#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from Tools.HMMER import HMMER3
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_hmm",
action="store",
dest="input",
help="Input hmm3 file")
parser.add_argument("-o",
"--output_file",
action="store",
dest="output",
default="stdout",
help="Output file with ids. Default: stdout")
args = parser.parse_args()
HMMER3.get_ids_from_hmm3(
args.input,
ids_file=None if args.output == 'stdout' else args.output,
return_ids_list=False)
help="Directory to write intermediate(splited) parseable table of per-sequence hits")
parser.add_argument("--domtblout_dir", action="store", dest="domtblout_dir",
default="domtblout_dir", type=check_path,
help="Directory to write intermediate(splited) parseable table of per-domain hits")
parser.add_argument("--pfamtblout_dir", action="store", dest="pfamtblout_dir",
default="pfamtblout_dir", type=check_path,
help="Directory to write intermediate(splited) table of hits and domains to file, in Pfam format ")
parser.add_argument("--tblout", action="store", dest="tblout",
help="File to save parseable table of per-sequence hits")
parser.add_argument("--domtblout", action="store", dest="domtblout",
help="File to save parseable table of per-domain hits")
parser.add_argument("--pfamtblout", action="store", dest="pfamtblout",
help="File to save table of hits and domains to file, in Pfam format ")
parser.add_argument("--hmmer_dir", action="store", dest="path", default="",
help="Path to directory with hmmer3.1 binaries")
args = parser.parse_args()
HMMER3.threads = 1
HMMER3.path = args.path
HMMER3.parallel_hmmscan(args.input, args.input_seq, args.output, num_of_seqs_per_scan=None, split_dir="splited_fasta",
splited_output_dir=args.hmmscan_output_dir, threads=args.threads,
combine_output_to_single_file=args.combine_output, dont_output_alignments=args.no_alignment,
tblout_outfile=args.tblout, domtblout_outfile=args.domtblout,
pfamtblout_outfile=args.pfamtblout,
splited_tblout_dir=args.tblout_dir, splited_domtblout_dir=args.domtblout_dir,
splited_pfamtblout_dir=args.pfamtblout_dir
)
def predict_genes(self,
output_prefix,
annotation_species_prefix,
genome_fasta,
augustus_species,
output_directory="./",
augustus_strand=None,
augustus_gene_model=None,
augustus_config_dir=None,
augustus_use_softmasking=None,
augustus_other_options="",
augustus_hintsfile=None,
augustus_extrinsicCfgFile=None,
augustus_predict_UTR=None,
augustus_min_intron_len=None,
threads=1,
augustus_dir="",
hmmer_dir="",
blast_dir="",
stop_codons_list=("TGA", "TAA", "TAG"),
genetic_code_table=1):
draft_file_prefix = "%s/raw/%s" % (output_directory, output_prefix)
augustus_splited_input_dir = "%s/splited_input/" % output_directory
augustus_splited_output_dir = "%s/splited_output_dir" % output_directory
output_raw_gff = "%s.raw.gff" % draft_file_prefix
output_gff = "%s.renamed.gff" % draft_file_prefix
augustus_pep = "%s.pep" % draft_file_prefix
AUGUSTUS.path = augustus_dir
AUGUSTUS.threads = threads
HMMER3.path = hmmer_dir
HMMER3.threads = threads
BLASTp.path = blast_dir
BLASTp.threads = threads
print("Annotating genes...")
AUGUSTUS.parallel_predict(
augustus_species,
genome_fasta,
output_raw_gff,
strand=augustus_strand,
gene_model=augustus_gene_model,
output_gff3=True,
other_options=augustus_other_options,
config_dir=augustus_config_dir,
use_softmasking=augustus_use_softmasking,
hints_file=augustus_hintsfile,
split_dir=augustus_splited_input_dir,
splited_output_dir=augustus_splited_output_dir,
extrinsicCfgFile=augustus_extrinsicCfgFile,
predict_UTR=augustus_predict_UTR,
combine_output_to_single_file=True,
min_intron_len=augustus_min_intron_len)
#replace_augustus_ids(augustus_gff, output_prefix, species_prefix=None, number_of_digits_in_id=8):
AUGUSTUS.replace_augustus_ids(output_raw_gff,
draft_file_prefix,
species_prefix=annotation_species_prefix,
number_of_digits_in_id=8)
#extract_transcript_sequences(self, input_gff_file, genomic_fasta_file, output_prefix, coding_only=False)
gffread_file_prefix = "%s.gffread" % draft_file_prefix
gffread_transcripts_file, gffread_cds_file, gffread_pep_file = Gffread.extract_transcript_sequences(
output_gff, genome_fasta, gffread_file_prefix)
gffread_trimmed_cds = ".".join(
gffread_cds_file.split(".")[:-1]) + ".trimmed.cds"
gffread_trimmed_pep = ".".join(
gffread_pep_file.split(".")[:-1]) + ".trimmed.pep"
self.trim_cds_and_remove_terminal_stop_codons(
gffread_cds_file,
gffread_trimmed_cds,
stop_codons_list=stop_codons_list
) # using default stop_codons(from universal genetic_code)/ Note that this will affect mtDNA proteins
inframe_stop_codons_file_prefix = "%s.inframe_stop_codon" % draft_file_prefix
self.translate_sequences_from_file(
gffread_trimmed_cds,
gffread_trimmed_pep,
format="fasta",
id_expression=None,
genetic_code_table=genetic_code_table,
translate_to_stop=False,
prefix_of_file_inframe_stop_codons_seqsin=
inframe_stop_codons_file_prefix) # Universal code !!!
AUGUSTUS.extract_gene_ids_from_output(output_gff,
all_annotated_genes_ids)
AUGUSTUS.extract_CDS_annotations_from_output(output_gff, CDS_gff)
print("Extracting peptides...")
AUGUSTUS.extract_proteins_from_output(
output_gff,
output_pep,
id_prefix="",
evidence_stats_file=output_evidence_stats,
supported_by_hints_file=output_supported_stats)
self.compare_sequences_from_files(output_pep,
"%s.trimmed.pep" % args.output,
"comparison_of_peptides",
format="fasta",
verbose=True)
os.system("awk -F'\\t' 'NR==1 {}; NR > 1 {print $2}' %s > %s" %
(output_supported_stats, output_supported_stats_ids))
print("Annotating domains(Pfam database)...")
HMMER3.parallel_hmmscan(
args.pfam_db,
output_pep,
output_hmmscan,
num_of_seqs_per_scan=None,
split_dir="splited_hmmscan_fasta/",
splited_output_dir="splited_hmmscan_output_dir",
tblout_outfile=None,
domtblout_outfile=output_domtblout,
pfamtblout_outfile=None,
splited_tblout_dir=None,
splited_domtblout_dir="hmmscan_domtblout/")
HMMER3.extract_dom_ids_hits_from_domtblout(
output_domtblout, output_pfam_annotated_dom_ids)
hits_dict = HMMER3.extract_dom_names_hits_from_domtblout(
output_domtblout, output_pfam_annotated_dom_names)
supported_ids = IdSet(hits_dict.keys())
supported_ids.write(output_pfam_supported_transcripts_ids)
remove_transcript_ids_str = "sed -re 's/\.t[0123456789]+//' %s | sort -k 1 | uniq > %s" % (
output_pfam_supported_transcripts_ids,
output_pfam_supported_genes_ids)
os.system(remove_transcript_ids_str)
print("Annotating peptides(Swissprot database)...")
BLASTp.parallel_blastp(output_pep,
args.swissprot_db,
evalue=0.0000001,
output_format=6,
outfile=output_swissprot_blastp_hits,
split_dir="splited_blastp_fasta",
splited_output_dir="splited_blastp_output_dir")
hits_dict = BLASTp.extract_hits_from_tbl_output(
output_swissprot_blastp_hits, output_swissprot_blastp_hits_names)
supported_ids = IdSet(hits_dict.keys())
supported_ids.write(output_swissprot_supported_transcripts_ids)
remove_transcript_ids_str = "sed -re 's/\.t[0123456789]+//' %s | sort -k 1 | uniq > %s" % (
output_swissprot_supported_transcripts_ids,
output_swissprot_supported_genes_ids)
os.system(remove_transcript_ids_str)
"""
"comparison_of_peptides",
format="fasta",
verbose=True)
os.system("awk -F'\\t' 'NR==1 {}; NR > 1 {print $2}' %s > %s" %
(output_supported_stats, output_supported_stats_ids))
if args.pfam_db:
print("Annotating domains(Pfam database)...")
HMMER3.threads = args.threads
HMMER3.parallel_hmmscan(args.pfam_db,
output_pep,
output_hmmscan,
num_of_seqs_per_scan=None,
split_dir="splited_hmmscan_fasta/",
splited_output_dir="splited_hmmscan_output_dir",
tblout_outfile=None,
domtblout_outfile=output_domtblout,
pfamtblout_outfile=None,
splited_tblout_dir=None,
splited_domtblout_dir="hmmscan_domtblout/")
HMMER3.extract_dom_ids_hits_from_domtblout(output_domtblout,
output_pfam_annotated_dom_ids)
hits_dict = HMMER3.extract_dom_names_hits_from_domtblout(
output_domtblout, output_pfam_annotated_dom_names)
supported_ids = IdSet(hits_dict.keys())
supported_ids.write(output_pfam_supported_transcripts_ids)
remove_transcript_ids_str = "sed -re 's/\.t[0123456789]+//' %s | sort -k 1 | uniq > %s" % (
output_pfam_supported_transcripts_ids, output_pfam_supported_genes_ids)
os.system(remove_transcript_ids_str)
"--header",
action="store_true",
dest="header",
help="Header is present in id file. Default: False")
parser.add_argument("-f",
"--format",
action="store",
dest="format",
required=True,
help="Format of the file with hits")
parser.add_argument("-o",
"--output_file",
action="store",
dest="output",
default="stdout",
help="Output file")
args = parser.parse_args()
out_fd = sys.stdout if args.output == "stdout" else open(args.output, "w")
id_list = IdList()
id_list = id_list.read(args.id_file, header=args.header)
HMMER3.extract_hits_by_query_ids(id_list,
args.input,
args.output,
fileformat=args.format,
close_after_if_file_object=True)
out_fd.close()
blastp_split_dir = "%ssplited_fasta_dir/" % blastp_dir
blastp_splited_output_dir = "%ssplited_output_dir" % blastp_dir
HMMER3.path = args.hmmer_dir
HMMER3.threads = args.threads
BLASTp.threads = args.threads
TransDecoder.extract_longest_orfs(
args.input,
genetic_code=args.genetic_code,
analyze_only_top_strand=args.analyze_only_top_strand,
minimum_protein_length=args.min_prot_len)
if args.pfam_database:
HMMER3.parallel_hmmscan(args.pfam_database,
pep_from_longest_orfs,
hmmscan_vs_pfam_output,
split_dir=hmmscan_splited_fasta_dir,
splited_domtblout_dir=splited_domtblout_dir,
domtblout_outfile=domtblout_outfile,
dont_output_alignments=True)
if args.blast_database:
BLASTp.parallel_blastp(pep_from_longest_orfs,
args.blast_database,
outfile=blastp_outfile,
evalue=0.00001,
output_format=6,
blast_options=" -max_target_seqs 1",
combine_output_to_single_file=True,
split_dir=blastp_split_dir,
splited_output_dir=blastp_splited_output_dir)
TransDecoder.predict_pep(
tblout_file = "%s.tblout" % args.output_prefix
domtblout_file = "%s.domtblout" % args.output_prefix
pfamtblout_file = "%s.pfamtblout" % args.output_prefix
HMMER3.threads = 1
HMMER3.path = args.path
HMMER3.timelog = "%s.timelog" % args.output_prefix
HMMER3.parallel_hmmscan(args.input,
args.input_seq,
hits_file,
num_of_seqs_per_scan=None,
split_dir="splited_fasta",
splited_output_dir=args.hmmscan_output_dir,
threads=args.threads,
combine_output_to_single_file=True,
dont_output_alignments=args.no_alignment,
tblout_outfile=tblout_file,
domtblout_outfile=domtblout_file,
pfamtblout_outfile=pfamtblout_file,
splited_tblout_dir=args.tblout_dir,
splited_domtblout_dir=args.domtblout_dir,
splited_pfamtblout_dir=args.pfamtblout_dir,
biopython_165_compartibility=True)
HMMER3.extract_top_hits(hits_file,
top_hits_file,
not_significant_ids_file=not_significant_ids_file,
not_found_ids_file=not_found_ids_file)
HMMER3.get_families_from_top_hits(top_hits_file, fam_file)
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from Tools.HMMER import HMMER3
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_hmm",
action="store",
dest="input",
required=True,
help="Input hmmer3 domtblout file")
parser.add_argument("-o",
"--output_prefix",
action="store",
dest="output_prefix",
required=True,
help="Output prefix")
args = parser.parse_args()
output_pfam_annotated_dom_ids = "%s.dom_ids" % args.output_prefix
output_pfam_annotated_dom_names = "%s.dom_names" % args.output_prefix
HMMER3.extract_dom_ids_hits_from_domtblout(args.input,
output_pfam_annotated_dom_ids)
HMMER3.extract_dom_names_hits_from_domtblout(args.input,
output_pfam_annotated_dom_names)