def extract_proteins_from_alignments(self, dir_with_alignments, output_dir):
out_dir = self.check_path(output_dir)
#print type(FileRoutines)
input_files = self.make_list_of_path_to_files([dir_with_alignments] if isinstance(dir_with_alignments, str) else dir_with_alignments)
self.safe_mkdir(out_dir)
from RouToolPa.Routines import MultipleAlignmentRoutines
for filename in input_files:
filename_list = self.split_filename(filename)
output_file = "%s%s%s" % (out_dir, filename_list[1], filename_list[2])
MultipleAlignmentRoutines.extract_sequences_from_alignment(filename, output_file)
args = parser.parse_args()
unique_position_dict = TwoLvlDict()
FileRoutines.safe_mkdir(args.output_dir)
for alignment_file in args.input:
alignment_name_list = FileRoutines.split_filename(alignment_file)
output_prefix = "%s/%s.unique_positions" % (args.output_dir,
alignment_name_list[1])
unique_position_dict[alignment_name_list[
1]] = MultipleAlignmentRoutines.count_unique_positions_per_sequence_from_file(
alignment_file,
output_prefix,
format=args.format,
gap_symbol="-",
return_mode="relative",
verbose=False)
species_list = unique_position_dict.sl_keys()
data_dict = OrderedDict()
for species in species_list:
data_dict[species] = []
for alignment in unique_position_dict:
data_dict[species].append(unique_position_dict[alignment][species])
data_list = [data_dict[species] for species in data_dict]
required=True,
help="Output file with protein alignment")
parser.add_argument("-f",
"--format",
action="store",
dest="format",
default="fasta",
help="Format of alignments. Default: fasta")
parser.add_argument("-g",
"--gap_symbol",
action="store",
dest="gap_symbol",
default="-",
help="Gap symbol in alignment. Default: '-'")
parser.add_argument(
"-t",
"--genetic_code",
action="store",
dest="genetic_code",
default=1,
type=int,
help="Genetic code to use(NCBI tables) . Default: 1(standart)")
args = parser.parse_args()
MultipleAlignmentRoutines.translate_codon_alignment(args.codon_alignment,
args.protein_alignment,
format=args.format,
gap_symbol=args.gap_symbol,
table=args.genetic_code)
parser.add_argument(
"-t",
"--type",
action="store",
dest="type",
default="nucleotide",
help="Alignment type. Allowed: nucleotide(default), codon, protein")
parser.add_argument(
"-l",
"--flank_length",
action="store",
dest="flank_length",
default=0,
type=int,
help=
"Flank length. Default: 0, i.e no flanks will be included in the output file"
)
args = parser.parse_args()
MultipleAlignmentRoutines.get_specific_positions(
args.input,
args.reference_sequence_id,
args.position_list,
args.output_prefix,
format=args.format,
gap_symbol=args.gap_symbol,
verbose=True,
alignment_type=args.type,
flank_length=args.flank_length)
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Routines import MultipleAlignmentRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input",
action="store",
dest="input",
required=True,
help="File with alignment")
parser.add_argument("-c",
"--coordinates",
action="store",
dest="coordinates",
required=True,
help="File with coordinates of gene alignments")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="File to write alignment prepared for Codeml")
args = parser.parse_args()
MultipleAlignmentRoutines.prepare_multigene_alignment_for_codeml(
args.input, args.coordinates, args.output, format="fasta")
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Routines import MultipleAlignmentRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input", action="store", dest="input", required=True,
help="Input file with alignment")
parser.add_argument("-o", "--output_prefix", action="store", dest="output_prefix", required=True,
help="Prefix of output files")
parser.add_argument("-f", "--format", action="store", dest="format", default="fasta",
help="Alignment format. Default: fasta")
parser.add_argument("-g", "--genetic_code_table", action="store", dest="genetic_code_table", type=int,
default=1,
help="Genetic code table number")
parser.add_argument("-r", "--remove_Ns", action="store_true", dest="remove_Ns", default=False,
help="Remove codon columns with Ns. Default:False")
args = parser.parse_args()
MultipleAlignmentRoutines.extract_degenerate_sites_from_codon_alignment_from_file(args.input, args.output_prefix,
genetic_code_table=args.genetic_code_table,
format=args.format,
remove_codon_columns_with_Ns=args.remove_Ns)
from RouToolPa.Routines import MultipleAlignmentRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input",
action="store",
dest="input",
required=True,
help="Input file with codon alignment")
parser.add_argument("-o",
"--output_prefix",
action="store",
dest="output_prefix",
required=True,
help="Prefix of output files")
parser.add_argument("-f",
"--format",
action="store",
dest="format",
default="fasta",
help="Format of thr input alignment. Default: fasta")
args = parser.parse_args()
MultipleAlignmentRoutines.extract_codon_positions_from_file(args.input,
args.output_prefix,
format=args.format)
type=lambda x: FileRoutines.make_list_of_path_to_files(x.split(",")),
help="Comma-separated list of files or directory with files "
"containing alignments(one alignment per file)")
parser.add_argument("-n", "--max_gap_number", action="store", dest="max_gap_number", default=0, type=int,
help="Maximum number of gaps to retain column")
parser.add_argument("-o", "--output_directory", action="store", dest="output", type=FileRoutines.check_path,
help="Output directory")
parser.add_argument("-g", "--gap_symbol", action="store", dest="gap_symbol", default="-",
help="Gap symbol")
parser.add_argument("-s", "--suffix", action="store", dest="suffix", default=".gaps_removed",
help="Suffix to use in output files. Default: '.gaps_removed'")
parser.add_argument("-f", "--format", action="store", dest="format", default="fasta",
help="Format of alignment")
parser.add_argument("-v", "--verbose", action="store_true", dest="verbose",
help="Print not found ids. Default - no")
args = parser.parse_args()
FileRoutines.safe_mkdir(args.output)
for alignment_file in args.input:
splited_filename = FileRoutines.split_filename(alignment_file)
if args.verbose:
print ("Handling %s ..." % alignment_file)
output_filename = "%s%s%s%s" % (args.output, splited_filename[1], args.suffix, splited_filename[2])
alignment = AlignIO.read(alignment_file, args.format)
filtered_alignment = MultipleAlignmentRoutines.remove_columns_with_gaps(alignment, args.max_gap_number,
gap_symbol=args.gap_symbol)
AlignIO.write(filtered_alignment, output_filename, args.format)
"--output_directory",
action="store",
dest="output_dir",
default="./",
help=
"Output directory to write resulting files. Default - current directory")
parser.add_argument("-f",
"--format",
action="store",
dest="format",
default="fasta",
help="Format of alignments")
parser.add_argument("-g",
"--gap_symbol",
action="store",
dest="gap_symbol",
default="-",
help="Gap symbol. Default - '-'")
args = parser.parse_args()
for alignment_file in args.input:
alignment_name_list = FileRoutines.split_filename(alignment_file)
output_file = "%s/%s.position_matrix" % (args.output_dir,
alignment_name_list[1])
MultipleAlignmentRoutines.get_position_presence_matrix_fom_file(
alignment_file,
output_file,
format=args.format,
gap_symbol=args.gap_symbol)
dest="format",
default="fasta",
help="Alignment file format. Default: fasta")
parser.add_argument(
"-a",
"--align_variants",
action="store_true",
dest="align_variants",
help="Align variants between species by coordinate. Default: False")
parser.add_argument(
"-t",
"--target_sequence_id",
action="store",
dest="target_sequence_id",
help="Target sequence id. Variants specific for this sequence will be "
"extracted into separated file. Default: not set")
args = parser.parse_args()
MultipleAlignmentRoutines.call_variants_from_multiple_alignment_from_file(
args.input,
args.output_prefix,
args.reference_sequence_id,
gap_symbol=args.gap_symbol,
verbose=True,
format="fasta",
align_variants=args.align_variants,
output_type="hgvs",
variant_separator=",",
target_sequence_id=args.target_sequence_id,
absent_symbol="")
"-t",
"--type",
action="store",
dest="type",
default="nucleotide",
help="Alignment type. Allowed: nucleotide(default), codon, protein")
parser.add_argument(
"-l",
"--flank_length",
action="store",
dest="flank_length",
default=0,
type=int,
help=
"Flank length. Default: 0, i.e no flanks will be included in the output file"
)
args = parser.parse_args()
MultipleAlignmentRoutines.get_specific_positions_for_multiple_files(
args.input_dir,
args.position_file,
args.reference_sequence_id,
args.output_dir,
alignment_file_suffix=args.alignment_file_suffix,
format=args.format,
gap_symbol=args.gap_symbol,
verbose=True,
alignment_type=args.type,
flank_length=args.flank_length)
help="Format of alignments. Default: fasta")
parser.add_argument("-n",
"--cds_seqs_format",
action="store",
dest="cds_format",
default="fasta",
help="Format of cds sequences. Default: fasta")
parser.add_argument(
"-i",
"--cds_index_file",
action="store",
dest="cds_index",
help="Biopython index of cds files. Default - construct new")
parser.add_argument(
"-r",
"--retain_cds_index",
action="store_true",
dest="retain_cds_index",
help="Retain constructed index after analysis. Default - False")
args = parser.parse_args()
MultipleAlignmentRoutines.get_codon_alignment_from_files(
args.pep_alignment,
args.cds_seqs,
args.output,
cds2protein_accordance_file=args.accordance_file,
alignment_format=args.alignment_format,
nucleotide_sequence_format=args.cds_format,
cds_index_file=args.cds_index,
retain_cds_index=args.retain_cds_index)
parser.add_argument(
"-o",
"--output_directory",
action="store",
dest="output_dir",
default="./",
help=
"Output directory to write resulting files. Default - current directory")
parser.add_argument("-f",
"--format",
action="store",
dest="format",
default="fasta",
help="Format of alignments")
parser.add_argument("-g",
"--gap_symbol",
action="store",
dest="gap_symbol",
default="-",
help="Gap symbol. Default - '-'")
args = parser.parse_args()
for alignment_file in args.input:
alignment_name_list = FileRoutines.split_filename(alignment_file)
output_prefix = "%s/%s.unique_positions" % (args.output_dir,
alignment_name_list[1])
MultipleAlignmentRoutines.count_unique_positions_per_sequence_from_file(
alignment_file, output_prefix, format=args.format, gap_symbol="-")
"--genetic_code_table",
action="store",
dest="genetic_code_table",
type=int,
default=1,
help="Genetic code table number")
parser.add_argument("-a",
"--gap_symbol_list",
action="store",
dest="gap_symbol_list",
type=lambda s: s.split(","),
default=["-"],
help="Comma-separated list of gap symbols. Default: '-'")
parser.add_argument("-b",
"--use_ambiguous_table",
action="store_true",
dest="use_ambiguous_table",
default=False,
help="Use ambiguous codon table. Default:False")
args = parser.parse_args()
MultipleAlignmentRoutines.count_dNdS_by_reference_seq_in_codon_alignment_from_file(
args.input,
args.ref_seq_id,
genetic_code_table=args.genetic_code_table,
gap_symbol_list=args.gap_symbol_list,
use_ambigious_table=args.ambigious_table,
output_file=args.output,
format="fasta")
"""
def expression_hsp(hsp):
# hit_span - length of hit for single-fragment HSP(blast etc). DO NOT work with exonerate
return (hsp.evalue <= args.max_e_value) and (hsp.hit_span >= args.min_alignment_length)
def iterator(blast_results):
for query_id in blast_results:
filtered_query = blast_results[query_id].hsp_filter(func=expression_hsp)
if filtered_query:
yield filtered_query
"""
print("Parsing input file...")
blast_results = SearchIO.index(args.input, args.format)
gi_ids_list = map(lambda x: x.split("|")[1], MultipleAlignmentRoutines.get_db_ids(blast_results))
#print(gi_ids_list)
print("Downloading sequence summaries...")
handle = Entrez.esummary(db=args.db, id=",".join(gi_ids_list))
summaries_list = Entrez.read(handle)
tax_id_list = set()
with open(args.out_prefix + ".taxid", "w") as out_fd:
for record in summaries_list:
if "TaxId" in record:
tax_id_list.add(str(record["TaxId"]))
out_fd.write(str(record["TaxId"]) + "\n")
print("Downloading species names...")
taxa_handle = Entrez.esummary(db="taxonomy", id=",".join(tax_id_list))
taxa_list = Entrez.read(taxa_handle)
with open(args.out_prefix + ".sciname", "w") as taxa_fd:
with open(args.out_prefix + ".commonname", "w") as com_fd:
required=True,
help="Output file")
parser.add_argument("-f",
"--format",
action="store",
dest="format",
default="fasta",
help="Alignment format. Default: fasta")
parser.add_argument("-r",
"--remove_Ns",
action="store_true",
dest="remove_Ns",
default=False,
help="Remove columns with Ns. Default:False")
parser.add_argument("-a",
"--remove_columns_with_ambigous_nucleotides",
action="store_true",
dest="remove_columns_with_ambigous_nucleotides",
default=False,
help="Remove columns with a. Default:False")
args = parser.parse_args()
MultipleAlignmentRoutines.extract_variable_sites_from_alignment_from_file(
args.input,
args.output,
format=args.format,
remove_columns_with_Ns=args.remove_Ns,
remove_columns_with_ambigous_nucleotides=args.
remove_columns_with_ambigous_nucleotides)
required=True,
type=lambda s: FileRoutines.make_list_of_path_to_files(s.split(",")),
help="Comma-separated list of files/directories with alignments")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="File to write merged alignment")
parser.add_argument(
"-c",
"--coordinates_file",
action="store",
dest="coords_file",
required=True,
help="File to write file with coordinates of alignments in merged alignment"
)
parser.add_argument("-f",
"--format",
action="store",
dest="format",
default="fasta",
help="Format of alignments")
args = parser.parse_args()
MultipleAlignmentRoutines.merge_alignment(args.input,
args.output,
args.coords_file,
format=args.format)
