def get_job_commands(python_exe_fp,alpha_diversity_fp,tree_fp,job_prefix,\
metrics,input_fps,output_dir,working_dir,\
command_prefix=None,command_suffix=None):
"""Generate alpha diversity commands to be submitted to cluster
"""
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
commands = []
result_filepaths = []
for input_fp in input_fps:
input_path, input_fn = split(input_fp)
output_fn = 'alpha_%s' % input_fn
rename_command, current_result_filepaths = get_rename_command(\
[output_fn],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -i %s -o %s -t %s -m %s %s %s' %\
(command_prefix,\
python_exe_fp,\
alpha_diversity_fp,\
input_fp,
working_dir + '/' + output_fn,
tree_fp,
metrics,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,alpha_diversity_fp,tree_fp,job_prefix,\
metrics,input_fps,output_dir,working_dir,\
command_prefix=None,command_suffix=None):
"""Generate alpha diversity commands to be submitted to cluster
"""
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
commands = []
result_filepaths = []
for input_fp in input_fps:
input_path, input_fn = split(input_fp)
output_fn = 'alpha_%s' % input_fn
rename_command, current_result_filepaths = get_rename_command(\
[output_fn],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -i %s -o %s -t %s -m %s %s %s' %\
(command_prefix,\
python_exe_fp,\
alpha_diversity_fp,\
input_fp,
working_dir + '/' + output_fn,
tree_fp,
metrics,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,align_seqs_fp,fasta_fps,template_aln_fp,\
pairwise_alignment_method,output_dir,blast_db,\
min_length,min_percent_id,job_prefix,working_dir,command_prefix=None,\
command_suffix=None):
"""Generate PyNAST commands which should be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_aligned.fasta',
job_prefix + '.%d_failures.fasta',
job_prefix + '.%d_log.txt']
# Initialize the command_prefix and command_suffix
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
# Create lists to store the results
commands = []
result_filepaths = []
# If there is a value for blast_db, pass it. If not, it
# will be created on-the-fly. Note that on-the-fly blast dbs
# are created with a string of random chars in the name, so this is safe.
# They shouldn't overwrite one another, and will be cleaned up.
if blast_db:
blast_option = '-d %s' % blast_db
else:
blast_option = ''
# Iterate over the input files
for i,fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = \
'%s %s %s %s -p %1.2f -e %d -m pynast -t %s -a %s -o %s -i %s %s %s' %\
(command_prefix,\
python_exe_fp,\
align_seqs_fp,\
blast_option,\
min_percent_id,\
min_length,\
template_aln_fp,\
pairwise_alignment_method,
working_dir,
fasta_fp,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands_single_otu_table(python_exe_fp,
beta_diversity_fp,
tree_fp,
job_prefix,
metrics,
input_fp,
output_dir,
working_dir,
jobs_to_start,
command_prefix=None,
command_suffix=None):
"""Generate beta diversity to split single OTU table to multiple jobs
always passes -f to beta_diversity.py
"""
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
commands = []
result_filepaths = []
sids = parse_otu_table(open(input_fp, 'U'))[0]
sample_id_groups = merge_to_n_commands(sids, jobs_to_start, ',', '', '')
for i, sample_id_group in enumerate(sample_id_groups):
working_dir_i = os.path.join(working_dir, str(i))
output_dir_i = os.path.join(output_dir, str(i))
input_dir, input_fn = split(input_fp)
sample_id_desc = sample_id_group.replace(',', '_')
output_fns = ['%s_%s' % (metric, input_fn) \
for metric in metrics.split(',')]
rename_command, current_result_filepaths = get_rename_command(\
output_fns,working_dir_i,output_dir_i)
result_filepaths += current_result_filepaths
command = '%s %s %s -i %s -o %s -t %s -m %s -f -r %s %s %s' %\
(command_prefix,\
python_exe_fp,\
beta_diversity_fp,\
input_fp,
working_dir_i + '/',
tree_fp,
metrics,
sample_id_group,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands_multiple_otu_tables(python_exe_fp,
beta_diversity_fp,
tree_fp,
job_prefix,
metrics,
input_fps,
output_dir,
working_dir,
command_prefix=None,
command_suffix=None,
full_tree=False):
"""Generate beta diversity to split multiple OTU tables to multiple jobs
"""
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
if full_tree:
full_tree_str = '-f'
else:
full_tree_str = ''
commands = []
result_filepaths = []
for input_fp in input_fps:
input_path, input_fn = split(input_fp)
output_fns = ['%s_%s' % (metric, input_fn) \
for metric in metrics.split(',')]
rename_command, current_result_filepaths = get_rename_command(\
output_fns,working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -i %s -o %s -t %s -m %s %s %s %s' %\
(command_prefix,\
python_exe_fp,\
beta_diversity_fp,\
input_fp,
working_dir + '/',
tree_fp,
metrics,
full_tree_str,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,
pick_otus_fp,
fasta_fps,
output_dir,
blast_db,
job_prefix,
working_dir,
max_e_value,
similarity,
min_aligned_percent,
command_prefix='/bin/bash; ',
command_suffix='; exit'):
"""Generate pick_otus commands which should be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_otus.log', job_prefix + '.%d_otus.txt']
# Create lists to store the results
commands = []
result_filepaths = []
# Iterate over the input files
for i, fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = \
'%s %s %s -i %s -b %s -m blast -o %s -e %s -s %s --min_aligned_percent %s %s %s' %\
(command_prefix,
python_exe_fp,
pick_otus_fp,
fasta_fp,
blast_db,
working_dir,
max_e_value,
similarity,
min_aligned_percent,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_commands(python_exe_fp,assign_taxonomy_fp,confidence,job_prefix,\
fasta_fps,rdp_jar_fp,output_dir,working_dir,\
command_prefix=None,command_suffix=None,\
id_to_taxonomy_fp=None,reference_seqs_fp=None):
"""Generate RDP classifier commands which should be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_tax_assignments.log',
job_prefix + '.%d_tax_assignments.txt']
command_prefix = command_prefix or\
'/bin/bash; export RDP_JAR_PATH=%s; ' % rdp_jar_fp
command_suffix = command_suffix or\
'; exit'
rdp_extra_params = ''
if id_to_taxonomy_fp and reference_seqs_fp:
rdp_extra_params = '-t %s -r %s' % (id_to_taxonomy_fp, reference_seqs_fp)
commands = []
result_filepaths = []
for i,fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)#,\
#id_to_taxonomy_fp,reference_seqs_fp)
result_filepaths += current_result_filepaths
command = '%s %s %s %s -c %1.2f -m rdp -o %s -i %s %s %s' %\
(command_prefix,\
python_exe_fp,\
assign_taxonomy_fp,\
rdp_extra_params,
confidence,
working_dir,
fasta_fp,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,assign_taxonomy_fp,id_to_taxonomy_fp,\
e_value,blast_db,job_prefix,\
blastmat_path,fasta_fps,output_dir,working_dir,\
command_prefix=None,command_suffix=None):
"""Generate BlastTaxonAssiger classifier commands to be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [
job_prefix + '.%d_tax_assignments.log',
job_prefix + '.%d_tax_assignments.txt'
]
command_prefix = command_prefix or\
'/bin/bash; cd %s; export BLASTMAT=%s;' \
% (working_dir,blastmat_path)
command_suffix = command_suffix or\
'; exit'
commands = []
result_filepaths = []
for i, fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -o %s -m blast -e %s -b %s -i %s -t %s %s %s' %\
(command_prefix,\
python_exe_fp,\
assign_taxonomy_fp,\
working_dir,
e_value,
blast_db,
fasta_fp,
id_to_taxonomy_fp,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,rarefaction_fp,job_prefix,\
input_fp,output_dir,working_dir,min_seqs,max_seqs,step,num_reps,\
lineages_included, command_prefix=None,command_suffix=None):
"""Generate alpha diversity commands to be submitted to cluster
"""
# Create data for each run (depth, output_fn)
run_parameters = []
for num_seqs in range(min_seqs,max_seqs+1, step):
for rep_num in range(num_reps):
run_parameters.append((\
num_seqs,'rarefaction_%d_%d.txt' % (num_seqs,rep_num)))
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
commands = []
result_filepaths = []
if lineages_included:
lineages_included_param = '--lineages_included'
else:
lineages_included_param = ''
for depth,output_fn in run_parameters:
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[output_fn],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -i %s -o %s %s -d %s %s %s' %\
(command_prefix,\
python_exe_fp,\
rarefaction_fp,\
input_fp,
working_dir + '/' + output_fn,
lineages_included_param,
depth,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,rarefaction_fp,job_prefix,\
input_fp,output_dir,working_dir,min_seqs,max_seqs,step,num_reps,\
lineages_included, command_prefix=None,command_suffix=None):
"""Generate alpha diversity commands to be submitted to cluster
"""
# Create data for each run (depth, output_fn)
run_parameters = []
for num_seqs in range(min_seqs, max_seqs + 1, step):
for rep_num in range(num_reps):
run_parameters.append((\
num_seqs,'rarefaction_%d_%d.txt' % (num_seqs,rep_num)))
command_prefix = command_prefix or '/bin/bash; '
command_suffix = command_suffix or '; exit'
commands = []
result_filepaths = []
if lineages_included:
lineages_included_param = '--lineages_included'
else:
lineages_included_param = ''
for depth, output_fn in run_parameters:
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[output_fn],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -i %s -o %s %s -d %s %s %s' %\
(command_prefix,\
python_exe_fp,\
rarefaction_fp,\
input_fp,
working_dir + '/' + output_fn,
lineages_included_param,
depth,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,assign_taxonomy_fp,id_to_taxonomy_fp,\
e_value,blast_db,job_prefix,\
blastmat_path,fasta_fps,output_dir,working_dir,\
command_prefix=None,command_suffix=None):
"""Generate BlastTaxonAssiger classifier commands to be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_tax_assignments.log',
job_prefix + '.%d_tax_assignments.txt']
command_prefix = command_prefix or\
'/bin/bash; cd %s; export BLASTMAT=%s;' \
% (working_dir,blastmat_path)
command_suffix = command_suffix or\
'; exit'
commands = []
result_filepaths = []
for i,fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -o %s -m blast -e %s -b %s -i %s -t %s %s %s' %\
(command_prefix,\
python_exe_fp,\
assign_taxonomy_fp,\
working_dir,
e_value,
blast_db,
fasta_fp,
id_to_taxonomy_fp,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,pick_otus_fp,fasta_fps,
output_dir,blast_db,job_prefix,working_dir,max_e_value,
similarity,min_aligned_percent,
command_prefix='/bin/bash; ',command_suffix='; exit'):
"""Generate pick_otus commands which should be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_otus.log',
job_prefix + '.%d_otus.txt']
# Create lists to store the results
commands = []
result_filepaths = []
# Iterate over the input files
for i,fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = \
'%s %s %s -i %s -b %s -m blast -o %s -e %s -s %s --min_aligned_percent %s %s %s' %\
(command_prefix,
python_exe_fp,
pick_otus_fp,
fasta_fp,
blast_db,
working_dir,
max_e_value,
similarity,
min_aligned_percent,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_commands(python_exe_fp,assign_taxonomy_fp,confidence,job_prefix,\
fasta_fps,rdp_jar_fp,output_dir,working_dir,\
command_prefix=None,command_suffix=None):
"""Generate RDP classifier commands which should be submitted to cluster
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [
job_prefix + '.%d_tax_assignments.log',
job_prefix + '.%d_tax_assignments.txt'
]
command_prefix = command_prefix or\
'/bin/bash; export RDP_JAR_PATH=%s; ' % rdp_jar_fp
command_suffix = command_suffix or\
'; exit'
commands = []
result_filepaths = []
for i, fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = '%s %s %s -c %1.2f -m rdp -o %s -i %s %s %s' %\
(command_prefix,\
python_exe_fp,\
assign_taxonomy_fp,\
confidence,
working_dir,
fasta_fp,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,pick_otus_fp,fasta_fps,
output_dir,refseqs_fp,job_prefix,working_dir,similarity,
enable_rev_strand_match,optimal_uclust,exact_uclust,
max_accepts,max_rejects,stepwords,word_length,
stable_sort,save_uc_files,command_prefix='/bin/bash; ',
command_suffix='; exit'):
"""Generate pick_otus commands which should be run
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_otus.log',
job_prefix + '.%d_otus.txt',
job_prefix + '.%s_failures.txt']
# Create lists to store the results
commands = []
result_filepaths = []
if enable_rev_strand_match:
enable_rev_strand_match_str = '-z'
else:
enable_rev_strand_match_str = ''
if optimal_uclust:
optimal_uclust_str = '-A'
else:
optimal_uclust_str = ''
if exact_uclust:
exact_uclust_str = '-E'
else:
exact_uclust_str = ''
if stable_sort:
stable_sort_str = ''
else:
stable_sort_str = '--suppress_uclust_stable_sort'
if save_uc_files:
save_uc_files = ''
out_filenames += [job_prefix + '%d_clusters.uc']
else:
save_uc_files = '-d'
# Iterate over the input files
for i,fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = \
'%s %s %s -i %s -r %s -m uclust_ref --suppress_new_clusters -o %s -s %s %s %s %s --max_accepts %s --max_rejects %s --stepwords %d --w %d %s %s %s %s' %\
(command_prefix,\
python_exe_fp,\
pick_otus_fp,\
fasta_fp,\
refseqs_fp,\
working_dir,\
similarity,\
enable_rev_strand_match_str,
optimal_uclust_str,
exact_uclust_str,
max_accepts,
max_rejects,
stepwords,
word_length,
stable_sort_str,
save_uc_files,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,
pick_otus_fp,
fasta_fps,
output_dir,
refseqs_fp,
job_prefix,
working_dir,
similarity,
enable_rev_strand_match,
optimal_uclust,
exact_uclust,
max_accepts,
max_rejects,
stable_sort,
save_uc_files,
command_prefix='/bin/bash; ',
command_suffix='; exit'):
"""Generate pick_otus commands which should be run
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [
job_prefix + '.%d_otus.log', job_prefix + '.%d_otus.txt',
job_prefix + '.%s_failures.txt'
]
# Create lists to store the results
commands = []
result_filepaths = []
if enable_rev_strand_match:
enable_rev_strand_match_str = '-z'
else:
enable_rev_strand_match_str = ''
if optimal_uclust:
optimal_uclust_str = '-A'
else:
optimal_uclust_str = ''
if exact_uclust:
exact_uclust_str = '-E'
else:
exact_uclust_str = ''
if stable_sort:
stable_sort_str = '--uclust_stable_sort'
else:
stable_sort_str = ''
if save_uc_files:
save_uc_files = ''
out_filenames += [job_prefix + '%d_clusters.uc']
else:
save_uc_files = '-d'
# Iterate over the input files
for i, fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames],working_dir,output_dir)
result_filepaths += current_result_filepaths
command = \
'%s %s %s -i %s -r %s -m uclust_ref --suppress_new_clusters -o %s -s %s %s %s %s --max_accepts %s --max_rejects %s %s %s %s %s' %\
(command_prefix,\
python_exe_fp,\
pick_otus_fp,\
fasta_fp,\
refseqs_fp,\
working_dir,\
similarity,\
enable_rev_strand_match_str,
optimal_uclust_str,
exact_uclust_str,
max_accepts,
max_rejects,
stable_sort_str,
save_uc_files,
rename_command,
command_suffix)
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp,
identify_chimeric_seqs_fp,
fasta_fps,
output_dir,
ref_seqs_fp,
job_prefix,
working_dir,
aligned_reference_seqs_fp,
blast_db,
chimera_detection_method,
min_div_ratio,
num_fragments,
taxonomy_depth,
max_e_value,
id_to_taxonomy_fp,
command_prefix='',
command_suffix=''):
# command_prefix='/bin/bash; ', command_suffix='; exit'):
"""Generate identify_chimeric_seqs commands which should be run
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_chimeric.txt']
# Create lists to store the results
commands = []
result_filepaths = []
# Iterate over the input files
for i, fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames], working_dir, output_dir)
result_filepaths += current_result_filepaths
#Need to be filled
optional_options = ""
if chimera_detection_method == 'blast_fragments':
if ref_seqs_fp:
optional_options += " -r %s" % ref_seqs_fp
if blast_db:
optional_options += " -b %s" % blast_db
command = \
'%s %s %s -i %s -t %s -m blast_fragments -o %s -n %s -d %s -e %s %s %s %s' %\
(command_prefix,
python_exe_fp,
identify_chimeric_seqs_fp,
fasta_fp,
id_to_taxonomy_fp,
working_dir+"/"+out_filenames[0] % i,
num_fragments,
taxonomy_depth,
max_e_value,
optional_options,
rename_command,
command_suffix)
elif chimera_detection_method == 'ChimeraSlayer':
if min_div_ratio:
optional_options += " --min_div_ratio %s" % min_div_ratio
if ref_seqs_fp:
optional_options += " -r %s" % ref_seqs_fp
command = \
'%s %s %s -i %s -a %s -m ChimeraSlayer -o %s %s %s %s' %\
(command_prefix,
python_exe_fp,
identify_chimeric_seqs_fp,
fasta_fp,
aligned_reference_seqs_fp,
working_dir+"/"+out_filenames[0] % i,
optional_options,
rename_command,
command_suffix)
else:
raise NotImplementedError
commands.append(command)
return commands, result_filepaths
def get_job_commands(python_exe_fp, identify_chimeric_seqs_fp, fasta_fps,
output_dir, ref_seqs_fp, job_prefix, working_dir,
aligned_reference_seqs_fp, blast_db,
chimera_detection_method, min_div_ratio, num_fragments,
taxonomy_depth, max_e_value, id_to_taxonomy_fp,
command_prefix='', command_suffix=''):
# command_prefix='/bin/bash; ', command_suffix='; exit'):
"""Generate identify_chimeric_seqs commands which should be run
"""
# Create basenames for each of the output files. These will be filled
# in to create the full list of files created by all of the runs.
out_filenames = [job_prefix + '.%d_chimeric.txt']
# Create lists to store the results
commands = []
result_filepaths = []
# Iterate over the input files
for i,fasta_fp in enumerate(fasta_fps):
# Each run ends with moving the output file from the tmp dir to
# the output_dir. Build the command to perform the move here.
rename_command, current_result_filepaths = get_rename_command(\
[fn % i for fn in out_filenames], working_dir, output_dir)
result_filepaths += current_result_filepaths
#Need to be filled
optional_options = ""
if chimera_detection_method=='blast_fragments':
if ref_seqs_fp:
optional_options += " -r %s" % ref_seqs_fp
if blast_db:
optional_options += " -b %s" % blast_db
command = \
'%s %s %s -i %s -t %s -m blast_fragments -o %s -n %s -d %s -e %s %s %s %s' %\
(command_prefix,
python_exe_fp,
identify_chimeric_seqs_fp,
fasta_fp,
id_to_taxonomy_fp,
working_dir+"/"+out_filenames[0] % i,
num_fragments,
taxonomy_depth,
max_e_value,
optional_options,
rename_command,
command_suffix)
elif chimera_detection_method=='ChimeraSlayer':
if min_div_ratio:
optional_options += " --min_div_ratio %s" % min_div_ratio
if ref_seqs_fp:
optional_options += " -r %s" % ref_seqs_fp
command = \
'%s %s %s -i %s -a %s -m ChimeraSlayer -o %s %s %s %s' %\
(command_prefix,
python_exe_fp,
identify_chimeric_seqs_fp,
fasta_fp,
aligned_reference_seqs_fp,
working_dir+"/"+out_filenames[0] % i,
optional_options,
rename_command,
command_suffix)
else:
raise NotImplementedError
commands.append(command)
return commands, result_filepaths