def plot_scatter_matrix(n_clicks, data, columns, selected, ndxs):
if n_clicks is None:
raise PreventUpdate
df = pd.DataFrame(data)
df["DateAcquired"] = pd.to_datetime(df["DateAcquired"])
numeric_columns = df.select_dtypes(include=np.number).columns
n_dimensions = len(numeric_columns)
if ndxs is not None:
df = df.reindex(ndxs)
fig = px.scatter_matrix(df, dimensions=columns)
fig.update_layout(
autosize=True,
height=1200,
showlegend=False,
margin=dict(l=50, r=10, b=200, t=50, pad=0),
hovermode="closest",
)
config = T.gen_figure_config(filename="PQC-scatter-matrix")
marker_color = df["Use Downstream"].replace({
True:
C.colors["use_downstream"],
False:
C.colors["dont_use_downstream"]
})
marker_line_color = df["Flagged"].replace({
True:
C.colors["flagged"],
False:
C.colors["not_flagged"]
})
marker_symbol = [0] * len(df)
for i, ndx in enumerate(ndxs):
if ndx in selected:
marker_color[i] = C.colors["selected"]
marker_symbol[i] = 1
fig.update_traces(
marker_symbol=marker_symbol,
marker_line_color=marker_line_color,
marker_line_width=2,
opacity=0.8,
)
fig.update_traces(marker_color=marker_color)
fig.update_traces(marker_size=20)
return fig, config
def plot_shapley(shapley_values, qc_data, options, ndxs, tab):
if tab != "anomaly": raise PreventUpdate
df_shap = pd.read_json(shapley_values)
qc_data = pd.DataFrame(qc_data)
qc_data = qc_data.iloc[ndxs]
if 'hide_rejected' in options:
qc_data = qc_data[qc_data['Use Downstream'] != False]
fns = qc_data["RawFile"]
df_shap = df_shap.loc[fns]
fig = T.px_heatmap(
df_shap.T,
layout_kws=dict(title="Anomaly feature score (shapley values)",
height=1200),
)
config = T.gen_figure_config(
filename="Anomaly-Detection-Shapley-values")
return fig, config
def plot_protein_figure(
n_clicks,
data,
ndxs,
plot_column,
project,
pipeline,
data_range,
qc_data,
derived_virtual_indices,
):
"""Create the protein groups figure."""
if (project is None) or (pipeline is None):
raise PreventUpdate
if (ndxs is None) or (ndxs == []):
raise PreventUpdate
if plot_column == "Reporter intensity corrected (normalized)":
plot_column = "Reporter intensity corrected"
normalized = True
else:
normalized = False
protein_names = list(pd.DataFrame(ndxs)["protein_names"])
qc_data = pd.DataFrame(qc_data)
if derived_virtual_indices is not None:
qc_data = qc_data.reindex(derived_virtual_indices)
raw_files = list(qc_data.RawFile.values)
data = T.get_protein_groups(
project,
pipeline,
protein_names=protein_names,
columns=[plot_column],
data_range=data_range,
raw_files=raw_files,
)
df = pd.read_json(data)
color = None
if plot_column == "Reporter intensity corrected":
id_vars = ["RawFile", "Majority protein IDs"]
df = (df.set_index(id_vars).filter(
regex=plot_column).reset_index().melt(id_vars=id_vars,
var_name="TMT Channel",
value_name=plot_column))
df["TMT Channel"] = df["TMT Channel"].apply(
lambda x: f"{int(x.split()[3]):02.0f}")
if normalized:
df[plot_column] = (
df[plot_column] /
df.groupby(["RawFile", "Majority protein IDs"
]).transform("sum")[plot_column])
color = "TMT Channel"
df = df.sort_values(["RawFile", "TMT Channel"])
else:
df = df.sort_values("RawFile")
n_rows = len(df["Majority protein IDs"].drop_duplicates())
height = 300 * n_rows + (100 * n_rows)
if n_rows <= 1:
facet_row_spacing = 0.04
else:
facet_row_spacing = min(0.04, (1 / (n_rows - 1)))
fig = px.bar(
data_frame=df,
x="RawFile",
y=plot_column,
facet_col="Majority protein IDs",
facet_col_wrap=1,
color=color,
color_discrete_sequence=px.colors.qualitative.Dark24,
color_continuous_scale=px.colors.sequential.Rainbow,
facet_row_spacing=facet_row_spacing,
height=height,
category_orders={"RawFile": raw_files},
)
fig.for_each_annotation(lambda a: a.update(text=a.text.split("=")[-1]))
fig.update(layout_showlegend=True)
fig.update_layout(hovermode="closest")
fig.update_xaxes(matches="x")
fig.update_xaxes(automargin=True)
fig.update_yaxes(automargin=True)
fig.update_yaxes(matches=None)
if normalized:
fig.update_layout(yaxis=dict(range=[0, 1]))
config = T.gen_figure_config(filename="PQC-protein-quant")
return fig, config
options=list_to_dropdown_options(plot_columns),
placeholder="Select data columns",
value="Reporter intensity corrected",
style={
"width": "100%",
"max-width": "100%",
"margin-top": "50px",
"margin-bottom": "50px",
},
),
html.Button("Update figure", id="proteins-fig-update"),
dcc.Loading([
html.Div(style={"min-width": 400}),
dcc.Graph(
id="protein-figure",
config=T.gen_figure_config(filename="protein-groups"),
),
]),
])
def callbacks(app):
@app.callback(
Output("proteins-table", "data"),
Input("proteins-update", "n_clicks"),
State("project", "value"),
State("pipeline", "value"),
State("qc-table", "data"),
State("tabs", "value"),
State("proteins-options", "value"),
)
def plot_qc_figure(refresh, selected, ndxs, x, data, optional_columns):
"""Creates the bar-plot figure"""
if (data is None) or (ndxs is None) or (len(ndxs) == 0):
raise PreventUpdate
if x is None:
x = "RawFile"
titles = [el["title"] for el in plot_map]
df = pd.DataFrame(data)
assert pd.value_counts(df.columns).max() == 1, pd.value_counts(df.columns)
df["DateAcquired"] = pd.to_datetime(df["DateAcquired"])
if ndxs is not None:
df = df.reindex(ndxs)
numeric_columns = df[optional_columns].head(1)._get_numeric_data().columns
fig = make_subplots(
cols=1,
rows=len(numeric_columns),
subplot_titles=numeric_columns,
shared_xaxes=True,
# vertical_spacing=0.05,
print_grid=True,
)
for i, col in enumerate(numeric_columns):
trace = go.Bar(
x=df[x],
y=df[col],
name=col,
text=None if x == "RawFile" else df["RawFile"],
)
fig.add_trace(trace, row=1 + i, col=1)
fig.update_layout(
hovermode="closest",
hoverlabel_namelength=-1,
height=200 + 250 * (i + 1),
showlegend=False,
margin=dict(l=50, r=10, b=200, t=50, pad=0),
)
marker_color = df["Use Downstream"].replace({
True: C.colors["accepted"],
False: C.colors["rejected"],
None: C.colors["unassigned"]
})
marker_line_color = df["Flagged"].replace({
True: C.colors["flagged"],
False: C.colors["not_flagged"]
})
for ndx in selected:
marker_color[ndx] = C.colors["selected"]
fig.update_traces(
marker_color=marker_color,
marker_line_color=marker_line_color,
marker_line_width=1,
opacity=0.8,
)
fig.update_xaxes(matches="x")
if x == "RawFile":
fig.update_layout(xaxis5=dict(tickmode="array",
tickvals=tuple(range(len(df))),
ticktext=tuple(df[x])))
config = T.gen_figure_config(filename="QC-barplot")
return fig, config
def explorer_plot(n_clicks, x, y, color, size, facet_row, facet_col, data,
selected, ndxs):
columns = [
x,
y,
color,
size,
facet_row,
facet_col,
]
if y is None:
raise PreventUpdate
if None in columns:
columns.remove(None)
columns = [c for c in columns if (c is not None)]
df = pd.DataFrame(data)
df["DateAcquired"] = pd.to_datetime(df["DateAcquired"])
if ndxs is not None:
df = df.reindex(ndxs)
if facet_row is not None:
n_rows = len(df[facet_row].value_counts())
else:
n_rows = 2
facet_col_wrap = 3
if facet_col is not None:
n_cols = len(df[facet_col].value_counts())
n_rows = min(2, int(n_cols / facet_col_wrap) + 2)
if size is not None:
# Plotly crashes if size column has NaNs
df[size] = df[size].fillna(0)
fig = px.scatter(
data_frame=df,
x=x,
y=y,
color=color,
size=size,
facet_row=facet_row,
facet_col=facet_col,
hover_data=["Index", "RawFile"],
facet_col_wrap=facet_col_wrap,
)
fig.update_layout(
autosize=True,
height=300 * n_rows + 200,
showlegend=False,
margin=dict(l=50, r=10, b=200, t=50, pad=0),
hovermode="closest",
)
marker_color = df["Use Downstream"].replace({
True: C.colors["accepted"],
False: C.colors["rejected"]
})
marker_line_color = df["Flagged"].replace({
True:
C.colors["flagged"],
False:
C.colors["not_flagged"]
})
marker_symbol = [0] * len(df)
for i, ndx in enumerate(ndxs):
if ndx in selected:
marker_color[i] = C.colors["selected"]
marker_symbol[i] = 1
fig.update_traces(
marker_symbol=marker_symbol,
marker_line_color=marker_line_color,
marker_line_width=2,
opacity=0.8,
)
if color is None:
fig.update_traces(marker_color=marker_color)
if size is None:
fig.update_traces(marker_size=20)
config = T.gen_figure_config(filename="PQC-explorer")
return fig, config