action="store",
dest="output_cluster_file",
required=True,
help="File to write clusters with renamed elements")
parser.add_argument(
"-a",
"--elements_without_synonyms_file",
action="store",
dest="elements_without_synonyms_file",
help="File to write cluster elements without synonyms. Default: don't write"
)
parser.add_argument(
"-r",
"--remove_clusters_with_not_renamed_elements",
action="store_true",
dest="remove_clusters_with_not_renamed_elements",
help="Remove clusters with not renamed elements. Default: false ")
args = parser.parse_args()
SequenceClusterRoutines.rename_elements_in_clusters(
args.input_cluster_file,
args.syn_file,
args.output_cluster_file,
remove_clusters_with_not_renamed_elements=args.
remove_clusters_with_not_renamed_elements,
syn_file_key_column_index=args.key_column_index,
syn_file_value_column_index=args.value_column_index,
syn_file_column_separator=args.column_separator,
elements_with_absent_synonyms_file=args.elements_without_synonyms_file)
dest="separator",
default="@",
help="Separator to use. default - '@'")
parser.add_argument("-k",
"--key_column_index",
action="store",
dest="key_column_index",
type=int,
default=0,
help="Index of key column in synonym file. Default: 0")
parser.add_argument("-v",
"--value_column_index",
action="store",
dest="value_column_index",
type=int,
default=1,
help="Index of value column in synonym file.Default: 1")
args = parser.parse_args()
label = args.label if args.label else FileRoutines.split_filename(
args.cluster_file)[1]
SequenceClusterRoutines.label_cluster_elements_from_file(
args.cluster_file,
label,
args.output,
separator=args.separator,
label_position=args.label_position,
key_index=args.key_column_index,
value_index=args.value_column_index)
dest="label_ids",
help="Label ids by species names. Default - don't label")
parser.add_argument("-g",
"--separator_for_labeling",
action="store",
dest="separator_for_labeling",
default="@",
help="Separator to use for labeling. Default - '@'")
parser.add_argument("-r",
"--label_last",
action="store_false",
dest="label_first",
default=True,
help="Place label at the end of id")
args = parser.parse_args()
FileRoutines.safe_mkdir(args.output_dir)
SequenceClusterRoutines.extract_sequences_by_clusters(
args.input_cluster_dir,
args.input_seq_dir,
args.output_dir,
file_with_white_list_cluster_ids=args.white_list_ids,
mode=args.mode,
sequence_file_extension=args.seq_extension,
sequence_file_format=args.format,
label_species=args.label_ids,
separator_for_labeling=args.separator_for_labeling,
species_label_first=args.label_first)
parser.add_argument(
"-a",
"--output_label position",
action="store",
dest="output_label_position",
default="first",
help=
"Position of label in output file. Allowed - first, last. Default - first")
parser.add_argument(
"-r",
"--output_separator",
action="store",
dest="output_separator",
default="@",
help="Separator between label and element id in output file. Default - '@'"
)
args = parser.parse_args()
label = args.label if args.label else FileRoutines.split_filename(
args.cluster_file)[1]
SequenceClusterRoutines.replace_label_from_file(
args.input_file,
args.output_file,
args.syn_file,
old_separator=args.input_separator,
old_label_position=args.input_label_position,
new_separator=args.output_separator,
new_label_position=args.output_label_position)
"--output",
action="store",
dest="output",
required=True,
help="File to write extracted clusters")
parser.add_argument("-c",
"--id_column_index",
action="store",
dest="id_column_index",
type=int,
help="Index(0-based) of id column in id file. ")
parser.add_argument(
"-m",
"--mode",
action="store",
dest="mode",
default="w",
help=
"extraction mode. Allowed - 'w' - if elements from element_id_list are present "
"in cluster extracts only that elements; 'a' - if elements from element_id_list are present "
"in cluster extracts all elements. Default - 'w'")
args = parser.parse_args()
SequenceClusterRoutines.extract_clusters_by_element_ids_from_file(
args.cluster_file,
args.element_file,
args.output,
mode=args.mode,
id_column=args.id_column_index)
"--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))
action="store",
dest="cluster_file",
required=True,
help="File with clusters")
parser.add_argument("-d",
"--black_list_file",
action="store",
dest="black_list_file",
required=True,
help="File with ids of elements")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="File to write extracted clusters")
parser.add_argument(
"-m",
"--mode",
action="store",
dest="mode",
default="full",
help="Element id comparison mode. Allowed: partial, full(comparison)")
args = parser.parse_args()
SequenceClusterRoutines.remove_elements_by_ids_from_files(args.cluster_file,
args.output,
args.black_list_file,
mode=args.mode)
parser.add_argument("-s",
"--species-gene_fam_file",
action="store",
dest="species_gene_fam_file",
required=True,
help="Input species-gene fam file")
parser.add_argument("-g",
"--gene-GO_fam_file",
action="store",
dest="gene_GO_fam_file",
required=True,
help="Input gene-GO fam file")
#parser.add_argument("-c", "--cluster_column_index", action="store", dest="cluster_column_index", type=int, default=0,
# help="Index of cluster column in synonym file. Default: 0")
#parser.add_argument("-v", "--element_column_index", action="store", dest="element_column_index", type=int, default=1,
# help="Index of element column in synonym file.Default: 1")
#parser.add_argument("-e", "--separator", action="store", dest="column_separator", default='\t',
# help="Column separator in synonym file. Default: \\t")
parser.add_argument("-o",
"--output_directory",
action="store",
dest="output_dir",
required=True,
help="Output directory")
args = parser.parse_args()
SequenceClusterRoutines.create_gvf_files_from_species_gene_fam_and_gene_GO_fam(
args.species_gene_fam_file, args.gene_GO_fam_file, args.output_dir)
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 - '@'")
parser.add_argument("-l",
"--label_list",
action="store",
dest="label_list",
type=lambda s: s.split(","),
help="Comma-separated list of element labels to extract")
args = parser.parse_args()
if args.label_file and args.label_list:
raise ValueError("Both --label_file and --label_list were set")
elif (not args.label_file) and (not args.label_list):
raise ValueError("Neither --label_file or --label_list was set")
SequenceClusterRoutines.extract_clusters_and_elements_by_labels_from_files(
args.input,
args.label_file if args.label_file else args.label_list,
args.output,
separator=args.separator,
label_position=args.label_position)
import argparse
from RouToolPa.Routines import SequenceClusterRoutines, FileRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_cluster_dir",
action="store",
dest="input_cluster_dir",
required=True,
type=FileRoutines.check_path,
help="Directory with files with clusters")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="File to write ids of monoclusters")
parser.add_argument("-w",
"--white_list_ids",
action="store",
dest="white_list_ids",
help="File with ids from white list. ")
args = parser.parse_args()
SequenceClusterRoutines.extract_monocluster_ids_from_file(
args.input_cluster_dir,
args.output,
file_with_white_list_ids=args.white_list_ids)
parser.add_argument("-i", "--cluster_id_file", action="store", dest="cluster_id_file",
help="File with ids of clusters to extract. Extract all clusters if not set")
parser.add_argument("-f", "--cluster_file", action="store", dest="cluster_file", required=True,
help="File with clusters")
parser.add_argument("-p", "--seq_file", action="store", dest="seq_file", required=True,
type=lambda s: FileRoutines.make_list_of_path_to_files(s.split(",")),
help="List of comma-separated files/directories with sequences")
parser.add_argument("-r", "--seq_file_format", action="store", dest="seq_file_format", default="fasta",
help="Format of file with sequences")
parser.add_argument("-c", "--create_dir_for_each_cluster", action="store_true", dest="create_dir_for_each_cluster",
help="Create separate directory for each cluster")
parser.add_argument("-o", "--output_prefix", action="store", dest="output",
help="Output prefix to use")
parser.add_argument("-d", "--output_directory", action="store", dest="out_dir", default="./",
help="Directory to write output")
parser.add_argument("-n", "--dont_skip_cluster_if_absent_element", action="store_true",
dest="dont_skip_cluster_if_absent_element", default=False,
help="Don't skip cluster with absent sequences")
args = parser.parse_args()
SequenceClusterRoutines.extract_sequences_from_selected_clusters(args.cluster_id_file, args.cluster_file,
args.seq_file, output_dir=args.out_dir,
seq_format=args.seq_file_format,
out_prefix=args.output,
create_dir_for_each_cluster=args.create_dir_for_each_cluster,
skip_cluster_if_no_sequence_for_element=not args.dont_skip_cluster_if_absent_element,
parsing_mode="parse")
parser.add_argument("-v",
"--element_column_index",
action="store",
dest="element_column_index",
type=int,
default=1,
help="Index of element column in synonym file.Default: 1")
parser.add_argument("-e",
"--separator",
action="store",
dest="column_separator",
default='\t',
help="Column separator in synonym file. Default: \\t")
parser.add_argument("-o",
"--output_directory",
action="store",
dest="output_dir",
required=True,
help="Output directory")
args = parser.parse_args()
SequenceClusterRoutines.create_per_cluster_element_id_files_from_file(
args.input_cluster_file,
args.output_dir,
cluster_column=args.cluster_column_index,
element_column=args.element_column_index,
column_separator=args.column_separator,
element_separator=",")