spatial-aim 1.0.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- aim/__init__.py +47 -0
- aim/__main__.py +6 -0
- aim/adata_schema.py +80 -0
- aim/aggregation.py +118 -0
- aim/aim_config.py +76 -0
- aim/analysis/__init__.py +13 -0
- aim/analysis/analysis.py +72 -0
- aim/analysis/biology.py +205 -0
- aim/analysis/confidence.py +49 -0
- aim/analysis/ksweep.py +184 -0
- aim/analysis/loading.py +70 -0
- aim/analysis/onehot.py +41 -0
- aim/analysis/reconstruction.py +131 -0
- aim/analysis/topology.py +142 -0
- aim/analysis/utils.py +16 -0
- aim/cli.py +371 -0
- aim/clustering.py +242 -0
- aim/data/__init__.py +0 -0
- aim/data/prepare/__init__.py +0 -0
- aim/data/prepare/build_imaging_pairs.py +397 -0
- aim/data/prepare/build_xenium_breast_pair.py +310 -0
- aim/data/prepare/convertTsvToCsv.py +39 -0
- aim/data/prepare/convert_csv_to_h5ad.py +217 -0
- aim/data/prepare/createOnlyHVGDataset.py +69 -0
- aim/data/prepare/createSmallerDataset.py +102 -0
- aim/data/prepare/normalize_gene_names.py +56 -0
- aim/data/prepare/perturb_sc_noise.py +107 -0
- aim/data/prepare/register_st_patches.py +180 -0
- aim/data/prepare/split_st_into_islands.py +551 -0
- aim/data/prepare/split_st_into_patches.py +240 -0
- aim/data/prepare/subset_st_hvg.py +43 -0
- aim/data/validate/__init__.py +35 -0
- aim/data/validate/common.py +141 -0
- aim/data/validate/runner.py +335 -0
- aim/data/validate/validate_pair.py +53 -0
- aim/data/validate/validate_sc.py +103 -0
- aim/data/validate/validate_st.py +74 -0
- aim/gui/__init__.py +8 -0
- aim/gui/__main__.py +77 -0
- aim/gui/app.py +1784 -0
- aim/gui/compute.py +106 -0
- aim/gui/data_access.py +292 -0
- aim/gui/render.py +1679 -0
- aim/gui/scaffold.py +129 -0
- aim/gui/widgets.py +675 -0
- aim/io.py +196 -0
- aim/mapping/__init__.py +14 -0
- aim/mapping/base.py +67 -0
- aim/mapping/confidence.py +51 -0
- aim/mapping/nearest_centroid.py +33 -0
- aim/mapping/reference.py +156 -0
- aim/mapping/wann.py +208 -0
- aim/metrics/__init__.py +26 -0
- aim/metrics/biology.py +69 -0
- aim/metrics/cossim.py +127 -0
- aim/metrics/kselection.py +272 -0
- aim/metrics/onehot.py +54 -0
- aim/metrics/reconstruction.py +73 -0
- aim/metrics/topology.py +62 -0
- aim/reference_aligners/__init__.py +0 -0
- aim/reference_aligners/environment_dot.yml +23 -0
- aim/reference_aligners/environment_tacco.yml +28 -0
- aim/reference_aligners/environment_tangram.yml +16 -0
- aim/reference_aligners/registry.py +350 -0
- aim/reference_aligners/run_dot.R +172 -0
- aim/reference_aligners/run_dot.py +116 -0
- aim/reference_aligners/run_tacco.py +143 -0
- aim/reference_aligners/run_tangram.py +210 -0
- aim/sweep.py +261 -0
- aim/tree.py +86 -0
- spatial_aim-1.0.0.dist-info/METADATA +1005 -0
- spatial_aim-1.0.0.dist-info/RECORD +76 -0
- spatial_aim-1.0.0.dist-info/WHEEL +5 -0
- spatial_aim-1.0.0.dist-info/entry_points.txt +2 -0
- spatial_aim-1.0.0.dist-info/licenses/LICENSE +674 -0
- spatial_aim-1.0.0.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,102 @@
|
|
|
1
|
+
import os
|
|
2
|
+
import anndata as ad
|
|
3
|
+
import numpy as np
|
|
4
|
+
from scipy.sparse import issparse
|
|
5
|
+
|
|
6
|
+
if __name__ == "__main__":
|
|
7
|
+
"""
|
|
8
|
+
Creates a smaller subset dataset from a full scRNA-seq + ST dataset.
|
|
9
|
+
Subsets cells, genes, and spots to configurable target counts, ensuring that
|
|
10
|
+
selected cells and spots each express at least one shared gene.
|
|
11
|
+
Reads from sc.h5ad + st.h5ad and writes sc.h5ad + st.h5ad.
|
|
12
|
+
"""
|
|
13
|
+
|
|
14
|
+
dataset_from = "/Users/domi/Dev/MPA_Workspace/MPA_DATA/01_Datasets/03_MouseSSP"
|
|
15
|
+
dataset_to = "/Users/domi/Dev/MPA_Workspace/MPA_DATA/01_Datasets/03_MouseSSP_Large"
|
|
16
|
+
|
|
17
|
+
# Config for mini
|
|
18
|
+
# target_nr_sc_cells = 15
|
|
19
|
+
# target_nr_sc_genes = 30
|
|
20
|
+
# target_nr_st_spots = 10
|
|
21
|
+
# target_nr_st_genes = 20
|
|
22
|
+
# target_nr_shared_genes = 5
|
|
23
|
+
|
|
24
|
+
# Config for midi
|
|
25
|
+
# target_nr_sc_cells = 100
|
|
26
|
+
# target_nr_sc_genes = 300
|
|
27
|
+
# target_nr_st_spots = 80
|
|
28
|
+
# target_nr_st_genes = 240
|
|
29
|
+
# target_nr_shared_genes = 15
|
|
30
|
+
|
|
31
|
+
# Config for large
|
|
32
|
+
target_nr_sc_cells = 1000
|
|
33
|
+
target_nr_sc_genes = 5000
|
|
34
|
+
target_nr_st_spots = 800
|
|
35
|
+
target_nr_st_genes = 33
|
|
36
|
+
target_nr_shared_genes = 33
|
|
37
|
+
|
|
38
|
+
rng: np.random.Generator = (
|
|
39
|
+
np.random.default_rng()
|
|
40
|
+
) # no fixed seed — sampling is non-deterministic across runs
|
|
41
|
+
|
|
42
|
+
""" Load datasets """
|
|
43
|
+
|
|
44
|
+
scData = ad.read_h5ad(os.path.join(dataset_from, "sc.h5ad")) # C x G
|
|
45
|
+
stData = ad.read_h5ad(os.path.join(dataset_from, "st.h5ad")) # S x G
|
|
46
|
+
|
|
47
|
+
""" Subset genes """
|
|
48
|
+
|
|
49
|
+
# Split genes into shared and non-shared genes
|
|
50
|
+
sharedGenes = scData.var_names.intersection(stData.var_names)
|
|
51
|
+
scNonSharedGenes = scData.var_names.difference(sharedGenes)
|
|
52
|
+
stNonSharedGenes = stData.var_names.difference(sharedGenes)
|
|
53
|
+
|
|
54
|
+
# Create list of genes to keep (target_nr, half shared, half non-shared)
|
|
55
|
+
scGenesToKeep = list(sharedGenes[:target_nr_shared_genes]) + list(
|
|
56
|
+
scNonSharedGenes[: target_nr_sc_genes - target_nr_shared_genes]
|
|
57
|
+
)
|
|
58
|
+
if len(stNonSharedGenes) >= target_nr_shared_genes:
|
|
59
|
+
stGenesToKeep = list(sharedGenes[:target_nr_shared_genes]) + list(
|
|
60
|
+
stNonSharedGenes[: target_nr_st_genes - target_nr_shared_genes]
|
|
61
|
+
)
|
|
62
|
+
else:
|
|
63
|
+
stGenesToKeep = list(sharedGenes[:target_nr_st_genes])
|
|
64
|
+
|
|
65
|
+
""" Subset cells """
|
|
66
|
+
|
|
67
|
+
# Select cells that express at least one shared gene
|
|
68
|
+
sc_mat = scData[:, sharedGenes[:target_nr_shared_genes]].X
|
|
69
|
+
if issparse(sc_mat):
|
|
70
|
+
sc_mask = np.asarray(sc_mat.getnnz(axis=1) > 0).reshape(-1)
|
|
71
|
+
else:
|
|
72
|
+
sc_mask = np.any(sc_mat != 0, axis=1).reshape(-1)
|
|
73
|
+
available_sc = scData.obs_names[sc_mask].tolist()
|
|
74
|
+
n_sc = min(len(available_sc), target_nr_sc_cells)
|
|
75
|
+
scCellsToKeep = rng.choice(available_sc, size=n_sc, replace=False).tolist()
|
|
76
|
+
|
|
77
|
+
""" Subset spots """
|
|
78
|
+
|
|
79
|
+
# Select spots that express at least one shared gene
|
|
80
|
+
st_mat = stData[:, sharedGenes].X
|
|
81
|
+
if issparse(st_mat):
|
|
82
|
+
st_mask = np.asarray(st_mat.getnnz(axis=1) > 0).reshape(-1)
|
|
83
|
+
else:
|
|
84
|
+
st_mask = np.any(st_mat != 0, axis=1).reshape(-1)
|
|
85
|
+
available_st = stData.obs_names[st_mask].tolist()
|
|
86
|
+
n_st = min(len(available_st), target_nr_st_spots)
|
|
87
|
+
stSpotsToKeep = rng.choice(available_st, size=n_st, replace=False).tolist()
|
|
88
|
+
|
|
89
|
+
""" Create subsets """
|
|
90
|
+
|
|
91
|
+
scData_mini = scData[scCellsToKeep, scGenesToKeep].copy()
|
|
92
|
+
stData_mini = stData[stSpotsToKeep, stGenesToKeep].copy()
|
|
93
|
+
|
|
94
|
+
""" Save to disk """
|
|
95
|
+
|
|
96
|
+
os.makedirs(dataset_to, exist_ok=True)
|
|
97
|
+
scData_mini.write_h5ad(os.path.join(dataset_to, "sc.h5ad"))
|
|
98
|
+
stData_mini.write_h5ad(os.path.join(dataset_to, "st.h5ad"))
|
|
99
|
+
|
|
100
|
+
print(f"Saved subset dataset to {dataset_to}")
|
|
101
|
+
print(f" scRNA: {scData_mini.n_obs} cells x {scData_mini.n_vars} genes")
|
|
102
|
+
print(f" ST: {stData_mini.n_obs} spots x {stData_mini.n_vars} genes")
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
"""
|
|
2
|
+
Uppercases var_names in all h5ad files under scRNA/ and ST/ subdirectories.
|
|
3
|
+
Run once after adding new datasets to ensure consistent gene name casing.
|
|
4
|
+
|
|
5
|
+
Usage:
|
|
6
|
+
python -m src.data_preparation.normalize_gene_names
|
|
7
|
+
python -m src.data_preparation.normalize_gene_names -d /path/to/01_Datasets
|
|
8
|
+
"""
|
|
9
|
+
|
|
10
|
+
import argparse
|
|
11
|
+
from pathlib import Path
|
|
12
|
+
import anndata as ad
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
def normalize_file(path: Path) -> None:
|
|
16
|
+
adata = ad.read_h5ad(path)
|
|
17
|
+
original = adata.var_names.tolist()
|
|
18
|
+
uppercased = [g.upper() for g in original]
|
|
19
|
+
|
|
20
|
+
if original == uppercased:
|
|
21
|
+
print(f" {path.name}: already uppercase, skipped")
|
|
22
|
+
return
|
|
23
|
+
|
|
24
|
+
changed = sum(1 for a, b in zip(original, uppercased) if a != b)
|
|
25
|
+
adata.var_names = uppercased
|
|
26
|
+
adata.write_h5ad(path)
|
|
27
|
+
print(f" {path.name}: uppercased {changed} gene names")
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
def main() -> None:
|
|
31
|
+
parser = argparse.ArgumentParser(
|
|
32
|
+
description="Uppercase var_names in all h5ad files"
|
|
33
|
+
)
|
|
34
|
+
parser.add_argument(
|
|
35
|
+
"--data-root",
|
|
36
|
+
"-d",
|
|
37
|
+
type=Path,
|
|
38
|
+
default=Path(r"/01_Datasets"),
|
|
39
|
+
)
|
|
40
|
+
args = parser.parse_args()
|
|
41
|
+
|
|
42
|
+
root: Path = args.data_root
|
|
43
|
+
for subdir in ["scRNA", "ST"]:
|
|
44
|
+
folder = root / subdir
|
|
45
|
+
h5ads = sorted(folder.glob("*.h5ad"))
|
|
46
|
+
if not h5ads:
|
|
47
|
+
continue
|
|
48
|
+
print(f"\n{subdir}/")
|
|
49
|
+
for path in h5ads:
|
|
50
|
+
normalize_file(path)
|
|
51
|
+
|
|
52
|
+
print("\nDone.")
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
if __name__ == "__main__":
|
|
56
|
+
main()
|
|
@@ -0,0 +1,107 @@
|
|
|
1
|
+
# Generates noise-perturbed versions of an SC dataset for metric validation.
|
|
2
|
+
#
|
|
3
|
+
# For each noise level alpha, adds isotropic Gaussian noise scaled to the
|
|
4
|
+
# global expression standard deviation:
|
|
5
|
+
# X_perturbed = clip(X + N(0, alpha * X.std()), min=0)
|
|
6
|
+
#
|
|
7
|
+
# alpha=0 → identity, alpha=1 → noise std equals the data std,
|
|
8
|
+
# higher alpha → progressively destroys cell-state structure.
|
|
9
|
+
# Values are clipped at 0 to preserve non-negativity.
|
|
10
|
+
#
|
|
11
|
+
# Usage:
|
|
12
|
+
# python -m src.data_preparation.perturb_sc_noise \
|
|
13
|
+
# --scdata <path/to/sc.h5ad> \
|
|
14
|
+
# --noise_levels 0.5 1.0 2.0 5.0 \
|
|
15
|
+
# [--output_dir <dir>] # default: same directory as input
|
|
16
|
+
# [--seed 42]
|
|
17
|
+
|
|
18
|
+
import argparse
|
|
19
|
+
import logging
|
|
20
|
+
from pathlib import Path
|
|
21
|
+
|
|
22
|
+
import anndata as ad
|
|
23
|
+
import numpy as np
|
|
24
|
+
import scipy.sparse as sp
|
|
25
|
+
|
|
26
|
+
logger = logging.getLogger(__name__)
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def perturb_sc(
|
|
30
|
+
sc_adata: ad.AnnData,
|
|
31
|
+
noise_level: float,
|
|
32
|
+
seed: int = 42,
|
|
33
|
+
) -> ad.AnnData:
|
|
34
|
+
"""
|
|
35
|
+
Return a copy of sc_adata with Gaussian noise added to the expression matrix.
|
|
36
|
+
Noise std = noise_level * global expression std. Values clipped at 0.
|
|
37
|
+
"""
|
|
38
|
+
X = (
|
|
39
|
+
sc_adata.X.toarray()
|
|
40
|
+
if sp.issparse(sc_adata.X)
|
|
41
|
+
else np.asarray(sc_adata.X, dtype=float)
|
|
42
|
+
)
|
|
43
|
+
|
|
44
|
+
if noise_level == 0.0:
|
|
45
|
+
return sc_adata.copy()
|
|
46
|
+
|
|
47
|
+
rng = np.random.default_rng(seed)
|
|
48
|
+
sigma = noise_level * X.std()
|
|
49
|
+
noise = rng.normal(0.0, sigma, size=X.shape)
|
|
50
|
+
X_perturbed = np.clip(X + noise, a_min=0.0, a_max=None)
|
|
51
|
+
|
|
52
|
+
result = sc_adata.copy()
|
|
53
|
+
result.X = X_perturbed.astype(np.float32)
|
|
54
|
+
result.uns["perturbation"] = {
|
|
55
|
+
"type": "gaussian_noise",
|
|
56
|
+
"noise_level": noise_level,
|
|
57
|
+
"seed": seed,
|
|
58
|
+
}
|
|
59
|
+
return result
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
def main(sc_path: Path, noise_levels: list[float], output_dir: Path, seed: int) -> None:
|
|
63
|
+
logger.info(f"Loading {sc_path} ...")
|
|
64
|
+
sc_adata = ad.read_h5ad(sc_path)
|
|
65
|
+
logger.info(f" {sc_adata.n_obs} cells x {sc_adata.n_vars} genes")
|
|
66
|
+
|
|
67
|
+
output_dir.mkdir(parents=True, exist_ok=True)
|
|
68
|
+
stem = sc_path.stem # e.g. "sc"
|
|
69
|
+
|
|
70
|
+
for alpha in noise_levels:
|
|
71
|
+
perturbed = perturb_sc(sc_adata, alpha, seed=seed)
|
|
72
|
+
label = f"{alpha:.2f}".replace(".", "p") # e.g. 0.50 → "0p50"
|
|
73
|
+
out_path = output_dir / f"{stem}_noise{label}.h5ad"
|
|
74
|
+
perturbed.write_h5ad(out_path)
|
|
75
|
+
logger.info(f" Saved noise_level={alpha}: {out_path}")
|
|
76
|
+
|
|
77
|
+
logger.info("Done.")
|
|
78
|
+
|
|
79
|
+
|
|
80
|
+
if __name__ == "__main__":
|
|
81
|
+
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
|
|
82
|
+
|
|
83
|
+
parser = argparse.ArgumentParser(
|
|
84
|
+
description="Generate noise-perturbed SC datasets for metric validation."
|
|
85
|
+
)
|
|
86
|
+
parser.add_argument("--scdata", required=True, type=Path, help="Path to sc.h5ad")
|
|
87
|
+
parser.add_argument(
|
|
88
|
+
"--noise_levels",
|
|
89
|
+
required=True,
|
|
90
|
+
type=float,
|
|
91
|
+
nargs="+",
|
|
92
|
+
help="One or more noise level multipliers (e.g. 0.5 1.0 2.0 5.0)",
|
|
93
|
+
)
|
|
94
|
+
parser.add_argument(
|
|
95
|
+
"--output_dir",
|
|
96
|
+
default=None,
|
|
97
|
+
type=Path,
|
|
98
|
+
help="Output directory (default: same directory as input)",
|
|
99
|
+
)
|
|
100
|
+
parser.add_argument(
|
|
101
|
+
"--seed", default=42, type=int, help="Random seed (default: 42)"
|
|
102
|
+
)
|
|
103
|
+
args = parser.parse_args()
|
|
104
|
+
|
|
105
|
+
output_dir = args.output_dir if args.output_dir is not None else args.scdata.parent
|
|
106
|
+
|
|
107
|
+
main(args.scdata, args.noise_levels, output_dir, args.seed)
|
|
@@ -0,0 +1,180 @@
|
|
|
1
|
+
"""
|
|
2
|
+
Register the output of split_st_into_patches.py into the database.
|
|
3
|
+
|
|
4
|
+
split_st_into_patches.py writes <base>_patches_NxN/patch_<r>_<c>/st.h5ad but does
|
|
5
|
+
NOT touch the database. This script copies those patch files into ST/ under the
|
|
6
|
+
slice naming convention {nn}_{i}_{tissue}.h5ad (as used by datasets 05/09/10) and
|
|
7
|
+
replaces the monolithic ST entry with one row per patch in ST/index.csv and pairs.csv.
|
|
8
|
+
|
|
9
|
+
Patches are numbered 1..N in row-major order over the non-empty patches. The
|
|
10
|
+
monolithic scRNA reference is reused for every patch (scName unchanged). The
|
|
11
|
+
monolithic ST h5ad is left on disk but removed from index.csv/pairs.csv (delete it
|
|
12
|
+
yourself once you are happy with the split).
|
|
13
|
+
|
|
14
|
+
Usage:
|
|
15
|
+
python -m data_preparation.register_st_patches \
|
|
16
|
+
--patches-dir "C:/Users/zi69hebi/Dev/10_Alignment/Data/01_Datasets/ST/11_human-breast-cancer_patches_5x5" \
|
|
17
|
+
[--data-root "C:/Users/zi69hebi/Dev/10_Alignment/Data/01_Datasets"] \
|
|
18
|
+
[--dry-run]
|
|
19
|
+
"""
|
|
20
|
+
|
|
21
|
+
import argparse
|
|
22
|
+
import csv
|
|
23
|
+
import logging
|
|
24
|
+
import re
|
|
25
|
+
import shutil
|
|
26
|
+
import sys
|
|
27
|
+
from pathlib import Path
|
|
28
|
+
|
|
29
|
+
import anndata as ad
|
|
30
|
+
|
|
31
|
+
logger = logging.getLogger(__name__)
|
|
32
|
+
|
|
33
|
+
DEFAULT_DATA_ROOT = Path(r"/01_Datasets")
|
|
34
|
+
_PATCH_RE = re.compile(r"^patch_(\d+)_(\d+)$")
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
def _st_sort_key(name: str) -> tuple[int, int, int]:
|
|
38
|
+
m = re.match(r"^(\d+)_(\d+)_(\d+)_", name)
|
|
39
|
+
if m:
|
|
40
|
+
return int(m.group(1)), int(m.group(2)), int(m.group(3))
|
|
41
|
+
m = re.match(r"^(\d+)_(\d+)_", name)
|
|
42
|
+
if m:
|
|
43
|
+
return int(m.group(1)), int(m.group(2)), 0
|
|
44
|
+
m = re.match(r"^(\d+)_", name)
|
|
45
|
+
if m:
|
|
46
|
+
return int(m.group(1)), 0, 0
|
|
47
|
+
return 999, 999, 999
|
|
48
|
+
|
|
49
|
+
|
|
50
|
+
def _ordered_patches(patches_dir: Path) -> list[tuple[Path, int]]:
|
|
51
|
+
"""Return [(patch_st_h5ad, n_spots), ...] in row-major (r, c) order, non-empty only."""
|
|
52
|
+
dirs = []
|
|
53
|
+
for d in patches_dir.glob("patch_*"):
|
|
54
|
+
m = _PATCH_RE.match(d.name)
|
|
55
|
+
if m and (d / "st.h5ad").exists():
|
|
56
|
+
dirs.append((int(m.group(1)), int(m.group(2)), d / "st.h5ad"))
|
|
57
|
+
dirs.sort()
|
|
58
|
+
out = []
|
|
59
|
+
for _, _, h5 in dirs:
|
|
60
|
+
n = ad.read_h5ad(h5).n_obs
|
|
61
|
+
out.append((h5, n))
|
|
62
|
+
return out
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
def main() -> None:
|
|
66
|
+
logging.basicConfig(
|
|
67
|
+
stream=sys.stdout,
|
|
68
|
+
level=logging.INFO,
|
|
69
|
+
format="%(asctime)s %(levelname)s %(message)s",
|
|
70
|
+
)
|
|
71
|
+
p = argparse.ArgumentParser(
|
|
72
|
+
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
|
|
73
|
+
)
|
|
74
|
+
p.add_argument("--patches-dir", type=Path, required=True)
|
|
75
|
+
p.add_argument("--data-root", type=Path, default=DEFAULT_DATA_ROOT)
|
|
76
|
+
p.add_argument("--dry-run", action="store_true")
|
|
77
|
+
args = p.parse_args()
|
|
78
|
+
|
|
79
|
+
st_dir = args.data_root / "ST"
|
|
80
|
+
st_index_path = st_dir / "index.csv"
|
|
81
|
+
pairs_path = args.data_root / "pairs.csv"
|
|
82
|
+
|
|
83
|
+
# Base ST name = patches dir name minus the "_patches_NxN" suffix
|
|
84
|
+
base_name = re.sub(r"_patches_\d+x\d+$", "", args.patches_dir.name)
|
|
85
|
+
m = re.match(r"^(\d+)_(.+)$", base_name)
|
|
86
|
+
if not m:
|
|
87
|
+
logger.error("Cannot parse dataset id from base name %r", base_name)
|
|
88
|
+
sys.exit(1)
|
|
89
|
+
dataset_id, tissue = m.group(1), m.group(2)
|
|
90
|
+
logger.info(
|
|
91
|
+
"Base ST dataset: %s (id=%s, tissue=%s)", base_name, dataset_id, tissue
|
|
92
|
+
)
|
|
93
|
+
|
|
94
|
+
patches = _ordered_patches(args.patches_dir)
|
|
95
|
+
if not patches:
|
|
96
|
+
logger.error(
|
|
97
|
+
"No non-empty patch st.h5ad files found under %s", args.patches_dir
|
|
98
|
+
)
|
|
99
|
+
sys.exit(1)
|
|
100
|
+
total = sum(n for _, n in patches)
|
|
101
|
+
logger.info("%d non-empty patches, %d spots total", len(patches), total)
|
|
102
|
+
|
|
103
|
+
# --- Load DB tables ---
|
|
104
|
+
with open(st_index_path, newline="") as f:
|
|
105
|
+
st_reader = csv.DictReader(f)
|
|
106
|
+
st_fields = list(st_reader.fieldnames or [])
|
|
107
|
+
st_rows = list(st_reader)
|
|
108
|
+
with open(pairs_path, newline="") as f:
|
|
109
|
+
pairs_reader = csv.DictReader(f)
|
|
110
|
+
pairs_fields = list(pairs_reader.fieldnames or [])
|
|
111
|
+
pairs_rows = list(pairs_reader)
|
|
112
|
+
|
|
113
|
+
st_template = next((r for r in st_rows if r.get("Name") == base_name), None)
|
|
114
|
+
if st_template is None:
|
|
115
|
+
logger.error("ST/index.csv has no row named %r", base_name)
|
|
116
|
+
sys.exit(1)
|
|
117
|
+
base_pairs = [r for r in pairs_rows if r.get("stName") == base_name]
|
|
118
|
+
if not base_pairs:
|
|
119
|
+
logger.error("pairs.csv has no pair with stName %r", base_name)
|
|
120
|
+
sys.exit(1)
|
|
121
|
+
|
|
122
|
+
# --- Build new slice rows / pairs / file copies ---
|
|
123
|
+
new_st_rows, new_pairs, copies = [], [], []
|
|
124
|
+
for i, (h5, n_spots) in enumerate(patches, start=1):
|
|
125
|
+
new_name = f"{dataset_id}_{i}_{tissue}"
|
|
126
|
+
copies.append((h5, st_dir / f"{new_name}.h5ad"))
|
|
127
|
+
new_st_rows.append({**st_template, "Name": new_name, "SpotCount": str(n_spots)})
|
|
128
|
+
for bp in base_pairs:
|
|
129
|
+
new_pairs.append({**bp, "stName": new_name})
|
|
130
|
+
|
|
131
|
+
# Replace monolith with slices
|
|
132
|
+
st_rows = [r for r in st_rows if r.get("Name") != base_name] + new_st_rows
|
|
133
|
+
pairs_rows = [r for r in pairs_rows if r.get("stName") != base_name] + new_pairs
|
|
134
|
+
st_rows.sort(key=lambda r: _st_sort_key(r["Name"]))
|
|
135
|
+
for new_id, r in enumerate(pairs_rows):
|
|
136
|
+
r["PairID"] = str(new_id)
|
|
137
|
+
|
|
138
|
+
if args.dry_run:
|
|
139
|
+
logger.info("[dry-run] would copy %d files, e.g.:", len(copies))
|
|
140
|
+
for src, dst in copies[:3]:
|
|
141
|
+
logger.info(" %s -> %s", src, dst.name)
|
|
142
|
+
logger.info("[dry-run] ST/index.csv: -1 monolith, +%d slices", len(new_st_rows))
|
|
143
|
+
logger.info(
|
|
144
|
+
"[dry-run] pairs.csv: -%d monolith pair(s), +%d, renumber to 0..%d",
|
|
145
|
+
len(base_pairs),
|
|
146
|
+
len(new_pairs),
|
|
147
|
+
len(pairs_rows) - 1,
|
|
148
|
+
)
|
|
149
|
+
return
|
|
150
|
+
|
|
151
|
+
for src, dst in copies:
|
|
152
|
+
shutil.copyfile(src, dst)
|
|
153
|
+
logger.info("Copied %d patch files into %s", len(copies), st_dir)
|
|
154
|
+
|
|
155
|
+
shutil.copyfile(st_index_path, st_index_path.with_suffix(".csv.bak"))
|
|
156
|
+
with open(st_index_path, "w", newline="") as f:
|
|
157
|
+
w = csv.DictWriter(f, fieldnames=st_fields)
|
|
158
|
+
w.writeheader()
|
|
159
|
+
w.writerows(st_rows)
|
|
160
|
+
logger.info("Updated %s (backup .bak): %d rows", st_index_path.name, len(st_rows))
|
|
161
|
+
|
|
162
|
+
shutil.copyfile(pairs_path, pairs_path.with_suffix(".csv.bak"))
|
|
163
|
+
with open(pairs_path, "w", newline="") as f:
|
|
164
|
+
w = csv.DictWriter(f, fieldnames=pairs_fields)
|
|
165
|
+
w.writeheader()
|
|
166
|
+
w.writerows(pairs_rows)
|
|
167
|
+
logger.info("Updated %s (backup .bak): %d pairs", pairs_path.name, len(pairs_rows))
|
|
168
|
+
|
|
169
|
+
logger.info(
|
|
170
|
+
"Monolith %s.h5ad left on disk (now unregistered); delete it when ready.",
|
|
171
|
+
base_name,
|
|
172
|
+
)
|
|
173
|
+
logger.info(
|
|
174
|
+
"Done. Validate with: aim validate --pairs_csv %s",
|
|
175
|
+
Path(args.data_root) / "pairs.csv",
|
|
176
|
+
)
|
|
177
|
+
|
|
178
|
+
|
|
179
|
+
if __name__ == "__main__":
|
|
180
|
+
main()
|