protdata 0.1.2__tar.gz → 0.1.4__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-0.1.4/LICENSE +28 -0
- protdata-0.1.4/PKG-INFO +130 -0
- protdata-0.1.4/README.md +88 -0
- protdata-0.1.4/docs/source/conf.py +102 -0
- {protdata-0.1.2 → protdata-0.1.4}/protdata/io/diann_loader.py +36 -20
- {protdata-0.1.2 → protdata-0.1.4}/protdata/io/fragpipe_loader.py +36 -20
- {protdata-0.1.2 → protdata-0.1.4}/protdata/io/maxquant_loader.py +48 -19
- {protdata-0.1.2 → protdata-0.1.4}/protdata/io/mztab_loader.py +23 -17
- protdata-0.1.4/protdata/io/utils.py +8 -0
- protdata-0.1.4/protdata.egg-info/PKG-INFO +130 -0
- {protdata-0.1.2 → protdata-0.1.4}/protdata.egg-info/SOURCES.txt +3 -0
- protdata-0.1.4/protdata.egg-info/requires.txt +28 -0
- {protdata-0.1.2 → protdata-0.1.4}/protdata.egg-info/top_level.txt +1 -0
- protdata-0.1.4/pyproject.toml +87 -0
- protdata-0.1.4/setup.cfg +26 -0
- {protdata-0.1.2 → protdata-0.1.4}/tests/test_loaders.py +21 -3
- protdata-0.1.2/LICENSE +0 -11
- protdata-0.1.2/PKG-INFO +0 -86
- protdata-0.1.2/README.md +0 -64
- protdata-0.1.2/protdata.egg-info/PKG-INFO +0 -86
- protdata-0.1.2/protdata.egg-info/requires.txt +0 -7
- protdata-0.1.2/pyproject.toml +0 -36
- protdata-0.1.2/setup.cfg +0 -4
- {protdata-0.1.2 → protdata-0.1.4}/protdata/__init__.py +0 -0
- {protdata-0.1.2 → protdata-0.1.4}/protdata/io/__init__.py +0 -0
- {protdata-0.1.2 → protdata-0.1.4}/protdata.egg-info/dependency_links.txt +0 -0
- {protdata-0.1.2 → protdata-0.1.4}/tests/test_maxquant_loader.py +0 -0
protdata-0.1.4/LICENSE
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
BSD 3-Clause License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2025, Chan Zuckerberg Biohub
|
|
4
|
+
|
|
5
|
+
Redistribution and use in source and binary forms, with or without
|
|
6
|
+
modification, are permitted provided that the following conditions are met:
|
|
7
|
+
|
|
8
|
+
1. Redistributions of source code must retain the above copyright notice, this
|
|
9
|
+
list of conditions and the following disclaimer.
|
|
10
|
+
|
|
11
|
+
2. Redistributions in binary form must reproduce the above copyright notice,
|
|
12
|
+
this list of conditions and the following disclaimer in the documentation
|
|
13
|
+
and/or other materials provided with the distribution.
|
|
14
|
+
|
|
15
|
+
3. Neither the name of the copyright holder nor the names of its
|
|
16
|
+
contributors may be used to endorse or promote products derived from
|
|
17
|
+
this software without specific prior written permission.
|
|
18
|
+
|
|
19
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
20
|
+
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
21
|
+
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
22
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
|
23
|
+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
24
|
+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
|
25
|
+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
|
26
|
+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
27
|
+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
28
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
protdata-0.1.4/PKG-INFO
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: protdata
|
|
3
|
+
Version: 0.1.4
|
|
4
|
+
Summary: Proteomics data loaders for AnnData format.
|
|
5
|
+
Author: Max Frank
|
|
6
|
+
License-Expression: MIT
|
|
7
|
+
Classifier: Programming Language :: Python :: 3
|
|
8
|
+
Classifier: Operating System :: OS Independent
|
|
9
|
+
Classifier: Development Status :: 3 - Alpha
|
|
10
|
+
Classifier: Intended Audience :: Science/Research
|
|
11
|
+
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
12
|
+
Requires-Python: <4.0,>=3.9
|
|
13
|
+
Description-Content-Type: text/markdown
|
|
14
|
+
License-File: LICENSE
|
|
15
|
+
Requires-Dist: anndata
|
|
16
|
+
Requires-Dist: pandas
|
|
17
|
+
Requires-Dist: numpy
|
|
18
|
+
Requires-Dist: pyteomics
|
|
19
|
+
Provides-Extra: dev
|
|
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: sphinx_design; extra == "docs"
|
|
36
|
+
Requires-Dist: myst-nb; extra == "docs"
|
|
37
|
+
Requires-Dist: scanpydoc[theme,typehints]>=0.15.3; extra == "docs"
|
|
38
|
+
Requires-Dist: awkward>=2.3; extra == "docs"
|
|
39
|
+
Requires-Dist: IPython; extra == "docs"
|
|
40
|
+
Requires-Dist: myst_parser; extra == "docs"
|
|
41
|
+
Dynamic: license-file
|
|
42
|
+
|
|
43
|
+
# protdata
|
|
44
|
+
|
|
45
|
+
[](https://github.com/czbiohub-sf/protdata/actions/workflows/test.yml)
|
|
46
|
+

|
|
47
|
+
[](https://protdata-czbiohub.vercel.app/)
|
|
48
|
+
|
|
49
|
+
Proteomics data loaders for the [AnnData](https://anndata.readthedocs.io/) format.
|
|
50
|
+
|
|
51
|
+
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.
|
|
52
|
+
|
|
53
|
+
## Features
|
|
54
|
+
|
|
55
|
+
- **Multiple formats**: Support for MaxQuant, FragPipe, DIA-NN, and mzTab files
|
|
56
|
+
- **Reads metadata**: Automatically extracts and organizes sample and protein metadata
|
|
57
|
+
|
|
58
|
+
## Installation
|
|
59
|
+
|
|
60
|
+
Protdata has minimal dependencies listed in [pyproject.toml](https://github.com/czbiohub-sf/protdata/blob/main/pyproject.toml)
|
|
61
|
+
|
|
62
|
+
To install the latest release from PyPI, run:
|
|
63
|
+
|
|
64
|
+
```bash
|
|
65
|
+
pip install protdata
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
Or install from source:
|
|
69
|
+
```bash
|
|
70
|
+
git clone https://github.com/czbiohub-sf/protdata.git
|
|
71
|
+
cd protdata
|
|
72
|
+
pip install -e . # or make setup-develop for developers
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
## Usage Example
|
|
76
|
+
|
|
77
|
+
### MaxQuant Import
|
|
78
|
+
|
|
79
|
+
You can download an example proteinGroups [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/proteinGroups.txt)
|
|
80
|
+
```python
|
|
81
|
+
import protdata
|
|
82
|
+
|
|
83
|
+
adata = load_maxquant_to_anndata("/path/to/proteinGroups.txt")
|
|
84
|
+
print(adata)
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
### DIA-NN Import
|
|
88
|
+
|
|
89
|
+
You can download an example DIA-NN report [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/report.pg_matrix.tsv)
|
|
90
|
+
|
|
91
|
+
```python
|
|
92
|
+
from protdata.io import read_diann
|
|
93
|
+
|
|
94
|
+
adata = read_diann("/path/to/report.pg_matrix.tsv")
|
|
95
|
+
print(adata)
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
### FragPipe Import
|
|
99
|
+
|
|
100
|
+
You can download an example FragPipe output [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/combined_protein.tsv)
|
|
101
|
+
|
|
102
|
+
```python
|
|
103
|
+
from protdata.io import read_fragpipe
|
|
104
|
+
|
|
105
|
+
adata = read_fragpipe("/path/to/combined_protein.tsv")
|
|
106
|
+
print(adata)
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
### mzTab Import
|
|
110
|
+
|
|
111
|
+
You can download an example mzTab [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/SILAC_SQ.mzTab)
|
|
112
|
+
|
|
113
|
+
```python
|
|
114
|
+
from protdata.io import read_mztab
|
|
115
|
+
|
|
116
|
+
adata = read_mztab("/path/to/SILAC_SQ.mzTab")
|
|
117
|
+
print(adata)
|
|
118
|
+
```
|
|
119
|
+
## Authors
|
|
120
|
+
|
|
121
|
+
`protdata` is created and maintained by the [Computational Biology Platform](https://www.czbiohub.org/comp-biology/) at the [Chan Zuckerberg Biohub San Francisco](https://www.czbiohub.org/sf/).
|
|
122
|
+
|
|
123
|
+
To get in touch please use the [GihHub issues](https://github.com/czbiohub-sf/protdata/issues) page.
|
|
124
|
+
|
|
125
|
+
## Contributing
|
|
126
|
+
|
|
127
|
+
If you want to contribute to `protdata`, please read the [Contribution Guide](https://prodata.sf.czbiohub.org/contributing)
|
|
128
|
+
|
|
129
|
+
## Changelog
|
|
130
|
+
See [Release Notes](https://prodata.sf.czbiohub.org/release_notes)
|
protdata-0.1.4/README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
# protdata
|
|
2
|
+
|
|
3
|
+
[](https://github.com/czbiohub-sf/protdata/actions/workflows/test.yml)
|
|
4
|
+

|
|
5
|
+
[](https://protdata-czbiohub.vercel.app/)
|
|
6
|
+
|
|
7
|
+
Proteomics data loaders for the [AnnData](https://anndata.readthedocs.io/) format.
|
|
8
|
+
|
|
9
|
+
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.
|
|
10
|
+
|
|
11
|
+
## Features
|
|
12
|
+
|
|
13
|
+
- **Multiple formats**: Support for MaxQuant, FragPipe, DIA-NN, and mzTab files
|
|
14
|
+
- **Reads metadata**: Automatically extracts and organizes sample and protein metadata
|
|
15
|
+
|
|
16
|
+
## Installation
|
|
17
|
+
|
|
18
|
+
Protdata has minimal dependencies listed in [pyproject.toml](https://github.com/czbiohub-sf/protdata/blob/main/pyproject.toml)
|
|
19
|
+
|
|
20
|
+
To install the latest release from PyPI, run:
|
|
21
|
+
|
|
22
|
+
```bash
|
|
23
|
+
pip install protdata
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
Or install from source:
|
|
27
|
+
```bash
|
|
28
|
+
git clone https://github.com/czbiohub-sf/protdata.git
|
|
29
|
+
cd protdata
|
|
30
|
+
pip install -e . # or make setup-develop for developers
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
## Usage Example
|
|
34
|
+
|
|
35
|
+
### MaxQuant Import
|
|
36
|
+
|
|
37
|
+
You can download an example proteinGroups [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/proteinGroups.txt)
|
|
38
|
+
```python
|
|
39
|
+
import protdata
|
|
40
|
+
|
|
41
|
+
adata = load_maxquant_to_anndata("/path/to/proteinGroups.txt")
|
|
42
|
+
print(adata)
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
### DIA-NN Import
|
|
46
|
+
|
|
47
|
+
You can download an example DIA-NN report [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/report.pg_matrix.tsv)
|
|
48
|
+
|
|
49
|
+
```python
|
|
50
|
+
from protdata.io import read_diann
|
|
51
|
+
|
|
52
|
+
adata = read_diann("/path/to/report.pg_matrix.tsv")
|
|
53
|
+
print(adata)
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
### FragPipe Import
|
|
57
|
+
|
|
58
|
+
You can download an example FragPipe output [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/combined_protein.tsv)
|
|
59
|
+
|
|
60
|
+
```python
|
|
61
|
+
from protdata.io import read_fragpipe
|
|
62
|
+
|
|
63
|
+
adata = read_fragpipe("/path/to/combined_protein.tsv")
|
|
64
|
+
print(adata)
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
### mzTab Import
|
|
68
|
+
|
|
69
|
+
You can download an example mzTab [file here](https://github.com/czbiohub-sf/protdata/raw/main/data/SILAC_SQ.mzTab)
|
|
70
|
+
|
|
71
|
+
```python
|
|
72
|
+
from protdata.io import read_mztab
|
|
73
|
+
|
|
74
|
+
adata = read_mztab("/path/to/SILAC_SQ.mzTab")
|
|
75
|
+
print(adata)
|
|
76
|
+
```
|
|
77
|
+
## Authors
|
|
78
|
+
|
|
79
|
+
`protdata` is created and maintained by the [Computational Biology Platform](https://www.czbiohub.org/comp-biology/) at the [Chan Zuckerberg Biohub San Francisco](https://www.czbiohub.org/sf/).
|
|
80
|
+
|
|
81
|
+
To get in touch please use the [GihHub issues](https://github.com/czbiohub-sf/protdata/issues) page.
|
|
82
|
+
|
|
83
|
+
## Contributing
|
|
84
|
+
|
|
85
|
+
If you want to contribute to `protdata`, please read the [Contribution Guide](https://prodata.sf.czbiohub.org/contributing)
|
|
86
|
+
|
|
87
|
+
## Changelog
|
|
88
|
+
See [Release Notes](https://prodata.sf.czbiohub.org/release_notes)
|
|
@@ -0,0 +1,102 @@
|
|
|
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
|
+
html_favicon = "_static/img/protdata_favicon.svg"
|
|
31
|
+
|
|
32
|
+
extensions = [
|
|
33
|
+
"myst_nb",
|
|
34
|
+
"sphinx_copybutton",
|
|
35
|
+
"sphinx.ext.autodoc",
|
|
36
|
+
"sphinx.ext.intersphinx",
|
|
37
|
+
"sphinx.ext.doctest",
|
|
38
|
+
"sphinx.ext.coverage",
|
|
39
|
+
"sphinx.ext.mathjax",
|
|
40
|
+
"sphinx.ext.napoleon",
|
|
41
|
+
"sphinx.ext.autosummary",
|
|
42
|
+
"sphinx_autodoc_typehints",
|
|
43
|
+
"sphinx_issues",
|
|
44
|
+
"sphinx_design",
|
|
45
|
+
"sphinxext.opengraph",
|
|
46
|
+
"scanpydoc",
|
|
47
|
+
"IPython.sphinxext.ipython_console_highlighting",
|
|
48
|
+
]
|
|
49
|
+
|
|
50
|
+
myst_enable_extensions = ["colon_fence", "dollarmath"]
|
|
51
|
+
myst_heading_anchors = 3
|
|
52
|
+
nb_execution_mode = "off"
|
|
53
|
+
|
|
54
|
+
autosummary_generate = True
|
|
55
|
+
autodoc_member_order = "bysource"
|
|
56
|
+
napoleon_google_docstring = False
|
|
57
|
+
napoleon_numpy_docstring = True
|
|
58
|
+
napoleon_use_rtype = True
|
|
59
|
+
napoleon_use_param = True
|
|
60
|
+
typehints_defaults = "braces"
|
|
61
|
+
issues_github_path = "czbiohub-sf/protdata"
|
|
62
|
+
|
|
63
|
+
nitpicky = True
|
|
64
|
+
nitpick_ignore = []
|
|
65
|
+
|
|
66
|
+
intersphinx_mapping = dict(
|
|
67
|
+
python=("https://docs.python.org/3", None),
|
|
68
|
+
numpy=("https://numpy.org/doc/stable", None),
|
|
69
|
+
pandas=("https://pandas.pydata.org/pandas-docs/stable", None),
|
|
70
|
+
anndata=("https://anndata.readthedocs.io/en/stable/", None),
|
|
71
|
+
scipy=("https://docs.scipy.org/doc/scipy", None),
|
|
72
|
+
h5py=("https://docs.h5py.org/en/latest", None),
|
|
73
|
+
)
|
|
74
|
+
|
|
75
|
+
# qualname_overrides = {
|
|
76
|
+
# "h5py._hl.group.Group": "h5py.Group",
|
|
77
|
+
# "h5py._hl.files.File": "h5py.File",
|
|
78
|
+
# "h5py._hl.dataset.Dataset": "h5py.Dataset",
|
|
79
|
+
# "anndata._core.anndata.AnnData": "anndata.AnnData",
|
|
80
|
+
# }
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
# -- Social cards ---------------------------------------------------------
|
|
84
|
+
|
|
85
|
+
# ogp_site_url = "https://protdata.readthedocs.io/"
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
# -- Options for HTML output ----------------------------------------------
|
|
89
|
+
|
|
90
|
+
html_theme = "scanpydoc"
|
|
91
|
+
html_theme_options = dict(
|
|
92
|
+
use_repository_button=True,
|
|
93
|
+
repository_url="https://github.com/czbiohub-sf/protdata",
|
|
94
|
+
repository_branch="main",
|
|
95
|
+
navigation_with_keys=False,
|
|
96
|
+
)
|
|
97
|
+
html_show_sphinx = False
|
|
98
|
+
html_logo = "_static/img/protdata_schema.svg"
|
|
99
|
+
|
|
100
|
+
|
|
101
|
+
def setup(app: Sphinx):
|
|
102
|
+
app.add_css_file("css/custom.css")
|
|
@@ -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 +16,22 @@ 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
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
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.
|
|
27
|
+
|
|
28
|
+
Returns
|
|
29
|
+
-------
|
|
30
|
+
:class:`anndata.AnnData` object with:
|
|
31
|
+
|
|
32
|
+
- ``X``: intensity matrix (samples x proteins)
|
|
33
|
+
- ``var``: protein metadata (indexed by protein group IDs)
|
|
34
|
+
- ``obs``: sample metadata (indexed by sample names)
|
|
27
35
|
"""
|
|
28
36
|
if isinstance(file, pd.DataFrame):
|
|
29
37
|
df = file.copy()
|
|
@@ -46,9 +54,11 @@ def read_diann(
|
|
|
46
54
|
]
|
|
47
55
|
|
|
48
56
|
df.columns = [
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
57
|
+
(
|
|
58
|
+
os.path.basename(col)
|
|
59
|
+
if isinstance(col, str) and col not in no_sample_column
|
|
60
|
+
else str(col)
|
|
61
|
+
)
|
|
52
62
|
for col in df.columns
|
|
53
63
|
]
|
|
54
64
|
|
|
@@ -59,7 +69,7 @@ def read_diann(
|
|
|
59
69
|
# Find intensity columns (all columns not in no_sample_column)
|
|
60
70
|
intensity_cols = df.columns.difference(no_sample_column, sort=False).tolist()
|
|
61
71
|
if not intensity_cols:
|
|
62
|
-
raise ValueError(
|
|
72
|
+
raise ValueError("No intensity columns found.")
|
|
63
73
|
|
|
64
74
|
# Build X matrix (proteins x samples)
|
|
65
75
|
X = df[intensity_cols].to_numpy(dtype=np.float32).T
|
|
@@ -67,12 +77,18 @@ def read_diann(
|
|
|
67
77
|
# Build var (proteins)
|
|
68
78
|
var = df[df.columns.intersection(no_sample_column, sort=False)].copy()
|
|
69
79
|
var.index = df[index_column]
|
|
80
|
+
var = cleanup_obsvar(var)
|
|
70
81
|
|
|
71
82
|
# Build obs (samples)
|
|
72
83
|
obs = pd.DataFrame(index=intensity_cols)
|
|
84
|
+
obs = cleanup_obsvar(obs)
|
|
73
85
|
|
|
74
86
|
# Build uns
|
|
75
|
-
uns = {
|
|
87
|
+
uns = {
|
|
88
|
+
"RawInfo": {
|
|
89
|
+
"Search_Engine": "DIANN",
|
|
90
|
+
},
|
|
91
|
+
}
|
|
76
92
|
|
|
77
93
|
# Create AnnData
|
|
78
94
|
adata = ad.AnnData(X=X, obs=obs, var=var)
|
|
@@ -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 warnings
|
|
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_fragpipe(
|
|
@@ -16,21 +19,28 @@ def read_fragpipe(
|
|
|
16
19
|
sep: str = "\t",
|
|
17
20
|
) -> ad.AnnData:
|
|
18
21
|
"""
|
|
19
|
-
Load FragPipe
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
22
|
+
Load a FragPipe protein group matrix into an AnnData object.
|
|
23
|
+
|
|
24
|
+
Parameters
|
|
25
|
+
----------
|
|
26
|
+
file
|
|
27
|
+
Path to the FragPipe combined_protein.tsv file or a pandas DataFrame containing the data.
|
|
28
|
+
intensity_column_suffixes
|
|
29
|
+
Suffix(es) for intensity columns to extract.
|
|
30
|
+
The first suffix is used for the main matrix (X), others are stored as layers if present.
|
|
31
|
+
index_column
|
|
32
|
+
Column name to use as protein index.
|
|
33
|
+
sep
|
|
34
|
+
File separator if reading from file.
|
|
35
|
+
|
|
36
|
+
Returns
|
|
37
|
+
-------
|
|
38
|
+
:class:`anndata.AnnData` object with:
|
|
39
|
+
|
|
40
|
+
- ``X``: intensity matrix (samples x proteins)
|
|
41
|
+
- ``var``: protein metadata (indexed by protein IDs)
|
|
42
|
+
- ``obs``: sample metadata (indexed by sample names)
|
|
43
|
+
- ``layers``: additional intensity matrices if multiple intensity column suffixes are provided
|
|
34
44
|
"""
|
|
35
45
|
if isinstance(intensity_column_suffixes, str):
|
|
36
46
|
intensity_column_suffixes = [intensity_column_suffixes]
|
|
@@ -74,12 +84,18 @@ def read_fragpipe(
|
|
|
74
84
|
)
|
|
75
85
|
var = df.loc[:, ~sample_columns].copy()
|
|
76
86
|
var.index = df[index_column]
|
|
87
|
+
var = cleanup_obsvar(var)
|
|
77
88
|
|
|
78
89
|
# Build obs (samples)
|
|
79
90
|
obs = pd.DataFrame(index=sample_names)
|
|
91
|
+
obs = cleanup_obsvar(obs)
|
|
80
92
|
|
|
81
93
|
# Build uns
|
|
82
|
-
uns = {
|
|
94
|
+
uns = {
|
|
95
|
+
"RawInfo": {
|
|
96
|
+
"Search_Engine": "FragPipe",
|
|
97
|
+
},
|
|
98
|
+
}
|
|
83
99
|
|
|
84
100
|
# Create AnnData
|
|
85
101
|
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 +29,28 @@ def read_maxquant(
|
|
|
20
29
|
"""
|
|
21
30
|
Load MaxQuant proteinGroups.txt into an AnnData object.
|
|
22
31
|
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
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.
|
|
45
|
+
|
|
46
|
+
Returns
|
|
47
|
+
-------
|
|
48
|
+
:class:`anndata.AnnData` object with:
|
|
49
|
+
|
|
50
|
+
- ``X``: intensity matrix (samples x proteins)
|
|
51
|
+
- ``var``: protein metadata (indexed by protein IDs)
|
|
52
|
+
- ``obs``: sample metadata (indexed by sample names)
|
|
53
|
+
- ``layers``: additional intensity matrices if multiple intensity column prefixes are provided
|
|
35
54
|
"""
|
|
36
55
|
if isinstance(intensity_column_prefixes, str):
|
|
37
56
|
intensity_column_prefixes = [intensity_column_prefixes]
|
|
@@ -65,7 +84,10 @@ def read_maxquant(
|
|
|
65
84
|
if col in [prefix + sample_name for sample_name in sample_names]
|
|
66
85
|
]
|
|
67
86
|
if len(prefix_cols) == len(sample_names):
|
|
68
|
-
|
|
87
|
+
# Cannot have '/' in the key (hdf5 interprets as a group for serialization)
|
|
88
|
+
layers[prefix.strip().replace("/", "_")] = (
|
|
89
|
+
df[prefix_cols].to_numpy(dtype=np.float32).T
|
|
90
|
+
)
|
|
69
91
|
else:
|
|
70
92
|
warnings.warn(
|
|
71
93
|
f"Number of columns for prefix '{prefix}' does not match number of samples."
|
|
@@ -78,12 +100,19 @@ def read_maxquant(
|
|
|
78
100
|
)
|
|
79
101
|
var = df.loc[:, ~sample_columns].copy()
|
|
80
102
|
var.index = df[index_column]
|
|
103
|
+
var = cleanup_obsvar(var)
|
|
81
104
|
|
|
82
105
|
# Build obs (samples)
|
|
83
106
|
obs = pd.DataFrame(index=sample_names)
|
|
107
|
+
obs = cleanup_obsvar(obs)
|
|
84
108
|
|
|
85
109
|
# Build uns
|
|
86
|
-
uns = {
|
|
110
|
+
uns = {
|
|
111
|
+
"RawInfo": {
|
|
112
|
+
"Search_Engine": "MaxQuant",
|
|
113
|
+
"filter_columns": filter_columns,
|
|
114
|
+
},
|
|
115
|
+
}
|
|
87
116
|
|
|
88
117
|
# Create AnnData
|
|
89
118
|
adata = ad.AnnData(X=X, obs=obs, var=var, layers=layers, uns=uns)
|