def main(sequencing_directory, library_prefix, num_libraries, raw_data_dir):
lpad = LaunchPad(**yaml.load(open("my_launchpad.yaml")))
workflow_fireworks = []
workflow_dependencies = collections.defaultdict(list)
library_dirs = [
os.path.join(sequencing_directory, library_prefix + str(i + 1))
for i in xrange(num_libraries)
]
subdirs = [
'unzipped', 'trimmed', 'aligned_kallisto', 'bammed', 'sorted',
'counted', 'pythonized'
]
for library_dir in library_dirs:
seq_functions.make_directories(library_dir, subdirs)
name = "Count_%s" % os.path.basename(library_dir)
fw_count = Firework(
[
CountTask(library_path=library_dir,
aligned_name="aligned_kallisto",
bammed_name="bammed",
counted_name="counted",
spikeids=['Spike1', 'Spike4', 'Spike7'])
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_count)
lpad.add_wf(Workflow(workflow_fireworks, links_dict=workflow_dependencies))
def main(sequencing_directory, library_prefix, num_libraries, raw_data_dir):
lpad = LaunchPad(**yaml.load(open("my_launchpad.yaml")))
workflow_fireworks = []
workflow_dependencies = collections.defaultdict(list)
library_dirs = [
os.path.join(sequencing_directory, library_prefix + str(i + 1))
for i in xrange(num_libraries)
]
subdirs = ["aligned_star", "quant_rsem", "counted_rsem"]
for library_dir in library_dirs:
seq_functions.make_directories(library_dir, subdirs)
for library_dir in library_dirs:
seq_functions.make_directories(library_dir, subdirs)
name = "AlignSTAR_%s" % os.path.basename(library_dir)
fw_align = Firework(
[
Align_star_Task(library_path=library_dir,
trimmed_name="trimmed",
aligned_name="aligned_star/",
quant_name="quant_rsem/")
],
name=name,
spec={
"_queueadapter": {
"job_name": name,
"ntasks_per_node": 8,
"walltime": '24:00:00'
}
},
)
workflow_fireworks.append(fw_align)
name = "Count_%s" % os.path.basename(library_dir)
fw_count = Firework(
[
Count_rsem_Task(library_path=library_dir,
aligned_name="aligned_star",
quant_name="quant_rsem",
counted_name="counted_rsem",
spikeids=[
'AM1780SpikeIn1', 'AM1780SpikeIn4',
'AM1780SpikeIn7'
])
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_count)
workflow_dependencies[fw_align].append(fw_count)
lpad.add_wf(Workflow(workflow_fireworks, links_dict=workflow_dependencies))
def main(sequencing_directory, library_prefix, num_libraries, raw_data_dir):
lpad = LaunchPad(**yaml.load(open("my_launchpad.yaml")))
workflow_fireworks = []
workflow_dependencies = collections.defaultdict(list)
library_dirs = [os.path.join(sequencing_directory, library_prefix + str(i + 1)) for i in xrange(num_libraries)]
subdirs = ['unzipped', 'trimmed', 'aligned', 'aligned_star', 'quant_rsem','bammed', 'sorted', 'counted']
for library_dir in library_dirs:
seq_functions.make_directories(library_dir, subdirs)
name = "AlignSTAR_%s" % os.path.basename(library_dir)
fw_count = Firework(
[
AlignSTARTask(library_path = library_dir, trimmed_name = "trimmed", aligned_name = "aligned_star/", quant_name = "quant_rsem/")
],
name = name,
spec = {"_queueadapter": {"job_name": name, "ntasks_per_node": 8}},
)
workflow_fireworks.append(fw_count)
lpad.add_wf(
Workflow(workflow_fireworks, links_dict = workflow_dependencies)
)
"""
Test scripts to align data with STAR
"""
import seq_functions
direc = "/scratch/PI/mcovert/dvanva/sequencing/library1"
seq_functions.make_directories(
direc, subdirecs_to_make=["aligned_star", "quant_rsem"])
seq_functions.run_star_rsem(direc, "1-10_S14")
def main(sequencing_directory, library_prefix, num_libraries, raw_data_dir):
lpad = LaunchPad(**yaml.load(open("my_launchpad.yaml")))
workflow_fireworks = []
workflow_dependencies = collections.defaultdict(list)
library_dirs = [
os.path.join(sequencing_directory, library_prefix + str(i + 1))
for i in xrange(num_libraries)
]
subdirs = ['unzipped', 'trimmed', 'aligned', 'pythonized', 'sorted']
for library_dir in library_dirs:
seq_functions.make_directories(library_dir, subdirs)
name = "Gunzip_%s" % os.path.basename(library_dir)
fw_gunzip = Firework(
[
ScriptTask(script="find " +
os.path.join(library_dir, raw_data_dir) +
" -name '*.gz' -print0 | xargs -0 gunzip"),
ScriptTask(
script="mv " + os.path.join(library_dir, raw_data_dir) +
"/*.fastq " + os.path.join(library_dir, "unzipped")),
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_gunzip)
name = "Trim_%s" % os.path.basename(library_dir)
fw_trim = Firework(
[
TrimTask(library_path=library_dir,
unzipped_name="unzipped",
trimmed_name="trimmed")
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_trim)
workflow_dependencies[fw_gunzip].append(fw_trim)
name = "Align_%s" % os.path.basename(library_dir)
fw_align = Firework(
[
AlignTask(library_path=library_dir,
trimmed_name="trimmed",
aligned_name="aligned")
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_align)
workflow_dependencies[fw_trim].append(fw_align)
name = "Sort_%s" % os.path.basename(library_dir)
fw_sort = Firework(
[
SortTask(library_path=library_dir,
aligned_name="aligned",
bammed_name="bammed",
sorted_name="sorted")
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_sort)
workflow_dependencies[fw_align].append(fw_sort)
name = "Count_%s" % os.path.basename(library_dir)
fw_count = Firework(
[
CountTask(library_path=library_dir,
aligned_name="aligned",
bammed_name="bammed",
counted_name="counted")
],
name=name,
spec={"_queueadapter": {
"job_name": name
}},
)
workflow_fireworks.append(fw_count)
workflow_dependencies[fw_sort].append(fw_count)
lpad.add_wf(Workflow(workflow_fireworks, links_dict=workflow_dependencies))