how="inner",
)
null_spot_df = complete_foci_df.loc[(
complete_foci_df.loc[:, spot_parent_cols] == 0).squeeze(), :]
cell_spot_df = complete_foci_df.loc[(
complete_foci_df.loc[:, spot_parent_cols] != 0).squeeze(), :]
num_assigned_cells = len(
cell_spot_df.loc[:, spot_parent_cols].squeeze().unique())
num_unassigned_spots = null_spot_df.shape[0]
num_assigned_spots = cell_spot_df.shape[0]
# Figure 1 - histogram of barcode counts per cell
fig_file = pathlib.Path(output_dir, "num_spots_per_cell_histogram.png")
if check_if_write(fig_file, force):
spot_counts_per_cell_histogram(cell_spot_df, spot_parent_cols,
fig_file)
# Figure 2 - histogram of barcode scores per spot
fig_file = pathlib.Path(output_dir,
"barcode_scores_per_spot_histogram.png")
if check_if_write(fig_file, force):
spot_score_histogram(cell_spot_df, spot_score_cols, fig_file)
# Figure 3 - Joint plot of relationship of barcode counts per cell and mean score
fig_file = pathlib.Path(
output_dir, "per_cell_barcode_count_by_mean_score_jointplot.png")
if check_if_write(fig_file, force):
spot_count_score_jointplot(cell_spot_df, spot_parent_cols[0],
spot_score_cols[0], fig_file)
columns={
quality_col: "cell_count"
}).assign(
site=site,
plate=plate,
well=well,
site_location=site_location,
))
output_folder = pathlib.Path(output_paintdir, site)
if output_folder.exists():
if force:
warnings.warn("Output files likely exist, now overwriting...")
else:
warnings.warn(
"Output files likely exist. If they do, NOT overwriting...")
os.makedirs(output_folder, exist_ok=True)
meta_output_file = pathlib.Path(output_folder, f"metadata_{site}.tsv.gz")
count_output_file = pathlib.Path(output_folder, f"cell_counts_{site}.tsv")
# Save files
if check_if_write(meta_output_file, force):
metadata_df.to_csv(meta_output_file, sep="\t", index=False)
if check_if_write(count_output_file, force):
cell_count_df.to_csv(count_output_file,
sep="\t",
index_label="Cell_Quality")
print("All sites complete.")
os.makedirs(output_figuresdir, exist_ok=True)
by_well_gg = (
gg.ggplot(cell_count_totalcells_df, gg.aes(x="x_loc", y="y_loc")) +
gg.geom_point(gg.aes(fill="total_cell_count"), size=10) +
gg.geom_text(gg.aes(label="site_location"), color="lightgrey") +
gg.facet_wrap("~well") + gg.coord_fixed() + gg.theme_bw() +
gg.ggtitle(f"Total Cells/Well\n{plate}") + gg.theme(
axis_text=gg.element_blank(),
axis_title=gg.element_blank(),
strip_background=gg.element_rect(colour="black", fill="#fdfff4"),
) + gg.labs(fill="Cells") + gg.scale_fill_cmap(name="magma"))
output_file = pathlib.Path(output_figuresdir,
"plate_layout_cells_count_per_well.png")
if check_if_write(output_file, force, throw_warning=True):
by_well_gg.save(output_file, dpi=300, verbose=False)
# Plot cell category ratios per well
ratio_df = pd.pivot_table(
cell_count_df,
values="cell_count",
index=["site", "plate", "well", "site_location", "x_loc", "y_loc"],
columns=["Cell_Quality"],
)
ratio_df = ratio_df.assign(Sum=ratio_df.sum(axis=1),
Pass_Filter=ratio_df[cell_filter].sum(axis=1))
fail_filter = [cat for cat in cell_category_order if cat not in cell_filter]
fail_filter_noempty = [
cat for cat in cell_category_order if cat not in cell_filter
if cat != "Empty"
cell_count_df.loc[:, "Cell_Quality"] = pd.Categorical(
cell_count_df.Cell_Quality, categories=cell_category_order
)
# Assigns the site column to the category datatype
cell_count_df.loc[:, "site"] = pd.Categorical(
cell_count_df.site,
categories=(
cell_count_df.groupby("site")["cell_count"]
.sum()
.sort_values(ascending=False)
.index.tolist()
),
)
if check_if_write(cell_count_output_file, force, throw_warning=True):
cell_count_df.to_csv(cell_count_output_file, sep="\t", index=False)
# Graph: Cell count with all wells in same graph
cell_count_gg = (
gg.ggplot(cell_count_df, gg.aes(x="site", y="cell_count"))
+ gg.geom_bar(gg.aes(fill="Cell_Quality"), stat="identity")
+ gg.theme_bw()
+ gg.theme(axis_text_x=gg.element_text(rotation=90, size=5))
+ gg.xlab("Sites")
+ gg.ylab("Cell Count")
+ gg.scale_fill_manual(
name="Cell Quality", labels=cell_category_list, values=cell_category_colors
)
)
Also check 'perform: true' is set in the config.
(Note that 'perform: false' will still output a file lacking prefiltered features.)
"""
force_warning = """
Warning, prefilter file already exists! Overwriting file. This may be intended.
"""
if prefilter_file.exists():
if not force:
warnings.warn(file_exist_warning)
logging.warning("Prefilter file exists. NOT overwriting")
else:
warnings.warn(force_warning)
logging.warning("Prefilter file exists. Overwriting")
# Perform prefiltering and output file
print("Starting 0.prefilter-features")
logging.info("0.prefilter-features started")
if perform:
features_df = prefilter_features(core_option_args, example_site_dir,
flag_cols)
else:
features_df = load_features(core_option_args, example_site_dir)
features_df = features_df.assign(prefilter_column=False)
if check_if_write(prefilter_file, force):
features_df.to_csv(prefilter_file, sep="\t", index=False)
print("Finished 0.prefilter-features")
logging.info("0.prefilter-features finished")