pepdata 1.2.2__tar.gz → 1.2.4__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.
- {pepdata-1.2.2 → pepdata-1.2.4}/MANIFEST.in +0 -1
- pepdata-1.2.4/PKG-INFO +86 -0
- pepdata-1.2.4/README.md +55 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/columns.py +3 -2
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/tcell.py +14 -9
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/version.py +2 -2
- pepdata-1.2.4/pepdata.egg-info/PKG-INFO +86 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata.egg-info/SOURCES.txt +3 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata.egg-info/top_level.txt +2 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pyproject.toml +5 -1
- pepdata-1.2.4/scripts/check_docs_examples.py +33 -0
- pepdata-1.2.4/scripts/check_docs_links.py +54 -0
- pepdata-1.2.4/tests/conftest.py +23 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_iedb_tcell.py +8 -15
- pepdata-1.2.2/PKG-INFO +0 -78
- pepdata-1.2.2/README.md +0 -51
- pepdata-1.2.2/pepdata.egg-info/PKG-INFO +0 -78
- {pepdata-1.2.2 → pepdata-1.2.4}/LICENSE.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/__init__.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/amino_acid.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/amino_acid_alphabet.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/amino_acid_properties.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/blosum.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/chou_fasman.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/common.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/__init__.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/alleles.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/common.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/memoize.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/iedb/mhc.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/BLOSUM30 +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/BLOSUM50 +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/BLOSUM62 +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/__init__.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/amino_acid_properties.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/helix_vs_coil.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/helix_vs_strand.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/pmbec.mat +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/matrices/strand_vs_coil.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/peptide_vectorizer.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/pmbec.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/reduced_alphabet.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/residue_contact_energies.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata/static_data.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata.egg-info/dependency_links.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/pepdata.egg-info/requires.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/requirements.txt +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/setup.cfg +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_amino_acids.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_blosum.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_iedb_alleles.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_iedb_mhc.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_ngram.py +0 -0
- {pepdata-1.2.2 → pepdata-1.2.4}/tests/test_pmbec.py +0 -0
pepdata-1.2.4/PKG-INFO
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: pepdata
|
|
3
|
+
Version: 1.2.4
|
|
4
|
+
Summary: Immunological peptide datasets and amino acid properties
|
|
5
|
+
Author-email: Alex Rubinsteyn <alex.rubinsteyn@mssm.edu>
|
|
6
|
+
Project-URL: Homepage, https://github.com/openvax/pepdata
|
|
7
|
+
Project-URL: Bug Tracker, https://github.com/openvax/pepdata/issues
|
|
8
|
+
Classifier: Development Status :: 4 - Beta
|
|
9
|
+
Classifier: Environment :: Console
|
|
10
|
+
Classifier: Operating System :: OS Independent
|
|
11
|
+
Classifier: Intended Audience :: Science/Research
|
|
12
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
13
|
+
Classifier: Programming Language :: Python
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
18
|
+
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
19
|
+
Requires-Python: >=3.11
|
|
20
|
+
Description-Content-Type: text/markdown
|
|
21
|
+
License-File: LICENSE.txt
|
|
22
|
+
Requires-Dist: numpy<3.0.0,>=2.0.0
|
|
23
|
+
Requires-Dist: scipy>=0.9
|
|
24
|
+
Requires-Dist: pandas>=0.17
|
|
25
|
+
Requires-Dist: scikit-learn>=0.14.1
|
|
26
|
+
Requires-Dist: progressbar33
|
|
27
|
+
Requires-Dist: biopython>=1.65
|
|
28
|
+
Requires-Dist: datacache>=0.4.4
|
|
29
|
+
Requires-Dist: lxml
|
|
30
|
+
Dynamic: license-file
|
|
31
|
+
|
|
32
|
+
# PepData
|
|
33
|
+
|
|
34
|
+
Look up shipped amino-acid properties and pairwise matrices, encode peptide
|
|
35
|
+
sequences, or load peptide assay tables from IEDB. Property lookups work offline;
|
|
36
|
+
IEDB tables require a download.
|
|
37
|
+
|
|
38
|
+
## Install
|
|
39
|
+
|
|
40
|
+
```sh
|
|
41
|
+
python -m pip install pepdata
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
Python 3.11 or later is required.
|
|
45
|
+
|
|
46
|
+
## Look up a peptide's residue properties
|
|
47
|
+
|
|
48
|
+
```python
|
|
49
|
+
from pepdata.amino_acid_properties import hydropathy
|
|
50
|
+
|
|
51
|
+
peptide = "ACD"
|
|
52
|
+
print([hydropathy[residue] for residue in peptide])
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
```text
|
|
56
|
+
[1.8, 2.5, -3.5]
|
|
57
|
+
```
|
|
58
|
+
|
|
59
|
+
The values come from the shipped residue-property table. The dictionary maps
|
|
60
|
+
single-letter residues to numeric values; it does not predict MHC binding or
|
|
61
|
+
clinical immunogenicity. Use uppercase canonical residue letters. A missing
|
|
62
|
+
letter raises `KeyError`.
|
|
63
|
+
|
|
64
|
+
## Find the interface you need
|
|
65
|
+
|
|
66
|
+
| Task | Module or object |
|
|
67
|
+
| --- | --- |
|
|
68
|
+
| Single-residue properties | `pepdata.amino_acid_properties` |
|
|
69
|
+
| BLOSUM substitution matrices | `pepdata.blosum` |
|
|
70
|
+
| PMBEC and contact tables | `pepdata.pmbec`, `pepdata.residue_contact_energies` |
|
|
71
|
+
| Residue alphabets | `pepdata.amino_acid_alphabet`, `pepdata.reduced_alphabet` |
|
|
72
|
+
| N-gram features | `pepdata.PeptideVectorizer` |
|
|
73
|
+
| MHC-binding assay tables | `pepdata.iedb.mhc` |
|
|
74
|
+
| T-cell assay tables | `pepdata.iedb.tcell` |
|
|
75
|
+
|
|
76
|
+
See [residue and pairwise tables](docs/guides/properties.md), then
|
|
77
|
+
[peptide features and IEDB tables](docs/guides/datasets.md). The
|
|
78
|
+
[API reference](docs/reference.md) follows those same tasks.
|
|
79
|
+
|
|
80
|
+
Older pepdata documentation placed the property tables in `amino_acid` and
|
|
81
|
+
described a `StringTransformer` interface. The property dictionaries are
|
|
82
|
+
in `amino_acid_properties`, and there is no `StringTransformer` class.
|
|
83
|
+
|
|
84
|
+
## Documentation development
|
|
85
|
+
|
|
86
|
+
Install `requirements-docs.txt`, run `./docs.sh`, then `python scripts/check_docs_examples.py`.
|
pepdata-1.2.4/README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
# PepData
|
|
2
|
+
|
|
3
|
+
Look up shipped amino-acid properties and pairwise matrices, encode peptide
|
|
4
|
+
sequences, or load peptide assay tables from IEDB. Property lookups work offline;
|
|
5
|
+
IEDB tables require a download.
|
|
6
|
+
|
|
7
|
+
## Install
|
|
8
|
+
|
|
9
|
+
```sh
|
|
10
|
+
python -m pip install pepdata
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
Python 3.11 or later is required.
|
|
14
|
+
|
|
15
|
+
## Look up a peptide's residue properties
|
|
16
|
+
|
|
17
|
+
```python
|
|
18
|
+
from pepdata.amino_acid_properties import hydropathy
|
|
19
|
+
|
|
20
|
+
peptide = "ACD"
|
|
21
|
+
print([hydropathy[residue] for residue in peptide])
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
```text
|
|
25
|
+
[1.8, 2.5, -3.5]
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
The values come from the shipped residue-property table. The dictionary maps
|
|
29
|
+
single-letter residues to numeric values; it does not predict MHC binding or
|
|
30
|
+
clinical immunogenicity. Use uppercase canonical residue letters. A missing
|
|
31
|
+
letter raises `KeyError`.
|
|
32
|
+
|
|
33
|
+
## Find the interface you need
|
|
34
|
+
|
|
35
|
+
| Task | Module or object |
|
|
36
|
+
| --- | --- |
|
|
37
|
+
| Single-residue properties | `pepdata.amino_acid_properties` |
|
|
38
|
+
| BLOSUM substitution matrices | `pepdata.blosum` |
|
|
39
|
+
| PMBEC and contact tables | `pepdata.pmbec`, `pepdata.residue_contact_energies` |
|
|
40
|
+
| Residue alphabets | `pepdata.amino_acid_alphabet`, `pepdata.reduced_alphabet` |
|
|
41
|
+
| N-gram features | `pepdata.PeptideVectorizer` |
|
|
42
|
+
| MHC-binding assay tables | `pepdata.iedb.mhc` |
|
|
43
|
+
| T-cell assay tables | `pepdata.iedb.tcell` |
|
|
44
|
+
|
|
45
|
+
See [residue and pairwise tables](docs/guides/properties.md), then
|
|
46
|
+
[peptide features and IEDB tables](docs/guides/datasets.md). The
|
|
47
|
+
[API reference](docs/reference.md) follows those same tasks.
|
|
48
|
+
|
|
49
|
+
Older pepdata documentation placed the property tables in `amino_acid` and
|
|
50
|
+
described a `StringTransformer` interface. The property dictionaries are
|
|
51
|
+
in `amino_acid_properties`, and there is no `StringTransformer` class.
|
|
52
|
+
|
|
53
|
+
## Documentation development
|
|
54
|
+
|
|
55
|
+
Install `requirements-docs.txt`, run `./docs.sh`, then `python scripts/check_docs_examples.py`.
|
|
@@ -47,8 +47,9 @@ def find(df : pd.DataFrame, group_candidates : list[str], column_candidates : li
|
|
|
47
47
|
|
|
48
48
|
if len(possible_matches) == 0:
|
|
49
49
|
return None
|
|
50
|
-
# get the shortest
|
|
51
|
-
|
|
50
|
+
# get the shortest match
|
|
51
|
+
best = min(possible_matches, key=lambda p: len(p[0]) + len(p[1]))
|
|
52
|
+
return df[best]
|
|
52
53
|
|
|
53
54
|
|
|
54
55
|
MHC_GROUP_CANDIDATES : list[str] = ["MHC", "MHC Restriction"]
|
|
@@ -62,8 +62,8 @@ def delete():
|
|
|
62
62
|
@memoize
|
|
63
63
|
def load_dataframe(
|
|
64
64
|
mhc_class : str | None = None, # 1, 2, or None for neither
|
|
65
|
-
|
|
66
|
-
|
|
65
|
+
hla : str | None = None,
|
|
66
|
+
exclude_hla : str | None = None,
|
|
67
67
|
human_only : bool =False,
|
|
68
68
|
peptide_length : int | None = None,
|
|
69
69
|
assay_method : str | None = None,
|
|
@@ -78,10 +78,10 @@ def load_dataframe(
|
|
|
78
78
|
mhc_class: {None, 1, 2}
|
|
79
79
|
Restrict to MHC Class I or Class II (or None for neither)
|
|
80
80
|
|
|
81
|
-
|
|
81
|
+
hla: regex pattern, optional
|
|
82
82
|
Restrict results to specific MHC used in assay
|
|
83
83
|
|
|
84
|
-
|
|
84
|
+
exclude_hla: regex pattern, optional
|
|
85
85
|
Exclude certain MHC allele patterns
|
|
86
86
|
|
|
87
87
|
human_only: bool
|
|
@@ -119,6 +119,11 @@ def load_dataframe(
|
|
|
119
119
|
organism = get_host_name(df)
|
|
120
120
|
assay_method_series = get_assay_method(df)
|
|
121
121
|
|
|
122
|
+
if epitopes is None:
|
|
123
|
+
raise ValueError(
|
|
124
|
+
"Could not find epitope name column in IEDB T-cell data. "
|
|
125
|
+
f"Available columns: {list(df.columns)}"
|
|
126
|
+
)
|
|
122
127
|
|
|
123
128
|
# Sometimes the IEDB seems to put in an extra comma in the
|
|
124
129
|
# header line, which creates an unnamed column of NaNs.
|
|
@@ -126,7 +131,7 @@ def load_dataframe(
|
|
|
126
131
|
df = df.dropna(axis=1, how="all")
|
|
127
132
|
|
|
128
133
|
n = len(df)
|
|
129
|
-
|
|
134
|
+
|
|
130
135
|
null_epitope_seq = epitopes.isnull()
|
|
131
136
|
n_null = null_epitope_seq.sum()
|
|
132
137
|
|
|
@@ -173,11 +178,11 @@ def load_dataframe(
|
|
|
173
178
|
# or
|
|
174
179
|
# "Class I,allele undetermined"
|
|
175
180
|
|
|
176
|
-
if
|
|
177
|
-
mask &= mhc.str.contains(
|
|
181
|
+
if hla:
|
|
182
|
+
mask &= mhc.str.contains(hla, na=False)
|
|
178
183
|
|
|
179
|
-
if
|
|
180
|
-
mask &= ~(mhc.str.contains(
|
|
184
|
+
if exclude_hla:
|
|
185
|
+
mask &= ~(mhc.str.contains(exclude_hla, na=False))
|
|
181
186
|
|
|
182
187
|
if assay_method is not None and assay_method_series is not None:
|
|
183
188
|
mask &= assay_method_series.str.contains(assay_method, na=False)
|
|
@@ -0,0 +1,86 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: pepdata
|
|
3
|
+
Version: 1.2.4
|
|
4
|
+
Summary: Immunological peptide datasets and amino acid properties
|
|
5
|
+
Author-email: Alex Rubinsteyn <alex.rubinsteyn@mssm.edu>
|
|
6
|
+
Project-URL: Homepage, https://github.com/openvax/pepdata
|
|
7
|
+
Project-URL: Bug Tracker, https://github.com/openvax/pepdata/issues
|
|
8
|
+
Classifier: Development Status :: 4 - Beta
|
|
9
|
+
Classifier: Environment :: Console
|
|
10
|
+
Classifier: Operating System :: OS Independent
|
|
11
|
+
Classifier: Intended Audience :: Science/Research
|
|
12
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
13
|
+
Classifier: Programming Language :: Python
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
18
|
+
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
19
|
+
Requires-Python: >=3.11
|
|
20
|
+
Description-Content-Type: text/markdown
|
|
21
|
+
License-File: LICENSE.txt
|
|
22
|
+
Requires-Dist: numpy<3.0.0,>=2.0.0
|
|
23
|
+
Requires-Dist: scipy>=0.9
|
|
24
|
+
Requires-Dist: pandas>=0.17
|
|
25
|
+
Requires-Dist: scikit-learn>=0.14.1
|
|
26
|
+
Requires-Dist: progressbar33
|
|
27
|
+
Requires-Dist: biopython>=1.65
|
|
28
|
+
Requires-Dist: datacache>=0.4.4
|
|
29
|
+
Requires-Dist: lxml
|
|
30
|
+
Dynamic: license-file
|
|
31
|
+
|
|
32
|
+
# PepData
|
|
33
|
+
|
|
34
|
+
Look up shipped amino-acid properties and pairwise matrices, encode peptide
|
|
35
|
+
sequences, or load peptide assay tables from IEDB. Property lookups work offline;
|
|
36
|
+
IEDB tables require a download.
|
|
37
|
+
|
|
38
|
+
## Install
|
|
39
|
+
|
|
40
|
+
```sh
|
|
41
|
+
python -m pip install pepdata
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
Python 3.11 or later is required.
|
|
45
|
+
|
|
46
|
+
## Look up a peptide's residue properties
|
|
47
|
+
|
|
48
|
+
```python
|
|
49
|
+
from pepdata.amino_acid_properties import hydropathy
|
|
50
|
+
|
|
51
|
+
peptide = "ACD"
|
|
52
|
+
print([hydropathy[residue] for residue in peptide])
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
```text
|
|
56
|
+
[1.8, 2.5, -3.5]
|
|
57
|
+
```
|
|
58
|
+
|
|
59
|
+
The values come from the shipped residue-property table. The dictionary maps
|
|
60
|
+
single-letter residues to numeric values; it does not predict MHC binding or
|
|
61
|
+
clinical immunogenicity. Use uppercase canonical residue letters. A missing
|
|
62
|
+
letter raises `KeyError`.
|
|
63
|
+
|
|
64
|
+
## Find the interface you need
|
|
65
|
+
|
|
66
|
+
| Task | Module or object |
|
|
67
|
+
| --- | --- |
|
|
68
|
+
| Single-residue properties | `pepdata.amino_acid_properties` |
|
|
69
|
+
| BLOSUM substitution matrices | `pepdata.blosum` |
|
|
70
|
+
| PMBEC and contact tables | `pepdata.pmbec`, `pepdata.residue_contact_energies` |
|
|
71
|
+
| Residue alphabets | `pepdata.amino_acid_alphabet`, `pepdata.reduced_alphabet` |
|
|
72
|
+
| N-gram features | `pepdata.PeptideVectorizer` |
|
|
73
|
+
| MHC-binding assay tables | `pepdata.iedb.mhc` |
|
|
74
|
+
| T-cell assay tables | `pepdata.iedb.tcell` |
|
|
75
|
+
|
|
76
|
+
See [residue and pairwise tables](docs/guides/properties.md), then
|
|
77
|
+
[peptide features and IEDB tables](docs/guides/datasets.md). The
|
|
78
|
+
[API reference](docs/reference.md) follows those same tasks.
|
|
79
|
+
|
|
80
|
+
Older pepdata documentation placed the property tables in `amino_acid` and
|
|
81
|
+
described a `StringTransformer` interface. The property dictionaries are
|
|
82
|
+
in `amino_acid_properties`, and there is no `StringTransformer` class.
|
|
83
|
+
|
|
84
|
+
## Documentation development
|
|
85
|
+
|
|
86
|
+
Install `requirements-docs.txt`, run `./docs.sh`, then `python scripts/check_docs_examples.py`.
|
|
@@ -37,6 +37,9 @@ pepdata/matrices/helix_vs_coil.txt
|
|
|
37
37
|
pepdata/matrices/helix_vs_strand.txt
|
|
38
38
|
pepdata/matrices/pmbec.mat
|
|
39
39
|
pepdata/matrices/strand_vs_coil.txt
|
|
40
|
+
scripts/check_docs_examples.py
|
|
41
|
+
scripts/check_docs_links.py
|
|
42
|
+
tests/conftest.py
|
|
40
43
|
tests/test_amino_acids.py
|
|
41
44
|
tests/test_blosum.py
|
|
42
45
|
tests/test_iedb_alleles.py
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "pepdata"
|
|
7
|
-
requires-python = ">=3.
|
|
7
|
+
requires-python = ">=3.11"
|
|
8
8
|
authors = [{name="Alex Rubinsteyn", email="alex.rubinsteyn@mssm.edu"}]
|
|
9
9
|
description = "Immunological peptide datasets and amino acid properties"
|
|
10
10
|
classifiers = [
|
|
@@ -14,6 +14,10 @@ classifiers = [
|
|
|
14
14
|
"Intended Audience :: Science/Research",
|
|
15
15
|
"License :: OSI Approved :: Apache Software License",
|
|
16
16
|
"Programming Language :: Python",
|
|
17
|
+
"Programming Language :: Python :: 3.11",
|
|
18
|
+
"Programming Language :: Python :: 3.12",
|
|
19
|
+
"Programming Language :: Python :: 3.13",
|
|
20
|
+
"Programming Language :: Python :: 3.14",
|
|
17
21
|
"Topic :: Scientific/Engineering :: Bio-Informatics",
|
|
18
22
|
]
|
|
19
23
|
readme = "README.md"
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
"""Execute documentation examples and compare the printed output."""
|
|
2
|
+
|
|
3
|
+
import contextlib
|
|
4
|
+
import io
|
|
5
|
+
import re
|
|
6
|
+
import sys
|
|
7
|
+
import types
|
|
8
|
+
from pathlib import Path
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def main():
|
|
12
|
+
count = 0
|
|
13
|
+
for path in sorted(Path("docs").rglob("*.md")):
|
|
14
|
+
module = types.ModuleType("docs_example_" + path.stem.replace("-", "_"))
|
|
15
|
+
sys.modules[module.__name__] = module
|
|
16
|
+
blocks = list(re.finditer(r"```(python|text)\n(.*?)\n```", path.read_text(), re.S))
|
|
17
|
+
for index, match in enumerate(blocks):
|
|
18
|
+
if match[1] != "python" or index + 1 == len(blocks) or blocks[index + 1][1] != "text":
|
|
19
|
+
continue
|
|
20
|
+
output = io.StringIO()
|
|
21
|
+
with contextlib.redirect_stdout(output):
|
|
22
|
+
exec(compile(match[2], str(path), "exec"), module.__dict__)
|
|
23
|
+
if index + 1 < len(blocks) and blocks[index + 1][1] == "text":
|
|
24
|
+
expected = blocks[index + 1][2].rstrip()
|
|
25
|
+
actual = output.getvalue().rstrip()
|
|
26
|
+
if actual != expected:
|
|
27
|
+
raise AssertionError(f"{path}: {actual!r} != {expected!r}")
|
|
28
|
+
count += 1
|
|
29
|
+
print(f"Executed {count} documentation examples.")
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
if __name__ == "__main__":
|
|
33
|
+
main()
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
"""Check rendered internal links and fragment targets."""
|
|
2
|
+
from html.parser import HTMLParser
|
|
3
|
+
from pathlib import Path
|
|
4
|
+
from urllib.parse import unquote, urlsplit
|
|
5
|
+
import yaml
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class Page(HTMLParser):
|
|
9
|
+
def __init__(self, text):
|
|
10
|
+
super().__init__()
|
|
11
|
+
self.ids = set()
|
|
12
|
+
self.links = []
|
|
13
|
+
self.feed(text)
|
|
14
|
+
|
|
15
|
+
def handle_starttag(self, tag, attrs):
|
|
16
|
+
attrs = dict(attrs)
|
|
17
|
+
if attrs.get("id"):
|
|
18
|
+
self.ids.add(attrs["id"])
|
|
19
|
+
if tag == "a" and attrs.get("href"):
|
|
20
|
+
self.links.append(attrs["href"])
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
def main():
|
|
24
|
+
root = Path("site").resolve()
|
|
25
|
+
base = urlsplit(yaml.safe_load(Path("mkdocs.yml").read_text())["site_url"]).path.rstrip("/")
|
|
26
|
+
pages = {p.resolve(): Page(p.read_text()) for p in root.rglob("*.html")}
|
|
27
|
+
failures = []
|
|
28
|
+
count = 0
|
|
29
|
+
for source, page in pages.items():
|
|
30
|
+
for href in page.links:
|
|
31
|
+
url = urlsplit(href)
|
|
32
|
+
if url.scheme or url.netloc:
|
|
33
|
+
continue
|
|
34
|
+
path = unquote(url.path)
|
|
35
|
+
if path.startswith("/"):
|
|
36
|
+
if not (path == base or path.startswith(base + "/")):
|
|
37
|
+
continue
|
|
38
|
+
target = (root / path[len(base):].lstrip("/")).resolve()
|
|
39
|
+
else:
|
|
40
|
+
target = (source.parent / path).resolve() if path else source
|
|
41
|
+
if target.is_dir():
|
|
42
|
+
target /= "index.html"
|
|
43
|
+
count += 1
|
|
44
|
+
if not target.is_relative_to(root) or not target.exists():
|
|
45
|
+
failures.append(f"{source.relative_to(root)}: missing {href}")
|
|
46
|
+
elif url.fragment and target in pages and unquote(url.fragment) not in pages[target].ids:
|
|
47
|
+
failures.append(f"{source.relative_to(root)}: missing fragment {href}")
|
|
48
|
+
if failures:
|
|
49
|
+
raise SystemExit("\n".join(failures))
|
|
50
|
+
print(f"Checked {len(pages)} pages and {count} internal links.")
|
|
51
|
+
|
|
52
|
+
|
|
53
|
+
if __name__ == "__main__":
|
|
54
|
+
main()
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
"""Use synthetic IEDB-format fixtures instead of live downloads in unit tests."""
|
|
2
|
+
|
|
3
|
+
import os
|
|
4
|
+
import pytest
|
|
5
|
+
|
|
6
|
+
FIXTURES_DIR = os.path.join(os.path.dirname(__file__), "data")
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
@pytest.fixture(autouse=True)
|
|
10
|
+
def patch_iedb_paths(monkeypatch):
|
|
11
|
+
"""Redirect assay tables and the allele catalogue to bundled fixtures."""
|
|
12
|
+
monkeypatch.setattr(
|
|
13
|
+
"pepdata.iedb.alleles.local_path",
|
|
14
|
+
lambda force_download=False: os.path.join(FIXTURES_DIR, "alleles_test_fixture.xml"),
|
|
15
|
+
)
|
|
16
|
+
monkeypatch.setattr(
|
|
17
|
+
"pepdata.iedb.tcell.local_path",
|
|
18
|
+
lambda auto_download=True: os.path.join(FIXTURES_DIR, "tcell_test_fixture.csv"),
|
|
19
|
+
)
|
|
20
|
+
monkeypatch.setattr(
|
|
21
|
+
"pepdata.iedb.mhc.local_path",
|
|
22
|
+
lambda auto_download=True: os.path.join(FIXTURES_DIR, "mhc_test_fixture.csv"),
|
|
23
|
+
)
|
|
@@ -1,16 +1,5 @@
|
|
|
1
|
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
2
|
-
# you may not use this file except in compliance with the License.
|
|
3
|
-
# You may obtain a copy of the License at
|
|
4
|
-
#
|
|
5
|
-
# http://www.apache.org/licenses/LICENSE-2.0
|
|
6
|
-
#
|
|
7
|
-
# Unless required by applicable law or agreed to in writing, software
|
|
8
|
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
9
|
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
10
|
-
# See the License for the specific language governing permissions and
|
|
11
|
-
# limitations under the License.
|
|
12
|
-
|
|
13
1
|
from pepdata import iedb
|
|
2
|
+
from pepdata.iedb.columns import get_mhc_allele
|
|
14
3
|
|
|
15
4
|
def test_tcell_hla_restrict_a24():
|
|
16
5
|
"""
|
|
@@ -37,13 +26,17 @@ def test_tcell_hla_exclude_a0201():
|
|
|
37
26
|
that allele
|
|
38
27
|
"""
|
|
39
28
|
df_all = iedb.tcell.load_dataframe(nrows=1000)
|
|
40
|
-
|
|
29
|
+
mhc_alleles = get_mhc_allele(df_all)
|
|
30
|
+
assert mhc_alleles is not None, "Could not find MHC allele column"
|
|
31
|
+
assert (mhc_alleles == "HLA-A*02:01").any()
|
|
41
32
|
|
|
42
33
|
df_exclude = iedb.tcell.load_dataframe(
|
|
43
34
|
nrows=1000,
|
|
44
|
-
exclude_hla="HLA-A\*02:01")
|
|
35
|
+
exclude_hla=r"HLA-A\*02:01")
|
|
45
36
|
|
|
46
|
-
|
|
37
|
+
mhc_alleles_filtered = get_mhc_allele(df_exclude)
|
|
38
|
+
assert mhc_alleles_filtered is not None
|
|
39
|
+
n_A0201_entries = (mhc_alleles_filtered == "HLA-A*02:01").sum()
|
|
47
40
|
assert n_A0201_entries == 0, \
|
|
48
41
|
("Not supposed to contain HLA-A*02:01, "
|
|
49
42
|
" but found %d rows of that allele") % n_A0201_entries
|
pepdata-1.2.2/PKG-INFO
DELETED
|
@@ -1,78 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: pepdata
|
|
3
|
-
Version: 1.2.2
|
|
4
|
-
Summary: Immunological peptide datasets and amino acid properties
|
|
5
|
-
Author-email: Alex Rubinsteyn <alex.rubinsteyn@mssm.edu>
|
|
6
|
-
Project-URL: Homepage, https://github.com/openvax/pepdata
|
|
7
|
-
Project-URL: Bug Tracker, https://github.com/openvax/pepdata/issues
|
|
8
|
-
Classifier: Development Status :: 4 - Beta
|
|
9
|
-
Classifier: Environment :: Console
|
|
10
|
-
Classifier: Operating System :: OS Independent
|
|
11
|
-
Classifier: Intended Audience :: Science/Research
|
|
12
|
-
Classifier: License :: OSI Approved :: Apache Software License
|
|
13
|
-
Classifier: Programming Language :: Python
|
|
14
|
-
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
15
|
-
Requires-Python: >=3.9
|
|
16
|
-
Description-Content-Type: text/markdown
|
|
17
|
-
License-File: LICENSE.txt
|
|
18
|
-
Requires-Dist: numpy<3.0.0,>=2.0.0
|
|
19
|
-
Requires-Dist: scipy>=0.9
|
|
20
|
-
Requires-Dist: pandas>=0.17
|
|
21
|
-
Requires-Dist: scikit-learn>=0.14.1
|
|
22
|
-
Requires-Dist: progressbar33
|
|
23
|
-
Requires-Dist: biopython>=1.65
|
|
24
|
-
Requires-Dist: datacache>=0.4.4
|
|
25
|
-
Requires-Dist: lxml
|
|
26
|
-
Dynamic: license-file
|
|
27
|
-
|
|
28
|
-
<a href="https://travis-ci.org/openvax/pepdata">
|
|
29
|
-
<img src="https://travis-ci.org/openvax/pepdata.svg?branch=master" alt="Build Status" />
|
|
30
|
-
</a>
|
|
31
|
-
<a href="https://coveralls.io/github/openvax/pepdata?branch=master">
|
|
32
|
-
<img src="https://coveralls.io/repos/openvax/pepdata/badge.svg?branch=master&service=github" alt="Coverage Status" />
|
|
33
|
-
</a>
|
|
34
|
-
<a href="https://pypi.python.org/pypi/pepdata/">
|
|
35
|
-
<img src="https://img.shields.io/pypi/v/pepdata.svg?maxAge=1000" alt="PyPI" />
|
|
36
|
-
</a>
|
|
37
|
-
|
|
38
|
-
PepData
|
|
39
|
-
=======
|
|
40
|
-
|
|
41
|
-
Formerly a repository for diverse peptide datasets, now only contains the [Immune Epitope Database](http://www.iedb.org) and a variety of amino acid property matrices. This package
|
|
42
|
-
will probably be eventually split and the IEDB portions placed into something
|
|
43
|
-
named `pyiedb`.
|
|
44
|
-
|
|
45
|
-
**Amino Acid Properties**
|
|
46
|
-
|
|
47
|
-
The `amino_acid` module contains a variety of physical/chemical properties for both single amino residues and interactions between pairs of residues.
|
|
48
|
-
|
|
49
|
-
Single residue feature tables are parsed into `StringTransformer` objects, which can be treated as dictionaries or will vectorize a string when you call their method `transform_string`.
|
|
50
|
-
|
|
51
|
-
Examples of single residue features:
|
|
52
|
-
- `hydropathy`
|
|
53
|
-
- `volume`
|
|
54
|
-
- `polarity`
|
|
55
|
-
- `pK_side_chain`
|
|
56
|
-
- `prct_exposed_residues`
|
|
57
|
-
- `hydrophilicity`
|
|
58
|
-
- `accessible_surface_area`
|
|
59
|
-
- `refractivity`
|
|
60
|
-
- `local_flexibility`
|
|
61
|
-
- `accessible_surface_area_folded`
|
|
62
|
-
- `alpha_helix_score` (Chou-Fasman)
|
|
63
|
-
- `beta_sheet_score` (Chou-Fasman)
|
|
64
|
-
- `turn_score` (Chou-Fasman)
|
|
65
|
-
|
|
66
|
-
Pairwise interaction tables are parsed into nested dictionaries, so that the interaction between amino acids `x` and `y` can be determined from `d[x][y]`.
|
|
67
|
-
|
|
68
|
-
Pairwise interaction dictionaries:
|
|
69
|
-
- `strand_vs_coil` (and its transpose `coil_vs_strand`)
|
|
70
|
-
- `helix_vs_strand` (and its transpose `strand_vs_helix`)
|
|
71
|
-
- `helix_vs_coil` (and its transpose `coil_vs_helix`)
|
|
72
|
-
- `blosum30`
|
|
73
|
-
- `blosum50`
|
|
74
|
-
- `blosum62`
|
|
75
|
-
|
|
76
|
-
There is also a function to parse the coefficients of the [PMBEC similarity matrix](http://www.biomedcentral.com/1471-2105/10/394), though this currently lives in the separate `pmbec` module.
|
|
77
|
-
|
|
78
|
-
|
pepdata-1.2.2/README.md
DELETED
|
@@ -1,51 +0,0 @@
|
|
|
1
|
-
<a href="https://travis-ci.org/openvax/pepdata">
|
|
2
|
-
<img src="https://travis-ci.org/openvax/pepdata.svg?branch=master" alt="Build Status" />
|
|
3
|
-
</a>
|
|
4
|
-
<a href="https://coveralls.io/github/openvax/pepdata?branch=master">
|
|
5
|
-
<img src="https://coveralls.io/repos/openvax/pepdata/badge.svg?branch=master&service=github" alt="Coverage Status" />
|
|
6
|
-
</a>
|
|
7
|
-
<a href="https://pypi.python.org/pypi/pepdata/">
|
|
8
|
-
<img src="https://img.shields.io/pypi/v/pepdata.svg?maxAge=1000" alt="PyPI" />
|
|
9
|
-
</a>
|
|
10
|
-
|
|
11
|
-
PepData
|
|
12
|
-
=======
|
|
13
|
-
|
|
14
|
-
Formerly a repository for diverse peptide datasets, now only contains the [Immune Epitope Database](http://www.iedb.org) and a variety of amino acid property matrices. This package
|
|
15
|
-
will probably be eventually split and the IEDB portions placed into something
|
|
16
|
-
named `pyiedb`.
|
|
17
|
-
|
|
18
|
-
**Amino Acid Properties**
|
|
19
|
-
|
|
20
|
-
The `amino_acid` module contains a variety of physical/chemical properties for both single amino residues and interactions between pairs of residues.
|
|
21
|
-
|
|
22
|
-
Single residue feature tables are parsed into `StringTransformer` objects, which can be treated as dictionaries or will vectorize a string when you call their method `transform_string`.
|
|
23
|
-
|
|
24
|
-
Examples of single residue features:
|
|
25
|
-
- `hydropathy`
|
|
26
|
-
- `volume`
|
|
27
|
-
- `polarity`
|
|
28
|
-
- `pK_side_chain`
|
|
29
|
-
- `prct_exposed_residues`
|
|
30
|
-
- `hydrophilicity`
|
|
31
|
-
- `accessible_surface_area`
|
|
32
|
-
- `refractivity`
|
|
33
|
-
- `local_flexibility`
|
|
34
|
-
- `accessible_surface_area_folded`
|
|
35
|
-
- `alpha_helix_score` (Chou-Fasman)
|
|
36
|
-
- `beta_sheet_score` (Chou-Fasman)
|
|
37
|
-
- `turn_score` (Chou-Fasman)
|
|
38
|
-
|
|
39
|
-
Pairwise interaction tables are parsed into nested dictionaries, so that the interaction between amino acids `x` and `y` can be determined from `d[x][y]`.
|
|
40
|
-
|
|
41
|
-
Pairwise interaction dictionaries:
|
|
42
|
-
- `strand_vs_coil` (and its transpose `coil_vs_strand`)
|
|
43
|
-
- `helix_vs_strand` (and its transpose `strand_vs_helix`)
|
|
44
|
-
- `helix_vs_coil` (and its transpose `coil_vs_helix`)
|
|
45
|
-
- `blosum30`
|
|
46
|
-
- `blosum50`
|
|
47
|
-
- `blosum62`
|
|
48
|
-
|
|
49
|
-
There is also a function to parse the coefficients of the [PMBEC similarity matrix](http://www.biomedcentral.com/1471-2105/10/394), though this currently lives in the separate `pmbec` module.
|
|
50
|
-
|
|
51
|
-
|
|
@@ -1,78 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: pepdata
|
|
3
|
-
Version: 1.2.2
|
|
4
|
-
Summary: Immunological peptide datasets and amino acid properties
|
|
5
|
-
Author-email: Alex Rubinsteyn <alex.rubinsteyn@mssm.edu>
|
|
6
|
-
Project-URL: Homepage, https://github.com/openvax/pepdata
|
|
7
|
-
Project-URL: Bug Tracker, https://github.com/openvax/pepdata/issues
|
|
8
|
-
Classifier: Development Status :: 4 - Beta
|
|
9
|
-
Classifier: Environment :: Console
|
|
10
|
-
Classifier: Operating System :: OS Independent
|
|
11
|
-
Classifier: Intended Audience :: Science/Research
|
|
12
|
-
Classifier: License :: OSI Approved :: Apache Software License
|
|
13
|
-
Classifier: Programming Language :: Python
|
|
14
|
-
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
15
|
-
Requires-Python: >=3.9
|
|
16
|
-
Description-Content-Type: text/markdown
|
|
17
|
-
License-File: LICENSE.txt
|
|
18
|
-
Requires-Dist: numpy<3.0.0,>=2.0.0
|
|
19
|
-
Requires-Dist: scipy>=0.9
|
|
20
|
-
Requires-Dist: pandas>=0.17
|
|
21
|
-
Requires-Dist: scikit-learn>=0.14.1
|
|
22
|
-
Requires-Dist: progressbar33
|
|
23
|
-
Requires-Dist: biopython>=1.65
|
|
24
|
-
Requires-Dist: datacache>=0.4.4
|
|
25
|
-
Requires-Dist: lxml
|
|
26
|
-
Dynamic: license-file
|
|
27
|
-
|
|
28
|
-
<a href="https://travis-ci.org/openvax/pepdata">
|
|
29
|
-
<img src="https://travis-ci.org/openvax/pepdata.svg?branch=master" alt="Build Status" />
|
|
30
|
-
</a>
|
|
31
|
-
<a href="https://coveralls.io/github/openvax/pepdata?branch=master">
|
|
32
|
-
<img src="https://coveralls.io/repos/openvax/pepdata/badge.svg?branch=master&service=github" alt="Coverage Status" />
|
|
33
|
-
</a>
|
|
34
|
-
<a href="https://pypi.python.org/pypi/pepdata/">
|
|
35
|
-
<img src="https://img.shields.io/pypi/v/pepdata.svg?maxAge=1000" alt="PyPI" />
|
|
36
|
-
</a>
|
|
37
|
-
|
|
38
|
-
PepData
|
|
39
|
-
=======
|
|
40
|
-
|
|
41
|
-
Formerly a repository for diverse peptide datasets, now only contains the [Immune Epitope Database](http://www.iedb.org) and a variety of amino acid property matrices. This package
|
|
42
|
-
will probably be eventually split and the IEDB portions placed into something
|
|
43
|
-
named `pyiedb`.
|
|
44
|
-
|
|
45
|
-
**Amino Acid Properties**
|
|
46
|
-
|
|
47
|
-
The `amino_acid` module contains a variety of physical/chemical properties for both single amino residues and interactions between pairs of residues.
|
|
48
|
-
|
|
49
|
-
Single residue feature tables are parsed into `StringTransformer` objects, which can be treated as dictionaries or will vectorize a string when you call their method `transform_string`.
|
|
50
|
-
|
|
51
|
-
Examples of single residue features:
|
|
52
|
-
- `hydropathy`
|
|
53
|
-
- `volume`
|
|
54
|
-
- `polarity`
|
|
55
|
-
- `pK_side_chain`
|
|
56
|
-
- `prct_exposed_residues`
|
|
57
|
-
- `hydrophilicity`
|
|
58
|
-
- `accessible_surface_area`
|
|
59
|
-
- `refractivity`
|
|
60
|
-
- `local_flexibility`
|
|
61
|
-
- `accessible_surface_area_folded`
|
|
62
|
-
- `alpha_helix_score` (Chou-Fasman)
|
|
63
|
-
- `beta_sheet_score` (Chou-Fasman)
|
|
64
|
-
- `turn_score` (Chou-Fasman)
|
|
65
|
-
|
|
66
|
-
Pairwise interaction tables are parsed into nested dictionaries, so that the interaction between amino acids `x` and `y` can be determined from `d[x][y]`.
|
|
67
|
-
|
|
68
|
-
Pairwise interaction dictionaries:
|
|
69
|
-
- `strand_vs_coil` (and its transpose `coil_vs_strand`)
|
|
70
|
-
- `helix_vs_strand` (and its transpose `strand_vs_helix`)
|
|
71
|
-
- `helix_vs_coil` (and its transpose `coil_vs_helix`)
|
|
72
|
-
- `blosum30`
|
|
73
|
-
- `blosum50`
|
|
74
|
-
- `blosum62`
|
|
75
|
-
|
|
76
|
-
There is also a function to parse the coefficients of the [PMBEC similarity matrix](http://www.biomedcentral.com/1471-2105/10/394), though this currently lives in the separate `pmbec` module.
|
|
77
|
-
|
|
78
|
-
|
|
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
|
|
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
|
|
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
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|