final_gff = "%s.final.gff" % args.output
final_CDS_gff = "%s.final.CDS.gff" % args.output
AUGUSTUS.path = args.augustus_dir
AUGUSTUS.threads = args.threads
print("Annotating genes...")
AUGUSTUS.parallel_predict(args.species,
args.input,
output_raw_gff,
strand=args.strand,
gene_model=args.gene_model,
output_gff3=True,
other_options=args.other_options,
config_dir=args.config_dir,
use_softmasking=args.softmasking,
hints_file=args.hintsfile,
extrinsicCfgFile=args.extrinsicCfgFile,
predict_UTR=args.predict_UTR,
parsing_mode="parse")
AUGUSTUS.replace_augustus_ids(output_raw_gff,
args.output,
species_prefix=args.species_prefix,
number_of_digits_in_id=8)
Gffread.extract_transcript_sequences(output_gff, args.input, args.output)
SequenceRoutines.trim_cds_and_remove_terminal_stop_codons(
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Tools.Annotation import AUGUSTUS
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input", action="store", dest="input", required=True,
help="File with junctions from STAR output")
parser.add_argument("-o", "--output", action="store", dest="output", required=True,
help="File to write gff with intron hints")
parser.add_argument("-m", "--min_supporting_uniquely_mapped_reads", action="store", dest="min_supporting_uniquely_mapped_reads", default=1,
type=int,
help="Minimum number of uniquely mapped reads supporting reads to retain junction. "
"Default: 1, i.e. only junctions supported by at least one uniquely mapped read will be "
".To retain all junctions set to 0")
parser.add_argument("-s", "--source", action="store", dest="source", default="RNASEQ",
help="Source of hints. Default: RNASEQ")
parser.add_argument("-p", "--priority", action="store", dest="priority", default=100, type=int,
help="Priority of hints. Default: 100")
args = parser.parse_args()
AUGUSTUS.convert_star_junctions_to_intron_hints(args.input, args.output,
min_supporting_uniquely_mapped_reads=args.min_supporting_uniquely_mapped_reads,
source=args.source, priority=100)
input_other_top_gff = "%s.other_top.target.gff" % args.input_prefix
input_other_secondary_gff = "%s.other_secondary.target.gff" % args.input_prefix
precise_top_hints = "%s.precise_top.target.hints.gff" % args.output_prefix
precise_secondary_hints = "%s.precise_secondary.target.hints.gff" % args.output_prefix
other_top_hints = "%s.other_top.target.hints.gff" % args.output_prefix
other_secondary_hints = "%s.other_secondary.target.hints.gff" % args.output_prefix
AUGUSTUS.path = args.augustus_script_dir
AUGUSTUS.exonerate_to_hints(input_precise_top_gff,
precise_top_hints,
priority=args.full_top_hits_priority,
min_intron_len=args.min_intron_len,
max_intron_len=args.max_intron_len,
CDS_part_cutoff=args.full_top_hits_CDS_part_cutoff,
source=args.source_for_full_top_hits,
with_utrs=args.include_utr_hints)
AUGUSTUS.exonerate_to_hints(
input_precise_secondary_gff,
precise_secondary_hints,
priority=args.full_secondary_hits_priority,
min_intron_len=args.min_intron_len,
max_intron_len=args.max_intron_len,
CDS_part_cutoff=args.full_secondary_hits_CDS_part_cutoff,
source=args.source_for_full_secondary_hits,
with_utrs=args.include_utr_hints)
AUGUSTUS.exonerate_to_hints(
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)
"""
def prepare_rnaseq_hints(self,
rnaseq_read_dir,
rnaseq_alignment_dir,
genome_dir,
hints_dir,
genome_fasta=None,
samples=None,
annotation_gtf=None,
sjdboverhang=None,
genomeSAindexNbases=None,
genomeChrBinNbits=None,
genome_size=None,
feature_from_gtf_to_use_as_exon=None,
exon_tag_to_use_as_transcript_id=None,
exon_tag_to_use_as_gene_id=None,
length_of_sequences_flanking_junction=None,
junction_tab_file_list=None,
three_prime_trim=None,
five_prime_trim=None,
adapter_seq_for_three_prime_clip=None,
max_mismatch_percent_for_adapter_trimming=None,
three_prime_trim_after_adapter_clip=None,
output_type="BAM",
sort_bam=True,
max_memory_for_bam_sorting=8000000000,
include_unmapped_reads_in_bam=True,
output_unmapped_reads=True,
two_pass_mode=True,
max_intron_length=None,
min_reads_supporting_junction_hint=1,
source="RNASEQ",
priority=100,
threads=1,
STAR_path=""):
STAR.threads = threads
STAR.path = STAR_path
samples = samples if samples else self.get_sample_list(rnaseq_read_dir)
STAR.align_samples(
rnaseq_read_dir,
rnaseq_alignment_dir,
genome_dir,
genome_fasta=genome_fasta,
samples=samples,
annotation_gtf=annotation_gtf,
sjdboverhang=sjdboverhang,
genomeSAindexNbases=genomeSAindexNbases,
genomeChrBinNbits=genomeChrBinNbits,
genome_size=genome_size,
feature_from_gtf_to_use_as_exon=feature_from_gtf_to_use_as_exon,
exon_tag_to_use_as_transcript_id=exon_tag_to_use_as_transcript_id,
exon_tag_to_use_as_gene_id=exon_tag_to_use_as_gene_id,
length_of_sequences_flanking_junction=
length_of_sequences_flanking_junction,
junction_tab_file_list=junction_tab_file_list,
three_prime_trim=three_prime_trim,
five_prime_trim=five_prime_trim,
adapter_seq_for_three_prime_clip=adapter_seq_for_three_prime_clip,
max_mismatch_percent_for_adapter_trimming=
max_mismatch_percent_for_adapter_trimming,
three_prime_trim_after_adapter_clip=
three_prime_trim_after_adapter_clip,
output_type=output_type,
sort_bam=sort_bam,
max_memory_for_bam_sorting=max_memory_for_bam_sorting,
include_unmapped_reads_in_bam=include_unmapped_reads_in_bam,
output_unmapped_reads=output_unmapped_reads,
two_pass_mode=two_pass_mode,
max_intron_length=max_intron_length)
for sample in samples:
sample_junction_file = "%s/%s/SJ.out.tab " % (rnaseq_alignment_dir,
sample)
sample_hint_gff = "%s/rnaseq.hints.%s.gff" % (hints_dir, sample)
AUGUSTUS.convert_star_junctions_to_intron_hints(
sample_junction_file,
sample_hint_gff,
min_supporting_reads=min_reads_supporting_junction_hint,
source=source,
priority=priority)
help="Output file with synonyms")
parser.add_argument("-p",
"--id_prefix",
action="store",
dest="id_prefix",
required=True,
help="Prefix of id")
parser.add_argument("-n",
"--number_of_digits_in_number",
action="store",
dest="number_of_digits_in_number",
type=int,
default=8,
help="Number of digits in id. Default - 8")
parser.add_argument(
"-f",
"--feature_type",
action="store",
dest="feature_type",
default="gene",
help="Type of feature to assign synonyms. Default - 'gene'")
args = parser.parse_args()
AUGUSTUS.assign_synonyms_to_features_from_augustus_gff(
args.input_gff,
args.output,
args.id_prefix,
number_of_digits_in_number=args.number_of_digits_in_number,
feature_type=args.feature_type)
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Tools.Annotation import AUGUSTUS
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input",
action="store",
dest="input",
required=True,
help="Input evidence file")
parser.add_argument("-o",
"--output_prefix",
action="store",
dest="output_prefix",
required=True,
help="Prefix of output files")
args = parser.parse_args()
AUGUSTUS.draw_evidence_figures(args.input, args.output_prefix)
dest="input_gff",
required=True,
help="Input gff from AUGUSTUS")
parser.add_argument("-o",
"--output_prefix",
action="store",
dest="output_prefix",
required=True,
help="Prefix of output files")
parser.add_argument("-p",
"--species_prefix",
action="store",
dest="species_prefix",
required=True,
help="Species prefix to use in ids")
parser.add_argument("-n",
"--number_of_digits_in_number",
action="store",
dest="number_of_digits_in_number",
type=int,
default=8,
help="Number of digits in id. Default - 8")
args = parser.parse_args()
AUGUSTUS.assign_synonyms_to_annotations_from_augustus_gff(
args.input_gff,
args.output_prefix,
args.species_prefix,
number_of_digits_in_number=args.number_of_digits_in_number)
secondary_hits_gff = "%s.target.secondary_hits.gff" % args.output_prefix
top_hits_gff_hints = "%s.target.top_hits.hints.gff" % args.output_prefix
secondary_hits_gff_hints = "%s.target.secondary_hits.hints.gff" % args.output_prefix
Exonerate.extract_top_hits_from_target_gff(
args.input,
top_hits_gff,
secondary_hits_gff,
id_white_list_file=args.white_id_file,
max_hits_per_query=args.max_hits_per_query)
AUGUSTUS.path = args.augustus_script_dir
AUGUSTUS.exonerate_to_hints(top_hits_gff,
top_hits_gff_hints,
priority=args.top_hits_priority,
min_intron_len=args.min_intron_len,
max_intron_len=args.max_intron_len,
CDS_part_cutoff=args.top_hits_CDS_part_cutoff,
source=args.source_for_top_hits,
with_utrs=args.include_utr_hints)
AUGUSTUS.exonerate_to_hints(
secondary_hits_gff,
secondary_hits_gff_hints,
priority=args.secondary_hits_priority,
min_intron_len=args.min_intron_len,
max_intron_len=args.max_intron_len,
CDS_part_cutoff=args.secondary_hits_CDS_part_cutoff,
source=args.source_for_secondary_hits,
with_utrs=args.include_utr_hints)
dest="id_prefix",
default="",
help="Prefix to use for protein ids")
parser.add_argument("-s",
"--stat_file",
action="store",
dest="stat_file",
help="File to write statistics about annotations")
parser.add_argument(
"-u",
"--supported_stat_file",
action="store",
dest="supp_stat_file",
help="File to write statistics about annotations supported by hints")
parser.add_argument("-c",
"--complete_protein_ids",
action="store",
dest="complete_protein_id_file",
help="File to write ids of complete proteins")
args = parser.parse_args()
AUGUSTUS.extract_proteins_from_output(
args.input,
args.output,
id_prefix=args.id_prefix,
evidence_stats_file=args.stat_file,
supported_by_hints_file=args.supp_stat_file,
complete_proteins_id_file=args.complete_protein_id_file)
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Tools.Annotation import AUGUSTUS
parser = argparse.ArgumentParser()
parser.add_argument(
"-i",
"--input",
action="store",
dest="input",
required=True,
help="Comma-separated list of input files with hints in gff")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="Output file with merged hints")
args = parser.parse_args()
AUGUSTUS.join_multiple_hints(args.input, args.output)
parser.add_argument("-i",
"--input",
action="store",
dest="input",
required=True,
help="Input file with AUGUSTUS evidence")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="Output file")
parser.add_argument("-d",
"--id_file",
action="store",
dest="id_file",
required=True,
help="File with ids to extract")
parser.add_argument("-m",
"--mode",
action="store",
dest="mode",
default="transcript",
help="Prefix of output files. Default - transcript")
args = parser.parse_args()
AUGUSTUS.extract_evidence_by_ids(args.input,
args.id_file,
args.output,
mode=args.mode)
import argparse
from RouToolPa.Tools.Annotation import AUGUSTUS
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input",
action="store",
dest="input",
required=True,
help="Input evidence file")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="File to write filtered evidence file")
parser.add_argument("-m",
"--min_fraction",
action="store",
dest="min_fraction",
default=0,
type=float,
help="Minimum fraction of transcript supported by hints")
args = parser.parse_args()
AUGUSTUS.extract_longest_isoforms(args.input,
args.output,
minimum_supported_fraction=args.min_fraction)
required=True,
help="Input AUGUSTUS GFF file")
parser.add_argument("-o",
"--output_gff",
action="store",
dest="output_gff",
required=True,
help="Output GFF with exon entries")
parser.add_argument("-e",
"--exon_id_prefix",
action="store",
dest="exon_id_prefix",
default="EXON",
help="Prefix of exon id. Default: EXON")
parser.add_argument("-n",
"--id_digit_num",
action="store",
dest="id_digit_num",
default=8,
type=int,
help="Number of digits in exon id. Default: 8")
args = parser.parse_args()
AUGUSTUS.add_exon_lines_to_augustus_gff(
args.input_gff,
args.output_gff,
number_of_digits_in_id=args.id_digit_num,
exon_id_prefix=args.exon_id_prefix,
new_exon_numering=False)
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from RouToolPa.Tools.Annotation import AUGUSTUS
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input_gff", action="store", dest="input_gff", required=True,
help="Input gff from AUGUSTUS")
parser.add_argument("-o", "--output_prefix", action="store", dest="output_prefix", required=True,
help="Prefix of output files")
parser.add_argument("-s", "--species_prefix", action="store", dest="species_prefix", required=True,
help="Species prefix for ids")
parser.add_argument("-d", "--number_of_digits_in_id", action="store", dest="number_of_digits_in_id", type=int,
default=8, help="Number of digits in ids. Default - 8")
args = parser.parse_args()
AUGUSTUS.replace_augustus_ids(args.input_gff, args.output_prefix, species_prefix=args.species_prefix,
number_of_digits_in_id=args.number_of_digits_in_id)
"--output_gff",
action="store",
dest="output_gff",
required=True,
help="Output gff with replaced ids")
parser.add_argument("-g",
"--gene_syn_file",
action="store",
dest="gene_syn_file",
required=True,
help="File with gene synonyms")
parser.add_argument("-t",
"--transcript_syn_file",
action="store",
dest="transcript_syn_file",
required=True,
help="File with transcript synonyms")
parser.add_argument("-c",
"--cds_syn_file",
action="store",
dest="cds_syn_file",
help="File with CDS synonyms")
args = parser.parse_args()
AUGUSTUS.replace_augustus_ids_by_syn(args.input_gff,
args.output_gff,
args.gene_syn_file,
args.transcript_syn_file,
cds_syn_file=args.cds_syn_file)
