def seq_header_to_chr(header): import re c = re.compile(r'\[segment (1|2)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['1', '2']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/human_picobirnavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/anhanga.fasta.gz", relative=True) sys.modules[__name__] = ds
from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/fugong/")): ds.add_fasta_path("data/fugong/" + f, relative=True) sys.modules[__name__] = ds
import sys from catch.datasets import GenomesDatasetMultiChrom def seq_header_to_chr(header): import re c = re.compile(r'\[segment (1|10|11|12|2|3|4|5|6|7|8|9)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['1', '10', '11', '12', '2', '3', '4', '5', '6', '7', '8', '9']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/colorado_tick_fever.fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/capim_orthobunyavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/tete/")): ds.add_fasta_path("data/tete/" + f, relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/bhanja.fasta.gz", relative=True) sys.modules[__name__] = ds
import sys from catch.datasets import GenomesDatasetMultiChrom def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/serra_do_navio_mammarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/mobala_mammarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/guaroa/")): ds.add_fasta_path("data/guaroa/" + f, relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (1|2|3|4|5|6)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['1', '2', '3', '4', '5', '6']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/thogoto_thogotovirus.fasta.gz", relative=True) sys.modules[__name__] = ds
import sys from catch.datasets import GenomesDatasetMultiChrom def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/flexal_mammarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/sathuperi_orthobunyavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/guanarito_mammarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
from os.path import join from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/bruges/")): ds.add_fasta_path("data/bruges/" + f, relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/thailand_orthohantavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/california_reptarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
c = re.compile(r'\[segment (1|2|3|4|5|6|7|8)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['1', '2', '3', '4', '5', '6', '7', '8'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) return m.group(1) ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) for seg in ['1', '2', '3', '4', '5', '6', '7', '8']: ds.add_fasta_path("data/influenza_a_segment" + seg + ".fasta.gz", relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/ryukyu_mammarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
import re c = re.compile(r'\[segment (1|10|11|2|3|4|5|6|7|8|9)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = [ "segment_" + seg for seg in ['1', '10', '11', '2', '3', '4', '5', '6', '7', '8', '9'] ] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/rotavirus_g.fasta.gz", relative=True) sys.modules[__name__] = ds
from os.path import join from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/thottapalayam/")): ds.add_fasta_path("data/thottapalayam/" + f, relative=True) sys.modules[__name__] = ds
__author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) return m.group(1) ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/rift_valley_fever.fasta", relative=True) sys.modules[__name__] = ds
from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/chapare/")): ds.add_fasta_path("data/chapare/" + f, relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/imjin_orthohantavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/shamonda/")): ds.add_fasta_path("data/shamonda/" + f, relative=True) sys.modules[__name__] = ds
import sys from catch.datasets import GenomesDatasetMultiChrom def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/arumowot.fasta.gz", relative=True) sys.modules[__name__] = ds
import sys from catch.datasets import GenomesDatasetMultiChrom def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/whitewater_arroyo_mammarenavirus.fasta.gz", relative=True) sys.modules[__name__] = ds
import sys from catch.datasets import GenomesDatasetMultiChrom def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise Exception("Unknown or invalid segment in header %s" % header) seg = m.group(1) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) if not m: raise Exception("Unknown genome in header %s" % header) return m.group(1) chrs = ["segment_" + seg for seg in ['L', 'M', 'S']] ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/ambe.fasta.gz", relative=True) sys.modules[__name__] = ds
from os import listdir import sys from catch.datasets import GenomesDatasetMultiChrom __author__ = 'Hayden Metsky <*****@*****.**>' chrs = ["segment_" + seg for seg in ['L', 'S']] def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr) for f in listdir(join(dirname(__file__), "data/pirital/")): ds.add_fasta_path("data/pirital/" + f, relative=True) sys.modules[__name__] = ds
def seq_header_to_chr(header): import re c = re.compile(r'\[segment (L|M|S)\]') m = c.search(header) if not m: raise ValueError("Unknown segment in header %s" % header) seg = m.group(1) valid_segs = ['L', 'M', 'S'] if seg not in valid_segs: raise ValueError("Unknown segment %s" % seg) return "segment_" + seg def seq_header_to_genome(header): import re c = re.compile(r'\[genome (.+)\]') m = c.search(header) return m.group(1) ds = GenomesDatasetMultiChrom(__name__, __file__, __spec__, chrs, seq_header_to_chr, seq_header_to_genome=seq_header_to_genome) ds.add_fasta_path("data/seoul.fasta", relative=True) sys.modules[__name__] = ds