Merge branch 'na_volcano_CW-7345' into 'dev'
Volcano filter NA [CW-7345] See merge request epi2melabs/workflows/wf-transcriptomes!335
This commit is contained in:
Neil Horner
commit
13ce17c631
@ -13,9 +13,9 @@ Users of wf-transcriptomes v2.0.0 who have encountered issues during discovery a
|
||||
### Fixed
|
||||
- "Error in full_join" encountered during `runPerSampleBambuQuant` when all read classes have no compatible transcript assignment. An empty quant table is correctly emitted instead.
|
||||
- "unable to find an inherited method for function 'rowData'" encountered during `runJointBambuDiscover` when providing many samples. The workflow now correctly handles data spilled to disk by bambu discover.
|
||||
- Volcano plot class counts incorrect when `log2FoldChange` or `padj` columns contained NA values.
|
||||
- Adjusted p-values below 0.001 in the volcano selection table are now shown in scientific notation instead of being rounded to 0.000.
|
||||
|
||||
|
||||
## [v2.0.0]
|
||||
|
||||
This release refreshes `wf-transcriptomes` around a new reference-guided transcriptomics workflow built on `bambu`, with `SQANTI3` transcript classification and QC, `DESeq2` for differential gene expression, `DEXSeq` for differential transcript usage, and per-sample modified base summarisation with `modkit` when modification tags are present in aligned BAMs.
|
||||
|
||||
@ -548,7 +548,7 @@ def _heatmap_style():
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
}
|
||||
.clustering-info {
|
||||
.info-text {
|
||||
font-size: 11px;
|
||||
}"""
|
||||
|
||||
@ -1384,7 +1384,7 @@ def main(args):
|
||||
EZChart(hierarchical_result.heatmap, width="100%")
|
||||
EZChart(hierarchical_result.pca, width="100%")
|
||||
EZChart(hierarchical_result.distance, width="100%")
|
||||
with div(cls="clustering-info"):
|
||||
with div(cls="info-text"):
|
||||
br()
|
||||
clustering_info('gene')
|
||||
tabs = Tabs()
|
||||
@ -1422,19 +1422,22 @@ def main(args):
|
||||
_round_de_table(table.head(args.de_table_size)),
|
||||
use_index=False
|
||||
)
|
||||
with div(cls="clustering-info"):
|
||||
with div(cls="info-text"):
|
||||
raw(
|
||||
f"Table showing the top {args.de_table_size} genes sorted "
|
||||
"by adjusted p-value. <br><br><br>"
|
||||
)
|
||||
|
||||
h3("Gene expression volcano Plot")
|
||||
gn_vol, gn_class_table, gn_selected_table = volcano(table)
|
||||
gn_vol, gn_class_table, gn_selected_table, vol_text = volcano(table)
|
||||
with div(_class="volcano-plot-grid"):
|
||||
EZChart(gn_vol, width="100%", height="550")
|
||||
with div(_class="volcano-side-panel"):
|
||||
EZChart(gn_class_table, width="100%", height="auto")
|
||||
EZChart(gn_selected_table, width="100%", height="auto")
|
||||
if vol_text is not None:
|
||||
with div(cls="info-text"):
|
||||
raw(vol_text)
|
||||
|
||||
with report.add_section("Differential transcript usage", "DTU"):
|
||||
p(
|
||||
@ -1467,7 +1470,7 @@ def main(args):
|
||||
EZChart(hierarchical_result.heatmap, width="100%")
|
||||
EZChart(hierarchical_result.pca, width="100%")
|
||||
EZChart(hierarchical_result.distance, width="100%")
|
||||
with div(cls="clustering-info"):
|
||||
with div(cls="info-text"):
|
||||
br()
|
||||
clustering_info('transcript')
|
||||
|
||||
@ -1511,19 +1514,24 @@ def main(args):
|
||||
_round_de_table(dtu_table.head(args.de_table_size)),
|
||||
use_index=False
|
||||
)
|
||||
with div(cls="clustering-info"):
|
||||
with div(cls="info-text"):
|
||||
raw(
|
||||
f"Table showing the top {args.de_table_size} "
|
||||
"transcripts sorted by adjusted p-value. <br><br><br>"
|
||||
)
|
||||
|
||||
h3("Transcript expression volcano Plot")
|
||||
tr_vol, tr_class_table, tr_selected_table = volcano(dtu_table)
|
||||
(
|
||||
tr_vol, tr_class_table, tr_selected_table, vol_text
|
||||
) = volcano(dtu_table)
|
||||
with div(_class="volcano-plot-grid"):
|
||||
EZChart(tr_vol, width="100%", height="550")
|
||||
with div(_class="volcano-side-panel"):
|
||||
EZChart(tr_class_table, width="100%", height="auto")
|
||||
EZChart(tr_selected_table, width="100%", height="auto")
|
||||
if vol_text is not None:
|
||||
with div(cls="info-text"):
|
||||
raw(vol_text)
|
||||
else:
|
||||
p("No DTU results available for this contrast.")
|
||||
|
||||
|
||||
@ -67,6 +67,10 @@ def _volcano_source_data(data, fold_threshold=1, p_threshold=0.05):
|
||||
input_columns = set(data.columns)
|
||||
data["log2FoldChange"] = pd.to_numeric(data["log2FoldChange"], errors="coerce")
|
||||
data["padj"] = pd.to_numeric(data["padj"], errors="coerce")
|
||||
|
||||
data.replace([np.inf, -np.inf], np.nan, inplace=True)
|
||||
data.dropna(subset=["log2FoldChange", "padj"], inplace=True)
|
||||
|
||||
is_transcript_plot = "featureID" in data.columns
|
||||
if is_transcript_plot:
|
||||
data.rename(columns={
|
||||
@ -267,6 +271,9 @@ def _tap_selection_callback_code(x_field, y_field):
|
||||
|
||||
def volcano(data, fold_threshold=1, p_threshold=0.05):
|
||||
"""Build an interactive volcano plot with selection and filtering widgets."""
|
||||
input_size = len(data)
|
||||
source_data = data.dropna(subset=["log2FoldChange", "padj"])
|
||||
n_filtered = input_size - len(source_data)
|
||||
source_data, original_columns = _volcano_source_data(
|
||||
data, fold_threshold=fold_threshold, p_threshold=p_threshold
|
||||
)
|
||||
@ -1321,4 +1328,15 @@ def volcano(data, fold_threshold=1, p_threshold=0.05):
|
||||
}
|
||||
""",
|
||||
))
|
||||
return volcano_ma_plot, classes_table, selected_plot
|
||||
message = None
|
||||
if n_filtered > 0:
|
||||
tx_file = (
|
||||
"results_dtu_transcript.tsv" if is_transcript_plot else "results_dge.tsv")
|
||||
message = (
|
||||
f"{n_filtered} features were omitted from the volcano plot because "
|
||||
"they do not have plottable log2 fold-change or adjusted p-values. "
|
||||
"<br>This is expected for low-information features filtered by the "
|
||||
"differential analysis method. Full results are available in "
|
||||
f"<i>{tx_file}</i>."
|
||||
)
|
||||
return volcano_ma_plot, classes_table, selected_plot, message
|
||||
|
||||
Loading…
Reference in New Issue
Block a user