def test_find_sets(tmpdir):
graph = '''p sp 6 7
n 1 1
n 2 2
n 3 1
n 4 4
n 5 5
n 6 6
e 1 2
e 1 3
e 2 3
e 2 4
e 4 5
e 4 6
e 5 6
'''
fp = tmpdir.join("testgraph")
fp.write(graph)
sets = find_sets(
min_bg_bind_dist=2,
min_size=3,
max_size=3,
bg_genome_len=10,
graph_fp=fp)
output = list(sets)
assert len(output) == 1
ids, bg_dist_mean = swga.score.read_set_finder_line(output[0])
assert ids == [1, 2, 3]
assert bg_dist_mean == 2.5
def main(argv, cfg_file):
cmd = Command('find_sets', cfg_file=cfg_file)
score_cmd = Command('score', cfg_file=cfg_file)
cmd.parse_args(argv)
score_cmd.parse_args(argv)
init_db(cmd.primer_db)
# We need to clear all the previously-used sets each time due to uniqueness
# constraints
allsets = Set.select()
if allsets.count() > 0:
if not cmd.force:
click.confirm("Remove all previously-found sets?", abort=True)
for s in progress.bar(allsets, expected_size=allsets.count()):
s.primers.clear()
s.delete_instance()
make_graph(cmd.max_dimer_bp, graph_fname)
swga.message("Now finding sets. If nothing appears, try relaxing your parameters.")
if cmd.workers <= 1:
setlines = setfinder.find_sets(
cmd.min_bg_bind_dist,
cmd.min_size,
cmd.max_size,
cmd.bg_genome_len,
graph_fp=graph_fname)
else:
setlines = setfinder.mp_find_sets(
nprocesses=cmd.workers,
graph_fp=graph_fname,
min_bg_bind_dist=cmd.min_bg_bind_dist,
min_size=cmd.min_size,
max_size=cmd.max_size,
bg_genome_len=cmd.bg_genome_len)
score_sets(
setlines,
cmd.fg_genome_fp,
score_cmd.score_expression,
cmd.max_fg_bind_dist,
cmd.max_sets)