Deepchem CGCNN#

We use the default Deepchem implementation of `Crystalgraph Convolutional Neural Networks (CGCNN)<https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.120.145301>`_. However, we simplify the edges by using the VESTA bond heuristic and not using a distance-based edge feature vector.

Model card#

Feature set description#

What features are used?#

We use the default atom.json, which is a one-hot encoding of the atom types

Why are the features informative?#

The features uniquely identify the atoms in the crystal structure. Beyond this, only the connectivity is used.

Why do the features not leak information?#

Because the input data for the model only contain structure information (actually, parts of it, i.e., the Cartesian coordinates aren’t even provided to the model).

Will the features be accessible in real-world test applications?#

Data split#

Describe preprocessing steps and how data leakage is avoided#

We did not perform any preprocessing.

Describe the feature selection steps and how data leakage is avoided#

We did not perform feature selection.

Describe the model selection steps and how data leakage is avoided#

We did not perform model selection.

Metric card#

Regression Metrics: deepchem-cgcnn-vesta-edges Rden-CGnK20220817012931 ../../../_images/arrow-right-circle.svg
start_time: 2022-08-17 01:29:31.619551+00:00
end_time: 2022-08-17 02:40:52.319336+00:00
version: v0.0.1
features: n/a
name: deepchem-cgcnn-vesta-edges
task: BenchTaskEnum.pbe_bandgap_id
model_type: CGCNN
reference: None
implementation: None
mofdscribe_version: 0.0.1-dev
mean_squared_error: 0.4
mean_absolute_error: 0.49
r2_score: 0.71
max_error: 2.65
mean_absolute_percentage_error: 0.99
top_5_in_top_5: 0
top_10_in_top_10: 0
top_50_in_top_50: 0
top_100_in_top_100: 0
top_500_in_top_500: 1
session_info: {'packages': {'alabaster': '0.7.12', 'alembic': '1.8.1', 'ansicolors': '1.1.8', 'anyio': '3.5.0', 'appdirs': '1.4.4', 'appnope': '0.1.3', 'argon2-cffi': '21.3.0', 'argon2-cffi-bindings': '21.2.0', 'ase': '3.22.1', 'asttokens': '2.0.5', 'attrs': '22.1.0', 'autopage': '0.5.1', 'average-minimum-distance': '1.3.0', 'Babel': '2.9.1', 'backcall': '0.2.0', 'backports.cached-property': '1.0.2', 'bandit': '1.7.4', 'beautifulsoup4': '4.11.1', 'black': '22.6.0', 'bleach': '5.0.1', 'bokeh': '2.4.3', 'brotlipy': '0.7.0', 'bump2version': '1.0.1', 'bumpversion': '0.6.0', 'catboost': '1.0.6', 'certifi': '2022.6.15', 'cffi': '1.15.1', 'cfgv': '3.3.1', 'charset-normalizer': '2.1.0', 'click': '8.1.3', 'cliff': '3.10.1', 'cloudpickle': '2.1.0', 'cmaes': '0.8.2', 'cmd2': '2.4.2', 'colorcet': '3.0.0', 'colorlog': '6.6.0', 'cryptography': '37.0.1', 'cycler': '0.11.0', 'dabest': '0.3.1', 'darglint': '1.8.1', 'debugpy': '1.6.2', 'decorator': '5.1.1', 'deepchem': '2.6.1.dev20220119163852', 'defusedxml': '0.7.1', 'dgl': '0.9.0', 'dill': '0.3.5.1', 'diode': '1.0.1', 'dionysus': '2.0.8', 'distlib': '0.3.5', 'docker-pycreds': '0.4.0', 'docutils': '0.19', 'dscribe': '1.2.2', 'element-coder': '0.0.5', 'entrypoints': '0.4', 'esbonio': '0.14.0', 'et-xmlfile': '1.1.0', 'executing': '0.9.1', 'fastjsonschema': '2.16.1', 'filelock': '3.7.1', 'flake8': '4.0.1', 'flake8-bandit': '3.0.0', 'flake8-black': '0.3.3', 'flake8-bugbear': '22.7.1', 'flake8-colors': '0.1.9', 'flake8-docstrings': '1.6.0', 'flake8-isort': '4.2.0', 'flake8-polyfill': '1.0.2', 'flake8-print': '5.0.0', 'fonttools': '4.34.4', 'furo': '2022.6.21', 'future': '0.18.2', 'gitdb': '4.0.9', 'GitPython': '3.1.27', 'graphviz': '0.20.1', 'greenlet': '1.1.2', 'h5py': '3.7.0', 'holoviews': '1.15.0', 'hpsklearn': '1.0.3', 'hyperopt': '0.2.7', 'identify': '2.5.2', 'idna': '3.3', 'imagesize': '1.4.1', 'importlib-metadata': '4.12.0', 'importlib-resources': '5.9.0', 'iniconfig': '1.1.1', 'ipykernel': '6.15.1', 'ipython': '8.4.0', 'ipython-genutils': '0.2.0', 'ipywidgets': '7.7.1', 'isort': '4.3.21', 'jedi': '0.18.1', 'jellyfish': '0.9.0', 'Jinja2': '3.1.2', 'joblib': '1.1.0', 'json5': '0.9.6', 'jsonpickle': '2.2.0', 'jsonpointer': '2.3', 'jsonschema': '3.2.0', 'jupyter-client': '7.3.4', 'jupyter-core': '4.11.1', 'jupyter-server': '1.18.1', 'jupyterlab': '3.4.4', 'jupyterlab-pygments': '0.2.2', 'jupyterlab-server': '2.12.0', 'jupyterlab-widgets': '1.1.1', 'kiwisolver': '1.4.4', 'latexcodec': '2.0.1', 'lightgbm': '3.3.2', 'llvmlite': '0.39.0', 'loguru': '0.6.0', 'LovelyPlots': '0.0.26', 'lqrt': '0.3.3', 'Mako': '1.2.1', 'Markdown': '3.4.1', 'MarkupSafe': '2.1.1', 'matminer': '0.7.3', 'matplotlib': '3.5.2', 'matplotlib-inline': '0.1.3', 'mccabe': '0.6.1', 'mistune': '0.8.4', 'mof-pricer': '0.1.0', 'mofchecker': '0.9.3', 'mofdscribe': '0.0.1.dev0', 'moffragmentor': '0.0.1.dev0', 'molecule-tda': '0.1.0', 'moleculetda': '0.1.0', 'moltda': '0.1.0', 'monty': '2022.4.26', 'more-itertools': '8.13.0', 'mpmath': '1.2.1', 'multiprocess': '0.70.13', 'munkres': '1.1.4', 'mypy-extensions': '0.4.3', 'nb-conda': '2.2.1', 'nb-conda-kernels': '2.3.1', 'nbclassic': '0.3.5', 'nbclient': '0.6.6', 'nbconvert': '6.5.0', 'nbformat': '5.4.0', 'nest-asyncio': '1.5.5', 'networkx': '2.8.5', 'nglview': '3.0.3', 'nodeenv': '1.7.0', 'notebook': '6.4.12', 'numba': '0.56.0', 'numpy': '1.21.0', 'openpyxl': '3.0.10', 'optuna': '2.10.1', 'packaging': '21.3', 'palettable': '3.3.0', 'pandas': '1.4.3', 'pandocfilters': '1.5.0', 'panel': '0.13.1', 'param': '1.12.2', 'parso': '0.8.3', 'pathspec': '0.9.0', 'pathtools': '0.1.2', 'pbr': '5.9.0', 'pep8-naming': '0.13.1', 'pervect': '0.0.2', 'pexpect': '4.8.0', 'pickleshare': '0.7.5', 'Pillow': '9.2.0', 'Pint': '0.19.2', 'pip': '22.1.2', 'pkgutil-resolve-name': '1.3.10', 'platformdirs': '2.5.2', 'plotly': '5.9.0', 'pluggy': '1.0.0', 'POT': '0.8.2', 'pre-commit': '2.20.0', 'prettytable': '3.3.0', 'progressbar2': '4.0.0', 'prometheus-client': '0.14.1', 'promise': '2.3', 'prompt-toolkit': '3.0.30', 'protobuf': '3.20.1', 'psutil': '5.9.1', 'ptyprocess': '0.7.0', 'PubChemPy': '1.0.4', 'pure-eval': '0.2.2', 'py': '1.11.0', 'py4j': '0.10.9.5', 'pybind11': '2.10.0', 'pybtex': '0.24.0', 'pycairo': '1.21.0', 'pyclustering': '0.10.1.2', 'pycodestyle': '2.8.0', 'pycparser': '2.21', 'pyct': '0.4.8', 'pydantic': '1.9.1', 'pydata-sphinx-theme': '0.8.1', 'pydocstyle': '6.1.1', 'pyeqeq': '0.0.9', 'pyflakes': '2.4.0', 'pygls': '0.12.1', 'Pygments': '2.12.0', 'pymatgen': '2022.7.25', 'pymongo': '4.2.0', 'pynndescent': '0.5.7', 'pyOpenSSL': '22.0.0', 'pyparsing': '3.0.9', 'pyperclip': '1.8.2', 'pyrsistent': '0.18.1', 'PySocks': '1.7.1', 'pyspellchecker': '0.6.3', 'pystow': '0.4.6', 'pytest': '7.1.2', 'python-dateutil': '2.8.2', 'python-utils': '3.3.3', 'pytz': '2022.1', 'pyviz-comms': '2.2.0', 'PyYAML': '6.0', 'pyzmq': '23.2.0', 'rdkit': '2022.3.4', 'reportlab': '3.5.68', 'requests': '2.28.1', 'requests-file': '1.5.1', 'ruamel.yaml': '0.17.21', 'ruamel.yaml.clib': '0.2.6', 'SciencePlots': '1.0.9', 'scikit-learn': '1.1.1', 'scikit-spatial': '6.4.1', 'scipy': '1.9.0', 'sciris': '1.3.3', 'seaborn': '0.11.2', 'Send2Trash': '1.8.0', 'sentry-sdk': '1.9.3', 'session-info': '1.0.0', 'setproctitle': '1.3.2', 'setuptools': '61.2.0', 'shortuuid': '1.0.9', 'six': '1.16.0', 'smmap': '5.0.0', 'sniffio': '1.2.0', 'snowballstemmer': '2.2.0', 'soupsieve': '2.3.2.post1', 'sparse': '0.13.0', 'spglib': '1.16.5', 'Sphinx': '5.1.1', 'sphinx-autodoc-typehints': '1.19.1', 'sphinx-automodapi': '0.14.1', 'sphinx-basic-ng': '0.0.1a12', 'sphinx-book-theme': '0.3.3', 'sphinx-click': '4.3.0', 'sphinx-copybutton': '0.5.0', 'sphinx-data-viewer': '0.1.2', 'sphinx-immaterial': '0.8.1', 'sphinx-jsonschema': '1.15', 'sphinx-needs': '1.0.1', 'sphinx-pydantic': '0.1.1', 'sphinxcontrib-applehelp': '1.0.2', 'sphinxcontrib-devhelp': '1.0.2', 'sphinxcontrib-htmlhelp': '2.0.0', 'sphinxcontrib-jsmath': '1.0.1', 'sphinxcontrib-katex': '0.8.6', 'sphinxcontrib-needs': '0.7.9', 'sphinxcontrib-plantuml': '0.24', 'sphinxcontrib-qthelp': '1.0.3', 'sphinxcontrib-serializinghtml': '1.1.5', 'SQLAlchemy': '1.4.39', 'stack-data': '0.3.0', 'stdlib-list': '0.8.0', 'stevedore': '4.0.0', 'structuregraph-helpers': '0.0.8', 'superpose3d': '1.4.1', 'sympy': '1.10.1', 'tabulate': '0.8.10', 'tenacity': '8.0.1', 'terminado': '0.15.0', 'testpath': '0.6.0', 'threadpoolctl': '3.1.0', 'timeout-decorator': '0.5.0', 'tinycss2': '1.1.1', 'toml': '0.10.2', 'tomli': '2.0.1', 'torch': '1.11.0', 'tornado': '6.2', 'tox': '3.25.1', 'tqdm': '4.64.0', 'traitlets': '5.3.0', 'typeguard': '2.13.3', 'typing-extensions': '4.1.1', 'umap-learn': '0.5.3', 'uncertainties': '3.1.7', 'unicodedata2': '14.0.0', 'urllib3': '1.26.11', 'virtualenv': '20.16.2', 'wandb': '0.13.1', 'watermark': '2.3.1', 'wcwidth': '0.2.5', 'webencodings': '0.5.1', 'websocket-client': '0.58.0', 'wheel': '0.37.1', 'widgetsnbextension': '3.6.1', 'xgboost': '1.6.1', 'XlsxWriter': '3.0.3', 'zipp': '3.8.1'}, 'system': {'OS Version': 'Darwin 21.4.0', 'Executable': '/Users/kevinmaikjablonka/miniconda3/envs/mofdscribe/bin/python', 'Build Date': 'Mar 25 2022 06:05:16', 'Compiler': 'Clang 12.0.1 ', 'Python API': 1013}}