def make_pipeline(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='md5')
# Get a list of paths to all the input files
input_files = state.config.get_option('files')
# Stages are dependent on the state
stages = Stages(state)
# The original FASTQ files
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_files,
name='original_files',
output=input_files)
# Align paired end reads in FASTQ to the reference producing a BAM file
pipeline.transform(
task_func=stages.md5_checksum,
name='md5_checksum',
input=output_from('original_files'),
filter=suffix(''),
output='.md5')
return pipeline
def test_newstyle_mkdir (self):
test_pipeline = Pipeline("test")
test_pipeline.follows(task_which_makes_directories, mkdir(directories), mkdir(tempdir + 'c'), mkdir(tempdir + 'd', tempdir + 'e'), mkdir(tempdir + 'e'))
test_pipeline.run(multiprocess = 10, verbose = 0)
for d in 'abcde':
fullpath = os.path.join(os.path.dirname(__file__), tempdir, d)
self.assertTrue(os.path.exists(fullpath))
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.parallel(parallel_task, [['A', 1], ['B',3], ['C',3], ['D',4], ['E',4], ['F',4]])
try:
test_pipeline.run(multiprocess = 50, verbose = 0)
except ruffus.ruffus_exceptions.RethrownJobError:
return
raise Exception("Missing exception")
def test_newstyle_ruffus(self):
test_pipeline = Pipeline("test")
test_pipeline.parallel(parallel_task, [["A", 1], ["B", 3], ["C", 3], ["D", 4], ["E", 4], ["F", 4]])
try:
test_pipeline.run(multiprocess=50, verbose=0)
except ruffus.ruffus_exceptions.RethrownJobError:
return
raise Exception("Missing exception")
def test_newstyle_task(self):
test_pipeline = Pipeline("test")
test_pipeline.files(task1, a)
save_to_str_logger = t_save_to_str_logger()
test_pipeline.run(multiprocess=10, logger=save_to_str_logger, verbose=1)
self.assertTrue("@files() was empty" in save_to_str_logger.warning_str)
print("\n Warning printed out correctly", file=sys.stderr)
def create_pipeline(self):
"""
Create new pipeline on the fly without using decorators
"""
global count_pipelines
count_pipelines = count_pipelines + 1
test_pipeline = Pipeline("test %d" % count_pipelines)
test_pipeline.transform(task_func=transform1,
input=input_file,
filter=suffix('.txt'),
output='.output',
extras=[runtime_data])
test_pipeline.transform(task_func=transform_raise_error,
input=input_file,
filter=suffix('.txt'),
output='.output',
extras=[runtime_data])
test_pipeline.split(task_func=split1,
input=input_file,
output=split1_outputs)
test_pipeline.merge(task_func=merge2,
input=split1,
output=merge2_output)
return test_pipeline
def test_newstyle_simpler (self):
test_pipeline = Pipeline("test")
test_pipeline.originate(task1, input_file_names, extras = [logger_proxy, logging_mutex])
test_pipeline.transform(task2, task1, suffix(".1"), ".2", extras = [logger_proxy, logging_mutex])
test_pipeline.transform(task3, task2, suffix(".2"), ".3", extras = [logger_proxy, logging_mutex])
test_pipeline.merge(task4, task3, final_file_name, extras = [logger_proxy, logging_mutex])
#test_pipeline.merge(task4, task3, final_file_name, extras = {"logger_proxy": logger_proxy, "logging_mutex": logging_mutex})
test_pipeline.run(multiprocess = 500, verbose = 0)
def test_newstyle_no_re_match (self):
try:
test_pipeline = Pipeline("test")
test_pipeline.transform(task_func = task_2,
input = None,
filter = regex(tempdir + "b"),
replace_inputs = inputs(tempdir + "a", tempdir + "b"),
output = "task_1.output")
test_pipeline.run(multiprocess = 10, verbose = 0)
except ruffus.ruffus_exceptions.error_task_transform_inputs_multiple_args:
print("\tExpected exception thrown 1")
return
except ruffus.ruffus_exceptions.error_inputs_multiple_args:
print("\tExpected exception thrown 2")
return
raise Exception("Inputs(...) with multiple arguments should have thrown an exception")
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.follows(setup_simulation_data, mkdir(gene_data_dir, simulation_data_dir))
test_pipeline.files(gwas_simulation, generate_simulation_params)\
.follows(setup_simulation_data)\
.follows(mkdir(working_dir, os.path.join(working_dir, "simulation_results")))
test_pipeline.collate(statistical_summary, gwas_simulation, regex(r"simulation_results/(\d+).\d+.simulation_res"), r"\1.mean")\
.posttask(lambda : sys.stdout.write("\nOK\n"))
test_pipeline.run(multiprocess = 50, verbose = 0)
for oo in "000.mean", "001.mean":
results_file_name = os.path.join(working_dir, oo)
if not os.path.exists(results_file_name):
raise Exception("Missing %s" % results_file_name)
def test_newstyle_no_re_match (self):
test_pipeline = Pipeline("test")
test_pipeline.originate(task_1, tempdir + "a").mkdir(tempdir)
test_pipeline.transform(task_2, task_1, regex("b"), "task_2.output")
save_to_str_logger = t_save_to_str_logger()
test_pipeline.run(multiprocess = 10, logger = save_to_str_logger, verbose = 1)
print(save_to_str_logger.warning_str)
self.assertTrue("no file names matched" in save_to_str_logger.warning_str)
print("\n Warning printed out correctly", file=sys.stderr)
def make_pipeline2( pipeline_name = "pipeline2"):
test_pipeline2 = Pipeline(pipeline_name)
test_pipeline2.transform(task_func = task_1_to_1,
# task name
name = "44_to_55",
# placeholder: will be replaced later with set_input()
input = None,
filter = suffix(".44"),
output = ".55")
test_pipeline2.merge( task_func = task_m_to_1,
input = test_pipeline2["44_to_55"],
output = tempdir + "/final.output",)
# Set head and tail
test_pipeline2.set_tail_tasks([test_pipeline2[task_m_to_1]])
if not DEBUG_do_not_define_head_task:
test_pipeline2.set_head_tasks([test_pipeline2["44_to_55"]])
return test_pipeline2
def test_newstyle_ruffus(self):
test_pipeline = Pipeline("test")
test_pipeline.split(task_func=prepare_files,
input=None,
output=tempdir + '*.animal')\
.follows(mkdir(tempdir, tempdir + "test"))\
.posttask(lambda: do_write(tempdir + "task.done", "Task 1 Done\n"))
test_pipeline.collate(task_func=summarise_by_grouping,
input=prepare_files,
filter=regex(r'(.*/).*\.(.*)\.animal'),
output=r'\1\2.results')\
.posttask(lambda: do_write(tempdir + "task.done", "Task 2 Done\n"))
test_pipeline.run(multiprocess=10, verbose=0)
check_species_correct()
def test_transform_with_missing_formatter_args_b(self):
test_pipeline = Pipeline("test")
test_pipeline.originate(task_func = generate_initial_files,
output = [os.path.join(tempdir, ff + ".tmp") for ff in "abcd"])\
.mkdir(tempdir)
test_pipeline.transform(task_func = transform_with_missing_formatter_args,
input = generate_initial_files,
filter = formatter(),
output = "{path[0]}/{basename[0]}.task1",
extras =['echo {dynamic_message} > {some_file}'])
s = StringIO()
test_pipeline.printout(s, [transform_with_missing_formatter_args], verbose=4, wrap_width = 10000, pipeline= "test")
self.assertIn("Missing key = {dynamic_message}", s.getvalue())
#log to stream
s = StringIO()
logger = t_stream_logger(s)
test_pipeline.run([transform_with_missing_formatter_args], verbose=5, pipeline= "test", logger=logger)
self.assertIn("Missing key = {dynamic_message}", s.getvalue())
def test_newstyle_mkdir (self):
test_pipeline = Pipeline("test")
test_pipeline.follows(task_which_makes_directories,
mkdir(directories),
mkdir(unicode(tempdir + "c")),
mkdir(unicode(tempdir + "d"),
unicode(tempdir + "e")),
mkdir(unicode(tempdir + "e")))\
.posttask(touch_file(unicode(tempdir + "f")))
test_pipeline.originate(task_which_makes_files, [tempdir + "g", tempdir + "h"])
test_pipeline.run(multiprocess = 10, verbose = 0)
for d in 'abcdefgh':
fullpath = os.path.join(os.path.dirname(__file__), tempdir, d)
self.assertTrue(os.path.exists(fullpath))
def test_newstyle_mkdir_run(self):
test_pipeline = Pipeline("test")
test_pipeline.split(task_func = generate_initial_files1,
input = 1,
output = [tempdir + "/" + prefix + "_name.tmp1" for prefix in "abcd"])
test_pipeline.transform( task_func = test_transform,
input = generate_initial_files1,
filter = formatter(),
output = "{path[0]}/{basename[0]}.dir/{basename[0]}.tmp2")\
.mkdir(tempdir + "/test1")\
.mkdir(tempdir + "/test2")\
.mkdir(generate_initial_files1, formatter(),
["{path[0]}/{basename[0]}.dir", 3, "{path[0]}/{basename[0]}.dir2"])
test_pipeline.mkdir(test_transform2, tempdir + "/test3")\
.mkdir(generate_initial_files1, formatter(),
"{path[0]}/{basename[0]}.dir2")
cleanup_tmpdir()
pipeline_run([test_transform, test_transform2], verbose=0, multiprocess = 2, pipeline= "main")
outf.write(prefices + ",")
def check_combinations_with_replacement3_merged_task(infiles, outfile):
with open(outfile, "w") as p:
for infile in sorted(infiles):
with open(infile) as ii:
p.write(ii.read())
def cleanup_tmpdir():
os.system('rm -f %s %s' %
(os.path.join(tempdir, '*'), RUFFUS_HISTORY_FILE))
test_pipeline1 = Pipeline("test1")
test_pipeline2 = Pipeline("test2")
gen_task1 = test_pipeline1.originate(task_func=generate_initial_files1,
name="WOWWWEEE",
output=[tempdir + "/" + prefix + "_name.tmp1" for prefix in "abcd"])
test_pipeline1.originate(task_func=generate_initial_files2,
output=[tempdir + "/e_name.tmp1", tempdir + "/f_name.tmp1"])
test_pipeline1.originate(task_func=generate_initial_files3,
output=[tempdir + "/g_name.tmp1", tempdir + "/h_name.tmp1"])
test_pipeline1.product(task_func=check_product_task,
input=[tempdir + "/" + prefix +
"_name.tmp1" for prefix in "abcd"],
filter=formatter(".*/(?P<FILE_PART>.+).tmp1$"),
input2=generate_initial_files2,
filter2=formatter(),
input3=generate_initial_files3,
def make_pipeline(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='hiplexpipe')
# Get a list of paths to all the FASTQ files
fastq_files = state.config.get_option('fastqs')
# Stages are dependent on the state
stages = Stages(state)
# The original FASTQ files
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_fastqs,
name='original_fastqs',
output=fastq_files)
# Align paired end reads in FASTQ to the reference producing a BAM file
pipeline.transform(
task_func=stages.align_bwa,
name='align_bwa',
input=output_from('original_fastqs'),
# Match the R1 (read 1) FASTQ file and grab the path and sample name.
# This will be the first input to the stage.
# Hi-Plex example: OHI031002-P02F04_S318_L001_R1_001.fastq
filter=formatter('.+/(?P<sample>[a-zA-Z0-9_-]+)_R1_(?P<lib>[a-zA-Z0-9-:]+).fastq.gz'),
# Add one more inputs to the stage:
# 1. The corresponding R2 FASTQ file
# Hi-Plex example: OHI031002-P02F04_S318_L001_R2_001.fastq
add_inputs=add_inputs(
'{path[0]}/{sample[0]}_R2_{lib[0]}.fastq.gz'),
# Add an "extra" argument to the state (beyond the inputs and outputs)
# which is the sample name. This is needed within the stage for finding out
# sample specific configuration options
extras=['{sample[0]}', '{lib[0]}'],
# The output file name is the sample name with a .bam extension.
output='alignments/{sample[0]}.clipped.bam')
# Call variants using undr_rover
pipeline.transform(
task_func=stages.apply_undr_rover,
name='apply_undr_rover',
input=output_from('original_fastqs'),
# Match the R1 (read 1) FASTQ file and grab the path and sample name.
# This will be the first input to the stage.
filter=formatter('.+/(?P<sample>[a-zA-Z0-9_-]+)_R1_(?P<lib>[a-zA-Z0-9-:]+).fastq.gz'),
add_inputs=add_inputs(
'{path[0]}/{sample[0]}_R2_{lib[0]}.fastq.gz'),
extras=['{sample[0]}'],
# The output file name is the sample name with a .bam extension.
output='variants/undr_rover/{sample[0]}.vcf')
# Sort the BAM file using Picard
pipeline.transform(
task_func=stages.sort_bam_picard,
name='sort_bam_picard',
input=output_from('align_bwa'),
filter=suffix('.clipped.bam'),
output='.clipped.sort.bam')
# High quality and primary alignments
pipeline.transform(
task_func=stages.primary_bam,
name='primary_bam',
input=output_from('sort_bam_picard'),
filter=suffix('.clipped.sort.bam'),
output='.clipped.sort.hq.bam')
# index bam file
pipeline.transform(
task_func=stages.index_sort_bam_picard,
name='index_bam',
input=output_from('primary_bam'),
filter=suffix('.clipped.sort.hq.bam'),
output='.clipped.sort.hq.bam.bai')
# generate mapping metrics.
pipeline.transform(
task_func=stages.intersect_bed,
name='intersect_bed',
input=output_from('primary_bam'),
filter=suffix('.clipped.sort.hq.bam'),
output='.intersectbed.bam')
pipeline.transform(
task_func=stages.coverage_bed,
name='coverage_bed',
input=output_from('intersect_bed'),
filter=suffix('.intersectbed.bam'),
output='.bedtools_hist_all.txt')
pipeline.transform(
task_func=stages.genome_reads,
name='genome_reads',
input=output_from('primary_bam'),
filter=suffix('.clipped.sort.hq.bam'),
output='.mapped_to_genome.txt')
pipeline.transform(
task_func=stages.target_reads,
name='target_reads',
input=output_from('intersect_bed'),
filter=suffix('.intersectbed.bam'),
output='.mapped_to_target.txt')
pipeline.transform(
task_func=stages.total_reads,
name='total_reads',
input=output_from('align_bwa'),
filter=suffix('.clipped.bam'),
output='.total_raw_reads.txt')
# pipeline.transform(
# task_func=stages.generate_stats,
# name='generate_stats',
# input=output_from(['coverage_bed', 'genome_reads', 'target_reads', 'total_reads']),
# filter=formatter('.+/(?P<sample>.+).txt'),
# extras=['{sample[0]}'],
# output='all_sample.summary.txt')
###### GATK VARIANT CALLING ######
# Call variants using GATK
(pipeline.transform(
task_func=stages.call_haplotypecaller_gatk,
name='call_haplotypecaller_gatk',
input=output_from('primary_bam'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9-_]+).clipped.sort.hq.bam'),
output='variants/gatk/{sample[0]}.g.vcf')
.follows('index_sort_bam_picard'))
# Combine G.VCF files for all samples using GATK
pipeline.merge(
task_func=stages.combine_gvcf_gatk,
name='combine_gvcf_gatk',
input=output_from('call_haplotypecaller_gatk'),
output='variants/gatk/ALL.combined.vcf')
# Genotype G.VCF files using GATK
pipeline.transform(
task_func=stages.genotype_gvcf_gatk,
name='genotype_gvcf_gatk',
input=output_from('combine_gvcf_gatk'),
filter=suffix('.combined.vcf'),
output='.raw.vcf')
# Annotate VCF file using GATK
pipeline.transform(
task_func=stages.variant_annotator_gatk,
name='variant_annotator_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.raw.vcf'),
output='.raw.annotate.vcf')
# Apply VariantFiltration using GATK
pipeline.transform(
task_func=stages.apply_variant_filtration_gatk,
name='apply_variant_filtration_gatk',
input=output_from('variant_annotator_gatk'),
filter=suffix('.raw.annotate.vcf'),
output='.raw.annotate.filtered.vcf')
# Apply VEP
(pipeline.transform(
task_func=stages.apply_vep,
name='apply_vep',
input=output_from('apply_variant_filtration_gatk'),
filter=suffix('.raw.annotate.filtered.vcf'),
output='.raw.annotate.filtered.vep.vcf')
.follows('apply_variant_filtration_gatk'))
pipeline.transform(
task_func=stages.sort_vcfs,
name='sort_vcfs',
input=output_from('apply_undr_rover'),
filter=suffix('.vcf'),
output='.sorted.vcf')
pipeline.transform(
task_func=stages.index_vcfs,
name='index_vcfs',
input=output_from('sort_vcfs'),
filter=suffix('.sorted.vcf'),
output='.sorted.vcf.tbi')
(pipeline.transform(
task_func=stages.concatenate_vcfs,
name='sort_vcfs',
input=output_from('apply_undr_rover'),
filter=suffix('.sorted.vcf'),
output='variants/undr_rover/combined_undr_rover.vcf')
.follows('index_vcfs'))
pipeline.transform(
task_func=stages.index_final_vcf,
name='index_final_vcf',
input=output_from('concatenate_vcfs'),
filter=suffix('.vcf'),
output='.vcf.tbi')
return pipeline
def test_newstyle_simpler(self):
test_pipeline = Pipeline("test")
test_pipeline.originate(task1,
input_file_names,
extras=[logger_proxy, logging_mutex])
test_pipeline.transform(task2,
task1,
suffix(".1"),
".2",
extras=[logger_proxy, logging_mutex])
test_pipeline.transform(task3,
task2,
suffix(".2"),
".3",
extras=[logger_proxy, logging_mutex])
test_pipeline.merge(task4,
task3,
final_file_name,
extras=[logger_proxy, logging_mutex])
#test_pipeline.merge(task4, task3, final_file_name, extras = {"logger_proxy": logger_proxy, "logging_mutex": logging_mutex})
test_pipeline.run(multiprocess=500, verbose=0)
"test_active_if/b.3" -> "test_active_if/b.4"
"test_active_if/b.4" -> "test_active_if/summary.5"
"""
expected_inactive_text = """null -> "test_active_if/a.1"
"test_active_if/a.1" -> "test_active_if/a.2"
"test_active_if/a.2" -> "test_active_if/a.4"
null -> "test_active_if/b.1"
"test_active_if/b.1" -> "test_active_if/b.2"
"test_active_if/b.2" -> "test_active_if/b.4"
"test_active_if/b.4" -> "test_active_if/summary.5"
"""
# alternative syntax
test_pipeline = Pipeline("test")
test_pipeline.originate(task1, ['test_active_if/a.1', 'test_active_if/b.1'], "an extra_parameter")\
.follows(mkdir("test_active_if"))
test_pipeline.transform(task2, task1, suffix(".1"), ".2")
test_pipeline.transform(task3, task1, suffix(
".1"), ".3").active_if(lambda: pipeline_active_if)
test_pipeline.collate(task4, [task2, task3], regex(r"(.+)\.[23]"), r"\1.4")
test_pipeline.merge(task5, task4, "test_active_if/summary.5")
class Test_ruffus(unittest.TestCase):
def setUp(self):
try:
shutil.rmtree(tempdir)
except:
pass
with open(output_file, "w") as oo: pass
#---------------------------------------------------------------
# first task
@transform(create_initial_file_pairs, suffix(".start"), ".output.1")
def first_task(input_files, output_file):
with open(output_file, "w"): pass
#---------------------------------------------------------------
# second task
@transform(first_task, suffix(".output.1"), ".output.2")
def second_task(input_files, output_file):
with open(output_file, "w"): pass
test_pipeline = Pipeline("test")
test_pipeline.originate(output = [ [tempdir + 'data/scratch/lg/what/one/two/three/four/five/six/seven/job1.a.start', tempdir + 'job1.b.start'],
[tempdir + 'data/scratch/lg/what/one/two/three/four/five/six/seven/job2.a.start', tempdir + 'job2.b.start'],
[tempdir + 'data/scratch/lg/what/one/two/three/four/five/six/seven/job3.a.start', tempdir + 'job3.b.start'] ],
task_func = create_initial_file_pairs)
test_pipeline.transform(task_func = first_task, input = create_initial_file_pairs, filter = suffix(".start"), output = ".output.1")
test_pipeline.transform(input = first_task, filter = suffix(".output.1"), output = ".output.2", task_func= second_task)
decorator_syntax = 0
oop_syntax = 1
class Test_verbosity(unittest.TestCase):
#___________________________________________________________________________
#
# test_printout_abbreviated_path1
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.split(task_func = split_fasta_file,
input = tempdir + "original.fa",
output = [tempdir + "files.split.success",
tempdir + "files.split.*.fa"])\
.posttask(lambda: verbose_output.write(" Split into %d files\n" % 10))
test_pipeline.transform(task_func = align_sequences,
input = split_fasta_file,
filter = suffix(".fa"),
output = ".aln" # fa -> aln
)\
.posttask(lambda: verbose_output.write(" Sequences aligned\n"))
test_pipeline.transform(task_func = percentage_identity,
input = align_sequences, # find all results from align_sequences
filter = suffix(".aln"), # replace suffix with:
output = [r".pcid", # .pcid suffix for the result
r".pcid_success"] # .pcid_success to indicate job completed
)\
.posttask(lambda: verbose_output.write(" %Identity calculated\n"))
test_pipeline.merge(task_func = combine_results,
input = percentage_identity,
output = [tempdir + "all.combine_results",
tempdir + "all.combine_results_success"])\
.posttask(lambda: verbose_output.write(" Results recombined\n"))
test_pipeline.run(multiprocess = 50, verbose = 0)
if not os.path.exists(tempdir + "all.combine_results"):
raise Exception("Missing %s" % (tempdir + "all.combine_results"))
def make_pipeline_process(state):
# Define empty pipeline
pipeline = Pipeline(name='genericpipe')
# Get a list of paths to all the directories to be combined for variant calling
run_directories = state.config.get_option('runs')
#grab files from each of the processed directories in "runs"
gatk_files = []
for directory in run_directories:
gatk_files.extend(glob.glob(directory + '/variants/gatk/*.g.vcf'))
# Stages are dependent on the state
stages = Stages(state)
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(task_func=stages.glob_gatk,
name='glob_gatk',
output=gatk_files)
safe_make_dir('variants')
safe_make_dir('variants/gatk')
# Combine G.VCF files for all samples using GATK
pipeline.merge(task_func=stages.combine_gvcf_gatk,
name='combine_gvcf_gatk',
input=output_from('glob_gatk'),
output='ALL.combined.vcf')
# Genotype G.VCF files using GATK
pipeline.transform(task_func=stages.genotype_gvcf_gatk,
name='genotype_gvcf_gatk',
input=output_from('combine_gvcf_gatk'),
filter=suffix('.combined.vcf'),
output='.raw.vcf')
# Apply GT filters to genotyped vcf
pipeline.transform(task_func=stages.genotype_filter_gatk,
name='genotype_filter_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.raw.vcf'),
output='.raw.gt-filter.vcf')
# Decompose and normalise multiallelic sites
pipeline.transform(task_func=stages.vt_decompose_normalise,
name='vt_decompose_normalise',
input=output_from('genotype_filter_gatk'),
filter=suffix('.raw.gt-filter.vcf'),
output='.raw.gt-filter.decomp.norm.vcf')
# Annotate VCF file using GATK
pipeline.transform(task_func=stages.variant_annotator_gatk,
name='variant_annotator_gatk',
input=output_from('vt_decompose_normalise'),
filter=suffix('.raw.gt-filter.decomp.norm.vcf'),
output='.raw.gt-filter.decomp.norm.annotate.vcf')
# Filter vcf
pipeline.transform(
task_func=stages.gatk_filter,
name='gatk_filter',
input=output_from('variant_annotator_gatk'),
filter=suffix('.raw.gt-filter.decomp.norm.annotate.vcf'),
output='.raw.gt-filter.decomp.norm.annotate.filter.vcf')
#Apply VEP
(pipeline.transform(
task_func=stages.apply_vep,
name='apply_vep',
input=output_from('gatk_filter'),
filter=suffix('.raw.gt-filter.decomp.norm.annotate.filter.vcf'),
output='.raw.gt-filter.decomp.norm.annotate.filter.vep.vcf').follows(
'index_final_vcf'))
return pipeline
def make_pipeline1(
pipeline_name, # Pipelines need to have a unique name
starting_file_names):
test_pipeline = Pipeline(pipeline_name)
# We can change the starting files later using
# set_input() for transform etc.
# or set_output() for originate
# But it can be more convenient to just pass this to the function making the pipeline
#
test_pipeline.originate(task_originate, starting_file_names)\
.follows(mkdir(tempdir), mkdir(tempdir + "/testdir", tempdir + "/testdir2"))\
.posttask(touch_file(tempdir + "/testdir/whatever.txt"))
test_pipeline.transform(
task_func=task_m_to_1,
name="add_input",
# Lookup Task from function name task_originate()
# So long as this is unique in the pipeline
input=task_originate,
# requires an anchor from 3.7 onwards, see
# https://bugs.python.org/issue34982
filter=regex(r"^(.*)"),
add_inputs=add_inputs(tempdir + "/testdir/whatever.txt"),
output=r"\1.22")
test_pipeline.transform(
task_func=task_1_to_1,
name="22_to_33",
# Lookup Task from Task name
# Function name is not unique in the pipeline
input=output_from("add_input"),
filter=suffix(".22"),
output=".33")
tail_task = test_pipeline.transform(
task_func=task_1_to_1,
name="33_to_44",
# Ask Pipeline to lookup Task from Task name
input=test_pipeline["22_to_33"],
filter=suffix(".33"),
output=".44")
# Set the tail task so that users of my sub pipeline can use it as a dependency
# without knowing the details of task names
#
# Use Task() object directly without having to lookup
test_pipeline.set_tail_tasks([tail_task])
# If we try to connect a Pipeline without tail tasks defined, we have to
# specify the exact task within the Pipeline.
# Otherwise Ruffus will not know which task we mean and throw an exception
if DEBUG_do_not_define_tail_task:
test_pipeline.set_tail_tasks([])
# Set the head task so that users of my sub pipeline send input into it
# without knowing the details of task names
test_pipeline.set_head_tasks([test_pipeline[task_originate]])
return test_pipeline
def make_pipeline(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='vcf_annotation')
# Get a list of paths to all the FASTQ files
vcf_files = state.config.get_option('vcfs')
# Stages are dependent on the state
stages = Stages(state)
# The original VCF files
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_vcf,
name='original_vcf',
output=vcf_file)
# Decompose VCF using Vt
pipeline.transform(
task_func=stages.decompose_vcf,
name='decompose_vcf',
input=output_from('original_vcf'),
# This will be the first input to the stage.
# We assume the sample name may consist of only alphanumeric
# characters.
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).vcf'),
# Add an "extra" argument to the state (beyond the inputs and outputs)
# which is the VCF file name (e.g. study/family name.
# This is needed within the stage for finding out sample specific
# configuration options
extras=['{sample[0]}'],
# The output file name is the sample name with a .bam extension.
output='{path[0]}/{sample[0]}.decompose.normalize.vcf')
# FILTER COMMON VARIANTS
# ADD FILTER COMMON VARIANTS USING VEP
# Annotate using VEP
pipeline.transform(
task_func=stages.annotate_vep,
name='annotate_vep',
input=output_from('decompose_vcf'),
filter=suffix('.vcf'),
output='.vep.vcf')
# Annotate using SnpEff
pipeline.transform(
task_func=stages.annotate_snpeff,
name='annotate_snpeff',
input=output_from('annotate_vep'),
filter=suffix('.vcf'),
output='.snpeff.vcf')
# Mark duplicates in the BAM file using Picard
pipeline.transform(
task_func=stages.mark_duplicates_picard,
name='mark_duplicates_picard',
input=output_from('sort_bam_picard'),
filter=suffix('.sort.bam'),
# XXX should make metricsup an extra output?
output=['.sort.dedup.bam', '.metricsdup'])
# Generate chromosome intervals using GATK
pipeline.transform(
task_func=stages.chrom_intervals_gatk,
name='chrom_intervals_gatk',
input=output_from('mark_duplicates_picard'),
filter=suffix('.sort.dedup.bam'),
output='.chr.intervals')
# Local realignment using GATK
(pipeline.transform(
task_func=stages.local_realignment_gatk,
name='local_realignment_gatk',
input=output_from('chrom_intervals_gatk'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).chr.intervals'),
add_inputs=add_inputs('{path[0]}/{sample[0]}.sort.dedup.bam'),
output='{path[0]}/{sample[0]}.sort.dedup.realn.bam')
.follows('mark_duplicates_picard'))
# Base recalibration using GATK
pipeline.transform(
task_func=stages.base_recalibration_gatk,
name='base_recalibration_gatk',
input=output_from('local_realignment_gatk'),
filter=suffix('.sort.dedup.realn.bam'),
output=['.recal_data.csv', '.count_cov.log'])
# Print reads using GATK
(pipeline.transform(
task_func=stages.print_reads_gatk,
name='print_reads_gatk',
input=output_from('base_recalibration_gatk'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).recal_data.csv'),
add_inputs=add_inputs('{path[0]}/{sample[0]}.sort.dedup.realn.bam'),
output='{path[0]}/{sample[0]}.sort.dedup.realn.recal.bam')
.follows('local_realignment_gatk'))
# Call variants using GATK
pipeline.transform(
task_func=stages.call_variants_gatk,
name='call_variants_gatk',
input=output_from('print_reads_gatk'),
filter=suffix('.sort.dedup.realn.recal.bam'),
output='.raw.snps.indels.g.vcf')
# Combine G.VCF files for all samples using GATK
pipeline.merge(
task_func=stages.combine_gvcf_gatk,
name='combine_gvcf_gatk',
input=output_from('call_variants_gatk'),
output='PCExomes.mergegvcf.vcf')
# Genotype G.VCF files using GATK
pipeline.transform(
task_func=stages.genotype_gvcf_gatk,
name='genotype_gvcf_gatk',
input=output_from('combine_gvcf_gatk'),
filter=suffix('.mergegvcf.vcf'),
output='.genotyped.vcf')
# SNP recalibration using GATK
pipeline.transform(
task_func=stages.snp_recalibrate_gatk,
name='snp_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
output=['.snp_recal', '.snp_tranches', '.snp_plots.R'])
# INDEL recalibration using GATK
pipeline.transform(
task_func=stages.indel_recalibrate_gatk,
name='indel_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
output=['.indel_recal', '.indel_tranches', '.indel_plots.R'])
# Apply SNP recalibration using GATK
(pipeline.transform(
task_func=stages.apply_snp_recalibrate_gatk,
name='apply_snp_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
add_inputs=add_inputs(['PCExomes.snp_recal', 'PCExomes.snp_tranches']),
output='.recal_SNP.vcf')
.follows('snp_recalibrate_gatk'))
# Apply INDEL recalibration using GATK
(pipeline.transform(
task_func=stages.apply_indel_recalibrate_gatk,
name='apply_indel_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
add_inputs=add_inputs(
['PCExomes.indel_recal', 'PCExomes.indel_tranches']),
output='.recal_INDEL.vcf')
.follows('indel_recalibrate_gatk'))
# Combine variants using GATK
(pipeline.transform(
task_func=stages.combine_variants_gatk,
name='combine_variants_gatk',
input=output_from('apply_snp_recalibrate_gatk'),
filter=suffix('.recal_SNP.vcf'),
add_inputs=add_inputs(['PCExomes.recal_INDEL.vcf']),
output='.combined.vcf')
.follows('apply_indel_recalibrate_gatk'))
# Select variants using GATK
pipeline.transform(
task_func=stages.select_variants_gatk,
name='select_variants_gatk',
input=output_from('combine_variants_gatk'),
filter=suffix('.combined.vcf'),
output='.selected.vcf')
return pipeline
extension):
raise Exception("Should blow up first")
# ___________________________________________________________________________
#
# check_regex_out_of_range_regex_reference_error_task
# ___________________________________________________________________________
def check_regex_out_of_range_regex_reference_error_task(infiles, outfile,
prefix1,
prefix2,
extension):
raise Exception("Should blow up first")
test_pipeline = Pipeline("test")
test_pipeline.originate(task_func=generate_initial_files1,
output=[tempdir + "/" + prefix + "_name.tmp1" for prefix in "abcdefghi"])
test_pipeline.transform(task_func=check_regex_task,
input=generate_initial_files1,
filter=regex("(.*)/(?P<PREFIX>[abcd])(_name)(.tmp1)"),
output=r"\1/\g<PREFIX>\3.tmp2", # output file
extras=[r"\2", # extra: prefix = \2
r"\g<PREFIX>", # extra: prefix = \2
r"\4"]) # extra: extension
test_pipeline.transform(task_func=check_regex_unmatched_task,
input=generate_initial_files1,
filter=regex("(.*)/(?P<PREFIX>[abcd])(_name)(.xxx)"),
output=r"\1/\g<PREFIXA>\3.tmp2", # output file
outf.write(prefices + ",")
def test_combinations_with_replacement3_merged_task(infiles, outfile):
with open(outfile, "w") as p:
for infile in sorted(infiles):
with open(infile) as ii:
p.write(ii.read())
def cleanup_tmpdir():
os.system('rm -f %s %s' %
(os.path.join(tempdir, '*'), RUFFUS_HISTORY_FILE))
test_pipeline1 = Pipeline("test1")
test_pipeline2 = Pipeline("test2")
gen_task1 = test_pipeline1.originate(
task_func=generate_initial_files1,
name="WOWWWEEE",
output=[tempdir + "/" + prefix + "_name.tmp1" for prefix in "abcd"])
test_pipeline1.originate(
task_func=generate_initial_files2,
output=[tempdir + "/e_name.tmp1", tempdir + "/f_name.tmp1"])
test_pipeline1.originate(
task_func=generate_initial_files3,
output=[tempdir + "/g_name.tmp1", tempdir + "/h_name.tmp1"])
test_pipeline1.product(
task_func=test_product_task,
input=[tempdir + "/" + prefix + "_name.tmp1" for prefix in "abcd"],
filter=formatter(".*/(?P<FILE_PART>.+).tmp1$"),
def test_newstyle_collate(self):
"""
As above but create pipeline on the fly using object orientated syntax rather than decorators
"""
#
# Create pipeline on the fly, joining up tasks
#
test_pipeline = Pipeline("test")
test_pipeline.originate(task_func = generate_initial_files,
output = original_files)\
.mkdir(tempdir, tempdir+"/test")
test_pipeline.subdivide( task_func = split_fasta_file,
input = generate_initial_files,
filter = regex(r".*\/original_(\d+).fa"), # match original files
output = [tempdir + r"/files.split.\1.success", # flag file for each original file
tempdir + r"/files.split.\1.*.fa"], # glob pattern
extras = [r"\1"])\
.posttask(lambda: sys.stderr.write("\tSplit into %d files each\n" % JOBS_PER_TASK))
test_pipeline.transform(task_func = align_sequences,
input = split_fasta_file,
filter = suffix(".fa"),
output = ".aln") \
.posttask(lambda: sys.stderr.write("\tSequences aligned\n"))
test_pipeline.transform(task_func = percentage_identity,
input = align_sequences, # find all results from align_sequences
filter = suffix(".aln"), # replace suffix with:
output = [r".pcid", # .pcid suffix for the result
r".pcid_success"] # .pcid_success to indicate job completed
)\
.posttask(lambda: sys.stderr.write("\t%Identity calculated\n"))
test_pipeline.collate(task_func = combine_results,
input = percentage_identity,
filter = regex(r".*files.split\.(\d+)\.\d+.pcid"),
output = [tempdir + r"/\1.all.combine_results",
tempdir + r"/\1.all.combine_results_success"])\
.posttask(lambda: sys.stderr.write("\tResults recombined\n"))
#
# Cleanup, printout and run
#
self.cleanup_tmpdir()
s = StringIO()
test_pipeline.printout(s, [combine_results],
verbose=5,
wrap_width=10000)
self.assertTrue(
re.search('Job needs update:.*Missing files.*', s.getvalue(),
re.DOTALL) is not None)
test_pipeline.run(verbose=0)
def create_pipeline(self):
# each pipeline has a different name
global cnt_pipelines
cnt_pipelines = cnt_pipelines + 1
test_pipeline = Pipeline("test %d" % cnt_pipelines)
test_pipeline.originate(task_func=generate_initial_files1,
output=[tempdir + prefix + "_name.tmp1" for prefix in "abcd"])
test_pipeline.originate(task_func=generate_initial_files2,
output=[tempdir + "e_name.tmp1", tempdir + "f_name.tmp1"])
test_pipeline.originate(task_func=generate_initial_files3,
output=[tempdir + "g_name.tmp1", tempdir + "h_name.tmp1"])
test_pipeline.originate(task_func=generate_initial_files4,
output=tempdir + "i_name.tmp1")
test_pipeline.collate(task_func=check_task2,
input=[generate_initial_files1,
generate_initial_files2,
generate_initial_files3,
generate_initial_files4],
filter=formatter(),
output="{path[0]}/all.tmp2")
test_pipeline.transform(task_func=check_task3,
input=check_task2,
filter=suffix(".tmp2"),
output=".tmp3")
test_pipeline.transform(task_func=check_task4,
input=check_task3,
filter=suffix(".tmp3"),
output=".tmp4")
return test_pipeline
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.files(create_random_numbers, None, tempdir + "random_numbers.list")\
.follows(mkdir(tempdir))
test_pipeline.split(task_func = step_4_split_numbers_into_chunks,
input = tempdir + "random_numbers.list",
output = tempdir + "*.chunks")\
.follows(create_random_numbers)
test_pipeline.transform(task_func = step_5_calculate_sum_of_squares,
input = step_4_split_numbers_into_chunks,
filter = suffix(".chunks"),
output = ".sums")
test_pipeline.merge(task_func = step_6_calculate_variance, input = step_5_calculate_sum_of_squares, output = os.path.join(tempdir, "variance.result"))\
.posttask(lambda: sys.stdout.write(" hooray\n"))\
.posttask(print_hooray_again, print_whoppee_again, touch_file(os.path.join(tempdir, "done")))
test_pipeline.run(multiprocess = 50, verbose = 0)
output_file = os.path.join(tempdir, "variance.result")
if not os.path.exists (output_file):
raise Exception("Missing %s" % output_file)
def make_pipeline1(pipeline_name, # Pipelines need to have a unique name
starting_file_names):
test_pipeline = Pipeline(pipeline_name)
# We can change the starting files later using
# set_input() for transform etc.
# or set_output() for originate
# But it can be more convenient to just pass this to the function making the pipeline
#
test_pipeline.originate(task_originate, starting_file_names)\
.follows(mkdir(tempdir), mkdir(tempdir + "/testdir", tempdir + "/testdir2"))\
.posttask(touch_file(tempdir + "/testdir/whatever.txt"))
test_pipeline.transform(task_func = task_m_to_1,
name = "add_input",
# Lookup Task from function name task_originate()
# So long as this is unique in the pipeline
input = task_originate,
filter = regex(r"(.*)"),
add_inputs = add_inputs(tempdir + "/testdir/whatever.txt"),
output = r"\1.22")
test_pipeline.transform(task_func = task_1_to_1,
name = "22_to_33",
# Lookup Task from Task name
# Function name is not unique in the pipeline
input = output_from("add_input"),
filter = suffix(".22"),
output = ".33")
tail_task = test_pipeline.transform(task_func = task_1_to_1,
name = "33_to_44",
# Ask Pipeline to lookup Task from Task name
input = test_pipeline["22_to_33"],
filter = suffix(".33"),
output = ".44")
# Set the tail task so that users of my sub pipeline can use it as a dependency
# without knowing the details of task names
#
# Use Task() object directly without having to lookup
test_pipeline.set_tail_tasks([tail_task])
# If we try to connect a Pipeline without tail tasks defined, we have to
# specify the exact task within the Pipeline.
# Otherwise Ruffus will not know which task we mean and throw an exception
if DEBUG_do_not_define_tail_task:
test_pipeline.set_tail_tasks([])
# Set the head task so that users of my sub pipeline send input into it
# without knowing the details of task names
test_pipeline.set_head_tasks([test_pipeline[task_originate]])
return test_pipeline
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.originate(start_task, ["a.1", "b.1"])
test_pipeline.transform(same_file_name_task, start_task, suffix(".1"), ".1")
test_pipeline.transform(linked_file_name_task, start_task, suffix(".1"), ".linked.1")
test_pipeline.transform(final_task, [linked_file_name_task, same_file_name_task], suffix(".1"), ".3")
test_pipeline.run(log_exceptions = True, verbose = 0)
def test_newstyle_collate(self):
"""
As above but create pipeline on the fly using object orientated syntax rather than decorators
"""
#
# Create pipeline on the fly, joining up tasks
#
test_pipeline = Pipeline("test")
test_pipeline.originate(task_func=generate_initial_files,
output=original_files)\
.mkdir(tempdir, tempdir+"/test")
test_pipeline.subdivide(task_func=split_fasta_file,
input=generate_initial_files,
# match original files
filter=regex(r".*\/original_(\d+).fa"),
output=[tempdir + r"/files.split.\1.success", # flag file for each original file
tempdir + r"/files.split.\1.*.fa"], # glob pattern
extras=[r"\1"])\
.posttask(lambda: sys.stderr.write("\tSplit into %d files each\n" % JOBS_PER_TASK))
test_pipeline.transform(task_func=align_sequences,
input=split_fasta_file,
filter=suffix(".fa"),
output=".aln") \
.posttask(lambda: sys.stderr.write("\tSequences aligned\n"))
test_pipeline.transform(task_func=percentage_identity,
input=align_sequences, # find all results from align_sequences
# replace suffix with:
filter=suffix(".aln"),
output=[r".pcid", # .pcid suffix for the result
r".pcid_success"] # .pcid_success to indicate job completed
)\
.posttask(lambda: sys.stderr.write("\t%Identity calculated\n"))
test_pipeline.collate(task_func=combine_results,
input=percentage_identity,
filter=regex(r".*files.split\.(\d+)\.\d+.pcid"),
output=[tempdir + r"/\1.all.combine_results",
tempdir + r"/\1.all.combine_results_success"])\
.posttask(lambda: sys.stderr.write("\tResults recombined\n"))
#
# Cleanup, printout and run
#
self.cleanup_tmpdir()
s = StringIO()
test_pipeline.printout(s, [combine_results],
verbose=5, wrap_width=10000)
self.assertTrue(re.search(
'Job needs update:.*Missing files.*', s.getvalue(), re.DOTALL) is not None)
test_pipeline.run(verbose=0)
def make_pipeline(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='complexo')
# Get a list of paths to all the FASTQ files
fastq_files = state.config.get_option('fastqs')
# Stages are dependent on the state
stages = Stages(state)
# The original FASTQ files
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_fastqs,
name='original_fastqs',
output=fastq_files)
# Align paired end reads in FASTQ to the reference producing a BAM file
pipeline.transform(
task_func=stages.align_bwa,
name='align_bwa',
input=output_from('original_fastqs'),
# Match the R1 (read 1) FASTQ file and grab the path and sample name.
# This will be the first input to the stage.
# We assume the sample name may consist of only alphanumeric
# characters.
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+)_R1.fastq.gz'),
# Add one more inputs to the stage:
# 1. The corresponding R2 FASTQ file
add_inputs=add_inputs('{path[0]}/{sample[0]}_R2.fastq.gz'),
# Add an "extra" argument to the state (beyond the inputs and outputs)
# which is the sample name. This is needed within the stage for finding out
# sample specific configuration options
extras=['{sample[0]}'],
# The output file name is the sample name with a .bam extension.
output='{path[0]}/{sample[0]}.bam')
# Sort the BAM file using Picard
pipeline.transform(
task_func=stages.sort_bam_picard,
name='sort_bam_picard',
input=output_from('align_bwa'),
filter=suffix('.bam'),
output='.sort.bam')
# Mark duplicates in the BAM file using Picard
pipeline.transform(
task_func=stages.mark_duplicates_picard,
name='mark_duplicates_picard',
input=output_from('sort_bam_picard'),
filter=suffix('.sort.bam'),
# XXX should make metricsup an extra output?
output=['.sort.dedup.bam', '.metricsdup'])
# Generate chromosome intervals using GATK
pipeline.transform(
task_func=stages.chrom_intervals_gatk,
name='chrom_intervals_gatk',
input=output_from('mark_duplicates_picard'),
filter=suffix('.sort.dedup.bam'),
output='.chr.intervals')
# Local realignment using GATK
(pipeline.transform(
task_func=stages.local_realignment_gatk,
name='local_realignment_gatk',
input=output_from('chrom_intervals_gatk'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).chr.intervals'),
add_inputs=add_inputs('{path[0]}/{sample[0]}.sort.dedup.bam'),
output='{path[0]}/{sample[0]}.sort.dedup.realn.bam')
.follows('mark_duplicates_picard'))
# Base recalibration using GATK
pipeline.transform(
task_func=stages.base_recalibration_gatk,
name='base_recalibration_gatk',
input=output_from('local_realignment_gatk'),
filter=suffix('.sort.dedup.realn.bam'),
output=['.recal_data.csv', '.count_cov.log'])
# Print reads using GATK
(pipeline.transform(
task_func=stages.print_reads_gatk,
name='print_reads_gatk',
input=output_from('base_recalibration_gatk'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).recal_data.csv'),
add_inputs=add_inputs('{path[0]}/{sample[0]}.sort.dedup.realn.bam'),
output='{path[0]}/{sample[0]}.sort.dedup.realn.recal.bam')
.follows('local_realignment_gatk'))
# Call variants using GATK
pipeline.transform(
task_func=stages.call_variants_gatk,
name='call_variants_gatk',
input=output_from('print_reads_gatk'),
filter=suffix('.sort.dedup.realn.recal.bam'),
output='.raw.snps.indels.g.vcf')
# Combine G.VCF files for all samples using GATK
pipeline.merge(
task_func=stages.combine_gvcf_gatk,
name='combine_gvcf_gatk',
input=output_from('call_variants_gatk'),
output='PCExomes.mergegvcf.vcf')
# Genotype G.VCF files using GATK
pipeline.transform(
task_func=stages.genotype_gvcf_gatk,
name='genotype_gvcf_gatk',
input=output_from('combine_gvcf_gatk'),
filter=suffix('.mergegvcf.vcf'),
output='.genotyped.vcf')
# SNP recalibration using GATK
pipeline.transform(
task_func=stages.snp_recalibrate_gatk,
name='snp_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
output=['.snp_recal', '.snp_tranches', '.snp_plots.R'])
# INDEL recalibration using GATK
pipeline.transform(
task_func=stages.indel_recalibrate_gatk,
name='indel_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
output=['.indel_recal', '.indel_tranches', '.indel_plots.R'])
# Apply SNP recalibration using GATK
(pipeline.transform(
task_func=stages.apply_snp_recalibrate_gatk,
name='apply_snp_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
add_inputs=add_inputs(['PCExomes.snp_recal', 'PCExomes.snp_tranches']),
output='.recal_SNP.vcf')
.follows('snp_recalibrate_gatk'))
# Apply INDEL recalibration using GATK
(pipeline.transform(
task_func=stages.apply_indel_recalibrate_gatk,
name='apply_indel_recalibrate_gatk',
input=output_from('genotype_gvcf_gatk'),
filter=suffix('.genotyped.vcf'),
add_inputs=add_inputs(['PCExomes.indel_recal', 'PCExomes.indel_tranches']),
output='.recal_INDEL.vcf')
.follows('indel_recalibrate_gatk'))
# Combine variants using GATK
(pipeline.transform(
task_func=stages.combine_variants_gatk,
name='combine_variants_gatk',
input=output_from('apply_snp_recalibrate_gatk'),
filter=suffix('.recal_SNP.vcf'),
add_inputs=add_inputs(['PCExomes.recal_INDEL.vcf']),
output='.combined.vcf')
.follows('apply_indel_recalibrate_gatk'))
# Select variants using GATK
pipeline.transform(
task_func=stages.select_variants_gatk,
name='select_variants_gatk',
input=output_from('combine_variants_gatk'),
filter=suffix('.combined.vcf'),
output='.selected.vcf')
return pipeline
@transform(create_initial_file_pairs, suffix(".start"), ".output.1")
def first_task(input_files, output_file):
with open(output_file, "w"):
pass
# ---------------------------------------------------------------
# second task
@transform(first_task, suffix(".output.1"), ".output.2")
def second_task(input_files, output_file):
with open(output_file, "w"):
pass
test_pipeline = Pipeline("test")
test_pipeline.originate(output=[
[
tempdir +
'data/scratch/lg/what/one/two/three/four/five/six/seven/job1.a.start',
tempdir + 'job1.b.start'
],
[
tempdir +
'data/scratch/lg/what/one/two/three/four/five/six/seven/job2.a.start',
tempdir + 'job2.b.start'
],
[
tempdir +
'data/scratch/lg/what/one/two/three/four/five/six/seven/job3.a.start',
tempdir + 'job3.b.start'
def make_pipeline(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='test_pipeline')
# Get a list of paths to all the FASTQ files
input_files = state.config.get_option('files')
# Stages are dependent on the state
stages = Stages(state)
# The original files
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_files,
name='original_files',
output=input_files)
pipeline.transform(
task_func=stages.stage1,
name='stage1',
input=output_from('original_files'),
filter=suffix('.0'),
output='.1')
pipeline.transform(
task_func=stages.stage2,
name='stage2',
input=output_from('stage1'),
filter=suffix('.1'),
output='.2')
pipeline.transform(
task_func=stages.stage3,
name='stage3',
input=output_from('stage2'),
filter=suffix('.2'),
output='.3')
pipeline.transform(
task_func=stages.stage4,
name='stage4',
input=output_from('stage3'),
filter=suffix('.3'),
output='.4')
pipeline.transform(
task_func=stages.stage5,
name='stage5',
input=output_from('stage4'),
filter=suffix('.4'),
output='.5')
return pipeline
def make_pipeline(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='crpipe')
# Get a list of paths to all the FASTQ files
fastq_files = state.config.get_option('fastqs')
# Find the path to the reference genome
reference_file = state.config.get_option('reference')
# Stages are dependent on the state
stages = Stages(state)
# The original FASTQ files
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_fastqs,
name='original_fastqs',
output=fastq_files)
# Convert FASTQ file to FASTA using fastx toolkit
# pipeline.transform(
# task_func=stages.fastq_to_fasta,
# name='fastq_to_fasta',
# input=output_from('original_fastqs'),
# filter=suffix('.fastq.gz'),
# output='.fasta')
# The original reference file
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(
task_func=stages.original_reference,
name='original_reference',
output=reference_file)
# Run fastQC on the FASTQ files
pipeline.transform(
task_func=stages.fastqc,
name='fastqc',
input=output_from('original_fastqs'),
filter=suffix('.fastq.gz'),
output='_fastqc')
# Index the reference using BWA
pipeline.transform(
task_func=stages.index_reference_bwa,
name='index_reference_bwa',
input=output_from('original_reference'),
filter=suffix('.fa'),
output=['.fa.amb', '.fa.ann', '.fa.pac', '.fa.sa', '.fa.bwt'])
# Index the reference using samtools
pipeline.transform(
task_func=stages.index_reference_samtools,
name='index_reference_samtools',
input=output_from('original_reference'),
filter=suffix('.fa'),
output='.fa.fai')
# Index the reference using bowtie 2
pipeline.transform(
task_func=stages.index_reference_bowtie2,
name='index_reference_bowtie2',
input=output_from('original_reference'),
filter=formatter('.+/(?P<refname>[a-zA-Z0-9]+\.fa)'),
output=['{path[0]}/{refname[0]}.1.bt2',
'{path[0]}/{refname[0]}.2.bt2',
'{path[0]}/{refname[0]}.3.bt2',
'{path[0]}/{refname[0]}.4.bt2',
'{path[0]}/{refname[0]}.rev.1.bt2',
'{path[0]}/{refname[0]}.rev.2.bt2'],
extras=['{path[0]}/{refname[0]}'])
# Create a FASTA sequence dictionary for the reference using picard
pipeline.transform(
task_func=stages.reference_dictionary_picard,
name='reference_dictionary_picard',
input=output_from('original_reference'),
filter=suffix('.fa'),
output='.dict')
# Align paired end reads in FASTQ to the reference producing a BAM file
(pipeline.transform(
task_func=stages.align_bwa,
name='align_bwa',
input=output_from('original_fastqs'),
# Match the R1 (read 1) FASTQ file and grab the path and sample name.
# This will be the first input to the stage.
# We assume the sample name may consist of only alphanumeric
# characters.
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+)_R1.fastq.gz'),
# Add two more inputs to the stage:
# 1. The corresponding R2 FASTQ file
# 2. The reference genome file
add_inputs=add_inputs(['{path[0]}/{sample[0]}_R2.fastq.gz', reference_file]),
# Add an "extra" argument to the state (beyond the inputs and outputs)
# which is the sample name. This is needed within the stage for finding out
# sample specific configuration options
extras=['{sample[0]}'],
# The output file name is the sample name with a .bam extension.
output='{path[0]}/{sample[0]}.bam')
# Ensure the reference is indexed before we run this stage
.follows('index_reference_bwa')
.follows('index_reference_samtools'))
# Sort alignment with sambamba
pipeline.transform(
task_func=stages.sort_bam_sambamba,
name='sort_alignment',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).bam'),
output='{path[0]}/{sample[0]}.sorted.bam')
# Extract MMR genes from the sorted BAM file
pipeline.transform(
task_func=stages.extract_genes_bedtools,
name='extract_genes_bedtools',
input=output_from('sort_alignment'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
output='{path[0]}/{sample[0]}.mmr.bam')
# Extract selected chromosomes from the sorted BAM file
pipeline.transform(
task_func=stages.extract_chromosomes_samtools,
name='extract_chromosomes_samtools',
input=output_from('sort_alignment'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
output='{path[0]}/{sample[0]}.chroms.bam')
# Index the MMR genes bam file with samtools
pipeline.transform(
task_func=stages.index_bam,
name='index_mmr_alignment',
input=output_from('extract_genes_bedtools'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).mmr.bam'),
output='{path[0]}/{sample[0]}.mmr.bam.bai')
# Compute depth of coverage of the alignment with GATK DepthOfCoverage
#pipeline.transform(
# task_func=stages.alignment_coverage_gatk,
# name='alignment_coverage_gatk',
# input=output_from('sort_alignment'),
# filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
# add_inputs=add_inputs([reference_file]),
# output='{path[0]}/{sample[0]}.coverage_summary',
# extras=['{path[0]}/{sample[0]}_coverage'])
# Index the alignment with samtools
pipeline.transform(
task_func=stages.index_bam,
name='index_alignment',
input=output_from('sort_alignment'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
output='{path[0]}/{sample[0]}.sorted.bam.bai')
# Generate alignment stats with bamtools
pipeline.transform(
task_func=stages.bamtools_stats,
name='bamtools_stats',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).bam'),
output='{path[0]}/{sample[0]}.stats.txt')
# Extract the discordant paired-end alignments
pipeline.transform(
task_func=stages.extract_discordant_alignments,
name='extract_discordant_alignments',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).bam'),
output='{path[0]}/{sample[0]}.discordants.unsorted.bam')
# Extract split-read alignments
pipeline.transform(
task_func=stages.extract_split_read_alignments,
name='extract_split_read_alignments',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).bam'),
output='{path[0]}/{sample[0]}.splitters.unsorted.bam')
# Sort discordant reads.
# Samtools annoyingly takes the prefix of the output bam name as its argument.
# So we pass this as an extra argument. However Ruffus needs to know the full name
# of the output bam file, so we pass that as the normal output parameter.
pipeline.transform(
task_func=stages.sort_bam,
name='sort_discordants',
input=output_from('extract_discordant_alignments'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).discordants.unsorted.bam'),
extras=['{path[0]}/{sample[0]}.discordants'],
output='{path[0]}/{sample[0]}.discordants.bam')
# Index the sorted discordant bam with samtools
# pipeline.transform(
# task_func=stages.index_bam,
# name='index_discordants',
# input=output_from('sort_discordants'),
# filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).discordants.bam'),
# output='{path[0]}/{sample[0]}.discordants.bam.bai')
# Sort discordant reads
# Samtools annoyingly takes the prefix of the output bam name as its argument.
# So we pass this as an extra argument. However Ruffus needs to know the full name
# of the output bam file, so we pass that as the normal output parameter.
pipeline.transform(
task_func=stages.sort_bam,
name='sort_splitters',
input=output_from('extract_split_read_alignments'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).splitters.unsorted.bam'),
extras=['{path[0]}/{sample[0]}.splitters'],
output='{path[0]}/{sample[0]}.splitters.bam')
# Index the sorted splitters bam with samtools
# pipeline.transform(
# task_func=stages.index_bam,
# name='index_splitters',
# input=output_from('sort_splitters'),
# filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).splitters.bam'),
# output='{path[0]}/{sample[0]}.splitters.bam.bai')
# Call structural variants with lumpy
(pipeline.transform(
task_func=stages.structural_variants_lumpy,
name='structural_variants_lumpy',
input=output_from('sort_alignment'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
add_inputs=add_inputs(['{path[0]}/{sample[0]}.splitters.bam', '{path[0]}/{sample[0]}.discordants.bam']),
output='{path[0]}/{sample[0]}.lumpy.vcf')
.follows('sort_splitters')
.follows('sort_discordants')
.follows('index_alignment'))
# Call genotypes on lumpy output using SVTyper
#(pipeline.transform(
# task_func=stages.genotype_svtyper,
# name='genotype_svtyper',
# input=output_from('structural_variants_lumpy'),
# filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).lumpy.vcf'),
# add_inputs=add_inputs(['{path[0]}/{sample[0]}.sorted.bam', '{path[0]}/{sample[0]}.splitters.bam']),
# output='{path[0]}/{sample[0]}.svtyper.vcf')
# .follows('align_bwa')
# .follows('sort_splitters')
# .follows('index_alignment')
# .follows('index_splitters')
# .follows('index_discordants'))
# Call SVs with Socrates
(pipeline.transform(
task_func=stages.structural_variants_socrates,
name='structural_variants_socrates',
input=output_from('sort_alignment'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
# output goes to {path[0]}/socrates/
output='{path[0]}/socrates/results_Socrates_paired_{sample[0]}.sorted_long_sc_l25_q5_m5_i95.txt',
extras=['{path[0]}'])
.follows('index_reference_bowtie2'))
# Join both read pair files using gustaf_mate_joining
#pipeline.transform(
# task_func=stages.gustaf_mate_joining,
# name='gustaf_mate_joining',
# input=output_from('fastq_to_fasta'),
# # Match the R1 (read 1) FASTA file and grab the path and sample name.
# # This will be the first input to the stage.
# # We assume the sample name may consist of only alphanumeric
# # characters.
# filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+)_R1.fasta'),
# # Add one more input to the stage:
# # 1. The corresponding R2 FASTA file
# add_inputs=add_inputs(['{path[0]}/{sample[0]}_R2.fasta']),
# output='{path[0]}/{sample[0]}.joined_mates.fasta')
# Call structural variants with pindel
(pipeline.transform(
task_func=stages.structural_variants_pindel,
name='structural_variants_pindel',
input=output_from('sort_alignment'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9]+).sorted.bam'),
add_inputs=add_inputs(['{path[0]}/{sample[0]}.pindel_config.txt', reference_file]),
output='{path[0]}/{sample[0]}.pindel')
.follows('index_reference_bwa')
.follows('index_reference_samtools'))
return pipeline
def test_newstyle_ruffus (self):
test_pipeline = Pipeline("test")
test_pipeline.originate(task_func = make_start, output = [tempdir + 'start'])
test_pipeline.split(task_func = split_start, input = make_start, output = tempdir + '*.split')
test_pipeline.subdivide(task_func = subdivide_start, input = split_start, filter = formatter(), output = tempdir + '{basename[0]}_*.subdivided', extras = [tempdir + '{basename[0]}'])
expected_files_after_1_runs = ["start", "0.split", "0_0.subdivided"]
expected_files_after_2_runs = ["1.split", "0_1.subdivided", "1_0.subdivided"]
expected_files_after_3_runs = ["2.split", "0_2.subdivided", "1_1.subdivided", "2_0.subdivided"]
expected_files_after_4_runs = ["3.split", "0_3.subdivided", "1_2.subdivided", "2_1.subdivided", "3_0.subdivided"]
print(" Run pipeline normally...")
test_pipeline.run(multiprocess = 10, verbose=0)
self.check_file_exists_or_not_as_expected(expected_files_after_1_runs,
expected_files_after_2_runs)
print(" Check that running again does nothing. (All up to date).")
test_pipeline.run(multiprocess = 10, verbose=0)
self.check_file_exists_or_not_as_expected(expected_files_after_1_runs,
expected_files_after_2_runs)
print(" Running again with forced tasks to generate more files...")
test_pipeline.run(forcedtorun_tasks = ["test::make_start"], multiprocess = 10, verbose=0)
self.check_file_exists_or_not_as_expected(expected_files_after_1_runs
+ expected_files_after_2_runs,
expected_files_after_3_runs)
print(" Check that running again does nothing. (All up to date).")
test_pipeline.run(multiprocess = 10, verbose=0)
self.check_file_exists_or_not_as_expected(expected_files_after_1_runs
+ expected_files_after_2_runs,
expected_files_after_3_runs)
print(" Running again with forced tasks to generate even more files...")
test_pipeline.run(forcedtorun_tasks = make_start, multiprocess = 10, verbose=0)
self.check_file_exists_or_not_as_expected(expected_files_after_1_runs
+ expected_files_after_2_runs
+ expected_files_after_3_runs,
expected_files_after_4_runs)
print(" Check that running again does nothing. (All up to date).")
test_pipeline.run(multiprocess = 10, verbose=0)
self.check_file_exists_or_not_as_expected(expected_files_after_1_runs
+ expected_files_after_2_runs
+ expected_files_after_3_runs,
expected_files_after_4_runs)
def test_newstyle_task(self):
test_pipeline = Pipeline("test")
test_pipeline.files(task1, [[None, tempdir + "a.1"], [None, tempdir + "b.1"]])\
.follows(mkdir(tempdir))
test_pipeline.files(task2, [[None, tempdir + "c.1"], [None, tempdir + "d.1"]])\
.follows(mkdir(tempdir))
test_pipeline.transform(task_func=task3,
input=task1,
filter=regex(r"(.+)"),
replace_inputs=ruffus.inputs(
((r"\1"), task2, "test_transform_inputs.*y")),
output=r"\1.output")
test_pipeline.merge(task4, (task3), tempdir + "final.output")
test_pipeline.run([task4], multiprocess=10, verbose=0)
correct_output = "{tempdir}a.1.output:test_transform_inputs.py,{tempdir}a.1,{tempdir}c.1,{tempdir}d.1;{tempdir}b.1.output:test_transform_inputs.py,{tempdir}b.1,{tempdir}c.1,{tempdir}d.1;".format(
tempdir=tempdir)
with open(tempdir + "final.output") as ff:
real_output = ff.read()
self.assertEqual(correct_output, real_output)
def test_newstyle_graphviz_dot(self):
test_pipeline = Pipeline("test")
test_pipeline.check_if_uptodate (Up_to_date_task1, lambda : (False, ""))
test_pipeline.follows(Up_to_date_task2, Up_to_date_task1)\
.check_if_uptodate (lambda : (False, ""))\
.graphviz(URL='"http://cnn.com"', fillcolor = '"#FFCCCC"',
color = '"#FF0000"', pencolor='"#FF0000"', fontcolor='"#4B6000"',
label_suffix = "???", label_prefix = "What is this?<BR/> ",
label = "<What <FONT COLOR=\"red\">is</FONT>this>",
shape= "component", height = 1.5, peripheries = 5,
style="dashed")
test_pipeline.follows(Up_to_date_task3, Up_to_date_task2)\
.check_if_uptodate (lambda : (False, ""))
test_pipeline.follows(Up_to_date_final_target, Up_to_date_task3)\
.check_if_uptodate (lambda : (False, ""))
test_pipeline.follows(Explicitly_specified_task, Up_to_date_task1)\
.check_if_uptodate (lambda : (False, ""))
test_pipeline.follows(Task_to_run1, Explicitly_specified_task)
test_pipeline.follows(Task_to_run2, Task_to_run1)
test_pipeline.follows(Task_to_run3, Task_to_run2)
test_pipeline.follows(Up_to_date_task_forced_to_rerun, Task_to_run2)\
.check_if_uptodate (lambda : (False, ""))
test_pipeline.follows(Final_target, Up_to_date_task_forced_to_rerun, Task_to_run3)
test_pipeline.follows(Downstream_task1_ignored, Final_target)
test_pipeline.follows(Downstream_task2_ignored, Final_target)
if sys.hexversion >= 0x03000000:
# everything is unicode in python3
s = BytesIO()
else:
s = StringIO()
test_pipeline.printout_graph (
s,
# use flowchart file name extension to decide flowchart format
# e.g. svg, jpg etc.
"dot",
[Final_target, Up_to_date_final_target])
self.assertTrue('[URL="http://cnn.com", color="#FF0000", fillcolor="#FFCCCC", fontcolor="#4B6000", height=1.5, label=<What is this?<BR/> What <FONT COLOR="red">is</FONT>this???>, pencolor="#FF0000", peripheries=5, shape=component, style=dashed]' in s.getvalue().decode())
def test_newstyle_ruffus(self):
test_pipeline = Pipeline("test")
test_pipeline.files(create_random_numbers, None, tempdir + "random_numbers.list")\
.follows(mkdir(tempdir))
test_pipeline.split(task_func=step_4_split_numbers_into_chunks,
input=tempdir + "random_numbers.list",
output=tempdir + "*.chunks")\
.follows(create_random_numbers)
test_pipeline.transform(task_func=step_5_calculate_sum_of_squares,
input=step_4_split_numbers_into_chunks,
filter=suffix(".chunks"),
output=".sums")
test_pipeline.merge(task_func=step_6_calculate_variance, input=step_5_calculate_sum_of_squares, output=os.path.join(tempdir, "variance.result"))\
.posttask(lambda: sys.stdout.write(" hooray\n"))\
.posttask(print_hooray_again, print_whoppee_again, touch_file(os.path.join(tempdir, "done")))
test_pipeline.run(multiprocess=50, verbose=0)
output_file = os.path.join(tempdir, "variance.result")
if not os.path.exists(output_file):
raise Exception("Missing %s" % output_file)
def test_newstyle_task (self):
"""
Same as above but construct a new pipeline on the fly without decorators
"""
test_pipeline = Pipeline("test")
test_pipeline.files(task1, None, tempdir + 'a.1')\
.follows(mkdir(tempdir))
test_pipeline.transform(task_func = task2,
input = task1,
filter = regex(r".*"),
output = tempdir + 'b.1')
test_pipeline.files(task3, task2, tempdir + 'c.1')
test_pipeline.files(task4, [[None, tempdir + 'd.1'], [None, tempdir + 'e.1']])\
.follows(task3)
test_pipeline.files(task5, task4, tempdir + "f.1")
test_pipeline.run(multiprocess = 10, verbose = 0)
def make_pipeline_map(state):
'''Build the pipeline by constructing stages and connecting them together'''
# Build an empty pipeline
pipeline = Pipeline(name='genericpipe')
# Stages are dependent on the state
stages = Stages(state)
safe_make_dir('alignments')
safe_make_dir('metrics')
safe_make_dir('metrics/amplicon')
safe_make_dir('metrics/summary')
# The original FASTQ files
fastq_files = glob.glob('fastqs/*')
# This is a dummy stage. It is useful because it makes a node in the
# pipeline graph, and gives the pipeline an obvious starting point.
pipeline.originate(task_func=stages.original_fastqs,
name='original_fastqs',
output=fastq_files)
# Align paired end reads in FASTQ to the reference producing a BAM file
pipeline.transform(
task_func=stages.align_bwa,
name='align_bwa',
input=output_from('original_fastqs'),
# Match the R1 (read 1) FASTQ file and grab the path and sample name.
# This will be the first input to the stage.
filter=formatter('fastqs/(?P<sample>[a-zA-Z0-9_-]+)_R1.fastq.gz'),
# Add one more inputs to the stage:
# 1. The corresponding R2 FASTQ file
add_inputs=add_inputs('fastqs/{sample[0]}_R2.fastq.gz'),
# Add an "extra" argument to the state (beyond the inputs and outputs)
# which is the sample name. This is needed within the stage for finding out
# sample specific configuration options
extras=['{sample[0]}'],
# The output file name is the sample name with a .bam extension.
output='alignments/{sample[0]}.sort.hq.bam')
# generate mapping metrics.
pipeline.transform(
task_func=stages.generate_amplicon_metrics,
name='generate_amplicon_metrics',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9_-]+).sort.hq.bam'),
output='metrics/amplicon/{sample[0]}.amplicon-metrics.txt',
extras=['{sample[0]}'])
pipeline.transform(
task_func=stages.intersect_bed,
name='intersect_bed',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9_-]+).sort.hq.bam'),
output='metrics/summary/{sample[0]}.intersectbed.bam')
pipeline.transform(task_func=stages.coverage_bed,
name='coverage_bed',
input=output_from('intersect_bed'),
filter=suffix('.intersectbed.bam'),
output='.bedtools_hist_all.txt')
pipeline.transform(
task_func=stages.genome_reads,
name='genome_reads',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9_-]+).sort.hq.bam'),
output='metrics/summary/{sample[0]}.mapped_to_genome.txt')
pipeline.transform(task_func=stages.target_reads,
name='target_reads',
input=output_from('intersect_bed'),
filter=suffix('.intersectbed.bam'),
output='.mapped_to_target.txt')
pipeline.transform(
task_func=stages.total_reads,
name='total_reads',
input=output_from('align_bwa'),
filter=formatter('.+/(?P<sample>[a-zA-Z0-9_-]+).sort.hq.bam'),
output='metrics/summary/{sample[0]}.total_raw_reads.txt')
pipeline.collate(
task_func=stages.generate_stats,
name='generate_stats',
input=output_from('coverage_bed', 'genome_reads', 'target_reads',
'total_reads'),
#filter=regex(r'.+/(.+BS\d{4,6}.+)\..+\.txt'),
filter=regex(
r'.+/(.+)\.(bedtools_hist_all|mapped_to_genome|mapped_to_target|total_raw_reads)\.txt'
),
output=r'metrics/summary/all_sample.summary.\1.txt',
extras=[r'\1', 'all_sample.summary.txt'])
summary_file = 'all_sample.summary.txt'
(pipeline.originate(task_func=stages.grab_summary_file,
name='grab_summary_file',
output=summary_file).follows('generate_stats'))
pipeline.transform(task_func=stages.filter_stats,
name='filter_stats',
input=output_from('grab_summary_file'),
filter=suffix('.summary.txt'),
output='.passed.summary.txt',
extras=['all_sample.failed.summary.txt'])
return pipeline
