def n50_barplot(df, figformat, path, title=None, palette=None):
n50_bar = Plot(path=path + "NanoComp_N50." + figformat,
title="Comparing read length N50")
if "aligned_lengths" in df:
n50s = [
get_N50(np.sort(df.loc[df["dataset"] == d, "aligned_lengths"]))
for d in df["dataset"].unique()
]
ylabel = 'Total gigabase aligned'
else:
n50s = [
get_N50(np.sort(df.loc[df["dataset"] == d, "lengths"]))
for d in df["dataset"].unique()
]
ylabel = 'Sequenced read length N50'
ax = sns.barplot(x=list(df["dataset"].unique()),
y=n50s,
palette=palette,
order=df["dataset"].unique())
ax.set(ylabel=ylabel, title=title or n50_bar.title)
plt.xticks(rotation=30, ha='center')
n50_bar.fig = ax.get_figure()
n50_bar.save(format=figformat)
plt.close("all")
return [n50_bar]
def n50_barplot(df, path, settings, title=None):
'''
Returns Plot object and creates figure(format specified)/html
containing bar chart of total gb aligned/sequenced read length n50
'''
n50_bar = Plot(path=path + "NanoComp_N50.html",
title="Comparing read length N50")
if "aligned_lengths" in df:
n50s = [
get_N50(np.sort(df.loc[df["dataset"] == d, "aligned_lengths"]))
for d in df["dataset"].unique()
]
ylabel = 'Total gigabase aligned'
else:
n50s = [
get_N50(np.sort(df.loc[df["dataset"] == d, "lengths"]))
for d in df["dataset"].unique()
]
ylabel = 'Sequenced read length N50'
idx = df["dataset"].unique()
n50_bar.fig = go.Figure()
for idx, n50 in zip(idx, n50s):
n50_bar.fig.add_trace(go.Bar(x=[idx], y=[n50], name=idx))
n50_bar.fig.update_layout(
title=title or n50_bar.title,
title_x=0.5,
yaxis_title=ylabel,
)
n50_bar.html = n50_bar.fig.to_html(full_html=False, include_plotlyjs='cdn')
n50_bar.save(settings)
return [n50_bar]
def make_plots(datadf, settings):
'''
Call plotting functions from nanoplotter
settings["lengths_pointer"] is a column in the DataFrame specifying which lengths to use
'''
plot_settings = dict(font_scale=settings["font_scale"])
nanoplotter.plot_settings(plot_settings, dpi=settings["dpi"])
color = nanoplotter.check_valid_color(settings["color"])
colormap = nanoplotter.check_valid_colormap(settings["colormap"])
plotdict = {
type: settings["plots"].count(type)
for type in ["kde", "hex", "dot", 'pauvre']
}
plots = []
if settings["N50"]:
n50 = nanomath.get_N50(np.sort(datadf["lengths"]))
else:
n50 = None
plots.extend(
nanoplotter.length_plots(
array=datadf[datadf["length_filter"]]["lengths"].astype('uint64'),
name="Read length",
path=settings["path"],
n50=n50,
color=color,
figformat=settings["format"],
title=settings["title"]))
logging.info("Created length plots")
if "quals" in datadf:
plots.extend(
nanoplotter.scatter(x=datadf[datadf["length_filter"]][
settings["lengths_pointer"].replace('log_', '')],
y=datadf[datadf["length_filter"]]["quals"],
names=['Read lengths', 'Average read quality'],
path=settings["path"] +
"LengthvsQualityScatterPlot",
color=color,
figformat=settings["format"],
plots=plotdict,
title=settings["title"],
plot_settings=plot_settings))
if settings["logBool"]:
plots.extend(
nanoplotter.scatter(
x=datadf[datadf["length_filter"]][
settings["lengths_pointer"]],
y=datadf[datadf["length_filter"]]["quals"],
names=['Read lengths', 'Average read quality'],
path=settings["path"] + "LengthvsQualityScatterPlot",
color=color,
figformat=settings["format"],
plots=plotdict,
log=True,
title=settings["title"],
plot_settings=plot_settings))
logging.info("Created LengthvsQual plot")
if "channelIDs" in datadf:
plots.extend(
nanoplotter.spatial_heatmap(array=datadf["channelIDs"],
title=settings["title"],
path=settings["path"] +
"ActivityMap_ReadsPerChannel",
color=colormap,
figformat=settings["format"]))
logging.info("Created spatialheatmap for succesfull basecalls.")
if "start_time" in datadf:
plots.extend(
nanoplotter.time_plots(df=datadf,
path=settings["path"],
color=color,
figformat=settings["format"],
title=settings["title"],
plot_settings=plot_settings))
if settings["logBool"]:
plots.extend(
nanoplotter.time_plots(df=datadf,
path=settings["path"],
color=color,
figformat=settings["format"],
title=settings["title"],
log_length=True,
plot_settings=plot_settings))
logging.info("Created timeplots.")
if "aligned_lengths" in datadf and "lengths" in datadf:
plots.extend(
nanoplotter.scatter(
x=datadf[datadf["length_filter"]]["aligned_lengths"],
y=datadf[datadf["length_filter"]]["lengths"],
names=["Aligned read lengths", "Sequenced read length"],
path=settings["path"] +
"AlignedReadlengthvsSequencedReadLength",
figformat=settings["format"],
plots=plotdict,
color=color,
title=settings["title"],
plot_settings=plot_settings))
logging.info("Created AlignedLength vs Length plot.")
if "mapQ" in datadf and "quals" in datadf:
plots.extend(
nanoplotter.scatter(
x=datadf["mapQ"],
y=datadf["quals"],
names=["Read mapping quality", "Average basecall quality"],
path=settings["path"] + "MappingQualityvsAverageBaseQuality",
color=color,
figformat=settings["format"],
plots=plotdict,
title=settings["title"],
plot_settings=plot_settings))
logging.info("Created MapQvsBaseQ plot.")
plots.extend(
nanoplotter.scatter(x=datadf[datadf["length_filter"]][
settings["lengths_pointer"].replace('log_', '')],
y=datadf[datadf["length_filter"]]["mapQ"],
names=["Read length", "Read mapping quality"],
path=settings["path"] +
"MappingQualityvsReadLength",
color=color,
figformat=settings["format"],
plots=plotdict,
title=settings["title"],
plot_settings=plot_settings))
if settings["logBool"]:
plots.extend(
nanoplotter.scatter(
x=datadf[datadf["length_filter"]][
settings["lengths_pointer"]],
y=datadf[datadf["length_filter"]]["mapQ"],
names=["Read length", "Read mapping quality"],
path=settings["path"] + "MappingQualityvsReadLength",
color=color,
figformat=settings["format"],
plots=plotdict,
log=True,
title=settings["title"],
plot_settings=plot_settings))
logging.info("Created Mapping quality vs read length plot.")
if "percentIdentity" in datadf:
minPID = np.percentile(datadf["percentIdentity"], 1)
if "aligned_quals" in datadf:
plots.extend(
nanoplotter.scatter(
x=datadf["percentIdentity"],
y=datadf["aligned_quals"],
names=["Percent identity", "Average Base Quality"],
path=settings["path"] +
"PercentIdentityvsAverageBaseQuality",
color=color,
figformat=settings["format"],
plots=plotdict,
stat=stats.pearsonr
if not settings["hide_stats"] else None,
minvalx=minPID,
title=settings["title"],
plot_settings=plot_settings))
logging.info("Created Percent ID vs Base quality plot.")
plots.extend(
nanoplotter.scatter(
x=datadf[datadf["length_filter"]][
settings["lengths_pointer"].replace('log_', '')],
y=datadf[datadf["length_filter"]]["percentIdentity"],
names=["Aligned read length", "Percent identity"],
path=settings["path"] + "PercentIdentityvsAlignedReadLength",
color=color,
figformat=settings["format"],
plots=plotdict,
stat=stats.pearsonr if not settings["hide_stats"] else None,
minvaly=minPID,
title=settings["title"],
plot_settings=plot_settings))
if settings["logBool"]:
plots.extend(
nanoplotter.scatter(
x=datadf[datadf["length_filter"]][
settings["lengths_pointer"]],
y=datadf[datadf["length_filter"]]["percentIdentity"],
names=["Aligned read length", "Percent identity"],
path=settings["path"] +
"PercentIdentityvsAlignedReadLength",
color=color,
figformat=settings["format"],
plots=plotdict,
stat=stats.pearsonr
if not settings["hide_stats"] else None,
log=True,
minvaly=minPID,
title=settings["title"],
plot_settings=plot_settings))
plots.append(
nanoplotter.dynamic_histogram(array=datadf["percentIdentity"],
name="percent identity",
path=settings["path"] +
"PercentIdentityHistogram",
title=settings["title"],
color=color))
logging.info("Created Percent ID vs Length plot")
return plots
def make_plots(datadf, settings):
'''
Call plotting functions from nanoplotter
settings["lengths_pointer"] is a column in the DataFrame specifying which lengths to use
'''
color = nanoplotter.check_valid_color(settings["color"])
plotdict = {
type: settings["plots"].count(type)
for type in ["kde", "hex", "dot", 'pauvre']
}
plots = []
if settings["no_N50"]:
n50 = None
else:
n50 = nanomath.get_N50(np.sort(datadf["lengths"]))
plots.extend(
nanoplotter.length_plots(array=datadf["lengths"],
name="Read length",
path=settings["path"],
n50=n50,
color=color,
figformat=settings["format"],
title=settings["title"]))
logging.info("Created length plots")
if "quals" in datadf:
plots.extend(
nanoplotter.scatter(x=datadf[settings["lengths_pointer"]],
y=datadf["quals"],
names=['Read lengths', 'Average read quality'],
path=settings["path"] +
settings["length_prefix"] +
"LengthvsQualityScatterPlot",
color=color,
figformat=settings["format"],
plots=plotdict,
log=settings["logBool"],
title=settings["title"]))
logging.info("Created LengthvsQual plot")
if "channelIDs" in datadf:
plots.extend(
nanoplotter.spatial_heatmap(array=datadf["channelIDs"],
title=settings["title"],
path=settings["path"] +
"ActivityMap_ReadsPerChannel",
color="Greens",
figformat=settings["format"]))
logging.info("Created spatialheatmap for succesfull basecalls.")
if "start_time" in datadf:
plots.extend(
nanoplotter.time_plots(df=datadf,
path=settings["path"],
color=color,
figformat=settings["format"],
title=settings["title"]))
logging.info("Created timeplots.")
if "aligned_lengths" in datadf and "lengths" in datadf:
plots.extend(
nanoplotter.scatter(
x=datadf["aligned_lengths"],
y=datadf["lengths"],
names=["Aligned read lengths", "Sequenced read length"],
path=settings["path"] +
"AlignedReadlengthvsSequencedReadLength",
figformat=settings["format"],
plots=plotdict,
color=color,
title=settings["title"]))
logging.info("Created AlignedLength vs Length plot.")
if "maqpQ" in datadf:
plots.extend(
nanoplotter.scatter(
x=datadf["mapQ"],
y=datadf["quals"],
names=["Read mapping quality", "Average basecall quality"],
path=settings["path"] + "MappingQualityvsAverageBaseQuality",
color=color,
figformat=settings["format"],
plots=plotdict,
title=settings["title"]))
logging.info("Created MapQvsBaseQ plot.")
plots.extend(
nanoplotter.scatter(x=datadf[settings["lengths_pointer"]],
y=datadf["mapQ"],
names=["Read length", "Read mapping quality"],
path=settings["path"] +
settings["length_prefix"] +
"MappingQualityvsReadLength",
color=color,
figformat=settings["format"],
plots=plotdict,
log=settings["logBool"],
title=settings["title"]))
logging.info("Created Mapping quality vs read length plot.")
if "percentIdentity" in datadf:
minPID = np.percentile(datadf["percentIdentity"], 1)
plots.extend(
nanoplotter.scatter(x=datadf["percentIdentity"],
y=datadf["aligned_quals"],
names=["Percent identity", "Read quality"],
path=settings["path"] +
"PercentIdentityvsAverageBaseQuality",
color=color,
figformat=settings["format"],
plots=plotdict,
stat=stats.pearsonr,
minvalx=minPID,
title=settings["title"]))
logging.info("Created Percent ID vs Base quality plot.")
plots.extend(
nanoplotter.scatter(
x=datadf[settings["lengths_pointer"]],
y=datadf["percentIdentity"],
names=["Aligned read length", "Percent identity"],
path=settings["path"] + "PercentIdentityvsAlignedReadLength",
color=color,
figformat=settings["format"],
plots=plotdict,
stat=stats.pearsonr,
log=settings["logBool"],
minvaly=minPID,
title=settings["title"]))
logging.info("Created Percent ID vs Length plot")
return plots