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)
print("Drawing histograms...")
for stat_file in output_evidence_stats, output_supported_stats, \
output_swissprot_pfam_or_hints_supported_transcripts_longest_pep_evidence, \
output_swissprot_pfam_and_hints_supported_transcripts_longest_pep_evidence, \
output_swissprot_pfam_or_hints_supported_transcripts_evidence, \
output_swissprot_pfam_and_hints_supported_transcripts_evidence:
MatplotlibRoutines.percent_histogram_from_file(
stat_file,
stat_file,
data_type=None,
column_list=(2, ),
comments="#",
n_bins=20,
title="Transcript support by hints",
extensions=("png", "svg"),
legend_location="upper center",
stats_as_legend=True)
print("Creating final directories...")
if args.pfam_db and args.swissprot_db:
db_or_hints_dir = "supported_by_db_or_hints/"
db_and_hints_dir = "supported_by_db_and_hints/"
for directory in db_and_hints_dir, db_or_hints_dir:
FileRoutines.safe_mkdir(directory)
os.system("mv %s.supported.transcripts.swissprot_or_pfam_or_hints* %s" %
(args.output, db_or_hints_dir))
os.system("mv %s.supported.transcripts.swissprot_or_pfam_and_hints* %s" %
(args.output, db_and_hints_dir))
"--min_species_number",
action="store",
dest="min_species_number",
default=1,
type=int,
help="Minimum number of species with family to retain family. Default: 1")
parser.add_argument("-f",
"--filtered_families_directory",
action="store",
dest="filtered_family_dir",
default="filtered_fam",
type=FileRoutines.check_path,
help="Directory to write filtered_families")
args = parser.parse_args()
FileRoutines.safe_mkdir(args.filtered_family_dir)
species_list = sorted(args.species_set)
if args.white_list_file and args.black_list_file:
raise ValueError("Black list and white list cant be set simultaneously")
black_list = IdList()
white_list = IdList()
if args.black_list_file:
black_list.read(args.black_list_file)
if args.white_list_file:
white_list.read(args.white_list_file)
out_fd = open(args.cafe_file, "w")
filtered_fd = open("%sfiltered_families.cafe" % args.filtered_family_dir, "w")
out_fd.write("FAMILYDESC\tFAMILY\t%s\n" % ("\t".join(species_list)))
filtered_fd.write("FAMILYDESC\tFAMILY\t%s\n" % ("\t".join(species_list)))
species_filtered_fd_list = OrderedDict()
parser.add_argument("-d",
"--top_hits_dir",
action="store",
dest="top_hits_dir",
default="top_hits_dir/",
type=FileRoutines.check_path,
help="Directory to write intermediate(splited) output")
parser.add_argument("-r",
"--retain_splited_output",
action="store_true",
dest="retain",
help="Retain splited output")
args = parser.parse_args()
FileRoutines.safe_mkdir(args.top_hits_dir)
def handle_input(filename):
sys.stdout.write("Handling %s\n" % filename)
not_significant_ids = IdList()
not_found_ids = IdList()
prefix = FileRoutines.split_filename(filename)[1]
index_file = "%s.tmp.idx" % prefix
hmm_dict = SearchIO.index_db(index_file, filename, args.format)
if args.output == "stdout":
out_fd = sys.stdout
else:
out_fd = open("%s%s.top_hits" % (args.top_hits_dir, prefix), "w")
out_fd.write("#query\thit\tevalue\tbitscore\n")
action="store",
dest="max_memory_per_thread",
default="1G",
help="Maximum memory per thread. Default - 1G")
args = parser.parse_args()
if args.prepare_bam and ((not args.prepared_bam_prefix) or
(not args.temp_dir)):
raise ValueError(
"Options -e/--prepared_bam_prefix and -m/--temp_dir must be set if -p/--prepare_bam option is used"
)
SamtoolsV1.threads = args.threads
if args.prepare_bam or args.mix_ends:
FileRoutines.safe_mkdir(FileRoutines.check_path(args.temp_dir))
prepared_pe_bam_file = "%s.bam" % args.prepared_bam_prefix
prepared_unpaired_bam_file = (
"%s.unpaired.bam" %
args.prepared_bam_prefix) if args.mix_ends else None
"""
SamtoolsV1.prepare_bam_for_read_extraction(args.input, args.prepared_bam, temp_file_prefix=args.temp_dir,
max_memory_per_thread=args.max_memory_per_thread)
"""
SamtoolsV1.prepare_bam_for_read_extraction(
args.input,
prepared_pe_bam_file,
temp_file_prefix=args.temp_dir,
max_memory_per_thread=args.max_memory_per_thread,
bam_file_to_write_unpaired_reads=prepared_unpaired_bam_file)
if args.paired:
dest="output",
type=FileRoutines.check_path,
help="Output directory")
#parser.add_argument("-p", "--convert_options", action="store", dest="convert_options",
# help="Options for convert")
parser.add_argument("-d",
"--dont_make_negative",
action="store_true",
dest="dont_negative",
help="Dont make negative")
args = parser.parse_args()
temp_dir = "temp/"
FileRoutines.safe_mkdir(temp_dir)
BioConvert.threads = args.threads
Convert.threads = args.threads
BioConvert.parallel_convert(args.input, temp_dir)
if args.dont_negative:
os.rename(temp_dir, args.output)
else:
converted_files = os.listdir(temp_dir)
converted_files = list(
map(lambda s: "%s%s" % (temp_dir, s), converted_files))
Convert.parallel_convert(
converted_files, args.output,
STAR.path = args.star_dir
if args.genome_fasta:
STAR.index(args.genome_dir,
args.genome_fasta,
annotation_gtf=args.annotation_gtf,
junction_tab_file=args.junction_tab_file,
sjdboverhang=None,
genomeSAindexNbases=None,
genomeChrBinNbits=None,
genome_size=args.genome_size)
sample_list = args.samples if args.samples else Pipeline.get_sample_list(
args.samples_dir)
FileRoutines.safe_mkdir(args.output_dir)
for sample in sample_list:
print("Handling %s" % sample)
sample_dir = "%s/%s/" % (args.samples_dir, sample)
alignment_sample_dir = "%s/%s/" % (args.output_dir, sample)
FileRoutines.safe_mkdir(alignment_sample_dir)
filetypes, forward_files, reverse_files, se_files = FileRoutines.make_lists_forward_and_reverse_files(
sample_dir)
print("\tAligning reads...")
STAR.align_miRNA(
args.genome_dir,
se_files,
output_dir=alignment_sample_dir,
args = parser.parse_args()
Trimmomatic.jar_path = args.path_to_trimmomatic_dir
Trimmomatic.threads = args.threads
#print(Trimmomatic.path)
#print(Trimmomatic.jar_path)
samples = args.samples.split(",") if args.samples else os.listdir(args.samples_dir)
for sample in samples:
print("Handling %s" % sample)
sample_dir = "%s%s/" % (args.samples_dir, sample)
sample_out_dir = "%s%s/" % (args.output_dir, sample)
FileRoutines.safe_mkdir(sample_out_dir)
trimmomatic_log = "%s/trimmomatic.log" % sample_out_dir
trimmomatic_time_log = "%s/trimmomatic.time.log" % sample_out_dir
output_prefix = "%s%s.TMF" % (sample_out_dir, sample)
files_from_sample_dir = os.listdir(sample_dir)
left_reads_file = None
right_reads_file = None
for filename in files_from_sample_dir:
if ("_1.fq" in filename) or ("_1.fastq" in filename):
left_reads_file = filename
elif ("_2.fq" in filename) or ("_2.fastq" in filename):
right_reads_file = filename
if (left_reads_file is None) and (right_reads_file is None):
dest="blast_dir",
default="",
help="Directory with BLAST+ binaries")
args = parser.parse_args()
input_filename_list = FileRoutines.split_filename(args.input)
input_filename = input_filename_list[1] + input_filename_list[2]
workdir_dir = "%s.transdecoder_dir/" % input_filename
pep_from_longest_orfs = "%s/longest_orfs.pep" % workdir_dir
hmmscan_dir = "hmmscan_vs_pfam/"
blastp_dir = "blastp_vs_uniref/"
FileRoutines.safe_mkdir(hmmscan_dir)
FileRoutines.safe_mkdir(blastp_dir)
hmmscan_splited_fasta_dir = "%ssplited_fasta_dir/" % hmmscan_dir
splited_domtblout_dir = "%ssplited_domtblout_dir/" % hmmscan_dir
hmmscan_vs_pfam_prefix = "%s.pfam" % input_filename
hmmscan_vs_pfam_output = "%s/%s.hits" % (hmmscan_dir, hmmscan_vs_pfam_prefix)
domtblout_outfile = "%s/%s.domtblout" % (hmmscan_dir, hmmscan_vs_pfam_prefix)
blastp_outfile = "%s%s.blastp.hits" % (
blastp_dir, input_filename) if args.blast_database else None
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