Skip to content

Use more modern approach to loading included databases and fix mouse …#358

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

Merged
newmana merged 1 commit into from
Jul 12, 2026
Merged

Use more modern approach to loading included databases and fix mouse … #358

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
141 changes: 67 additions & 74 deletions stlearn/tl/cci/analysis.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
"""Loads inputted LR database, & concatenates into consistent database set of
pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
if isinstance(names, str):
names = [names]

path = os.path.dirname(os.path.realpath(__file__))
dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
lrs_full = []
for db in dbs:
lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
lrs_full.extend(lrs)
lrs_full_arr = np.unique(np.array(lrs_full))
db_dir = files("stlearn.tl.cci") / "databases"
lrs: set[str] = set()
for name in names:
with (db_dir / f"{name}.txt").open("rb") as fh:
db = pd.read_csv(fh, sep="\t")
lrs.update(
f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
)
# If dealing with mouse, need to reformat #
if species == "mouse":
genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
lrs_full_arr = np.array(
[
genes1[i][0]
+ genes1[i][1:].lower()
+ "_"
+ genes2[i][0]
+ genes2[i][1:].lower()
for i in range(len(lrs_full))
],
)

return lrs_full_arr
lrs = {
f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
for ligand, receptor in (lr_.split("_") for lr_ in lrs)
}
return np.array(sorted(lrs), dtype=np.str_)


def grid(
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
"""Creates a new anndata representing a gridded version of the data; can be
used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
"""Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
"""Performs p-value adjustment and determination of significant spots.
Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
"""Runs a basic GO analysis on the genes in the top ranked LR pairs.
Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
"""Calls significant celltype-celltype interactions based on cell-type data
randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
if not cols_present or not rows_present:
if not cols_present:
msg = (
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
)
elif not rows_present:
msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
lr_n_cci_sig = np.zeros(lr_summary.shape[0])
with tqdm(
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
) as pbar:
for i, best_lr in enumerate(best_lrs):
ligand, receptor = best_lr.split("_")
Expand Down
4 changes: 4 additions & 0 deletions tests/tl/test_cci.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

# Should not have duplicates.
self.assertEqual(len(lrs), len(set(lrs)))
self.assertLessEqual(len(lrs), sizes[1])

# Important, granular tests related to LR scoring

# Important, granular tests related to CCI counting
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
Use more modern approach to loading included databases and fix mouse … by newmana · Pull Request #358 · BiomedicalMachineLearning/stLearn · GitHub
Skip to content
Use more modern approach to loading included databases and fix mouse …#358

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

 Merged

newmana
merged 1 commit into

from

Jul 12, 2026
 Merged


Use more modern approach to loading included databases and fix mouse …
#358
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


141 changes: 67 additions & 74 deletions
stlearn/tl/cci/analysis.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,7 @@
"""

import os
from importlib.resources import files

import numba
import numpy as np
Expand All@@ -27,7 +28,7 @@

# Functions related to Ligand-Receptor interactions
def load_lrs(
 names: str | list | None = None, species: str = "human"
names: str | list[str] | None = None, species: str = "human",
) -> npt.NDArray[np.str_]:
 """Loads inputted LR database, & concatenates into consistent database set of
 pairs without duplicates. If None loads 'connectomeDB2020_lit'.
Expand All@@ -50,38 +51,30 @@ def load_lrs(
 if isinstance(names, str):
 names = [names]

 path = os.path.dirname(os.path.realpath(__file__))
 dbs = [pd.read_csv(f"{path}/databases/{name}.txt", sep="\t") for name in names]
 lrs_full = []
 for db in dbs:
 lrs = [f"{db.values[i, 0]}_{db.values[i, 1]}" for i in range(db.shape[0])]
 lrs_full.extend(lrs)
 lrs_full_arr = np.unique(np.array(lrs_full))
 db_dir = files("stlearn.tl.cci") / "databases"
 lrs: set[str] = set()
 for name in names:
 with (db_dir / f"{name}.txt").open("rb") as fh:
 db = pd.read_csv(fh, sep="\t")
 lrs.update(
 f"{ligand}_{receptor}" for ligand, receptor in db.iloc[:, :2].values
 )
 # If dealing with mouse, need to reformat #
 if species == "mouse":
 genes1 = [lr_.split("_")[0] for lr_ in lrs_full]
 genes2 = [lr_.split("_")[1] for lr_ in lrs_full]
 lrs_full_arr = np.array(
 [
 genes1[i][0]
 + genes1[i][1:].lower()
 + "_"
 + genes2[i][0]
 + genes2[i][1:].lower()
 for i in range(len(lrs_full))
 ],
 )

 return lrs_full_arr
 lrs = {
 f"{ligand[0]}{ligand[1:].lower()}_{receptor[0]}{receptor[1:].lower()}"
 for ligand, receptor in (lr_.split("_") for lr_ in lrs)
 }
 return np.array(sorted(lrs), dtype=np.str_)


def grid(
 adata: AnnData,
 n_row: int = 10,
 n_col: int = 10,
 use_label: str | None = None,
 n_cpus: int | None = None,
 verbose: bool = True,
adata: AnnData,
n_row: int = 10,
n_col: int = 10,
use_label: str | None = None,
n_cpus: int | None = None,
verbose: bool = True,
) -> AnnData:
 """Creates a new anndata representing a gridded version of the data; can be
 used upstream of CCI pipeline. NOTE: intended use is for single cell
Expand DownExpand Up@@ -199,20 +192,20 @@ def grid(


def run(
 adata: AnnData,
 lrs: npt.NDArray[np.str_],
 min_spots: int = 10,
 distance: float | None = None,
 n_pairs: int = 1000,
 n_cpus: int | None = None,
 use_label: str | None = None,
 adj_method: str = "fdr_bh",
 pval_adj_cutoff: float = 0.05,
 min_expr: float = 0.0,
 save_bg: bool = False,
 neg_binom: bool = False,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
lrs: npt.NDArray[np.str_],
min_spots: int = 10,
distance: float | None = None,
n_pairs: int = 1000,
n_cpus: int | None = None,
use_label: str | None = None,
adj_method: str = "fdr_bh",
pval_adj_cutoff: float = 0.05,
min_expr: float = 0.0,
save_bg: bool = False,
neg_binom: bool = False,
random_state: int = 0,
verbose: bool = True,
) -> None:
 """Performs stLearn LR analysis.

Expand DownExpand Up@@ -373,10 +366,10 @@ def run(


def adj_pvals(
 adata,
 pval_adj_cutoff: float = 0.05,
 correct_axis: str = "spot",
 adj_method: str = "fdr_bh",
adata,
pval_adj_cutoff: float = 0.05,
correct_axis: str = "spot",
adj_method: str = "fdr_bh",
):
 """Performs p-value adjustment and determination of significant spots.
 Default settings of this function are already run in st.tl.cci.run.
Expand DownExpand Up@@ -455,16 +448,16 @@ def adj_pvals(


def run_lr_go(
 adata: AnnData,
 r_path: str,
 n_top: int = 100,
 bg_genes: np.ndarray | None = None,
 min_sig_spots: int = 1,
 species: str = "human",
 p_cutoff: float = 0.01,
 q_cutoff: float = 0.5,
 onts: str = "BP",
 verbose: bool = True,
adata: AnnData,
r_path: str,
n_top: int = 100,
bg_genes: np.ndarray | None = None,
min_sig_spots: int = 1,
species: str = "human",
p_cutoff: float = 0.01,
q_cutoff: float = 0.5,
onts: str = "BP",
verbose: bool = True,
):
 """Runs a basic GO analysis on the genes in the top ranked LR pairs.
 Only supported for human and mouse species.
Expand DownExpand Up@@ -533,17 +526,17 @@ def run_lr_go(

# Functions for calling Celltype-Celltype interactions
def run_cci(
 adata: AnnData,
 use_label: str,
 spot_mixtures: bool = False,
 min_spots: int = 3,
 sig_spots: bool = True,
 cell_prop_cutoff: float = 0.2,
 p_cutoff: float = 0.05,
 n_perms: int = 100,
 n_cpus: int | None = None,
 random_state: int = 0,
 verbose: bool = True,
adata: AnnData,
use_label: str,
spot_mixtures: bool = False,
min_spots: int = 3,
sig_spots: bool = True,
cell_prop_cutoff: float = 0.2,
p_cutoff: float = 0.05,
n_perms: int = 100,
n_cpus: int | None = None,
random_state: int = 0,
verbose: bool = True,
):
 """Calls significant celltype-celltype interactions based on cell-type data
 randomisation.
Expand DownExpand Up@@ -658,8 +651,8 @@ def run_cci(
 if not cols_present or not rows_present:
 if not cols_present:
 msg = (
 msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
 f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
msg + f"Cell types missing from adata.uns[{uns_key}] columns:\n"
f"{[cell for cell in all_set if cell not in adata.uns[uns_key]]}\n"
 )
 elif not rows_present:
 msg = msg + "Rows do not correspond to adata.obs_names.\n"
Expand DownExpand Up@@ -706,11 +699,11 @@ def run_cci(
 lr_n_spot_cci_sig = np.zeros(lr_summary.shape[0])
 lr_n_cci_sig = np.zeros(lr_summary.shape[0])
 with tqdm(
 total=len(best_lrs),
 desc="Counting celltype-celltype interactions per LR and permuting "
 + f"{n_perms} times.",
 bar_format="{l_bar}{bar} [ time left: {remaining} ]",
 disable=not verbose,
total=len(best_lrs),
desc="Counting celltype-celltype interactions per LR and permuting "
+ f"{n_perms} times.",
bar_format="{l_bar}{bar} [ time left: {remaining} ]",
disable=not verbose,
 ) as pbar:
 for i, best_lr in enumerate(best_lrs):
 ligand, receptor = best_lr.split("_")
Expand Down

4 changes: 4 additions & 0 deletions
tests/tl/test_cci.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def test_load_lrs(self):
 self.assertTrue(np.all([gene[0].isupper() for gene in genes2]))
 self.assertTrue(np.all([gene[1:] == gene[1:].lower() for gene in genes2]))

 # Should not have duplicates.
 self.assertEqual(len(lrs), len(set(lrs)))
 self.assertLessEqual(len(lrs), sizes[1])

 # Important, granular tests related to LR scoring

 # Important, granular tests related to CCI counting
Expand Down