protdata 0.1.1__tar.gz → 0.1.3__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.
- {protdata-0.1.1/protdata/protdata.egg-info → protdata-0.1.3}/PKG-INFO +24 -4
- {protdata-0.1.1 → protdata-0.1.3}/README.md +3 -2
- protdata-0.1.3/docs/source/conf.py +101 -0
- protdata-0.1.3/protdata/__init__.py +1 -0
- {protdata-0.1.1 → protdata-0.1.3}/protdata/io/diann_loader.py +35 -18
- {protdata-0.1.1 → protdata-0.1.3}/protdata/io/fragpipe_loader.py +28 -13
- {protdata-0.1.1 → protdata-0.1.3}/protdata/io/maxquant_loader.py +47 -17
- {protdata-0.1.1 → protdata-0.1.3}/protdata/io/mztab_loader.py +23 -16
- protdata-0.1.3/protdata/io/utils.py +8 -0
- {protdata-0.1.1 → protdata-0.1.3/protdata.egg-info}/PKG-INFO +24 -4
- protdata-0.1.3/protdata.egg-info/SOURCES.txt +19 -0
- protdata-0.1.3/protdata.egg-info/requires.txt +27 -0
- protdata-0.1.3/protdata.egg-info/top_level.txt +5 -0
- {protdata-0.1.1 → protdata-0.1.3}/pyproject.toml +24 -4
- protdata-0.1.3/setup.cfg +26 -0
- {protdata-0.1.1 → protdata-0.1.3}/tests/test_loaders.py +15 -1
- protdata-0.1.1/protdata/protdata.egg-info/SOURCES.txt +0 -15
- protdata-0.1.1/protdata/protdata.egg-info/requires.txt +0 -7
- protdata-0.1.1/protdata/protdata.egg-info/top_level.txt +0 -1
- protdata-0.1.1/setup.cfg +0 -4
- {protdata-0.1.1 → protdata-0.1.3}/LICENSE +0 -0
- {protdata-0.1.1 → protdata-0.1.3}/protdata/io/__init__.py +0 -0
- {protdata-0.1.1/protdata → protdata-0.1.3}/protdata.egg-info/dependency_links.txt +0 -0
- {protdata-0.1.1 → protdata-0.1.3}/tests/test_maxquant_loader.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: protdata
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.3
|
|
4
4
|
Summary: Proteomics data loaders for AnnData format.
|
|
5
5
|
Author: Max Frank
|
|
6
6
|
License-Expression: MIT
|
|
@@ -9,7 +9,7 @@ Classifier: Operating System :: OS Independent
|
|
|
9
9
|
Classifier: Development Status :: 3 - Alpha
|
|
10
10
|
Classifier: Intended Audience :: Science/Research
|
|
11
11
|
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
12
|
-
Requires-Python:
|
|
12
|
+
Requires-Python: <4.0,>=3.9
|
|
13
13
|
Description-Content-Type: text/markdown
|
|
14
14
|
License-File: LICENSE
|
|
15
15
|
Requires-Dist: anndata
|
|
@@ -18,6 +18,25 @@ Requires-Dist: numpy
|
|
|
18
18
|
Requires-Dist: pyteomics
|
|
19
19
|
Provides-Extra: dev
|
|
20
20
|
Requires-Dist: pytest>=7.0.0; extra == "dev"
|
|
21
|
+
Requires-Dist: black~=25.1; extra == "dev"
|
|
22
|
+
Requires-Dist: flake8~=7.0; extra == "dev"
|
|
23
|
+
Requires-Dist: isort~=5.0; extra == "dev"
|
|
24
|
+
Requires-Dist: pre-commit~=3.0; extra == "dev"
|
|
25
|
+
Requires-Dist: pylint~=3.0; extra == "dev"
|
|
26
|
+
Requires-Dist: pytest~=8.0; extra == "dev"
|
|
27
|
+
Provides-Extra: docs
|
|
28
|
+
Requires-Dist: sphinx>=8.2.1; extra == "docs"
|
|
29
|
+
Requires-Dist: sphinx-book-theme>=1.1.0; extra == "docs"
|
|
30
|
+
Requires-Dist: sphinx-autodoc-typehints>=2.2.0; extra == "docs"
|
|
31
|
+
Requires-Dist: sphinx-issues>=5.0.1; extra == "docs"
|
|
32
|
+
Requires-Dist: sphinx-copybutton; extra == "docs"
|
|
33
|
+
Requires-Dist: sphinx-toolbox>=3.8.0; extra == "docs"
|
|
34
|
+
Requires-Dist: sphinxext.opengraph; extra == "docs"
|
|
35
|
+
Requires-Dist: myst-nb; extra == "docs"
|
|
36
|
+
Requires-Dist: scanpydoc[theme,typehints]>=0.15.3; extra == "docs"
|
|
37
|
+
Requires-Dist: awkward>=2.3; extra == "docs"
|
|
38
|
+
Requires-Dist: IPython; extra == "docs"
|
|
39
|
+
Requires-Dist: myst_parser; extra == "docs"
|
|
21
40
|
Dynamic: license-file
|
|
22
41
|
|
|
23
42
|
# protdata
|
|
@@ -29,8 +48,9 @@ Proteomics data loaders for the [AnnData](https://anndata.readthedocs.io/) forma
|
|
|
29
48
|
This package provides loader functions to import proteomics data (e.g., MaxQuant) into the AnnData structure for downstream analysis and integration with single-cell and multi-omics workflows.
|
|
30
49
|
|
|
31
50
|
## Features
|
|
32
|
-
|
|
33
|
-
-
|
|
51
|
+
|
|
52
|
+
- **Multiple formats**: Support for MaxQuant, FragPipe, DIA-NN, and mzTab files
|
|
53
|
+
- **Reads metadata**: Automatically extracts and organizes sample and protein metadata
|
|
34
54
|
|
|
35
55
|
## Installation
|
|
36
56
|
```bash
|
|
@@ -7,8 +7,9 @@ Proteomics data loaders for the [AnnData](https://anndata.readthedocs.io/) forma
|
|
|
7
7
|
This package provides loader functions to import proteomics data (e.g., MaxQuant) into the AnnData structure for downstream analysis and integration with single-cell and multi-omics workflows.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
|
-
|
|
11
|
-
-
|
|
10
|
+
|
|
11
|
+
- **Multiple formats**: Support for MaxQuant, FragPipe, DIA-NN, and mzTab files
|
|
12
|
+
- **Reads metadata**: Automatically extracts and organizes sample and protein metadata
|
|
12
13
|
|
|
13
14
|
## Installation
|
|
14
15
|
```bash
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
from __future__ import annotations
|
|
2
|
+
|
|
3
|
+
import sys
|
|
4
|
+
from datetime import datetime
|
|
5
|
+
from importlib import metadata
|
|
6
|
+
from pathlib import Path
|
|
7
|
+
|
|
8
|
+
from sphinx.application import Sphinx
|
|
9
|
+
|
|
10
|
+
HERE = Path(__file__).parent
|
|
11
|
+
sys.path.insert(0, str(HERE.parent.parent))
|
|
12
|
+
|
|
13
|
+
import protdata
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
# -- General configuration ------------------------------------------------
|
|
17
|
+
|
|
18
|
+
project = "protdata"
|
|
19
|
+
author = "Max Frank"
|
|
20
|
+
copyright = f"{datetime.now():%Y}, Max Frank"
|
|
21
|
+
release = version = metadata.version("protdata")
|
|
22
|
+
|
|
23
|
+
templates_path = ["_templates"]
|
|
24
|
+
html_static_path = ["_static"]
|
|
25
|
+
source_suffix = {".rst": "restructuredtext", ".md": "myst-nb"}
|
|
26
|
+
master_doc = "index"
|
|
27
|
+
default_role = "literal"
|
|
28
|
+
exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", "**.ipynb_checkpoints"]
|
|
29
|
+
pygments_style = "sphinx"
|
|
30
|
+
|
|
31
|
+
extensions = [
|
|
32
|
+
"myst_nb",
|
|
33
|
+
"sphinx_copybutton",
|
|
34
|
+
"sphinx.ext.autodoc",
|
|
35
|
+
"sphinx.ext.intersphinx",
|
|
36
|
+
"sphinx.ext.doctest",
|
|
37
|
+
"sphinx.ext.coverage",
|
|
38
|
+
"sphinx.ext.mathjax",
|
|
39
|
+
"sphinx.ext.napoleon",
|
|
40
|
+
"sphinx.ext.autosummary",
|
|
41
|
+
"sphinx_autodoc_typehints",
|
|
42
|
+
"sphinx_issues",
|
|
43
|
+
"sphinx_design",
|
|
44
|
+
"sphinxext.opengraph",
|
|
45
|
+
"scanpydoc",
|
|
46
|
+
"IPython.sphinxext.ipython_console_highlighting",
|
|
47
|
+
]
|
|
48
|
+
|
|
49
|
+
myst_enable_extensions = ["colon_fence", "dollarmath"]
|
|
50
|
+
myst_heading_anchors = 3
|
|
51
|
+
nb_execution_mode = "off"
|
|
52
|
+
|
|
53
|
+
autosummary_generate = True
|
|
54
|
+
autodoc_member_order = "bysource"
|
|
55
|
+
napoleon_google_docstring = False
|
|
56
|
+
napoleon_numpy_docstring = True
|
|
57
|
+
napoleon_use_rtype = True
|
|
58
|
+
napoleon_use_param = True
|
|
59
|
+
typehints_defaults = "braces"
|
|
60
|
+
issues_github_path = "czbiohub-sf/protdata"
|
|
61
|
+
|
|
62
|
+
nitpicky = True
|
|
63
|
+
nitpick_ignore = []
|
|
64
|
+
|
|
65
|
+
intersphinx_mapping = dict(
|
|
66
|
+
python=("https://docs.python.org/3", None),
|
|
67
|
+
numpy=("https://numpy.org/doc/stable", None),
|
|
68
|
+
pandas=("https://pandas.pydata.org/pandas-docs/stable", None),
|
|
69
|
+
anndata=("https://anndata.readthedocs.io/en/stable/", None),
|
|
70
|
+
scipy=("https://docs.scipy.org/doc/scipy", None),
|
|
71
|
+
h5py=("https://docs.h5py.org/en/latest", None),
|
|
72
|
+
)
|
|
73
|
+
|
|
74
|
+
# qualname_overrides = {
|
|
75
|
+
# "h5py._hl.group.Group": "h5py.Group",
|
|
76
|
+
# "h5py._hl.files.File": "h5py.File",
|
|
77
|
+
# "h5py._hl.dataset.Dataset": "h5py.Dataset",
|
|
78
|
+
# "anndata._core.anndata.AnnData": "anndata.AnnData",
|
|
79
|
+
# }
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
# -- Social cards ---------------------------------------------------------
|
|
83
|
+
|
|
84
|
+
# ogp_site_url = "https://protdata.readthedocs.io/"
|
|
85
|
+
|
|
86
|
+
|
|
87
|
+
# -- Options for HTML output ----------------------------------------------
|
|
88
|
+
|
|
89
|
+
html_theme = "scanpydoc"
|
|
90
|
+
html_theme_options = dict(
|
|
91
|
+
use_repository_button=True,
|
|
92
|
+
repository_url="https://github.com/czbiohub-sf/protdata",
|
|
93
|
+
repository_branch="main",
|
|
94
|
+
navigation_with_keys=False,
|
|
95
|
+
)
|
|
96
|
+
html_show_sphinx = False
|
|
97
|
+
html_logo = "_static/img/protdata_schema.svg"
|
|
98
|
+
|
|
99
|
+
|
|
100
|
+
def setup(app: Sphinx):
|
|
101
|
+
app.add_css_file("css/custom.css")
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
from . import io
|
|
@@ -1,8 +1,11 @@
|
|
|
1
|
-
import pandas as pd
|
|
2
|
-
import numpy as np
|
|
3
|
-
import anndata as ad
|
|
4
|
-
from typing import Union
|
|
5
1
|
import os
|
|
2
|
+
from typing import Union
|
|
3
|
+
|
|
4
|
+
import anndata as ad
|
|
5
|
+
import numpy as np
|
|
6
|
+
import pandas as pd
|
|
7
|
+
|
|
8
|
+
from .utils import cleanup_obsvar
|
|
6
9
|
|
|
7
10
|
|
|
8
11
|
def read_diann(
|
|
@@ -13,17 +16,23 @@ def read_diann(
|
|
|
13
16
|
"""
|
|
14
17
|
Load DIA-NN protein group matrix (report.pg_matrix.tsv) into an AnnData object.
|
|
15
18
|
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
19
|
+
Parameters
|
|
20
|
+
----------
|
|
21
|
+
file
|
|
22
|
+
Path to DIA-NN report.pg_matrix.tsv file or a pandas DataFrame containing the data.
|
|
23
|
+
index_column
|
|
24
|
+
Column name for protein group IDs.
|
|
25
|
+
sep
|
|
26
|
+
File separator.
|
|
21
27
|
|
|
22
|
-
Returns
|
|
28
|
+
Returns
|
|
29
|
+
-------
|
|
30
|
+
anndata.AnnData
|
|
23
31
|
AnnData object with:
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
32
|
+
|
|
33
|
+
- X: intensity matrix (samples x proteins)
|
|
34
|
+
- var: protein metadata (indexed by protein group IDs)
|
|
35
|
+
- obs: sample metadata (indexed by sample names)
|
|
27
36
|
"""
|
|
28
37
|
if isinstance(file, pd.DataFrame):
|
|
29
38
|
df = file.copy()
|
|
@@ -46,9 +55,11 @@ def read_diann(
|
|
|
46
55
|
]
|
|
47
56
|
|
|
48
57
|
df.columns = [
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
58
|
+
(
|
|
59
|
+
os.path.basename(col)
|
|
60
|
+
if isinstance(col, str) and col not in no_sample_column
|
|
61
|
+
else str(col)
|
|
62
|
+
)
|
|
52
63
|
for col in df.columns
|
|
53
64
|
]
|
|
54
65
|
|
|
@@ -59,7 +70,7 @@ def read_diann(
|
|
|
59
70
|
# Find intensity columns (all columns not in no_sample_column)
|
|
60
71
|
intensity_cols = df.columns.difference(no_sample_column, sort=False).tolist()
|
|
61
72
|
if not intensity_cols:
|
|
62
|
-
raise ValueError(
|
|
73
|
+
raise ValueError("No intensity columns found.")
|
|
63
74
|
|
|
64
75
|
# Build X matrix (proteins x samples)
|
|
65
76
|
X = df[intensity_cols].to_numpy(dtype=np.float32).T
|
|
@@ -67,12 +78,18 @@ def read_diann(
|
|
|
67
78
|
# Build var (proteins)
|
|
68
79
|
var = df[df.columns.intersection(no_sample_column, sort=False)].copy()
|
|
69
80
|
var.index = df[index_column]
|
|
81
|
+
var = cleanup_obsvar(var)
|
|
70
82
|
|
|
71
83
|
# Build obs (samples)
|
|
72
84
|
obs = pd.DataFrame(index=intensity_cols)
|
|
85
|
+
obs = cleanup_obsvar(obs)
|
|
73
86
|
|
|
74
87
|
# Build uns
|
|
75
|
-
uns = {
|
|
88
|
+
uns = {
|
|
89
|
+
"RawInfo": {
|
|
90
|
+
"Search_Engine": "DIANN",
|
|
91
|
+
},
|
|
92
|
+
}
|
|
76
93
|
|
|
77
94
|
# Create AnnData
|
|
78
95
|
adata = ad.AnnData(X=X, obs=obs, var=var)
|
|
@@ -3,6 +3,7 @@ import numpy as np
|
|
|
3
3
|
import anndata as ad
|
|
4
4
|
from typing import Union
|
|
5
5
|
import warnings
|
|
6
|
+
from .utils import cleanup_obsvar
|
|
6
7
|
|
|
7
8
|
|
|
8
9
|
def read_fragpipe(
|
|
@@ -16,21 +17,29 @@ def read_fragpipe(
|
|
|
16
17
|
sep: str = "\t",
|
|
17
18
|
) -> ad.AnnData:
|
|
18
19
|
"""
|
|
19
|
-
Load FragPipe
|
|
20
|
+
Load a FragPipe protein group matrix into an AnnData object.
|
|
20
21
|
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
22
|
+
Parameters
|
|
23
|
+
----------
|
|
24
|
+
file
|
|
25
|
+
Path to the FragPipe combined_protein.tsv file or a pandas DataFrame containing the data.
|
|
26
|
+
intensity_column_suffixes
|
|
27
|
+
Suffix(es) for intensity columns to extract.
|
|
28
|
+
The first suffix is used for the main matrix (X), others are stored as layers if present.
|
|
29
|
+
index_column
|
|
30
|
+
Column name to use as protein index.
|
|
31
|
+
sep
|
|
32
|
+
File separator if reading from file.
|
|
28
33
|
|
|
29
|
-
Returns
|
|
34
|
+
Returns
|
|
35
|
+
-------
|
|
36
|
+
anndata.AnnData
|
|
30
37
|
AnnData object with:
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
38
|
+
|
|
39
|
+
- X: intensity matrix (samples x proteins)
|
|
40
|
+
- var: protein metadata (indexed by protein IDs)
|
|
41
|
+
- obs: sample metadata (indexed by sample names)
|
|
42
|
+
- layers: additional intensity matrices if multiple intensity column suffixes are provided
|
|
34
43
|
"""
|
|
35
44
|
if isinstance(intensity_column_suffixes, str):
|
|
36
45
|
intensity_column_suffixes = [intensity_column_suffixes]
|
|
@@ -74,12 +83,18 @@ def read_fragpipe(
|
|
|
74
83
|
)
|
|
75
84
|
var = df.loc[:, ~sample_columns].copy()
|
|
76
85
|
var.index = df[index_column]
|
|
86
|
+
var = cleanup_obsvar(var)
|
|
77
87
|
|
|
78
88
|
# Build obs (samples)
|
|
79
89
|
obs = pd.DataFrame(index=sample_names)
|
|
90
|
+
obs = cleanup_obsvar(obs)
|
|
80
91
|
|
|
81
92
|
# Build uns
|
|
82
|
-
uns = {
|
|
93
|
+
uns = {
|
|
94
|
+
"RawInfo": {
|
|
95
|
+
"Search_Engine": "FragPipe",
|
|
96
|
+
},
|
|
97
|
+
}
|
|
83
98
|
|
|
84
99
|
# Create AnnData
|
|
85
100
|
adata = ad.AnnData(X=X, obs=obs, var=var, layers=layers)
|
|
@@ -1,13 +1,22 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
import anndata as ad
|
|
4
|
-
from typing import Optional, Union, List
|
|
1
|
+
from __future__ import annotations
|
|
2
|
+
|
|
5
3
|
import warnings
|
|
4
|
+
from typing import List, Union
|
|
5
|
+
|
|
6
|
+
import anndata as ad
|
|
7
|
+
import numpy as np
|
|
8
|
+
import pandas as pd
|
|
9
|
+
|
|
10
|
+
from .utils import cleanup_obsvar
|
|
6
11
|
|
|
7
12
|
|
|
8
13
|
def read_maxquant(
|
|
9
14
|
file: Union[str, pd.DataFrame],
|
|
10
|
-
intensity_column_prefixes: List[str] | str = [
|
|
15
|
+
intensity_column_prefixes: List[str] | str = [
|
|
16
|
+
"LFQ intensity ",
|
|
17
|
+
"Intensity ",
|
|
18
|
+
"MS/MS count ",
|
|
19
|
+
],
|
|
11
20
|
index_column: str = "Protein IDs",
|
|
12
21
|
filter_columns: list[str] = [
|
|
13
22
|
"Only identified by site",
|
|
@@ -20,18 +29,29 @@ def read_maxquant(
|
|
|
20
29
|
"""
|
|
21
30
|
Load MaxQuant proteinGroups.txt into an AnnData object.
|
|
22
31
|
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
32
|
+
Parameters
|
|
33
|
+
----------
|
|
34
|
+
file
|
|
35
|
+
Path to the MaxQuant proteinGroups.txt file or a pandas DataFrame containing the data.
|
|
36
|
+
intensity_column_prefixes
|
|
37
|
+
Prefix(es) for intensity columns to extract.
|
|
38
|
+
The first prefix is used for the main matrix (X), others are stored as layers if present.
|
|
39
|
+
index_column
|
|
40
|
+
Column name to use as protein index.
|
|
41
|
+
filter_columns
|
|
42
|
+
Columns to use for filtering out contaminants or unwanted entries.
|
|
43
|
+
sep
|
|
44
|
+
File separator if reading from file.
|
|
29
45
|
|
|
30
|
-
Returns
|
|
46
|
+
Returns
|
|
47
|
+
-------
|
|
48
|
+
anndata.AnnData
|
|
31
49
|
AnnData object with:
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
50
|
+
|
|
51
|
+
- X: intensity matrix (samples x proteins)
|
|
52
|
+
- var: protein metadata (indexed by protein IDs)
|
|
53
|
+
- obs: sample metadata (indexed by sample names)
|
|
54
|
+
- layers: additional intensity matrices if multiple intensity column prefixes are provided
|
|
35
55
|
"""
|
|
36
56
|
if isinstance(intensity_column_prefixes, str):
|
|
37
57
|
intensity_column_prefixes = [intensity_column_prefixes]
|
|
@@ -65,7 +85,10 @@ def read_maxquant(
|
|
|
65
85
|
if col in [prefix + sample_name for sample_name in sample_names]
|
|
66
86
|
]
|
|
67
87
|
if len(prefix_cols) == len(sample_names):
|
|
68
|
-
|
|
88
|
+
# Cannot have '/' in the key (hdf5 interprets as a group for serialization)
|
|
89
|
+
layers[prefix.strip().replace("/", "_")] = (
|
|
90
|
+
df[prefix_cols].to_numpy(dtype=np.float32).T
|
|
91
|
+
)
|
|
69
92
|
else:
|
|
70
93
|
warnings.warn(
|
|
71
94
|
f"Number of columns for prefix '{prefix}' does not match number of samples."
|
|
@@ -78,12 +101,19 @@ def read_maxquant(
|
|
|
78
101
|
)
|
|
79
102
|
var = df.loc[:, ~sample_columns].copy()
|
|
80
103
|
var.index = df[index_column]
|
|
104
|
+
var = cleanup_obsvar(var)
|
|
81
105
|
|
|
82
106
|
# Build obs (samples)
|
|
83
107
|
obs = pd.DataFrame(index=sample_names)
|
|
108
|
+
obs = cleanup_obsvar(obs)
|
|
84
109
|
|
|
85
110
|
# Build uns
|
|
86
|
-
uns = {
|
|
111
|
+
uns = {
|
|
112
|
+
"RawInfo": {
|
|
113
|
+
"Search_Engine": "MaxQuant",
|
|
114
|
+
"filter_columns": filter_columns,
|
|
115
|
+
},
|
|
116
|
+
}
|
|
87
117
|
|
|
88
118
|
# Create AnnData
|
|
89
119
|
adata = ad.AnnData(X=X, obs=obs, var=var, layers=layers, uns=uns)
|
|
@@ -1,9 +1,12 @@
|
|
|
1
|
-
import pandas as pd
|
|
2
|
-
import numpy as np
|
|
3
|
-
import anndata as ad
|
|
4
1
|
from typing import Union
|
|
2
|
+
|
|
3
|
+
import anndata as ad
|
|
4
|
+
import numpy as np
|
|
5
|
+
import pandas as pd
|
|
5
6
|
from pyteomics import mztab
|
|
6
7
|
|
|
8
|
+
from .utils import cleanup_obsvar
|
|
9
|
+
|
|
7
10
|
|
|
8
11
|
def read_mztab(
|
|
9
12
|
file: Union[str, pd.DataFrame],
|
|
@@ -12,16 +15,21 @@ def read_mztab(
|
|
|
12
15
|
"""
|
|
13
16
|
Load mzTab protein table into an AnnData object.
|
|
14
17
|
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
|
|
18
|
+
Parameters
|
|
19
|
+
----------
|
|
20
|
+
file
|
|
21
|
+
Path to mzTab file or a pandas DataFrame containing the protein table.
|
|
22
|
+
index_column
|
|
23
|
+
Column indicating the protein groups.
|
|
19
24
|
|
|
20
|
-
Returns
|
|
25
|
+
Returns
|
|
26
|
+
-------
|
|
27
|
+
anndata.AnnData
|
|
21
28
|
AnnData object with:
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
29
|
+
|
|
30
|
+
- X: intensity matrix (proteins x samples)
|
|
31
|
+
- var: protein metadata (indexed by protein accession)
|
|
32
|
+
- obs: sample metadata (indexed by sample names)
|
|
25
33
|
"""
|
|
26
34
|
if isinstance(file, pd.DataFrame):
|
|
27
35
|
df = file.copy()
|
|
@@ -35,26 +43,25 @@ def read_mztab(
|
|
|
35
43
|
]
|
|
36
44
|
if not intensity_cols:
|
|
37
45
|
raise ValueError(
|
|
38
|
-
|
|
46
|
+
"No columns starting with 'protein_abundance_study_variable' found."
|
|
39
47
|
)
|
|
40
48
|
|
|
41
|
-
# Extract sample names from intensity columns
|
|
42
|
-
sample_names = [col.split("[")[1].split("]")[0] for col in intensity_cols]
|
|
43
|
-
|
|
44
49
|
# Build X matrix (proteins x samples)
|
|
45
50
|
X = df[intensity_cols].to_numpy(dtype=np.float32).T
|
|
46
51
|
|
|
47
52
|
# Build var (proteins)
|
|
48
53
|
var = df.drop(columns=intensity_cols).copy()
|
|
49
54
|
var.index = df[index_column].astype(str)
|
|
55
|
+
var = cleanup_obsvar(var)
|
|
50
56
|
|
|
51
57
|
# Build obs (samples)
|
|
52
58
|
obs = pd.DataFrame.from_dict(tables.study_variables, orient="index")
|
|
53
59
|
obs.index.name = "sample"
|
|
54
60
|
obs.index = obs.index.astype(str)
|
|
61
|
+
obs = cleanup_obsvar(obs)
|
|
55
62
|
|
|
56
63
|
# Build uns
|
|
57
|
-
uns = {"Search_Engine": df.search_engine.iloc[0]}
|
|
64
|
+
uns = {"RawInfo": {"Search_Engine": str(df.search_engine.iloc[0])}}
|
|
58
65
|
|
|
59
66
|
# Create AnnData
|
|
60
67
|
adata = ad.AnnData(X=X, obs=obs, var=var, uns=uns)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: protdata
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.3
|
|
4
4
|
Summary: Proteomics data loaders for AnnData format.
|
|
5
5
|
Author: Max Frank
|
|
6
6
|
License-Expression: MIT
|
|
@@ -9,7 +9,7 @@ Classifier: Operating System :: OS Independent
|
|
|
9
9
|
Classifier: Development Status :: 3 - Alpha
|
|
10
10
|
Classifier: Intended Audience :: Science/Research
|
|
11
11
|
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
12
|
-
Requires-Python:
|
|
12
|
+
Requires-Python: <4.0,>=3.9
|
|
13
13
|
Description-Content-Type: text/markdown
|
|
14
14
|
License-File: LICENSE
|
|
15
15
|
Requires-Dist: anndata
|
|
@@ -18,6 +18,25 @@ Requires-Dist: numpy
|
|
|
18
18
|
Requires-Dist: pyteomics
|
|
19
19
|
Provides-Extra: dev
|
|
20
20
|
Requires-Dist: pytest>=7.0.0; extra == "dev"
|
|
21
|
+
Requires-Dist: black~=25.1; extra == "dev"
|
|
22
|
+
Requires-Dist: flake8~=7.0; extra == "dev"
|
|
23
|
+
Requires-Dist: isort~=5.0; extra == "dev"
|
|
24
|
+
Requires-Dist: pre-commit~=3.0; extra == "dev"
|
|
25
|
+
Requires-Dist: pylint~=3.0; extra == "dev"
|
|
26
|
+
Requires-Dist: pytest~=8.0; extra == "dev"
|
|
27
|
+
Provides-Extra: docs
|
|
28
|
+
Requires-Dist: sphinx>=8.2.1; extra == "docs"
|
|
29
|
+
Requires-Dist: sphinx-book-theme>=1.1.0; extra == "docs"
|
|
30
|
+
Requires-Dist: sphinx-autodoc-typehints>=2.2.0; extra == "docs"
|
|
31
|
+
Requires-Dist: sphinx-issues>=5.0.1; extra == "docs"
|
|
32
|
+
Requires-Dist: sphinx-copybutton; extra == "docs"
|
|
33
|
+
Requires-Dist: sphinx-toolbox>=3.8.0; extra == "docs"
|
|
34
|
+
Requires-Dist: sphinxext.opengraph; extra == "docs"
|
|
35
|
+
Requires-Dist: myst-nb; extra == "docs"
|
|
36
|
+
Requires-Dist: scanpydoc[theme,typehints]>=0.15.3; extra == "docs"
|
|
37
|
+
Requires-Dist: awkward>=2.3; extra == "docs"
|
|
38
|
+
Requires-Dist: IPython; extra == "docs"
|
|
39
|
+
Requires-Dist: myst_parser; extra == "docs"
|
|
21
40
|
Dynamic: license-file
|
|
22
41
|
|
|
23
42
|
# protdata
|
|
@@ -29,8 +48,9 @@ Proteomics data loaders for the [AnnData](https://anndata.readthedocs.io/) forma
|
|
|
29
48
|
This package provides loader functions to import proteomics data (e.g., MaxQuant) into the AnnData structure for downstream analysis and integration with single-cell and multi-omics workflows.
|
|
30
49
|
|
|
31
50
|
## Features
|
|
32
|
-
|
|
33
|
-
-
|
|
51
|
+
|
|
52
|
+
- **Multiple formats**: Support for MaxQuant, FragPipe, DIA-NN, and mzTab files
|
|
53
|
+
- **Reads metadata**: Automatically extracts and organizes sample and protein metadata
|
|
34
54
|
|
|
35
55
|
## Installation
|
|
36
56
|
```bash
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
LICENSE
|
|
2
|
+
README.md
|
|
3
|
+
pyproject.toml
|
|
4
|
+
setup.cfg
|
|
5
|
+
docs/source/conf.py
|
|
6
|
+
protdata/__init__.py
|
|
7
|
+
protdata.egg-info/PKG-INFO
|
|
8
|
+
protdata.egg-info/SOURCES.txt
|
|
9
|
+
protdata.egg-info/dependency_links.txt
|
|
10
|
+
protdata.egg-info/requires.txt
|
|
11
|
+
protdata.egg-info/top_level.txt
|
|
12
|
+
protdata/io/__init__.py
|
|
13
|
+
protdata/io/diann_loader.py
|
|
14
|
+
protdata/io/fragpipe_loader.py
|
|
15
|
+
protdata/io/maxquant_loader.py
|
|
16
|
+
protdata/io/mztab_loader.py
|
|
17
|
+
protdata/io/utils.py
|
|
18
|
+
tests/test_loaders.py
|
|
19
|
+
tests/test_maxquant_loader.py
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
anndata
|
|
2
|
+
pandas
|
|
3
|
+
numpy
|
|
4
|
+
pyteomics
|
|
5
|
+
|
|
6
|
+
[dev]
|
|
7
|
+
pytest>=7.0.0
|
|
8
|
+
black~=25.1
|
|
9
|
+
flake8~=7.0
|
|
10
|
+
isort~=5.0
|
|
11
|
+
pre-commit~=3.0
|
|
12
|
+
pylint~=3.0
|
|
13
|
+
pytest~=8.0
|
|
14
|
+
|
|
15
|
+
[docs]
|
|
16
|
+
sphinx>=8.2.1
|
|
17
|
+
sphinx-book-theme>=1.1.0
|
|
18
|
+
sphinx-autodoc-typehints>=2.2.0
|
|
19
|
+
sphinx-issues>=5.0.1
|
|
20
|
+
sphinx-copybutton
|
|
21
|
+
sphinx-toolbox>=3.8.0
|
|
22
|
+
sphinxext.opengraph
|
|
23
|
+
myst-nb
|
|
24
|
+
scanpydoc[theme,typehints]>=0.15.3
|
|
25
|
+
awkward>=2.3
|
|
26
|
+
IPython
|
|
27
|
+
myst_parser
|
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "protdata"
|
|
3
|
-
version = "0.1.
|
|
3
|
+
version = "0.1.3"
|
|
4
4
|
description = "Proteomics data loaders for AnnData format."
|
|
5
|
+
requires-python = ">=3.9, <4.0"
|
|
5
6
|
authors = [
|
|
6
7
|
{ name = "Max Frank" }
|
|
7
8
|
]
|
|
8
9
|
readme = "README.md"
|
|
9
|
-
requires-python = ">=3.10"
|
|
10
10
|
dependencies = [
|
|
11
11
|
"anndata",
|
|
12
12
|
"pandas",
|
|
@@ -25,7 +25,27 @@ license-files = ["LICENSE"]
|
|
|
25
25
|
|
|
26
26
|
[project.optional-dependencies]
|
|
27
27
|
dev = [
|
|
28
|
-
"pytest>=7.0.0"
|
|
28
|
+
"pytest>=7.0.0",
|
|
29
|
+
"black~=25.1",
|
|
30
|
+
"flake8~=7.0",
|
|
31
|
+
"isort~=5.0",
|
|
32
|
+
"pre-commit~=3.0",
|
|
33
|
+
"pylint~=3.0",
|
|
34
|
+
"pytest~=8.0",
|
|
35
|
+
]
|
|
36
|
+
docs = [
|
|
37
|
+
"sphinx>=8.2.1",
|
|
38
|
+
"sphinx-book-theme>=1.1.0",
|
|
39
|
+
"sphinx-autodoc-typehints>=2.2.0",
|
|
40
|
+
"sphinx-issues>=5.0.1",
|
|
41
|
+
"sphinx-copybutton",
|
|
42
|
+
"sphinx-toolbox>=3.8.0",
|
|
43
|
+
"sphinxext.opengraph",
|
|
44
|
+
"myst-nb",
|
|
45
|
+
"scanpydoc[theme,typehints] >=0.15.3",
|
|
46
|
+
"awkward>=2.3",
|
|
47
|
+
"IPython", # For syntax highlighting in notebooks
|
|
48
|
+
"myst_parser",
|
|
29
49
|
]
|
|
30
50
|
|
|
31
51
|
[build-system]
|
|
@@ -33,4 +53,4 @@ requires = ["setuptools>=61.0"]
|
|
|
33
53
|
build-backend = "setuptools.build_meta"
|
|
34
54
|
|
|
35
55
|
[tool.setuptools.packages.find]
|
|
36
|
-
where = ["
|
|
56
|
+
where = ["."]
|
protdata-0.1.3/setup.cfg
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
[flake8]
|
|
2
|
+
max-line-length = 95
|
|
3
|
+
ignore =
|
|
4
|
+
E203,
|
|
5
|
+
W503,
|
|
6
|
+
E128,
|
|
7
|
+
E226,
|
|
8
|
+
E501,
|
|
9
|
+
per-file-ignores =
|
|
10
|
+
*/__init__.py: F401
|
|
11
|
+
exclude =
|
|
12
|
+
.git,
|
|
13
|
+
__pycache__,
|
|
14
|
+
build,
|
|
15
|
+
dist,
|
|
16
|
+
docs,
|
|
17
|
+
notebooks,
|
|
18
|
+
ignore,
|
|
19
|
+
.venv,
|
|
20
|
+
.eggs,
|
|
21
|
+
.tox,
|
|
22
|
+
|
|
23
|
+
[egg_info]
|
|
24
|
+
tag_build =
|
|
25
|
+
tag_date = 0
|
|
26
|
+
|
|
@@ -16,10 +16,24 @@ data_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "../data"))
|
|
|
16
16
|
("SILAC_SQ.mzTab", read_mztab),
|
|
17
17
|
],
|
|
18
18
|
)
|
|
19
|
-
def test_loader(filename, loader):
|
|
19
|
+
def test_loader(filename, loader, tmp_path):
|
|
20
20
|
path = os.path.join(data_dir, filename)
|
|
21
21
|
if not os.path.isfile(path):
|
|
22
22
|
pytest.skip(f"Test data file {filename} not found.")
|
|
23
23
|
adata = loader(path)
|
|
24
24
|
assert isinstance(adata, ad.AnnData)
|
|
25
25
|
assert adata.shape[0] > 0 and adata.shape[1] > 0
|
|
26
|
+
# Make sure the anndata file can be saved and loaded
|
|
27
|
+
test_file = tmp_path / "test.h5ad"
|
|
28
|
+
adata.write_h5ad(test_file)
|
|
29
|
+
adata2 = ad.read_h5ad(test_file)
|
|
30
|
+
assert adata2.shape == adata.shape
|
|
31
|
+
assert (
|
|
32
|
+
adata2.uns["RawInfo"]["Search_Engine"] == adata.uns["RawInfo"]["Search_Engine"]
|
|
33
|
+
)
|
|
34
|
+
if "filter_columns" in adata.uns["RawInfo"]:
|
|
35
|
+
assert list(adata2.uns["RawInfo"]["filter_columns"]) == list(
|
|
36
|
+
adata.uns["RawInfo"]["filter_columns"]
|
|
37
|
+
)
|
|
38
|
+
assert adata2.var.equals(adata.var)
|
|
39
|
+
assert adata2.obs.equals(adata.obs)
|
|
@@ -1,15 +0,0 @@
|
|
|
1
|
-
LICENSE
|
|
2
|
-
README.md
|
|
3
|
-
pyproject.toml
|
|
4
|
-
protdata/io/__init__.py
|
|
5
|
-
protdata/io/diann_loader.py
|
|
6
|
-
protdata/io/fragpipe_loader.py
|
|
7
|
-
protdata/io/maxquant_loader.py
|
|
8
|
-
protdata/io/mztab_loader.py
|
|
9
|
-
protdata/protdata.egg-info/PKG-INFO
|
|
10
|
-
protdata/protdata.egg-info/SOURCES.txt
|
|
11
|
-
protdata/protdata.egg-info/dependency_links.txt
|
|
12
|
-
protdata/protdata.egg-info/requires.txt
|
|
13
|
-
protdata/protdata.egg-info/top_level.txt
|
|
14
|
-
tests/test_loaders.py
|
|
15
|
-
tests/test_maxquant_loader.py
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
io
|
protdata-0.1.1/setup.cfg
DELETED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|