gotmap 0.1.0__tar.gz → 0.2.0__tar.gz
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.
- {gotmap-0.1.0 → gotmap-0.2.0}/PKG-INFO +2 -2
- {gotmap-0.1.0 → gotmap-0.2.0}/README.md +1 -1
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/__init__.py +1 -1
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/mapper.py +11 -11
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/tl.py +12 -12
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/update.py +9 -9
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/utils.py +8 -8
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap.egg-info/PKG-INFO +2 -2
- {gotmap-0.1.0 → gotmap-0.2.0}/pyproject.toml +1 -1
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/confidence.py +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/knn_map.py +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/nn_map.py +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/pl.py +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap/pp.py +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap.egg-info/SOURCES.txt +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap.egg-info/dependency_links.txt +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap.egg-info/requires.txt +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/gotmap.egg-info/top_level.txt +0 -0
- {gotmap-0.1.0 → gotmap-0.2.0}/setup.cfg +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: gotmap
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.2.0
|
|
4
4
|
Summary: Query-to-Reference Atlas Mapping for Single-Cell Data via Grassmann Optimal Transport
|
|
5
5
|
Author: GOTMap Developers
|
|
6
6
|
License: MIT
|
|
@@ -113,7 +113,7 @@ label_transfer_confidence(labelled, label_key="cell_type")
|
|
|
113
113
|
```python
|
|
114
114
|
from gotmap import GOTMap
|
|
115
115
|
|
|
116
|
-
mapper = GOTMap(ref_adata=ref,
|
|
116
|
+
mapper = GOTMap(ref_adata=ref, use_rep="X_pca", k=30, p=3, reg=0.1)
|
|
117
117
|
mapper.fit(query)
|
|
118
118
|
|
|
119
119
|
# neural-network projection
|
|
@@ -96,7 +96,7 @@ label_transfer_confidence(labelled, label_key="cell_type")
|
|
|
96
96
|
```python
|
|
97
97
|
from gotmap import GOTMap
|
|
98
98
|
|
|
99
|
-
mapper = GOTMap(ref_adata=ref,
|
|
99
|
+
mapper = GOTMap(ref_adata=ref, use_rep="X_pca", k=30, p=3, reg=0.1)
|
|
100
100
|
mapper.fit(query)
|
|
101
101
|
|
|
102
102
|
# neural-network projection
|
|
@@ -21,7 +21,7 @@ class GOTMap:
|
|
|
21
21
|
----------
|
|
22
22
|
ref_adata : AnnData
|
|
23
23
|
Reference atlas (well-annotated, stable).
|
|
24
|
-
|
|
24
|
+
use_rep : str, default='X_pca'
|
|
25
25
|
Key in obsm for PCA coordinates.
|
|
26
26
|
k : int, default=30
|
|
27
27
|
Neighborhood size for Grassmann construction.
|
|
@@ -44,10 +44,10 @@ class GOTMap:
|
|
|
44
44
|
Trained neural mapper (available after transform(method='nn')).
|
|
45
45
|
"""
|
|
46
46
|
|
|
47
|
-
def __init__(self, ref_adata,
|
|
47
|
+
def __init__(self, ref_adata, use_rep="X_pca",
|
|
48
48
|
k=30, p=3, reg=0.1, backend="batched", device=None):
|
|
49
49
|
self.ref_adata = ref_adata.copy()
|
|
50
|
-
self.
|
|
50
|
+
self.use_rep = use_rep
|
|
51
51
|
self.k = k
|
|
52
52
|
self.p = p
|
|
53
53
|
self.reg = reg
|
|
@@ -76,8 +76,8 @@ class GOTMap:
|
|
|
76
76
|
-------
|
|
77
77
|
self
|
|
78
78
|
"""
|
|
79
|
-
H_X = self.ref_adata.obsm[self.
|
|
80
|
-
H_Y = query_adata.obsm[self.
|
|
79
|
+
H_X = self.ref_adata.obsm[self.use_rep].T.astype(np.float64)
|
|
80
|
+
H_Y = query_adata.obsm[self.use_rep].T.astype(np.float64)
|
|
81
81
|
|
|
82
82
|
got = GrassmannOT(
|
|
83
83
|
k=self.k, p=self.p, reg=self.reg,
|
|
@@ -121,8 +121,8 @@ class GOTMap:
|
|
|
121
121
|
def _transform_nn(self, query_adata, hidden_dim=128, epochs=200, lr=1e-3):
|
|
122
122
|
from .nn_map import train_neural_mapper, apply_neural_mapper
|
|
123
123
|
|
|
124
|
-
ref_pca = self.ref_adata.obsm[self.
|
|
125
|
-
query_pca = query_adata.obsm[self.
|
|
124
|
+
ref_pca = self.ref_adata.obsm[self.use_rep]
|
|
125
|
+
query_pca = query_adata.obsm[self.use_rep]
|
|
126
126
|
|
|
127
127
|
# anchor supervision
|
|
128
128
|
anchor_ref = ref_pca[self.anchors_[:, 0]]
|
|
@@ -150,8 +150,8 @@ class GOTMap:
|
|
|
150
150
|
def _transform_knn(self, query_adata, n_neighbors=15):
|
|
151
151
|
from .knn_map import knn_projection
|
|
152
152
|
|
|
153
|
-
ref_pca = self.ref_adata.obsm[self.
|
|
154
|
-
query_pca = query_adata.obsm[self.
|
|
153
|
+
ref_pca = self.ref_adata.obsm[self.use_rep]
|
|
154
|
+
query_pca = query_adata.obsm[self.use_rep]
|
|
155
155
|
projected = knn_projection(
|
|
156
156
|
ref_pca, query_pca,
|
|
157
157
|
self.anchors_, self.gamma_,
|
|
@@ -194,7 +194,7 @@ class GOTMap:
|
|
|
194
194
|
ref_labels = self.ref_adata.obs[label_key].values
|
|
195
195
|
|
|
196
196
|
pred_labels, conf = weighted_knn_labels(
|
|
197
|
-
self.ref_adata.obsm[self.
|
|
197
|
+
self.ref_adata.obsm[self.use_rep],
|
|
198
198
|
query.obsm["X_gotmap"],
|
|
199
199
|
ref_labels,
|
|
200
200
|
gamma=self.gamma_,
|
|
@@ -233,7 +233,7 @@ class GOTMap:
|
|
|
233
233
|
from .confidence import mapping_confidence
|
|
234
234
|
|
|
235
235
|
return mapping_confidence(
|
|
236
|
-
self.ref_adata.obsm[self.
|
|
236
|
+
self.ref_adata.obsm[self.use_rep],
|
|
237
237
|
query.obsm["X_gotmap"],
|
|
238
238
|
self.anchors_,
|
|
239
239
|
self.gamma_
|
|
@@ -15,7 +15,7 @@ from .mapper import GOTMap
|
|
|
15
15
|
def map_query_to_reference(
|
|
16
16
|
query,
|
|
17
17
|
reference,
|
|
18
|
-
|
|
18
|
+
use_rep="X_pca",
|
|
19
19
|
k=30,
|
|
20
20
|
p=3,
|
|
21
21
|
reg=0.1,
|
|
@@ -34,10 +34,10 @@ def map_query_to_reference(
|
|
|
34
34
|
Parameters
|
|
35
35
|
----------
|
|
36
36
|
query : AnnData
|
|
37
|
-
Query data (must have .obsm[
|
|
37
|
+
Query data (must have .obsm[use_rep]).
|
|
38
38
|
reference : AnnData
|
|
39
|
-
Reference atlas (must have .obsm[
|
|
40
|
-
|
|
39
|
+
Reference atlas (must have .obsm[use_rep] and .varm['PCs']).
|
|
40
|
+
use_rep : str
|
|
41
41
|
Key for PCA coordinates.
|
|
42
42
|
k, p, reg, backend : GrassmannOT parameters.
|
|
43
43
|
method : str
|
|
@@ -62,7 +62,7 @@ def map_query_to_reference(
|
|
|
62
62
|
|
|
63
63
|
mapper = GOTMap(
|
|
64
64
|
ref_adata=reference,
|
|
65
|
-
|
|
65
|
+
use_rep=use_rep,
|
|
66
66
|
k=k, p=p, reg=reg, backend=backend,
|
|
67
67
|
)
|
|
68
68
|
mapper.fit(query)
|
|
@@ -89,7 +89,7 @@ def transfer_labels(
|
|
|
89
89
|
query,
|
|
90
90
|
reference,
|
|
91
91
|
label_key,
|
|
92
|
-
|
|
92
|
+
use_rep="X_pca",
|
|
93
93
|
k=30,
|
|
94
94
|
p=3,
|
|
95
95
|
reg=0.1,
|
|
@@ -106,7 +106,7 @@ def transfer_labels(
|
|
|
106
106
|
query, reference : AnnData
|
|
107
107
|
label_key : str
|
|
108
108
|
Column in reference.obs containing labels to transfer.
|
|
109
|
-
|
|
109
|
+
use_rep : str
|
|
110
110
|
Key for PCA coordinates.
|
|
111
111
|
method : str
|
|
112
112
|
'weighted_knn' (default) or 'nn' (requires mapping first).
|
|
@@ -126,14 +126,14 @@ def transfer_labels(
|
|
|
126
126
|
|
|
127
127
|
mapper = GOTMap(
|
|
128
128
|
ref_adata=reference,
|
|
129
|
-
|
|
129
|
+
use_rep=use_rep,
|
|
130
130
|
k=k, p=p, reg=reg, backend=backend,
|
|
131
131
|
)
|
|
132
132
|
mapped = mapper.fit(query).transform(query, method="knn")
|
|
133
133
|
|
|
134
134
|
from .knn_map import weighted_knn_labels
|
|
135
135
|
pred, conf = weighted_knn_labels(
|
|
136
|
-
reference.obsm[
|
|
136
|
+
reference.obsm[use_rep],
|
|
137
137
|
mapped,
|
|
138
138
|
reference.obs[label_key].values,
|
|
139
139
|
gamma=mapper.gamma_,
|
|
@@ -152,7 +152,7 @@ def transfer_labels(
|
|
|
152
152
|
def evaluate_mapping(
|
|
153
153
|
query,
|
|
154
154
|
reference,
|
|
155
|
-
|
|
155
|
+
use_rep="X_pca",
|
|
156
156
|
k=30,
|
|
157
157
|
p=3,
|
|
158
158
|
reg=0.1,
|
|
@@ -167,7 +167,7 @@ def evaluate_mapping(
|
|
|
167
167
|
Parameters
|
|
168
168
|
----------
|
|
169
169
|
query, reference : AnnData
|
|
170
|
-
|
|
170
|
+
use_rep : str
|
|
171
171
|
key_added : str
|
|
172
172
|
Column name in query.obs for confidence scores.
|
|
173
173
|
|
|
@@ -178,7 +178,7 @@ def evaluate_mapping(
|
|
|
178
178
|
"""
|
|
179
179
|
mapper = GOTMap(
|
|
180
180
|
ref_adata=reference,
|
|
181
|
-
|
|
181
|
+
use_rep=use_rep,
|
|
182
182
|
k=k, p=p, reg=reg, backend=backend,
|
|
183
183
|
)
|
|
184
184
|
quality = mapper.fit(query).evaluate_mapping(query)
|
|
@@ -43,16 +43,16 @@ class FrozenReference:
|
|
|
43
43
|
----------
|
|
44
44
|
adata : AnnData
|
|
45
45
|
Reference atlas (already preprocessed).
|
|
46
|
-
|
|
46
|
+
use_rep : str
|
|
47
47
|
obsm key for PCA coordinates.
|
|
48
48
|
use_highly_variable : bool
|
|
49
49
|
Whether PCA was trained on highly variable genes.
|
|
50
50
|
"""
|
|
51
51
|
|
|
52
|
-
def __init__(self, adata,
|
|
53
|
-
if
|
|
52
|
+
def __init__(self, adata, use_rep="X_pca", use_highly_variable=True):
|
|
53
|
+
if use_rep not in adata.obsm:
|
|
54
54
|
raise ValueError(
|
|
55
|
-
f"{
|
|
55
|
+
f"{use_rep} not found in adata.obsm. "
|
|
56
56
|
f"Run sc.pp.pca(adata, n_comps=...) first."
|
|
57
57
|
)
|
|
58
58
|
|
|
@@ -65,7 +65,7 @@ class FrozenReference:
|
|
|
65
65
|
"This is required to project new data into the same PCA space."
|
|
66
66
|
)
|
|
67
67
|
|
|
68
|
-
self.
|
|
68
|
+
self.use_rep = use_rep
|
|
69
69
|
self.use_highly_variable = use_highly_variable
|
|
70
70
|
|
|
71
71
|
self.PCs = adata.varm["PCs"].copy() # (n_genes_or_hvg, n_comps)
|
|
@@ -80,7 +80,7 @@ class FrozenReference:
|
|
|
80
80
|
self.mean = X.mean(axis=0)
|
|
81
81
|
|
|
82
82
|
# PCA coordinates of reference cells (frozen)
|
|
83
|
-
self.pca = adata.obsm[
|
|
83
|
+
self.pca = adata.obsm[use_rep].copy()
|
|
84
84
|
|
|
85
85
|
# gene names used for PCA (for alignment)
|
|
86
86
|
self.var_names = adata.var_names.copy()
|
|
@@ -119,7 +119,7 @@ class FrozenReference:
|
|
|
119
119
|
)
|
|
120
120
|
|
|
121
121
|
meta = {
|
|
122
|
-
"
|
|
122
|
+
"use_rep": self.use_rep,
|
|
123
123
|
"use_highly_variable": self.use_highly_variable,
|
|
124
124
|
"n_comps": int(self.n_comps),
|
|
125
125
|
"n_obs": int(self.n_obs),
|
|
@@ -160,7 +160,7 @@ class FrozenReference:
|
|
|
160
160
|
|
|
161
161
|
with open(os.path.join(path, "meta.json")) as f:
|
|
162
162
|
meta = json.load(f)
|
|
163
|
-
self.
|
|
163
|
+
self.use_rep = meta["use_rep"]
|
|
164
164
|
self.use_highly_variable = meta["use_highly_variable"]
|
|
165
165
|
self.version = meta["version"]
|
|
166
166
|
self.history = meta.get("history", [])
|
|
@@ -309,7 +309,7 @@ class FrozenReference:
|
|
|
309
309
|
sc.pp.pca(adata, n_comps=n_comps)
|
|
310
310
|
|
|
311
311
|
self.PCs = adata.varm["PCs"].copy()
|
|
312
|
-
self.pca = adata.obsm[self.
|
|
312
|
+
self.pca = adata.obsm[self.use_rep].copy()
|
|
313
313
|
self.n_comps = n_comps
|
|
314
314
|
self.n_obs = adata.n_obs
|
|
315
315
|
self.var_names = adata.var_names.copy()
|
|
@@ -4,16 +4,16 @@ import numpy as np
|
|
|
4
4
|
import scanpy as sc
|
|
5
5
|
|
|
6
6
|
|
|
7
|
-
def check_pca(adata,
|
|
8
|
-
"""Ensure that
|
|
9
|
-
if
|
|
7
|
+
def check_pca(adata, use_rep="X_pca"):
|
|
8
|
+
"""Ensure that use_rep exists in adata.obsm."""
|
|
9
|
+
if use_rep not in adata.obsm:
|
|
10
10
|
raise ValueError(
|
|
11
|
-
f"'{
|
|
11
|
+
f"'{use_rep}' not found in adata.obsm. "
|
|
12
12
|
f"Run sc.tl.pca(adata, n_comps=...) first."
|
|
13
13
|
)
|
|
14
14
|
|
|
15
15
|
|
|
16
|
-
def prep_adata(adata, n_comps=50,
|
|
16
|
+
def prep_adata(adata, n_comps=50, use_rep="X_pca"):
|
|
17
17
|
"""
|
|
18
18
|
Run standard preprocessing + PCA if not already done.
|
|
19
19
|
|
|
@@ -21,15 +21,15 @@ def prep_adata(adata, n_comps=50, pca_key="X_pca"):
|
|
|
21
21
|
----------
|
|
22
22
|
adata : AnnData
|
|
23
23
|
n_comps : int, default=50
|
|
24
|
-
|
|
24
|
+
use_rep : str, default='X_pca'
|
|
25
25
|
|
|
26
26
|
Returns
|
|
27
27
|
-------
|
|
28
28
|
AnnData
|
|
29
|
-
A copy with adata.obsm[
|
|
29
|
+
A copy with adata.obsm[use_rep] populated.
|
|
30
30
|
"""
|
|
31
31
|
adata = adata.copy()
|
|
32
|
-
if
|
|
32
|
+
if use_rep not in adata.obsm:
|
|
33
33
|
if "log1p" not in adata.uns:
|
|
34
34
|
sc.pp.normalize_total(adata)
|
|
35
35
|
sc.pp.log1p(adata)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: gotmap
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.2.0
|
|
4
4
|
Summary: Query-to-Reference Atlas Mapping for Single-Cell Data via Grassmann Optimal Transport
|
|
5
5
|
Author: GOTMap Developers
|
|
6
6
|
License: MIT
|
|
@@ -113,7 +113,7 @@ label_transfer_confidence(labelled, label_key="cell_type")
|
|
|
113
113
|
```python
|
|
114
114
|
from gotmap import GOTMap
|
|
115
115
|
|
|
116
|
-
mapper = GOTMap(ref_adata=ref,
|
|
116
|
+
mapper = GOTMap(ref_adata=ref, use_rep="X_pca", k=30, p=3, reg=0.1)
|
|
117
117
|
mapper.fit(query)
|
|
118
118
|
|
|
119
119
|
# neural-network projection
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "gotmap"
|
|
7
|
-
version = "0.
|
|
7
|
+
version = "0.2.0"
|
|
8
8
|
description = "Query-to-Reference Atlas Mapping for Single-Cell Data via Grassmann Optimal Transport"
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
requires-python = ">=3.9"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|