Commit 894bffce authored by aknecht2's avatar aknecht2
Browse files

Added remove_duplicates workflow generation.

parent d27ccfd7
......@@ -57,6 +57,7 @@ class Workflow(object):
# All required information is loaded, start queuing jobs
self._add_download()
self._add_align()
self._add_remove_duplicates()
# Create pegasus important stuff
self._create_setup()
self._add_notify()
......@@ -304,6 +305,22 @@ class Workflow(object):
self.modules["align"].add_jobs(self.dax, self.jobs, self.files, prefix, markers, input_files, additional_files)
return
def _add_remove_duplicates(self):
markers = {}
for run in self.run_data["runs"]:
input_files = {}
additional_files = {}
for pair in run["input_sets"]:
for file_tuple in pair:
if len(file_tuple) == 2:
# Its a paired end read
prefix = "%s_%s_%s" % (run["experiment"], file_tuple[0]["accession"], file_tuple[1]["accession"])
else:
# It's a single end read
prefix = "%s_%s" % (run["experiment"], file_tuple[0]["accession"])
self.modules["remove_duplicates"].add_jobs(self.dax, self.jobs, self.files, prefix, markers, input_files, additional_files)
return
def _create_setup(self):
"""
Creates the base structure for job submission. Everything is contained
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment