# locates all reconstructed files
reconstructed_files = comp_directory_name+"/reconstructed_single_contigs.fasta "
for comp in new_components:
dir_base = comp_directory_name + "/" + sample_name + str(comp)
dir_out = dir_base + "algo_output"
reconstructed_files += (dir_out + '/' + 'reconstructed.fasta ')
# Creates new directory with concatenation of all reconstructed files
dir_base = comp_directory_name + "/" + sample_name + "all"
dir_out = dir_base + "algo_output"
run_cmd("mkdir " + dir_out)
out_file = dir_out + "/" + "all_reconstructed.fasta"
run_cmd("cat " + reconstructed_files + " > " + out_file)
process_concatenated_fasta(out_file, dir_out + "/reconstructed_org.fasta",original_ds)
f_log.write(str(time.asctime()) + ': All partitions completed.\n')
#run_cmd('cp ' + dir_out + "/reconstructed.fasta " + dir_out + "/reconstructed_org.fasta")
if find_reps:
f_log.write(str(time.asctime()) + ': Finding representative outputs\n')
run_cmd('cat ' + dir_out + "/reconstructed_org.fasta | perl -e 'while (<>) {$h=$_; $s=<>; $seqs{$h}=$s;} foreach $header (sort {length($seqs{$a}) <=> length($seqs{$b})} keys %seqs) {print $header.$seqs{$header}}' > " + dir_out + "/reconstructed_sorted.fasta " )
run_cmd(python_path + ' ' + shannon_dir + 'faster_reps.py -d ' + dir_out + "/reconstructed_sorted.fasta " + dir_out + "/reconstructed.fasta ")
f_log.write(str(time.asctime()) + ': Representative outputs found.\n')
else:
run_cmd('mv ' + dir_out + "/reconstructed_org.fasta " + dir_out + "/reconstructed.fasta ")
#------Filter using Kallisto-------#
if run_kallisto:
run_cmd('mv ' + dir_out+"/reconstructed.fasta " + dir_out+"/rec_before_kallisto.fasta")
'reconstructed.fasta')
else:
reconstructed_files[comp[0]] = [dir + '/' + 'reconstructed.fasta']
# Creates new directory with concatenation of all reconstructed files
dir_base = comp_directory_name + "/" + sample_name + "_all"
dir_out = dir_base + "algo_output"
run_cmd("mkdir " + dir_out)
temp_file = dir_out + "/" + "all_reconstructed.fasta"
temp_file_args = ""
for comp in reconstructed_files:
for file_name in reconstructed_files[comp]:
temp_file_args = temp_file_args + file_name + " "
run_cmd("cat " + temp_file_args + " > " + temp_file)
process_concatenated_fasta(temp_file, dir_out + "/reconstructed_org.fasta")
#run_cmd('cp ' + dir_out + "/reconstructed.fasta " + dir_out + "/reconstructed_org.fasta")
run_cmd(
'cat ' + dir_out +
"/reconstructed_org.fasta | perl -e 'while (<>) {$h=$_; $s=<>; $seqs{$h}=$s;} foreach $header (sort {length($seqs{$a}) <=> length($seqs{$b})} keys %seqs) {print $header.$seqs{$header}}' > "
+ dir_out + "/reconstructed_sorted.fasta ")
run_cmd('python ' + shannon_dir + 'fast_reps.py -d ' + dir_out +
"/reconstructed_sorted.fasta " + dir_out + "/reconstructed.fasta ")
# Compares reconstructed file against reference
if compare_ans:
run_cmd("cp " + ref_file + ' ' + dir_out + "/reference.fasta")
run_cmd("python " + shannon_dir + "run_MB_SF.py " + dir_base +
reconstructed_files[comp[0]].append(dir + '/' + 'reconstructed.fasta')
else:
reconstructed_files[comp[0]] = [dir + '/' + 'reconstructed.fasta']
# Creates new directory with concatenation of all reconstructed files
dir_base = comp_directory_name + "/" + sample_name + "_all"
dir_out = dir_base + "algo_output"
run_cmd("mkdir " + dir_out)
temp_file = dir_out + "/" + "all_reconstructed.fasta"
temp_file_args = ""
for comp in reconstructed_files:
for file_name in reconstructed_files[comp]:
temp_file_args = temp_file_args + file_name + " "
run_cmd("cat " + temp_file_args + " > " + temp_file)
process_concatenated_fasta(temp_file, dir_out + "/reconstructed_org.fasta")
#run_cmd('cp ' + dir_out + "/reconstructed.fasta " + dir_out + "/reconstructed_org.fasta")
run_cmd('cat ' + dir_out + "/reconstructed_org.fasta | perl -e 'while (<>) {$h=$_; $s=<>; $seqs{$h}=$s;} foreach $header (sort {length($seqs{$a}) <=> length($seqs{$b})} keys %seqs) {print $header.$seqs{$header}}' > " + dir_out + "/reconstructed_sorted.fasta " )
run_cmd('python ' + shannon_dir + 'fast_reps.py -d ' + dir_out + "/reconstructed_sorted.fasta " + dir_out + "/reconstructed.fasta ")
# Compares reconstructed file against reference
if compare_ans:
run_cmd("cp " + ref_file + ' ' + dir_out + "/reference.fasta")
run_cmd("python " + shannon_dir + "run_MB_SF.py " + dir_base + " --compare ")
# updates log
if os.path.exists(comp_directory_name+"/before_sp_log.txt"):
# locates all reconstructed files
reconstructed_files = comp_directory_name+"/reconstructed_single_contigs.fasta "
for comp in new_components:
dir_base = comp_directory_name + "/" + sample_name + str(comp)
dir_out = dir_base + "algo_output"
reconstructed_files += (dir_out + '/' + 'reconstructed.fasta ')
# Creates new directory with concatenation of all reconstructed files
dir_base = comp_directory_name + "/" + sample_name + "all"
dir_out = dir_base + "algo_output"
run_cmd("mkdir " + dir_out)
out_file = dir_out + "/" + "all_reconstructed.fasta"
run_cmd("cat " + reconstructed_files + " > " + out_file)
process_concatenated_fasta(out_file, dir_out + "/reconstructed_org.fasta",original_ds)
f_log.write(str(time.asctime()) + ': All partitions completed.\n')
#run_cmd('cp ' + dir_out + "/reconstructed.fasta " + dir_out + "/reconstructed_org.fasta")
if find_reps:
f_log.write(str(time.asctime()) + ': Finding representative outputs\n')
run_cmd('cat ' + dir_out + "/reconstructed_org.fasta | perl -e 'while (<>) {$h=$_; $s=<>; $seqs{$h}=$s;} foreach $header (sort {length($seqs{$a}) <=> length($seqs{$b})} keys %seqs) {print $header.$seqs{$header}}' > " + dir_out + "/reconstructed_sorted.fasta " )
run_cmd(python_path + ' ' + shannon_dir + 'faster_reps.py -d ' + dir_out + "/reconstructed_sorted.fasta " + dir_out + "/reconstructed.fasta ")
f_log.write(str(time.asctime()) + ': Representative outputs found.\n')
else:
run_cmd('mv ' + dir_out + "/reconstructed_org.fasta " + dir_out + "/reconstructed.fasta ")
#------Filter using Kallisto-------#
if run_kallisto:
run_cmd('mv ' + dir_out+"/reconstructed.fasta " + dir_out+"/rec_before_kallisto.fasta")
