def get_plot_objs(self, files):
plot_objs = {}
for f in files:
plot_objs[f] = PlotParser(f)
self.genome_size = len(plot_objs[f].combined)
if self.verbose:
print(plot_objs[f])
return plot_objs
def masking(self):
masking_plot = PlotParser(self.masking_plot_file)
output_plot_files = {}
for insertion_filename in self.insertion_plot_files:
insertion_plot = PlotParser(insertion_filename)
for i, mask in enumerate(masking_plot.combined):
if mask == 0 and self.strict_signal:
insertion_plot.forward[i] = 0
insertion_plot.reverse[i] = 0
fd, output_filename = mkstemp()
pg = PlotGenerator(insertion_plot.forward, insertion_plot.reverse, output_filename)
pg.construct_file()
output_plot_files[insertion_filename] = output_filename
return output_plot_files
def block_generator(self):
combined_plot = PlotParser(self.combined_mask_file)
forward_masking_plot = PlotParser(self.forward_mask_file)
reverse_masking_plot = PlotParser(self.reverse_mask_file)
masking_plot = self.merge_all_plots_choosing_peak_logfc(
combined_plot, forward_masking_plot, reverse_masking_plot)
blocks = self.increased_insertions_blocks(
masking_plot) + self.decreased_insertions_blocks(masking_plot)
block_filename = "block_report.csv"
with open(block_filename, 'w') as bf:
for b in blocks:
bf.write("Start: " + str(b.start) + " end: " + str(b.end) +
"\n")
bf.write("Length: " + str(b.block_length) + "\n")
'''Filter out blocks which are less than the window size'''
filtered_blocks: List[Block] = [
b for b in blocks if b.block_length >= self.window_size
]
block_length_Array = []
for b in filtered_blocks:
block_length_Array.append(b.end - b.start)
average_block_length = numpy.mean(block_length_Array)
print(average_block_length)
for b in filtered_blocks:
b.direction = self.direction_for_block(b, forward_masking_plot,
reverse_masking_plot)
block_filename = "filtered_block_report.csv"
with open(block_filename, 'w') as bf:
for b in filtered_blocks:
bf.write("Start: " + str(b.start) + " end: " + str(b.end) +
"\n")
bf.write("Length: " + str(b.block_length) + "\n")
return filtered_blocks
def test_generate_and_read(self):
filename = os.path.join(data_dir, 'plot.test')
p = PlotGenerator([0, 0, 0, 0, 0, 1, 1, 3], [9, 9, 0, 9, 9, 1, 1, 3],
filename)
p.construct_file()
d = PlotParser(filename, 0)
self.assertTrue(
self.check_arrays_equal(d.forward, [0, 0, 0, 0, 0, 1, 1, 3]))
self.assertTrue(
self.check_arrays_equal(d.reverse, [9, 9, 0, 9, 9, 1, 1, 3]))
self.assertTrue(
self.check_arrays_equal(d.combined, [9, 9, 0, 9, 9, 2, 2, 6]))
os.remove(filename)
def plot_parser(self): return PlotParser(self.plotfile,self.minimum_threshold)
def test_large_file_zipped(self): d = PlotParser(os.path.join(data_dir,'Control2.out.CP009273.insert_site_plot.gz'),3) self.assertEqual(d.total_reads, 7684360)
def test_valid_threshold(self): d = PlotParser(os.path.join(data_dir,'valid'), 3) self.assertTrue(self.check_arrays_equal(d.forward, [0,0,0,0,0,0,0,3])) self.assertTrue(self.check_arrays_equal(d.reverse, [0,0,4,5,0,0,0,0])) self.assertTrue(self.check_arrays_equal(d.combined, [0,0,4,5,0,0,0,3]))
def test_valid_ziped(self): d = PlotParser(os.path.join(data_dir,'valid.gz'),0) self.assertTrue(self.check_arrays_equal(d.forward, [0,0,0,0,0,1,1,3])) self.assertTrue(self.check_arrays_equal(d.reverse, [0,1,4,5,0,0,0,0])) self.assertTrue(self.check_arrays_equal(d.combined, [0,1,4,5,0,1,1,3]))
def read_plots(self):
plot_objs = {}
for p in self.plotfiles:
pp = PlotParser(p)
plot_objs[p] = pp
return plot_objs