#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Tools.MultipleAlignment import GUIDANCE2
from RouToolPa.Routines import FileRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input", action="store", dest="input", required=True,
type=lambda x: FileRoutines.make_list_of_path_to_files(x.split(",")),
help="Comma-separated list of files or directory with files containing sequences to be aligned")
parser.add_argument("-p", "--processes", action="store", dest="processes", type=int, default=1,
help="Number of simultaneously running alignments")
parser.add_argument("-o", "--output_directory", action="store", dest="output",
type=FileRoutines.check_path,
required=True,
help="Output directory")
parser.add_argument("-d", "--handling_mode", action="store", dest="handling_mode", default="local",
help="Handling mode. Allowed: local(default), slurm")
parser.add_argument("-j", "--slurm_job_name", action="store", dest="slurm_job_name", default="JOB",
help="Slurm job name. Default: JOB")
parser.add_argument("-m", "--slurm_max_jobs", action="store", dest="slurm_max_jobs", default=1000, type=int,
help="Slurm max jobs. Default: 1000")
parser.add_argument("-y", "--slurm_log_prefix", action="store", dest="slurm_log_prefix",
help="Slurm log prefix. ")
parser.add_argument("-z", "--slurm_cmd_log_file", action="store", dest="slurm_cmd_log_file",
help="Slurm cmd logfile")
parser.add_argument("-l", "--slurm_error_log_prefix", action="store", dest="slurm_error_log_prefix",
help="Slurm error log prefix")
parser.add_argument("-e", "--max_memory_per_task", action="store", dest="max_memory_per_task", default="5000",
#!/usr/bin/env python
import os
from Bio import SeqIO
from RouToolPa.Routines import FileRoutines
workdir = "/home/mahajrod/Genetics/Projects/nxf/nxf_arthropoda/"
data_dir = "/home/mahajrod/Genetics/Projects/nxf/nxf_arthropoda/data/"
os.chdir(workdir)
data_files = FileRoutines.make_list_of_path_to_files([data_dir])
record_dict = SeqIO.index_db("tmp.idx", data_files, format="genbank")
print("#organism\ttaxonomy\tregion_id\ttranscript_id\tproduct\texon_len")
for record_id in record_dict:
for feature in record_dict[record_id].features:
if feature.type == "mRNA":
mRNA_string = ""
mRNA_string += "%s" % record_dict[record_id].annotations["organism"]
mRNA_string += "\t%s" % (";".join(
record_dict[record_id].annotations["taxonomy"]))
mRNA_string += "\t%s" % record_id
mRNA_string += "\t%s" % (feature.qualifiers["transcript_id"][0]
if "transcript_id" in feature.qualifiers
else ".")
mRNA_string += "\t%s" % (feature.qualifiers["product"][0] if
"product" in feature.qualifiers else ".")
location_lenths = []
"--output",
action="store",
dest="output",
required=True,
help="File to write clusters with single-copy clusters")
parser.add_argument(
"-p",
"--label position",
action="store",
dest="label_position",
default="first",
help="Position of label. Allowed - first, last. Default - first")
parser.add_argument("-s",
"--separator",
action="store",
dest="separator",
default="@",
help="Separator to use. default - '@'")
args = parser.parse_args()
list_of_cluster_files = FileRoutines.make_list_of_path_to_files(args.input)
single_copy_clusters = SequenceClusterRoutines.extract_single_copy_clusters_from_files(
list_of_cluster_files,
args.output,
label_elements=args.label,
separator=args.separator,
label_position=args.label_position)
print("Was found %i single-copy clusters" % len(single_copy_clusters))
def make_list_of_path_to_files_from_comma_sep_string(string):
return FileRoutines.make_list_of_path_to_files(string.split(","))
type=float,
help="Maximum number of iterations")
parser.add_argument("-f",
"--offset",
action="store",
dest="offset",
type=float,
help="Offset (works like gap extension penalty)")
parser.add_argument("-g",
"--gap_open_penalty",
action="store",
dest="gap_open_penalty",
type=float,
help="Gap open penalty")
args = parser.parse_args()
FileRoutines.safe_mkdir(args.output)
MAFFT.threads = args.threads
MAFFT.parallel_align(FileRoutines.make_list_of_path_to_files(args.input),
args.output,
output_suffix="alignment",
gap_open_penalty=args.gap_open_penalty,
offset=args.offset,
maxiterate=args.maxiterate,
quiet=args.quiet,
mode=args.mode,
number_of_processes=args.processes,
anysymbol=True)
