kfukuta/wf-transcriptomes-v202
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch '20_volcano_points_cw-7277' into 'dev'

Browse Source 
Use all point for volcano and tables [CW-7277]

See merge request epi2melabs/workflows/wf-transcriptomes!300
This commit is contained in:
Neil Horner 2026-05-26 17:12:20 +00:00
commit abf467e528
1 changed files with 35 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
bin/workflow_glue/report.py
View File

@ -4,6 +4,7 @@ import json
import math import math
import os import os
from pathlib import Path from pathlib import Path
import warnings
from bokeh.resources import INLINE as BOKEH_INLINE from bokeh.resources import INLINE as BOKEH_INLINE
from dominate.tags import ( from dominate.tags import (
@ -18,12 +19,19 @@ from ezcharts.layout.resource import Resource as EZC_Resource
from ezcharts.layout.snippets import Tabs from ezcharts.layout.snippets import Tabs
from ezcharts.layout.snippets.table import DataTable from ezcharts.layout.snippets.table import DataTable
import pandas as pd import pandas as pd
from .hierarchical_clustering import hierarchical, clustering_info # noqa: ABS101 from .hierarchical_clustering import hierarchical, clustering_info # noqa: ABS101
from .util import get_named_logger, wf_parser # noqa: ABS101 from .util import get_named_logger, wf_parser # noqa: ABS101
from .volcano import volcano # noqa: ABS101 from .volcano import volcano # noqa: ABS101
# Suppress asyncio deprecation warning triggered by dominate on Python 3.10+.
# dominate calls asyncio.get_event_loop() outside a running async context.
warnings.filterwarnings(
"ignore",
message="There is no current event loop",
category=DeprecationWarning,
)
classification_categories = { classification_categories = {
"Full splice match": ( "Full splice match": (
"Reference and query isoforms have the same number of exons and " "Reference and query isoforms have the same number of exons and "
@ -207,7 +215,9 @@ def _contrast_results(de_dir, filename, n=None):
data = table data = table
if n is not None: if n is not None:
data = data.head(n) data = data.head(n)
data.sort_values("padj", ascending=True, inplace=True)
tables[contrast_dir.name] = data tables[contrast_dir.name] = data
return tables return tables
@ -1074,7 +1084,7 @@ def main(args):
clustering_info('gene') clustering_info('gene')
tabs = Tabs() tabs = Tabs()
for contrast, table in _contrast_results( for contrast, table in _contrast_results(
args.de_dir, "results_dge.tsv", n=20 args.de_dir, "results_dge.tsv"
).items(): ).items():
with tabs.add_tab(contrast): with tabs.add_tab(contrast):
# Check for contrast-specific warnings # Check for contrast-specific warnings
@ -1103,7 +1113,14 @@ def main(args):
with p(): with p():
strong("Note: ") strong("Note: ")
raw(contrast_data["dtu_power_warning"]) raw(contrast_data["dtu_power_warning"])
DataTable.from_pandas(table, use_index=False) DataTable.from_pandas(
table.head(args.de_table_size), use_index=False
)
with div(cls="clustering-info"):
raw(
f"Table showing the top {args.de_table_size} genes sorted "
"by adjusted p-value. <br><br><br>"
)
h3("Gene expression volcano Plot") h3("Gene expression volcano Plot")
gn_vol, gn_class_table, gn_selected_table = volcano(table) gn_vol, gn_class_table, gn_selected_table = volcano(table)
@ -1139,7 +1156,7 @@ def main(args):
tabs = Tabs() tabs = Tabs()
dtu_tables = _contrast_results( dtu_tables = _contrast_results(
args.de_dir, "results_dtu_transcript.tsv", n=20) args.de_dir, "results_dtu_transcript.tsv")
for contrast in sorted(Path(args.de_dir).iterdir()): for contrast in sorted(Path(args.de_dir).iterdir()):
if not contrast.is_dir(): if not contrast.is_dir():
@ -1173,7 +1190,14 @@ def main(args):
if contrast_name in dtu_tables: if contrast_name in dtu_tables:
dtu_table = dtu_tables[contrast_name] dtu_table = dtu_tables[contrast_name]
DataTable.from_pandas(dtu_table, use_index=False) DataTable.from_pandas(
dtu_table.head(args.de_table_size), use_index=False
)
with div(cls="clustering-info"):
raw(
f"Table showing the top {args.de_table_size} "
"transcripts sorted by adjusted p-value. <br><br><br>"
)
h3("Transcript expression volcano Plot") h3("Transcript expression volcano Plot")
tr_vol, tr_class_table, tr_selected_table = volcano(dtu_table) tr_vol, tr_class_table, tr_selected_table = volcano(dtu_table)
@ -1224,6 +1248,12 @@ def argparser():
default=None, default=None,
help="Annotation reference summary TSV.", help="Annotation reference summary TSV.",
) )
parser.add_argument(
"--de_table_size",
default=500,
type=int,
help="Number of rows to show in DE/DTU result tables.",
)
parser.add_argument("--versions", required=True, help="Versions directory.") parser.add_argument("--versions", required=True, help="Versions directory.")
parser.add_argument("--params", required=True, help="Workflow params JSON.") parser.add_argument("--params", required=True, help="Workflow params JSON.")
parser.add_argument( parser.add_argument(