inputfile,
method="hypergeom",
scoring=None,
outfile=None,
motiffile=None,
pwmfile=None,
genome=None,
fpr=0.01,
ncpus=None,
subsample=None):
"""Run a single motif activity prediction algorithm.
Parameters
----------
inputfile : str
:1File with regions (chr:start-end) in first column and either cluster
name in second column or a table with values.
method : str, optional
Motif activity method to use. Any of 'hypergeom', 'lasso',
'lightningclassification', 'lightningregressor', 'bayesianridge',
'rf', 'xgboost'. Default is 'hypergeom'.
scoring: str, optional
Either 'score' or 'count'
outfile : str, optional
Name of outputfile to save the fitted activity values.
motiffile : str, optional
Table with motif scan results. First column should be exactly the same
regions as in the inputfile.
pwmfile : str, optional
File with motifs in pwm format. Required when motiffile is not
supplied.
genome : str, optional
Genome name, as indexed by gimme. Required when motiffile is not
supplied
fpr : float, optional
FPR for motif scanning
ncpus : int, optional
Number of threads to use. Default is the number specified in the config.
Returns
-------
pandas DataFrame with motif activity
"""
if scoring and scoring not in ['score', 'count']:
raise ValueError("valid values are 'score' and 'count'")
config = MotifConfig()
if inputfile.endswith("feather"):
df = pd.read_feather(inputfile)
df = df.set_index(df.columns[0])
else:
# read data
df = pd.read_table(inputfile, index_col=0, comment="#")
clf = Moap.create(method, ncpus=ncpus)
if clf.ptype == "classification":
if df.shape[1] != 1:
raise ValueError("1 column expected for {}".format(method))
else:
if np.dtype('object') in set(df.dtypes):
raise ValueError(
"columns should all be numeric for {}".format(method))
if motiffile is None:
if genome is None:
raise ValueError("need a genome")
pwmfile = pwmfile_location(pwmfile)
try:
motifs = read_motifs(pwmfile)
except:
sys.stderr.write("can't read motifs from {}".format(pwmfile))
raise
# initialize scanner
s = Scanner(ncpus=ncpus)
sys.stderr.write(pwmfile + "\n")
s.set_motifs(pwmfile)
s.set_genome(genome)
s.set_background(genome=genome)
# scan for motifs
sys.stderr.write("scanning for motifs\n")
motif_names = [m.id for m in read_motifs(pwmfile)]
scores = []
if method == 'classic' or scoring == "count":
s.set_threshold(fpr=fpr)
for row in s.count(list(df.index)):
scores.append(row)
else:
for row in s.best_score(list(df.index), normalize=True):
scores.append(row)
motifs = pd.DataFrame(scores, index=df.index, columns=motif_names)
else:
motifs = pd.read_table(motiffile, index_col=0, comment="#")
if outfile and os.path.exists(outfile):
out = pd.read_table(outfile, index_col=0, comment="#")
ncols = df.shape[1]
if ncols == 1:
ncols = len(df.iloc[:, 0].unique())
if out.shape[0] == motifs.shape[1] and out.shape[1] == ncols:
logger.warn("%s output already exists... skipping", method)
return out
if subsample is not None:
n = int(subsample * df.shape[0])
logger.debug("Subsampling %d regions", n)
df = df.sample(n)
motifs = motifs.loc[df.index]
if method == "lightningregressor":
outdir = os.path.dirname(outfile)
tmpname = os.path.join(outdir, ".lightning.tmp")
clf.fit(motifs, df, tmpdir=tmpname)
shutil.rmtree(tmpname)
else:
clf.fit(motifs, df)
if outfile:
with open(outfile, "w") as f:
f.write(
"# maelstrom - GimmeMotifs version {}\n".format(__version__))
f.write("# method: {} with motif {}\n".format(method, scoring))
if genome:
f.write("# genome: {}\n".format(genome))
if motiffile:
f.write("# motif table: {}\n".format(motiffile))
f.write("# {}\n".format(clf.act_description))
with open(outfile, "a") as f:
clf.act_.to_csv(f, sep="\t")
return clf.act_
def scan_to_table(input_table, genome, scoring, pwmfile=None, ncpus=None):
"""Scan regions in input table with motifs.
Parameters
----------
input_table : str
Filename of input table. Can be either a text-separated tab file or a
feather file.
genome : str
Genome name. Can be either the name of a FASTA-formatted file or a
genomepy genome name.
scoring : str
"count" or "score"
pwmfile : str, optional
Specify a PFM file for scanning.
ncpus : int, optional
If defined this specifies the number of cores to use.
Returns
-------
table : pandas.DataFrame
DataFrame with motif ids as column names and regions as index. Values
are either counts or scores depending on the 'scoring' parameter.s
"""
config = MotifConfig()
if pwmfile is None:
pwmfile = config.get_default_params().get("motif_db", None)
if pwmfile is not None:
pwmfile = os.path.join(config.get_motif_dir(), pwmfile)
if pwmfile is None:
raise ValueError("no pwmfile given and no default database specified")
logger.info("reading table")
if input_table.endswith("feather"):
df = pd.read_feather(input_table)
idx = df.iloc[:,0].values
else:
df = pd.read_table(input_table, index_col=0, comment="#")
idx = df.index
regions = list(idx)
s = Scanner(ncpus=ncpus)
s.set_motifs(pwmfile)
s.set_genome(genome)
s.set_background(genome=genome)
nregions = len(regions)
scores = []
if scoring == "count":
logger.info("setting threshold")
s.set_threshold(fpr=FPR)
logger.info("creating count table")
for row in s.count(regions):
scores.append(row)
logger.info("done")
else:
s.set_threshold(threshold=0.0)
logger.info("creating score table")
for row in s.best_score(regions, normalize=True):
scores.append(row)
logger.info("done")
motif_names = [m.id for m in read_motifs(pwmfile)]
logger.info("creating dataframe")
return pd.DataFrame(scores, index=idx, columns=motif_names)
def scan(self,
background_length=200,
fpr=0.02,
n_cpus=-1,
verbose=True,
motifs=None,
TF_evidence_level="direct_and_indirect",
TF_formatting="auto"):
"""
Scan DNA sequences searching for TF binding motifs.
Args:
background_length (int): background length. This is used for the calculation of the binding score.
fpr (float): False positive rate for motif identification.
n_cpus (int): number of CPUs for parallel calculation.
verbose (bool): Whether to show a progress bar.
motifs (list): a list of gimmemotifs motifs, will revert to default_motifs() if None
TF_evidence_level (str): Please select one from ["direct", "direct_and_indirect"]. If "direct" is selected, TFs that have a binding evidence were used.
If "direct_and_indirect" is selected, TFs with binding evidence and inferred TFs are used.
For more information, please read explanation of Motif class in gimmemotifs documentation (https://gimmemotifs.readthedocs.io/en/master/index.html)
"""
self.fpr = fpr
self.background_length = background_length
## 1. initialilze scanner ##
# load motif
if motifs is None:
if verbose:
print(
"No motif data entered. Loading default motifs for your species ..."
)
if self.species in [
"Mouse", "Human", "Rat"
]: # If species is vertebrate, we use gimmemotif default motifs as a default.
motifs = default_motifs()
self.motif_db_name = "gimme.vertebrate.v5.0"
self.TF_formatting = True
if verbose:
print(
" Default motif for vertebrate: gimme.vertebrate.v5.0. \n For more information, please go https://gimmemotifs.readthedocs.io/en/master/overview.html \n"
)
elif self.species in [
"Zebrafish"
]: # If species is Zebrafish, we use CisBP database.
self.motif_db_name = 'CisBP_ver2_Danio_rerio.pfm'
motifs = load_motifs(self.motif_db_name)
self.TF_formatting = False
if verbose:
print(
f" Default motif for {self.species}: {self.motif_db_name}. \n For more information, please go celloracle documentation. \n"
)
elif self.species in [
"S.cerevisiae"
]: # If species is S.cerevisiae, we use CisBP database.
self.motif_db_name = 'CisBP_ver2_Saccharomyces_cerevisiae.pfm'
motifs = load_motifs(self.motif_db_name)
self.TF_formatting = False
if verbose:
print(
f" Default motif for {self.species}: {self.motif_db_name}. \n For more information, please go celloracle documentation. \n"
)
elif self.species in [
"Xenopus"
]: # If species is S.cerevisiae, we use CisBP database.
self.motif_db_name = 'CisBP_ver2_Xenopus_tropicalis_and_Xenopus_laevis.pfm'
motifs = load_motifs(self.motif_db_name)
self.TF_formatting = False
if verbose:
print(
f" Default motif for {self.species}: {self.motif_db_name}. \n For more information, please go celloracle documentation. \n"
)
elif self.species in [
"Drosophila"
]: # If species is S.cerevisiae, we use CisBP database.
self.motif_db_name = 'CisBP_ver2_Drosophila_mix.pfm'
motifs = load_motifs(self.motif_db_name)
self.TF_formatting = False
if verbose:
print(
f" Default motif for {self.species}: {self.motif_db_name}. \n For more information, please go celloracle documentation. \n"
)
elif self.species in [
"C.elegans"
]: # If species is S.cerevisiae, we use CisBP database.
self.motif_db_name = 'CisBP_ver2_Caenorhabditis_elegans.pfm'
motifs = load_motifs(self.motif_db_name)
self.TF_formatting = False
if verbose:
print(
f" Default motif for {self.species}: {self.motif_db_name}. \n For more information, please go celloracle documentation. \n"
)
elif self.species in [
"Arabidopsis"
]: # If species is S.cerevisiae, we use CisBP database.
self.motif_db_name = 'CisBP_ver2_Arabidopsis_thaliana.pfm'
motifs = load_motifs(self.motif_db_name)
self.TF_formatting = False
if verbose:
print(
f" Default motif for {self.species}: {self.motif_db_name}. \n For more information, please go celloracle documentation. \n"
)
else:
raise ValueError(
f"We have no default motifs for your species, {self.species}. Please set motifs."
)
else:
# Check format
if isinstance(motifs, list):
if isinstance(motifs[0], Motif):
if verbose:
print(
"Checking your motifs... Motifs format looks good. \n"
)
else:
raise ValueError(f"Motif data type was invalid.")
else:
raise ValueError(
f"motifs should be a list of Motif object in gimmemotifs.")
self.motif_db_name = "custom_motifs"
if TF_formatting == "auto":
self.TF_formatting = False
else:
self.TF_formatting = TF_formatting
self.motifs = motifs
self.dic_motif2TFs = _get_dic_motif2TFs(
species=self.species,
motifs=motifs,
TF_evidence_level=TF_evidence_level,
formatting=self.TF_formatting)
self.TF_evidence_level = TF_evidence_level
# initialize scanner
if verbose:
print("Initiating scanner... \n")
s = Scanner(ncpus=n_cpus)
# set parameters
s.set_motifs(motifs)
try:
s.set_background(
genome=self.ref_genome,
size=background_length) # For gimmemotifs ver 14.4
except:
s.set_background(
genome=self.ref_genome,
length=background_length) # For old gimmemotifs ver 13
#s.set_background(genome="mm9", length=400)
if verbose:
print(
"Calculating FPR-based threshold. This step may take substantial time when you load a new ref-genome. It will be done quicker on the second time. \n"
)
s.set_threshold(fpr=fpr)
## 2. motif scan ##
print("Convert peak info into DNA sequences ... \n")
# Get DNA sequences
target_sequences = peak2fasta(self.all_peaks, self.ref_genome)
# Remove DNA sequence with zero length
target_sequences = remove_zero_seq(fasta_object=target_sequences)
print(
"Scanning motifs ... It may take several hours if you proccess many peaks. \n"
)
self.scanned_df = scan_dna_for_motifs(s, motifs, target_sequences,
verbose)
self.__addLog("scanMotifs")
