def __init__(self, fasta, length=None, number=None, k=1, matrix_only=False): self.k = k # Initialize super Fasta object Fasta.__init__(self) # Initialize Markov transition matrix self._initialize_matrices(fasta.seqs, k=k) if matrix_only: return c = 0 if not number: number = len(fasta) while len(self) < number: seq = choice(fasta.seqs) id = "random_Markov%s_%s" % (k,c) if length: random_seq = self._generate_sequence(length) else: random_seq = self._generate_sequence(len(seq)) self.add(id, random_seq) c += 1
def __init__(self, fasta, size=None, n=None, k=1, matrix_only=False): self.k = k # Initialize super Fasta object Fasta.__init__(self) # Initialize Markov transition matrix self._initialize_matrices(fasta.seqs, k=k) if matrix_only: return c = 0 if not n: n = len(fasta) while len(self) < n: seq = choice(fasta.seqs) name = "random_Markov%s_%s" % (k, c) if size: random_seq = self._generate_sequence(size) else: random_seq = self._generate_sequence(len(seq)) self.add(name, random_seq) c += 1
def __init__(self, matchfile, genome="hg19", number=None, size=None): # Create temporary files tmpbed = NamedTemporaryFile(dir=mytmpdir()).name tmpfasta = NamedTemporaryFile(dir=mytmpdir()).name # Create bed-file with coordinates of random sequences matched_gc_bedfile(tmpbed, matchfile, genome, number, size=size) # Convert track to fasta Genome(genome).track2fasta(tmpbed, fastafile=tmpfasta) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, fasta, length=None, multiply=10): # Initialize super Fasta object Fasta.__init__(self) # Initialize Markov transition matrix self._initialize_matrices(fasta.seqs) c = 0 for seq in fasta.seqs: for i in range(multiply): id = "random_1st_order_%s" % (c) if length: random_seq = self._generate_sequence(length) else: random_seq = self._generate_sequence(len(seq)) self.add(id, random_seq) c += 1
def __init__(self, genome, size=None, n=None): size = int(size) # Create temporary files tmpbed = NamedTemporaryFile(dir=mytmpdir()).name tmpfasta = NamedTemporaryFile(dir=mytmpdir()).name # Create bed-file with coordinates of random sequences create_random_genomic_bedfile(tmpbed, genome, size, n) # Convert track to fasta Genome(genome).track2fasta(tmpbed, fastafile=tmpfasta, stranded=True) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, bedfile, genefile, index="/usr/share/gimmemotifs/genome_index/hg18", length=None, multiply=10, match_chromosome=True): self.match_chromosome = match_chromosome # Create temporary files tmpbed = NamedTemporaryFile().name tmpfasta = NamedTemporaryFile().name # Create bed-file with coordinates of random sequences self._create_bedfile(tmpbed, bedfile, genefile, length, multiply) # Convert track to fasta track2fasta(index, tmpbed, tmpfasta) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, index="/usr/share/gimmemotifs/genome_index/hg18", length=None, n=None): length = int(length) # Create temporary files tmpbed = NamedTemporaryFile(dir=mytmpdir()).name tmpfasta = NamedTemporaryFile(dir=mytmpdir()).name # Create bed-file with coordinates of random sequences create_random_genomic_bedfile(tmpbed, index, length, n) # Convert track to fasta track2fasta(index, tmpbed, tmpfasta, use_strand=True) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, genefile, index="/usr/share/gimmemotifs/genome_index/hg18", length=None, n=None): length = int(length) # Create temporary files tmpbed = NamedTemporaryFile().name tmpfasta = NamedTemporaryFile().name # Create bed-file with coordinates of random sequences self._create_promoter_bedfile(tmpbed, genefile, length, n) # Convert track to fasta track2fasta(index, tmpbed, tmpfasta, use_strand=True) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, matchfile, genome="hg19", number=None): config = MotifConfig() index = os.path.join(config.get_index_dir(), genome) # Create temporary files tmpbed = NamedTemporaryFile(dir=mytmpdir()).name tmpfasta = NamedTemporaryFile(dir=mytmpdir()).name # Create bed-file with coordinates of random sequences matched_gc_bedfile(tmpbed, matchfile, genome, number) # Convert track to fasta track2fasta(index, tmpbed, tmpfasta) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, bedfile, genefile, index="/usr/share/gimmemotifs/genome_index/hg18", length=None, multiply=10, match_chromosome=True): self.match_chromosome = match_chromosome length = int(length) # Create temporary files tmpbed = NamedTemporaryFile().name tmpfasta = NamedTemporaryFile().name # Create bed-file with coordinates of random sequences self._create_bedfile(tmpbed, bedfile, genefile, length, multiply) # Convert track to fasta track2fasta(index, tmpbed, tmpfasta) # Initialize super Fasta object Fasta.__init__(self, tmpfasta) # Delete the temporary files os.remove(tmpbed) os.remove(tmpfasta)
def __init__(self, fasta, length=None, multiply=10, k=1, matrix_only=False): self.k = k # Initialize super Fasta object Fasta.__init__(self) # Initialize Markov transition matrix self._initialize_matrices(fasta.seqs, k=k) if matrix_only: return c = 0 for seq in fasta.seqs: for i in range(multiply): id = "random_Markov%s_%s" % (k,c) if length: random_seq = self._generate_sequence(length) else: random_seq = self._generate_sequence(len(seq)) self.add(id, random_seq) c += 1