Merge pull request #40 from theochem/update_license

Clean up and fix PyPI packaging configurations

Author: FanwangM

MANIFEST.in

@@ -1,4 +1,4 @@
-# Explicitly include only what we want
+# Only include essential files
 include README.md
 include LICENSE
 include CITATION.cff
@@ -10,16 +10,3 @@ recursive-include B3DB *.tsv *.tsv.gz *.csv
 
 # Exclude everything else
 global-exclude *
-exclude *.pyc
-exclude __pycache__
-exclude *.egg-info
-exclude .git*
-exclude .github
-exclude build
-exclude dist
-exclude .tox
-exclude .pytest_cache
-exclude .coverage
-exclude htmlcov
-exclude .mypy_cache
-exclude .ruff_cache

README.md

@@ -139,18 +139,3 @@ pip install -r requirements.txt
 
 The materials and data under this repo are distributed under the
 [CC0 Licence](http://creativecommons.org/publicdomain/zero/1.0/).
-
-## Update: New External Dataset Available
-
-We’ve expanded the B3DB dataset by adding a new file: `B3DB_classification_external.tsv`. This file introduces additional compounds (171 BBB+ and 4 BBB-) that were not present in the original B3DB dataset. These compounds were carefully selected and incorporated to further enrich B3DB.
-
-### Usage
-
-To load and work with the new classification data in Python, you can use the following code snippet:
-
-```python
-import pandas as pd
-
-# Load the new external classification dataset
-external_classification_data = pd.read_csv("B3DB/B3DB_classification_external.tsv", sep="\t")
-```

data_curation/README.md

@@ -1,83 +1,4 @@
-# About *B3DB*
-
-In this repo, we present a large benchmark dataset, [Blood-Brain Barrier Database (B3DB)](https://www.nature.com/articles/s41597-021-01069-5), compiled
-from 50 published resources (as summarized at
-[raw_data/raw_data_summary.tsv](raw_data/raw_data_summary.tsv)) and categorized based on
-the consistency between different experimental references/measurements. This dataset was [published in Scientific Data](https://www.nature.com/articles/s41597-021-01069-5) and this repository is occasionally uploaded with new experimental data. Scientists who would like to contribute data should contact the database's maintainers (e.g., by creating a new Issue in this database).
-
-A subset of the
-molecules in B3DB has numerical `logBB` values (1058 compounds), while the whole dataset
-has categorical (BBB+ or BBB-) BBB permeability labels (7807 compounds). Some physicochemical properties
-of the molecules are also provided.
-
-## Citation
-
-Please use the following citation in any publication using our *B3DB* dataset:
-
-```md
-@article{Meng_A_curated_diverse_2021,
-author = {Meng, Fanwang and Xi, Yang and Huang, Jinfeng and Ayers, Paul W.},
-doi = {10.1038/s41597-021-01069-5},
-journal = {Scientific Data},
-number = {289},
-title = {A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors},
-volume = {8},
-year = {2021},
-url = {https://www.nature.com/articles/s41597-021-01069-5},
-publisher = {Springer Nature}
-}
-```
-
-## Features of *B3DB*
-
-1. The largest dataset with numerical and categorical values for Blood-Brain Barrier small molecules
-    (to the best of our knowledge, as of February 25, 2021).
-
-2. Inclusion of stereochemistry information with isomeric SMILES with chiral specifications if
-    available. Otherwise, canonical SMILES are used.
-
-3. Characterization of uncertainty of experimental measurements by grouping the collected molecular
-    data records.
-
-4. Extended datasets for numerical and categorical data with precomputed physicochemical properties
-    using [mordred](https://github.com/mordred-descriptor/mordred).
-
-## Usage
-
-There are two types of dataset in [B3DB](B3DB), [regression data](B3DB/B3DB_regression.tsv)
-and [classification data](B3DB/B3DB_classification.tsv) and they can be loaded simply using *pandas*. For example
-
-```python
-import pandas as pd
-
-# load regression dataset
-regression_data = pd.read_csv("B3DB/B3DB_regression.tsv",
-                              sep="\t")
-
-# load classification dataset
-classification_data = pd.read_csv("B3DB/B3DB_classification.tsv",
-                                  sep="\t")
-
-# load extended regression dataset
-regression_data_extended = pd.read_csv("B3DB/B3DB_regression_extended.tsv.gz",
-                                       sep="\t", compression="gzip")
-
-# load extended classification dataset
-classification_data_extended = pd.read_csv("B3DB/B3DB_classification_extended.tsv.gz",
-                                           sep="\t", compression="gzip")
-
-```
-
-We also have three examples to show how to use our dataset,
-[numerical_data_analysis.ipynb](notebooks/numerical_data_analysis.ipynb),
-[PCA_projection_fingerprint.ipynb](notebooks/PCA_projection_fingerprint.ipynb) and
-[PCA_projection_descriptors.ipynb](notebooks/PCA_projection_descriptors.ipynb).
-[PCA_projection_descriptors.ipynb](notebooks/PCA_projection_descriptors.ipynb) uses precomputed
-chemical descriptors for visualization of chemical space of `B3DB`, and can be used directly
-using *MyBinder*,
-[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/theochem/B3DB/main?filepath=notebooks%2FPCA_projection_descriptors.ipynb).
-Due to the difficulty of installing `RDKit` in *MyBinder*, only `PCA_projection_descriptors.
-ipynb` is set up in *MyBinder*.
+# Data Curation Process of B3DB
 
 ## Working environment setting up
 
@@ -136,21 +57,3 @@ pip install -r requirements.txt
 ```
 
 `ALOGPS` version 2.1 can be accessed at http://www.vcclab.org/lab/alogps/.
-
-The materials and data under this repo are distributed under the
-[CC0 Licence](http://creativecommons.org/publicdomain/zero/1.0/).
-
-## Update: New External Dataset Available
-
-We’ve expanded the B3DB dataset by adding a new file: `B3DB_classification_external.tsv`. This file introduces additional compounds (171 BBB+ and 4 BBB-) that were not present in the original B3DB dataset. These compounds were carefully selected and incorporated to further enrich B3DB.
-
-### Usage
-
-To load and work with the new classification data in Python, you can use the following code snippet:
-
-```python
-import pandas as pd
-
-# Load the new external classification dataset
-external_classification_data = pd.read_csv("B3DB/B3DB_classification_external.tsv", sep="\t")
-```

pyproject.toml

@@ -19,7 +19,7 @@ description = "A rich molecule dataset for Blood-Brain Barrier (BBB) permeabilit
 readme = {file = 'README.md', content-type='text/markdown'}
 requires-python = ">=3.9"
 # "LICENSE" is name of the license file, which must be in root of project folder
-license = {file = "LICENSE"}
+license = "CC0-1.0"
 authors = [
     {name = "QC-Devs Community", email = "qcdevs@gmail.com"},
 ]
@@ -37,7 +37,6 @@ keywords = [
 classifiers = [
     "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
-    "License :: CC0 1.0 Universal (CC0 1.0) Public Domain Dedication",
     "Natural Language :: English",
     "Operating System :: MacOS",
     "Operating System :: Microsoft :: Windows",
@@ -51,6 +50,7 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
     "Topic :: Scientific/Engineering",
     "Topic :: Scientific/Engineering :: Chemistry",
 ]
@@ -83,7 +83,7 @@ build-backend = "setuptools.build_meta"
 
 [tool.setuptools.dynamic]
 dependencies = {file = ["requirements.txt"]}
-optional-dependencies = {dev = { file = ["requirements_dev.txt"] }}
+# optional-dependencies = {dev = { file = ["requirements_dev.txt"] }}
 
 [tool.setuptools_scm]
 # can be empty if no extra settings are needed, presence enables setuptools-scm
@@ -95,15 +95,11 @@ include-package-data = true
 # This just means it's safe to zip up the bdist
 zip-safe = true
 
-# Non-code data that should be included in the package source code
-# https://setuptools.pypa.io/en/latest/userguide/datafiles.html
-[tool.setuptools.package-data]
-B3DB = ["*.csv", "*.tsv", "*.tsv.gz"]
-
 # Python modules and packages that are included in the
 # distribution package (and therefore become importable)
 [tool.setuptools.packages.find]
-where = ["B3DB"]
+where = ["."]
+include = ["B3DB"]
 exclude = [
     "*/*/tests",
     "tests_*",
@@ -114,8 +110,44 @@ exclude = [
     "grouping",
     "preprocessing",
     "raw_data",
+    "data_curation/**/*",
+    "notebooks/**/*",
+]
+
+# Non-code data that should be included in the package source code
+# https://setuptools.pypa.io/en/latest/userguide/datafiles.html
+[tool.setuptools.package-data]
+B3DB = ["*.csv", "*.tsv", "*.tsv.gz"]
+
+
+
+
+
+[tool.setuptools.exclude-package-data]
+# exclude all files in data_curation folder from all packages
+"*" = [
+    "data_curation/*",
+    "data_curation/**/*",
+    "notebooks/*",
+    "notebooks/**/*",
+    "*.pyc",
+    "__pycache__/*",
+    "*.egg-info/*",
+    ".git*",
+    ".github/*",
+    "build/*",
+    "dist/*",
+    ".tox/*",
+    ".pytest_cache/*",
+    ".coverage",
+    "htmlcov/*",
+    ".mypy_cache/*",
+    ".ruff_cache/*",
 ]
 
+
+
+
 [tool.black]
 line-length = 100
 
@@ -269,10 +301,10 @@ markers = [
 # Configuration for coverage.py
 [tool.coverage.run]
 # files or directories to exclude from coverage calculations
-omit = [
-    'B3DB/measures/tests/*',
-    'B3DB/methods/tests/*',
-]
+# omit = [
+#     'B3DB/measures/tests/*',
+#     'B3DB/methods/tests/*',
+# ]
 
 
 # Configuration for vulture