def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for i, f in enumerate(input_files):
folder_path = os.path.dirname(f)
if f.endswith('.gz'):
print('Unzipping: ', f)
f = useful.gunzip_python(f)
# Run trimmomatic
trimming_parameters = {
'SLIDINGWINDOW': str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'SE'
trimmedf = processing.run_trimmomatic(f, folder_path, method, phred_encode, trimming_parameters)[0]
# Run quality filtering
filtered_trimmed_file = fastx.Run_Quality_Filter(trimmedf, output_dir=folder_path, quality=quality_cutoff, percent=percent_bases)
os.remove(trimmedf)
processed_files.append(filtered_trimmed_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
annotated_f = igfft.igfft_multiprocess(f, file_type='FASTQ', species=species, locus=loci, parsing_settings={'isotype': isotyping_barcodes, 'remove_insertions': remove_insertions}, num_processes=number_threads, delete_alignment_file=True)
annotated_files.append(annotated_f[0])
print('Pairing sequences')
output_dir = os.path.dirname(annotated_files[0])
pairing.RunPairing(annotated_files, annotated_file_formats='TAB', analysis_method='GEORGIOU_INHOUSE', output_folder_path=output_dir, prefix_output_files=group_name, cluster_cutoff=cluster_setting, annotation_cluster_setting=annotation_cluster_cutoff)
print('Pipeline complete')
def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for i, f in enumerate(input_files):
folder_path = os.path.dirname(f)
if f.endswith('.gz'):
print('Unzipping: ', f)
f = useful.gunzip_python(f)
# Run trimmomatic
trimming_parameters = {
'SLIDINGWINDOW': str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'SE'
trimmedf = processing.run_trimmomatic(f, folder_path, method,
phred_encode,
trimming_parameters)[0]
# Run quality filtering
filtered_trimmed_file = fastx.Run_Quality_Filter(
trimmedf,
output_dir=folder_path,
quality=quality_cutoff,
percent=percent_bases)
os.remove(trimmedf)
processed_files.append(filtered_trimmed_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
annotated_f = igfft.igfft_multiprocess(f,
file_type='FASTQ',
species=species,
locus=loci,
parsing_settings={
'isotype':
isotyping_barcodes,
'remove_insertions':
remove_insertions
},
num_processes=number_threads,
delete_alignment_file=True)
annotated_files.append(annotated_f[0])
print('Pairing sequences')
output_dir = os.path.dirname(annotated_files[0])
pairing.RunPairing(annotated_files,
annotated_file_formats='TAB',
analysis_method='GEORGIOU_INHOUSE',
output_folder_path=output_dir,
prefix_output_files=group_name,
cluster_cutoff=cluster_setting,
annotation_cluster_setting=annotation_cluster_cutoff)
print('Pipeline complete')
def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for pair_of_files in input_files:
folder_path = os.path.dirname(pair_of_files[0])
for i, f in enumerate(pair_of_files):
if f.endswith('.gz'):
print('Unzipping: ', f)
pair_of_files[i] = useful.gunzip_python(f)
# Run trimmomatic
if trim_seqs:
print('Trimming low quality bases')
trimming_parameters = {
'SLIDINGWINDOW': str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'PE'
input_files = processing.run_trimmomatic(pair_of_files, folder_path, method, phred_encode, trimming_parameters)
else:
input_files = pair_of_files
# Stitch R1-R2 files
pairing_parameters = {
'v': min_overlap_length,
'm': max_assembly_length,
'n': min_assembly_length,
'u': max_fraction_uncalled,
}
print('Stitching R1-R2 reads')
pear_results = processing.run_pear(input_files[0], input_files[1], working_directory=folder_path, parameters=pairing_parameters, num_threads=number_threads, memory=pear_memory)[0]
# Run quality filtering
filtered_file = fastx.Run_Quality_Filter(pear_results, output_dir=folder_path, quality=quality_cutoff, percent=percent_bases)
os.remove(pear_results)
processed_files.append(filtered_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
output_file = useful.removeFileExtension(f) + '.mixcr.alignment'
output_file_annotation = useful.removeFileExtension(f) + '.mixcr.annotation'
# Run MIXCR file
print('Running MIXCR')
[annotated_f, command_val] = mixcr.RunMixcr(f, output_file, filetype='FASTQ', loci=[], species='', exportPrettyAlignment=False, num_threads=number_threads)
# Parse MIXCR file
print('Parsing MIXCR')
annotated_file = mixcr.parseMIXCR(f, output_file, 'FASTQ', output_file_annotation, command_val=command_val) # again, annotated_file should be equal to outfile_annotation
annotated_files.append(annotated_file[0])
print('Pipeline complete')
def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for pair_of_files in input_files:
folder_path = os.path.dirname(pair_of_files[0])
for i, f in enumerate(pair_of_files):
if f.endswith('.gz'):
print('Unzipping: ', f)
pair_of_files[i] = useful.gunzip_python(f)
# Run trimmomatic
if trim_seqs:
print('Trimming low quality bases')
trimming_parameters = {
'SLIDINGWINDOW': str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'PE'
input_files = processing.run_trimmomatic(pair_of_files, folder_path, method, phred_encode, trimming_parameters)
else:
input_files = pair_of_files
# Stitch R1-R2 files
pairing_parameters = {
'v': min_overlap_length,
'm': max_assembly_length,
'n': min_assembly_length,
'u': max_fraction_uncalled,
}
print('Stitching R1-R2 reads')
pear_results = processing.run_pear(input_files[0], input_files[1], working_directory=folder_path, parameters=pairing_parameters, num_threads=number_threads, memory=pear_memory)[0]
# Run quality filtering
filtered_file = fastx.Run_Quality_Filter(pear_results, output_dir=folder_path, quality=quality_cutoff, percent=percent_bases)
os.remove(pear_results)
processed_files.append(filtered_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
annotated_f = igfft.igfft_multiprocess(f, species=species, locus=loci, parsing_settings={'isotype': isotyping_barcodes, 'remove_insertions': remove_insertions}, num_processes=number_threads, delete_alignment_file=True)
annotated_files.append(annotated_f[0])
print('Pipeline complete')
def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for i, f in enumerate(input_files):
folder_path = os.path.dirname(f)
if f.endswith('.gz'):
print('Unzipping: ', f)
f = useful.gunzip_python(f)
# Run trimmomatic
trimming_parameters = {
'SLIDINGWINDOW': str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'SE'
trimmedf = processing.run_trimmomatic(f, folder_path, method, phred_encode, trimming_parameters)[0]
# Run quality filtering
filtered_trimmed_file = fastx.Run_Quality_Filter(trimmedf, output_dir=folder_path, quality=quality_cutoff, percent=percent_bases)
os.remove(trimmedf)
processed_files.append(filtered_trimmed_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
output_file = useful.removeFileExtension(f) + '.mixcr.alignment'
output_file_annotation = useful.removeFileExtension(f) + '.mixcr.annotation'
# Run MIXCR file
print('Running MIXCR')
[annotated_f, command_val] = mixcr.RunMixcr(f, output_file, filetype='FASTQ', loci=[], species='', exportPrettyAlignment=False, num_threads=number_threads)
# Parse MIXCR file
print('Parsing MIXCR')
annotated_file = mixcr.parseMIXCR(f, output_file, 'FASTQ', output_file_annotation, command_val=command_val) # again, annotated_file should be equal to outfile_annotation
annotated_files.append(annotated_file)
print('Pairing sequences')
output_dir = os.path.dirname(annotated_files[0])
pairing.RunPairing(annotated_files, annotated_file_formats='TAB', analysis_method='MIXCR', output_folder_path=output_dir, prefix_output_files=group_name, cluster_cutoff=cluster_setting, annotation_cluster_setting=annotation_cluster_cutoff)
print('Pipeline complete')
def run_gglab_pipeline(input_files, species, loci, group_name=""):
# Unzip files
print("Processing raw fastq files")
processed_files = []
for pair_of_files in input_files:
folder_path = os.path.dirname(pair_of_files[0])
for i, f in enumerate(pair_of_files):
if f.endswith(".gz"):
print("Unzipping: ", f)
pair_of_files[i] = useful.gunzip_python(f)
# Run trimmomatic
if trim_seqs:
print("Trimming low quality bases")
trimming_parameters = {
"SLIDINGWINDOW": str(window_trim) + ":" + str(quality_cutoff_trim),
"MINLEN": min_read_len_post_trim,
}
method = "PE"
input_files = processing.run_trimmomatic(
pair_of_files, folder_path, method, phred_encode, trimming_parameters
)
else:
input_files = pair_of_files
# Stitch R1-R2 files
pairing_parameters = {
"v": min_overlap_length,
"m": max_assembly_length,
"n": min_assembly_length,
"u": max_fraction_uncalled,
}
print("Stitching R1-R2 reads")
pear_results = processing.run_pear(
input_files[0],
input_files[1],
working_directory=folder_path,
parameters=pairing_parameters,
num_threads=number_threads,
memory=pear_memory,
)[0]
# Run quality filtering
filtered_file = fastx.Run_Quality_Filter(
pear_results, output_dir=folder_path, quality=quality_cutoff, percent=percent_bases
)
os.remove(pear_results)
processed_files.append(filtered_file)
print("Annotating processed fastq files")
annotated_files = []
for i, f in enumerate(processed_files):
output_file = useful.removeFileExtension(f) + ".mixcr.alignment"
output_file_annotation = useful.removeFileExtension(f) + ".mixcr.annotation"
# Run MIXCR file
print("Running MIXCR")
[annotated_f, command_val] = mixcr.RunMixcr(
f,
output_file,
filetype="FASTQ",
loci=[],
species="",
exportPrettyAlignment=False,
num_threads=number_threads,
)
# Parse MIXCR file
print("Parsing MIXCR")
annotated_file = mixcr.parseMIXCR(
f, output_file, "FASTQ", output_file_annotation, command_val=command_val
) # again, annotated_file should be equal to outfile_annotation
annotated_files.append(annotated_file[0])
print("Pipeline complete")
def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for i, f in enumerate(input_files):
folder_path = os.path.dirname(f)
if f.endswith('.gz'):
print('Unzipping: ', f)
f = useful.gunzip_python(f)
# Run trimmomatic
trimming_parameters = {
'SLIDINGWINDOW': str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'SE'
trimmedf = processing.run_trimmomatic(f, folder_path, method,
phred_encode,
trimming_parameters)[0]
# Run quality filtering
filtered_trimmed_file = fastx.Run_Quality_Filter(
trimmedf,
output_dir=folder_path,
quality=quality_cutoff,
percent=percent_bases)
os.remove(trimmedf)
processed_files.append(filtered_trimmed_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
output_file = useful.removeFileExtension(f) + '.mixcr.alignment'
output_file_annotation = useful.removeFileExtension(
f) + '.mixcr.annotation'
# Run MIXCR file
print('Running MIXCR')
[annotated_f,
command_val] = mixcr.RunMixcr(f,
output_file,
filetype='FASTQ',
loci=[],
species='',
exportPrettyAlignment=False,
num_threads=number_threads)
# Parse MIXCR file
print('Parsing MIXCR')
annotated_file = mixcr.parseMIXCR(
f,
output_file,
'FASTQ',
output_file_annotation,
command_val=command_val
) # again, annotated_file should be equal to outfile_annotation
annotated_files.append(annotated_file)
print('Pairing sequences')
output_dir = os.path.dirname(annotated_files[0])
pairing.RunPairing(annotated_files,
annotated_file_formats='TAB',
analysis_method='MIXCR',
output_folder_path=output_dir,
prefix_output_files=group_name,
cluster_cutoff=cluster_setting,
annotation_cluster_setting=annotation_cluster_cutoff)
print('Pipeline complete')
def run_gglab_pipeline(input_files, species, loci, group_name=''):
# Unzip files
print('Processing raw fastq files')
processed_files = []
for pair_of_files in input_files:
folder_path = os.path.dirname(pair_of_files[0])
for i, f in enumerate(pair_of_files):
if f.endswith('.gz'):
print('Unzipping: ', f)
pair_of_files[i] = useful.gunzip_python(f)
# Run trimmomatic
if trim_seqs:
print('Trimming low quality bases')
trimming_parameters = {
'SLIDINGWINDOW':
str(window_trim) + ':' + str(quality_cutoff_trim),
'MINLEN': min_read_len_post_trim
}
method = 'PE'
input_files = processing.run_trimmomatic(pair_of_files,
folder_path, method,
phred_encode,
trimming_parameters)
else:
input_files = pair_of_files
# Stitch R1-R2 files
pairing_parameters = {
'v': min_overlap_length,
'm': max_assembly_length,
'n': min_assembly_length,
'u': max_fraction_uncalled,
}
print('Stitching R1-R2 reads')
pear_results = processing.run_pear(input_files[0],
input_files[1],
working_directory=folder_path,
parameters=pairing_parameters,
num_threads=number_threads,
memory=pear_memory)[0]
# Run quality filtering
filtered_file = fastx.Run_Quality_Filter(pear_results,
output_dir=folder_path,
quality=quality_cutoff,
percent=percent_bases)
os.remove(pear_results)
processed_files.append(filtered_file)
print('Annotating processed fastq files')
annotated_files = []
for i, f in enumerate(processed_files):
annotated_f = igfft.igfft_multiprocess(f,
species=species,
locus=loci,
parsing_settings={
'isotype':
isotyping_barcodes,
'remove_insertions':
remove_insertions
},
num_processes=number_threads,
delete_alignment_file=True)
annotated_files.append(annotated_f[0])
print('Pipeline complete')