def get_qscore_dataframe(run_folder: Path) -> pd.DataFrame:
"""
Returns a pandas DataFrame containing x (Q-score), y (Total in millions) values for the run
"""
df_dict = {}
x_vals = []
y_vals = []
run_metrics = py_interop_run_metrics.run_metrics()
valid_to_load = py_interop_run.uchar_vector(py_interop_run.MetricCount, 0)
valid_to_load[py_interop_run.Q] = 1
run_metrics.read(str(run_folder), valid_to_load)
bar_data = py_interop_plot.bar_plot_data()
boundary = 30
options = py_interop_plot.filter_options(
run_metrics.run_info().flowcell().naming_method())
py_interop_plot.plot_qscore_histogram(run_metrics, options, bar_data,
boundary)
for i in range(bar_data.size() - 1):
x = [bar_data.at(i).at(j).x() for j in range(bar_data.at(i).size())]
y = [bar_data.at(i).at(j).y() for j in range(bar_data.at(i).size())]
x_vals += x
y_vals += y
df_dict['x'] = x_vals
df_dict['y'] = y_vals
df = pd.DataFrame.from_dict(df_dict)
return df
def test_invalid_filter_option(self):
"""
Test that exceptions can be caught and they have the expected message
"""
run_info = py_interop_run.info()
options = py_interop_plot.filter_options(py_interop_run.FourDigit)
try:
options.validate(py_interop_run.Intensity, run_info)
self.fail("invalid_filter_option should have been thrown")
except py_interop_plot.invalid_filter_option as ex:
self.assertEqual(str(ex).split('\n')[0], "Invalid tile naming method: does not match RunInfo.xml")
def test_plot_qscore_heatmap(self):
"""
Test that plot_flowcell_map is properly wrapped
"""
run = py_interop_run_metrics.run_metrics()
options = py_interop_plot.filter_options(run.run_info().flowcell().naming_method())
rows = py_interop_plot.count_rows_for_heatmap(run)
cols = py_interop_plot.count_columns_for_heatmap(run)
dataBuffer = numpy.zeros((rows, cols), dtype=numpy.float32)
data = py_interop_plot.heatmap_data()
try:
py_interop_plot.plot_qscore_heatmap(run, options, data, dataBuffer.ravel())
except py_interop_plot.invalid_filter_option: pass
def test_plot_flowcell_map(self):
"""
Test that plot_flowcell_map is properly wrapped
"""
run = py_interop_run_metrics.run_metrics()
options = py_interop_plot.filter_options(run.run_info().flowcell().naming_method())
bufferSize = py_interop_plot.calculate_flowcell_buffer_size(run, options)
dataBuffer = numpy.zeros(bufferSize, dtype=numpy.float32)
idBuffer = numpy.zeros(bufferSize, dtype=numpy.uint32)
data = py_interop_plot.flowcell_data()
try:
py_interop_plot.plot_flowcell_map2(run, py_interop_run.Intensity, options, data, dataBuffer, idBuffer)
except py_interop_plot.invalid_filter_option:
pass
def plot_percent_base(run_folder: str, output_svg="percent_base.svg"):
"""
Plots the base % across each cycle. Each line represents a different base.
Reference lines are added for each read.
Base %: The percentage of clusters for which the selected base (A, C, T, or G) has been called.
"""
# Initialize interop objects
run_metrics = py_interop_run_metrics.run_metrics()
valid_to_load = py_interop_run.uchar_vector(py_interop_run.MetricCount, 0)
py_interop_run_metrics.list_summary_metrics_to_load(valid_to_load)
# Read from the run folder
run_metrics.read(run_folder, valid_to_load)
logger.info('Generating % base plot')
plot_data = py_interop_plot.candle_stick_plot_data()
options = py_interop_plot.filter_options(run_metrics.run_info().flowcell().naming_method())
py_interop_plot.plot_by_cycle(run_metrics, "BasePercent", options, plot_data)
# Plot each base
for base_index in range(plot_data.size()):
line_data = plot_data.at(base_index)
x = [line_data.at(i).x() for i in range(line_data.size())]
y = [line_data.at(i).y() for i in range(line_data.size())]
plt.plot(x, y, color=line_data.color(), linewidth=0.5, label=line_data.title())
# Plot reference lines for reads
read_vector = run_metrics.run_info().reads()
for read_index in range(read_vector.size()):
read_name = f'R{read_vector[read_index].number()}'
cycle_start = read_vector[read_index].first_cycle()
plt.axvline(x=cycle_start, color='purple', linestyle='--', linewidth=0.35)
plt.text(cycle_start, plt.gca().get_ylim()[1], read_name, fontsize=8, color='purple')
# Plot settings
axes_data = plot_data.xyaxes()
plt.xlabel(axes_data.x().label(), fontsize=10)
plt.ylabel(axes_data.y().label(), fontsize=10)
plt.title(plot_data.title(), fontsize=10)
plt.legend()
plt.ylim([axes_data.y().min(), axes_data.y().max()])
plt.xlim([axes_data.x().min(), axes_data.x().max()])
# Save figure
plt.savefig(output_svg)
