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 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 moap(
inputfile,
method="hypergeom",
scoring=None,
outfile=None,
motiffile=None,
pfmfile=None,
genome=None,
fpr=0.01,
ncpus=None,
subsample=None,
zscore=True,
gc=True,
):
"""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.
pfmfile : 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.
zscore : bool, optional
Use z-score normalized motif scores.
gc : bool optional
Use GC% bins for z-score.
Returns
-------
pandas DataFrame with motif activity
"""
if scoring and scoring not in ["score", "count"]:
raise ValueError("valid values are 'score' and 'count'")
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")
pfmfile = pfmfile_location(pfmfile)
try:
motifs = read_motifs(pfmfile)
except Exception:
sys.stderr.write("can't read motifs from {}".format(pfmfile))
raise
# initialize scanner
s = Scanner(ncpus=ncpus)
s.set_motifs(pfmfile)
s.set_genome(genome)
s.set_background(genome=genome)
# scan for motifs
motif_names = [m.id for m in read_motifs(pfmfile)]
scores = []
if method == "classic" or scoring == "count":
logger.info("motif scanning (scores)")
scores = scan_to_table(
inputfile,
genome,
"count",
pfmfile=pfmfile,
ncpus=ncpus,
zscore=zscore,
gc=gc,
)
else:
logger.info("motif scanning (scores)")
scores = scan_to_table(
inputfile,
genome,
"score",
pfmfile=pfmfile,
ncpus=ncpus,
zscore=zscore,
gc=gc,
)
motifs = pd.DataFrame(scores, index=df.index, columns=motif_names)
elif isinstance(motiffile, pd.DataFrame):
motifs = motiffile
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 isinstance(motiffile, str):
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, 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 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")
