def analyze_assembly_rna(self, query=None, name=None):
self.print_start_of_process_pid()
if query:
if not name:
name = self.get_output_header()
rnammer_output = os.path.join(
self.get_work_dir(),
self.__concatenate_file_name(name, 'rnammer.out'))
rdp_output = os.path.join(
self.get_work_dir(),
self.__concatenate_file_name(name, 'rdp.out'))
table_output = os.path.join(self.get_table_dir(), name)
cmd_list = [
'run_rna_analysis.py', '-c', '-f', rnammer_output, '-r',
rdp_output, query
]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
cmd_list = [
'analyze_rna_hits.py', '-c', '-r', rdp_output, '-o',
table_output, rnammer_output
]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def main():
# set up command
cmd = None
task = options.task
if options.make_blastdb:
type = 'nucl'
if options.is_protein:
type = 'prot'
cmd_list = [constant.MAKEBLASTDB, '-in', args[0], '-dbtype', type]
rc = RunCommand(cmd_list)
print "Running command: " + rc.get_command() + '\n'
rc.run_command()
if options.vec_screen:
cmd = NcbiblastnCommandline(query=args[1], db=args[0], evalue=700, outfmt=options.outfmt, reward=1,
penalty=-5, gapopen=3, gapextend=3, dust='yes', searchsp=1750000000000,
out=options.output, task=task, num_threads=options.threads)
elif options.ncbi_screen:
# Note: new NCBI requirements say to use lcase_masking (See GAAG-510 for documentation)
cmd = NcbiblastnCommandline(query=args[1], db=args[0], outfmt=options.outfmt, dust='yes',
perc_identity=90, lcase_masking='true', task='megablast',
out=options.output, num_threads=options.threads)
#Blast documentation says soft_masking option if not specified defaults to true so even though
#this biopython class does not support it the feature should be enabled by default
elif options.mito_screen:
# Note: new NCBI requirements say to use lcase_masking (See GAAG-510 for documentation)
cmd = NcbiblastnCommandline(query=args[1], db=args[0], outfmt=options.outfmt, dust='yes',
perc_identity=98.6, lcase_masking='true', task='blastn',
out=options.output, num_threads=options.threads)
#Blast documentation says soft_masking option if not specified defaults to true so even though
#this biopython class does not support it the feature should be enabled by default
elif options.rRNA_screen:
cmd = NcbiblastnCommandline(query=args[1], db=args[0], outfmt=options.outfmt, dust='yes',
perc_identity=95, lcase_masking='', task='megablast',
out=options.output, num_threads=options.threads, evalue=1e-9, window_size=120, gapextend=2, gapopen=4,
no_greedy='', penalty=-4, reward=3, word_size=12, xdrop_gap=20)
#Options not supported: in_pssm='',soft_masking='true', matrix=5000000, max_intron_length=18, db_gencode=3,
else:
if options.task in TASKS:
program = TASKS[options.task]
if re.search("Ncbiblastn", str(program)):
cmd = program(query=args[1], db=args[0], evalue=options.evalue,
outfmt=options.outfmt, out=options.output,
num_threads=options.threads, max_target_seqs=options.max_targets,
task=task)
else:
cmd = program(query=args[1], db=args[0], evalue=options.evalue,
outfmt=options.outfmt, out=options.output,
num_threads=options.threads, max_target_seqs=options.max_targets)
else:
print "Unrecognized blast task, " + options.task
sys.exit(-1)
print "Running BLAST command: " + str(cmd) + '\n'
out, err = cmd()
# print "out: out\terr: err"
return 0
def main():
output_header = options.output
if not output_header:
output_header = __make_prefix_from_files(args[0])
rc = RunCommand(__build_insert_size_command(args[0],output_header,options.insert_size,options.std_dev))
out = rc.run_command()
return 0
def main():
delta = args[0]
# get information about our inputs
reference, query = _get_query_and_reference_from_delta_file(delta)
query_seqs = _get_query_sequences(query)
reference_list, reference_lengths = _get_reference_details(reference)
# get alignment information
command = _get_show_tilings_command(options.output, options.id,
options.coverage, options.circular,
delta)
reference_tilings = _get_tilings_information(command)
# see if we need circular query information
circular_queries = {}
if options.circular:
command = _get_circular_show_tilings_command(options.output, delta)
circular_queries = _get_circular_alignments(command)
print "Ordering and orienting using", delta
print "Reference", reference
print "Query", query
# get ono information from our gathered data
ono_sequences_list, ono_details_list = _parse_tilings(
reference_list, reference_lengths, reference_tilings, query_seqs,
circular_queries)
# print out our output
_write_details_to_file(ono_details_list,
options.output + ".ono.details.txt")
interim_fasta = options.output + ".interim.fasta"
SeqIO.write(ono_sequences_list, interim_fasta, "fasta")
make_assembly_command = [
"make_standard_assembly_files.py", "-S", interim_fasta, "-o",
options.output + ".ono"
]
if options.rename:
make_assembly_command += ['-r']
rc = RunCommand(make_assembly_command)
print "Executing", rc.get_command()
rc.run_command()
return 0
def generate_bam_plots(self,
bam_files=[],
ref=None,
name=None,
ref_header='reference',
window_size=1000):
self.print_start_of_process_pid()
if bam_files and ref:
if not name:
name = self.get_output_header()
analysis_output_header = self.__concatenate_file_name(
name, ref_header)
data_dump_file = os.path.join(
self.get_work_dir(),
self.__concatenate_file_name(analysis_output_header,
'gc_cvg.details.txt'))
plot_output_header = os.path.join(self.get_chart_dir(),
analysis_output_header)
histo_plot = self.__concatenate_file_name(plot_output_header,
'gc_cvg')
cmd_list = [
"generate_bam_plots.py", "-g", ref, "-d", data_dump_file, "-w",
str(window_size), "-o", plot_output_header, "-hi", histo_plot
] + bam_files
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def align_reads(self,
unmapped_bam=None,
ref=None,
threads=None,
aligner='BWA',
ref_header='reference',
make_index=True,
align_type='-s'):
self.print_start_of_process_pid()
if unmapped_bam and ref:
if not threads:
threads = self.get_num_threads()
output_header = re.sub("unmapped.bam", ref_header, unmapped_bam)
cmd_list = [
'align_reads.py', '-i', unmapped_bam, '-o', output_header,
'-r', ref, '-a', aligner, align_type, '-t',
str(threads), '-T',
self.get_work_dir()
]
if not make_index:
cmd_list += ['-x']
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return self.__concatenate_file_name(output_header, 'bam')
def revert_to_bam(self, files=[], output_base='reads', direction='fr'):
self.print_start_of_process_pid()
if files:
output_bam = os.path.join(
self.get_work_dir(),
self.__concatenate_file_name(output_base, 'unmapped.bam'))
for i in files:
if self.__is_bam(i) and not self.__is_aligned_bam(i):
os.symlink(i, output_bam)
self.print_end_of_process_pid()
return output_bam
cmd_list = ['read_format_converter.py', '-o', output_bam]
if direction:
cmd_list += ['-d', direction]
cmd_list += files
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
if not os.path.exists(output_bam):
return None
return output_bam
def run_nucmer(self,
query=None,
ref=None,
name=None,
extension='ref_vs_assembly'):
self.print_start_of_process_pid()
if query and ref:
if not name:
name = self.get_output_header()
prefix = os.path.join(
self.get_work_dir(),
self.__concatenate_file_name(name, extension))
cmd_list = [
'run_nucmer.py', '--mummerplot', '-p', prefix, ref, query
]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.link_files(self.get_chart_dir(),
[self.__concatenate_file_name(prefix, 'png')])
self.print_end_of_process_pid()
return self.__concatenate_file_name(prefix, 'coords')
def make_detailed_table(self, name=None, aligned_bam_dict=None, contigs=None, agp=None, taxonomy_output=None):
self.print_start_of_process_pid()
# aligned_bam_dict=["type" =
# ["group1 = [
# [file1, file2, filen]
#
# ]
# ]
# ]
if contigs and agp:
if not name:
name = self.get_output_header()
out_header = os.path.join(self.get_table_dir(),name)
cmd_list = ['make_detailed_assembly_table.py','-c',out_header,'-s',out_header,'-a',agp]
if taxonomy_output:
cmd_list += ['-t',taxonomy_output]
if aligned_bam_dict:
for type in aligned_bam_dict.keys():
arg = "--" + str(type) + "_bam"
bam_file_string = ''
for group in aligned_bam_dict[type].keys():
bam_file_string += aligned_bam_dict[type][group]['file'] + ','
cmd_list += [arg,bam_file_string[:-1]]
cmd_list += [contigs]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return self.__concatenate_file_name(out_header, 'contig_detail.table.txt')
def run_blast(self,
query=None,
db=constant.BLAST_NT,
threads=None,
extension='blast.xml',
name=None,
blast_task='megablast'):
self.print_start_of_process_pid()
if query:
if not threads:
threads = self.get_num_threads()
if not name:
name = self.get_output_header()
blast_output = self.__concatenate_file_name(
os.path.join(self.get_work_dir(), name), extension)
rc = RunCommand([
'run_blast.py', '-o', blast_output, '-b', blast_task, '-t',
str(threads), db, query
])
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return blast_output
def standardize_file_inputs(self, scaffolds=None, contigs=None, agp=None, minScaffSize=1, minConSize=1, minGapSize=10, rename=True):
# We will make the assembly files from the inputs to ensure minimum NCBI gap size is enforce
#if contigs and agp and scaffolds:
# return self.copy_files(self.get_work_dir(),[scaffolds,contigs,agp])
self.print_start_of_process_pid()
if not contigs and not scaffolds:
print "Must give a fasta file for make_standard_assembly_files."
sys.exit(-1)
out_header = os.path.join(self.get_work_dir(),self.get_output_header())
cmd_list = ['make_standard_assembly_files.py','-o',out_header,'-s', str(minScaffSize),'-c', str(minConSize), '-g', str(minGapSize)]
if rename:
cmd_list += ['--rename']
if contigs:
cmd_list += ['-C', contigs]
if agp:
cmd_list += ['-A', agp]
if scaffolds:
cmd_list += ['-S', scaffolds]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return self.__concatenate_file_name(out_header,"scaffolds.fasta"),\
self.__concatenate_file_name(out_header, "contigs.fasta"), \
self.__concatenate_file_name(out_header, "agp")
def get_simple_bam_stats(self, bam_files=[], name=None, ref_header='reference'):
self.print_start_of_process_pid()
if bam_files:
if not name:
name = self.get_output_header()
cmd_list = ['get_simple_bam_stats.py','-o', os.path.join(self.get_table_dir(),self.__concatenate_file_name(name, ref_header))] + bam_files
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def parse_blast_xml(self, blast_xml=None):
self.print_start_of_process_pid()
if blast_xml:
parse_output = re.sub("xml", "parsed.txt", blast_xml)
rc = RunCommand(
['parse_blast_xml.py', '-o', parse_output, blast_xml])
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return parse_output
def main():
if __check_inputs(options.classify, options.rdp_out):
rnammer_cmd = __build_rnammer_cmd(args[0], options.rnammer_out,
options.gene, options.superkingdom)
rc = RunCommand(rnammer_cmd)
print "RUNNING: " + rc.get_command()
rc.run_command()
if options.classify:
rdp_cmd = __build_rdp_cmd(options.rnammer_out, options.rdp_out)
rc = RunCommand(rdp_cmd)
print "RUNNING: " + rc.get_command()
rc.run_command()
return 0
else:
print "If classifying hits, must supply classify flag and rdp output file."
sys.exit(-1)
def _get_circular_show_tilings_command(output_header, delta):
"""
Build up the circular show-tilings command from output header and
the nucmer delta file.
"""
arg_list = [
'-R', '-a', '-v 5', '-g -1', '-V 0', '-u', output_header + '.unplaced',
'-c'
]
return RunCommand(_build_showtiling_command(delta, arg_list))
def get_kmer_copy_number(self, fasta=None, name=None, kmer_size=29):
self.print_start_of_process_pid()
if fasta:
if not name:
name = self.get_output_header()
cmd_list = ['kmer_copy_number.py', '-k', str(kmer_size), '-o', os.path.join(self.get_table_dir(), name), fasta]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def run_kmer_coverage(self, ref=None, query=None, name=None, kmer_size=29):
self.print_start_of_process_pid()
if ref and query:
if not name:
name = self.get_output_header()
cmd_list = ['kmer_coverage.py', '-k', str(kmer_size), '-o', os.path.join(self.get_table_dir(), name), ref, query]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def plot_insert_size(self, insert_size_files=[], direction='fr', ref_header='reference', output_base='reads'):
self.print_start_of_process_pid()
if insert_size_files:
type_output_header = os.path.join(self.get_table_dir(),self.__concatenate_file_name(output_base, ref_header))
plot_output_header = os.path.join(self.get_chart_dir(),self.__concatenate_file_name(output_base, ref_header))
cmd_list = ['plot_insert_size.py', '-o', plot_output_header,'-m', type_output_header, '-d', direction] + insert_size_files
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def run_scaffold_accuracy(self, ref=None, query=None, name=None):
self.print_start_of_process_pid()
if ref and query:
if not name:
name = self.get_output_header()
cmd_list = ['run_scaffold_accuracy.py', '-o', os.path.join(self.get_work_dir(), name), '-t', os.path.join(self.get_table_dir(), name),
ref, query]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def get_bam_coverage_stats(self, bam_files=[], name=None, ref_header='reference', want_phys_cvg=False):
self.print_start_of_process_pid()
if bam_files:
if not name:
name = self.get_output_header()
cmd_list = ['get_bam_coverage_stats.py','-o', os.path.join(self.get_table_dir(),self.__concatenate_file_name(name, ref_header))]
if want_phys_cvg:
cmd_list += ['-p']
cmd_list += bam_files
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def compare_to_reference(self, coords_file=None, name=None):
self.print_start_of_process_pid()
if coords_file:
if not name:
name = self.get_output_header()
table = os.path.join(self.get_table_dir(), name)
cmd_list = ['compare_to_reference.py', '-o',table, '-n', '-c', coords_file]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def identify_coverage_anomalies(self, bam_files=[], name=None, ref_header='reference', window_size=1000):
self.print_start_of_process_pid()
if bam_files and ref_header:
if not name:
name = self.get_output_header()
analysis_output_header = self.__concatenate_file_name(name, ref_header)
coverage_anomalies = os.path.join(self.get_chart_dir(), self.__concatenate_file_name(analysis_output_header, "coverage_anomalies"))
cmd_list = ['identify_coverage_anomalies.py','--window_size', str(window_size)] + bam_files + [coverage_anomalies]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def parse_blast_xml(self, blast_xml=None, no_blast_filter=False ):
self.print_start_of_process_pid()
if blast_xml:
parse_output = re.sub("xml", "parsed.txt", blast_xml)
cmd = ['parse_blast_xml.py', '-o', parse_output]
if no_blast_filter:
cmd += ['--no_filter']
rc = RunCommand(cmd + [blast_xml])
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return parse_output
def _get_show_tilings_command(output_header, id, coverage, circular, delta):
"""
Build up the basic show-tilings command from output header, an identity cutoff,
a coverage cutoff, whether or not we want circular alignments, and the nucmer
delta file.
"""
arg_list = [
'-R', '-u', output_header + '.unplaced', "-i", id, "-v", coverage
]
if circular:
arg_list += ["-c"]
return RunCommand(_build_showtiling_command(delta, arg_list))
def analyze_gap_ends(self, name=None, contigs=None, agp=None, extension='analyze_gap_ends'):
self.print_start_of_process_pid()
if contigs and agp:
if not name:
name = self.get_output_header()
output = os.path.join(self.get_table_dir(), name)
chart = self.__concatenate_file_name(os.path.join(self.get_chart_dir(), name), extension)
cmd_list = ['analyze_gap_ends.py', '-c', chart, '-t', output, contigs, agp]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def blast_bubbles(self, name=None, taxonomy_output=None, contig_detail=None):
self.print_start_of_process_pid()
if taxonomy_output and contig_detail:
if not name:
name = self.get_output_header()
blast_bubble_output = os.path.join(self.get_chart_dir(),name)
blast_bubble_detail = os.path.join(self.get_work_dir(),name)
cmd_list = ['blast_bubbles.py', '-v', blast_bubble_detail,'-o', blast_bubble_output, contig_detail, taxonomy_output]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def get_blast_hit_taxonomy(self, parsed_blast=None, query=None, nodes=constant.BLAST_NODES, names=constant.BLAST_NAMES, name=None):
self.print_start_of_process_pid()
if parsed_blast and query:
if not name:
name = self.get_output_header()
tax_output = os.path.join(self.get_table_dir(), name)
taxonomy_heatmap = re.sub("txt", "heatmap", parsed_blast)
if nodes and names:
rc = RunCommand(['get_blast_hit_taxonomy.py', '-o', tax_output,'-m', taxonomy_heatmap, parsed_blast, query])
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return taxonomy_heatmap
def blast_map(self, taxonomy_heatmap=None, agp=None, name=None):
self.print_start_of_process_pid()
if taxonomy_heatmap:
if not name:
name = self.get_output_header()
blast_map_output = os.path.join(self.get_chart_dir(), name)
cmd = ['blast_map.py', '-o', blast_map_output]
if agp:
cmd += ['-g', agp]
cmd += [taxonomy_heatmap]
rc = RunCommand(cmd)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
def run_insert_size(self, bam_file=None, insert_size=None, std_dev=None):
self.print_start_of_process_pid()
if bam_file:
output_header = re.sub(".bam", "", bam_file)
cmd_list = ['run_insert_size_from_bam.py','-o',output_header]
if insert_size:
cmd_list += ['-i', str(insert_size)]
if std_dev:
cmd_list += ['-s', str(std_dev)]
cmd_list += [bam_file]
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()
return self.__concatenate_file_name(output_header, 'insert_size.metrics')
def get_basic_assembly_stats(self, name=None, contigs=None, agp=None, assembler='assembler', extension='cumulative_sizes', extra_args = []):
self.print_start_of_process_pid()
if not name:
name = self.get_output_header()
output = os.path.join(self.get_table_dir(), name)
chart = self.__concatenate_file_name(os.path.join(self.get_chart_dir(), name), extension)
cmd_list = ['basic_assembly_stats.py','-n',name,'-a',assembler,'-o', output,'-C','-S','-t',chart] + extra_args
if contigs and agp:
cmd_list += ['-f', agp, contigs]
elif not agp:
cmd_list += [contigs]
else:
print "No file given for assembly stats."
return
rc = RunCommand(cmd_list)
self.print_and_run_command(rc)
self.print_end_of_process_pid()