def prepare_denovo_input_bed(inputfile, params, outdir):
"""Prepare a BED file for de novo motif prediction.
All regions to same size; split in test and validation set;
converted to FASTA.
Parameters
----------
inputfile : str
BED file with input regions.
params : dict
Dictionary with parameters.
outdir : str
Output directory to save files.
"""
logger.info("preparing input (BED)")
# Create BED file with regions of equal size
width = int(params["width"])
bedfile = os.path.join(outdir, "input.bed")
write_equalwidth_bedfile(inputfile, width, bedfile)
abs_max = int(params["abs_max"])
fraction = float(params["fraction"])
pred_bedfile = os.path.join(outdir, "prediction.bed")
val_bedfile = os.path.join(outdir, "validation.bed")
# Split input into prediction and validation set
logger.debug(
"Splitting %s into prediction set (%s) and validation set (%s)",
bedfile, pred_bedfile, val_bedfile)
divide_file(bedfile, pred_bedfile, val_bedfile, fraction, abs_max)
config = MotifConfig()
genome = Genome(params["genome"])
for infile in [pred_bedfile, val_bedfile]:
genome.track2fasta(
infile,
infile.replace(".bed", ".fa"),
)
# Create file for location plots
lwidth = int(params["lwidth"])
extend = (lwidth - width) // 2
genome.track2fasta(
val_bedfile,
os.path.join(outdir, "localization.fa"),
extend_up=extend,
extend_down=extend,
stranded=params["use_strand"],
)
def prepare_denovo_input_bed(inputfile, params, outdir):
"""Prepare a BED file for de novo motif prediction.
All regions to same size; split in test and validation set;
converted to FASTA.
Parameters
----------
inputfile : str
BED file with input regions.
params : dict
Dictionary with parameters.
outdir : str
Output directory to save files.
"""
logger.info("preparing input (BED)")
# Create BED file with regions of equal size
width = int(params["width"])
bedfile = os.path.join(outdir, "input.bed")
write_equalwidth_bedfile(inputfile, width, bedfile)
abs_max = int(params["abs_max"])
fraction = float(params["fraction"])
pred_bedfile = os.path.join(outdir, "prediction.bed")
val_bedfile = os.path.join(outdir, "validation.bed")
# Split input into prediction and validation set
logger.debug(
"Splitting %s into prediction set (%s) and validation set (%s)",
bedfile, pred_bedfile, val_bedfile)
divide_file(bedfile, pred_bedfile, val_bedfile, fraction, abs_max)
config = MotifConfig()
genome = Genome(params["genome"])
for infile in [pred_bedfile, val_bedfile]:
genome.track2fasta(
infile,
infile.replace(".bed", ".fa"),
)
# Create file for location plots
lwidth = int(params["lwidth"])
extend = (lwidth - width) // 2
genome.track2fasta(
val_bedfile,
os.path.join(outdir, "localization.fa"),
extend_up=extend,
extend_down=extend,
stranded=params["use_strand"],
)
def prepare_input_bed(self, inputfile, organism="hg18", width=200, fraction=0.2, abs_max=1000, use_strand=False):
""" Create all the bed- and fasta-files necessary for motif prediction and validation """
self.inputfile = inputfile
width = int(width)
fraction = float(fraction)
abs_max = int(abs_max)
use_strand = bool(use_strand)
self.logger.info("preparing input (BED)")
# Set all peaks to specific width
self.logger.debug("Creating inputfile %s, width %s", self.input_bed, width)
# if not self.weird:
write_equalwidth_bedfile(inputfile, width, self.input_bed)
# Split input_bed in prediction and validation set
self.logger.debug(
"Splitting %s into prediction set (%s) and validation set (%s)",
self.input_bed, self.prediction_bed, self.validation_bed)
#if not self.weird:
self.prediction_num, self.validation_num = divide_file(self.input_bed, self.prediction_bed, self.validation_bed, fraction, abs_max)
# Make fasta files
index_dir = os.path.join(self.config.get_index_dir(), organism)
self.logger.debug("Creating %s", self.prediction_fa)
genome_index.track2fasta(index_dir, self.prediction_bed, self.prediction_fa, use_strand=use_strand, ignore_missing=True)
self.logger.debug("Creating %s", self.validation_fa)
genome_index.track2fasta(index_dir, self.validation_bed, self.validation_fa, use_strand=use_strand, ignore_missing=True)
def prepare_input_bed(self,
inputfile,
organism="hg18",
width=200,
fraction=0.2,
abs_max=1000,
use_strand=False):
""" Create all the bed- and fasta-files necessary for motif prediction and validation """
self.inputfile = inputfile
width = int(width)
fraction = float(fraction)
abs_max = int(abs_max)
use_strand = bool(use_strand)
self.logger.info("preparing input (BED)")
# Set all peaks to specific width
self.logger.debug("Creating inputfile %s, width %s", self.input_bed,
width)
# if not self.weird:
write_equalwidth_bedfile(inputfile, width, self.input_bed)
# Split input_bed in prediction and validation set
self.logger.debug(
"Splitting %s into prediction set (%s) and validation set (%s)",
self.input_bed, self.prediction_bed, self.validation_bed)
#if not self.weird:
self.prediction_num, self.validation_num = divide_file(
self.input_bed, self.prediction_bed, self.validation_bed, fraction,
abs_max)
# Make fasta files
index_dir = os.path.join(self.config.get_index_dir(), organism)
self.logger.debug("Creating %s", self.prediction_fa)
genome_index.track2fasta(index_dir,
self.prediction_bed,
self.prediction_fa,
use_strand=use_strand,
ignore_missing=True)
self.logger.debug("Creating %s", self.validation_fa)
genome_index.track2fasta(index_dir,
self.validation_bed,
self.validation_fa,
use_strand=use_strand,
ignore_missing=True)