Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Reorganize pseudobulk and deseq2 functions #300

Merged
merged 2 commits into from
Jun 2, 2024
Merged

Reorganize pseudobulk and deseq2 functions #300

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7e61b3b
Add pydeseq2 backend for deseq2; fix issue with matplotlib v3.9+; imp…
yihming Jun 1, 2024
e368e45
fix bug
yihming Jun 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions pegasus/plotting/plot_library.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,7 +353,7 @@ def scatter(
fontsize=legend_fontsize[attr_id],
ncol=_get_legend_ncol(label_size, legend_ncol),
)
for handle in legend.legendHandles:
for handle in legend.legend_handles:
handle.set_sizes([300.0 if scale_factor is None else 100.0])
elif legend_loc[attr_id] == "on data":
texts = []
Expand Down Expand Up @@ -588,7 +588,7 @@ def scatter_groups(
fontsize=legend_fontsize,
ncol=legend_ncol,
)
for handle in legend.legendHandles:
for handle in legend.legend_handles:
handle.set_sizes([300.0])
elif legend_loc == "on data":
texts = []
Expand Down Expand Up @@ -2092,7 +2092,7 @@ def volcano(
fontsize=8,
ncol=4,
)
for handle in legend.legendHandles: # adjust legend size
for handle in legend.legend_handles: # adjust legend size
handle.set_sizes([50.0])

ax.axhline(y = yconst, c = 'k', lw = 0.5, ls = '--')
Expand Down Expand Up @@ -2355,7 +2355,7 @@ def wordcloud(
>>> fig = pg.wordcloud(data, factor=0)
"""
fig, ax = _get_subplot_layouts(panel_size=panel_size, dpi=dpi) # default nrows = 1 & ncols = 1

assert 'W' in data.uns
hvg = data.var_names[data.var[features]]
word_dict = {}
Expand Down
23 changes: 16 additions & 7 deletions pegasus/pseudo/convenient.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ def markers(
if de_key not in pseudobulk.varm.keys():
raise ValueError("Please run DE analysis first")

res_dict = {}
res_dict = {}
df = pd.DataFrame(data=pseudobulk.varm[de_key], index=pseudobulk.var_names)
idx = df["padj"] <= alpha

Expand Down Expand Up @@ -206,11 +206,20 @@ def volcano(
logger.warning("Please conduct DE test first!")
return None

log2fc = de_res[fcstr]
pvals = de_res[pstr]
qvals = de_res[qstr]
# Ignore genes with q-value NaN
idx_select = np.where(~np.isnan(qvals))[0]
if idx_select.size == 0:
logger.warning("All genes have NaN adjusted p-values!")
return None
qvals = qvals[idx_select]
log2fc = de_res[fcstr][idx_select]
pvals = de_res[pstr][idx_select]
gene_names = pseudobulk.var_names[idx_select]

pvals[pvals == 0.0] = 1e-45 # very small pvalue to avoid log10 0
neglog10p = -np.log10(pvals)
yconst = min(neglog10p[de_res[qstr] <= qval_threshold])
yconst = min(neglog10p[qvals <= qval_threshold])

from pegasus.plotting.plot_utils import _get_subplot_layouts
fig, ax = _get_subplot_layouts(panel_size=panel_size, dpi=dpi)
Expand Down Expand Up @@ -239,7 +248,7 @@ def volcano(
fontsize=8,
ncol=4,
)
for handle in legend.legendHandles: # adjust legend size
for handle in legend.legend_handles: # adjust legend size
handle.set_sizes([50.0])

ax.axhline(y = yconst, c = 'k', lw = 0.5, ls = '--')
Expand All @@ -252,13 +261,13 @@ def volcano(
posvec = np.argsort(log2fc[idx])[::-1][0:top_n]
for pos in posvec:
gid = idx[pos]
texts.append(ax.text(log2fc[gid], neglog10p[gid], pseudobulk.var_names[gid], fontsize=5))
texts.append(ax.text(log2fc[gid], neglog10p[gid], gene_names[gid], fontsize=5))

idx = np.where(idxsig & (log2fc <= -log2fc_threshold))[0]
posvec = np.argsort(log2fc[idx])[0:top_n]
for pos in posvec:
gid = idx[pos]
texts.append(ax.text(log2fc[gid], neglog10p[gid], pseudobulk.var_names[gid], fontsize=5))
texts.append(ax.text(log2fc[gid], neglog10p[gid], gene_names[gid], fontsize=5))

from adjustText import adjust_text
adjust_text(texts, arrowprops=dict(arrowstyle='-', color='k', lw=0.5))
Expand Down
10 changes: 4 additions & 6 deletions pegasus/tools/clustering.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
from sklearn.cluster import KMeans
from typing import List, Optional, Union

from pegasus.tools import eff_n_jobs, construct_graph, calc_stat_per_batch, X_from_rep, slicing
from pegasus.tools import eff_n_jobs, construct_graph, calc_stat_per_batch, update_rep, X_from_rep, slicing

import logging
logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -780,10 +780,8 @@ def calc_dendrogram(
"""
# Set up embedding or count matrix to use
if genes is None:
if rep:
embed_df = pd.DataFrame(X_from_rep(data, rep))
else:
embed_df = pd.DataFrame(data.X.toarray() if issparse(data.X) else data.X)
rep = update_rep(rep)
embed_df = pd.DataFrame(X_from_rep(data, rep))
else:
embed_df = pd.DataFrame(slicing(data[:, genes].X))

Expand Down Expand Up @@ -825,4 +823,4 @@ def calc_dendrogram(
np.fill_diagonal(dissim_df.to_numpy(), 0) # Enforce main diagonal to be 0 to pass squareform requirement
Z = linkage(squareform(dissim_df), method=linkage_method, optimal_ordering=True)

data.uns[res_key] = (Z, csi_df)
data.uns[res_key] = (Z, csi_df)
Loading
Loading