The SPP 2363, entitled "Use and Development of Machine Learning for Molecular Applications - Molecular Machine Learning", is an interdisciplinary and collaborative Priority Program funded by the DFG. The goals of the program include the development of new molecular representations, the establishment of machine learning as a tool for theoretical and organic chemistry, and the application of machine learning for medicinal chemistry and drug design. These objectives will be based on the generation and evaluation of high quality data sets and the utilization and development of modern and explainable machine learning algorithms.
SPP 2363 - Molecular Machine Learning
This is the Github of the SPP 2363, entitled "Use and Development of Machine Learning for Molecular Applications - Molecular Machine Learning".
Pinned Loading
Repositories
Showing 10 of 22 repositories
- QeMFi Public Forked from vivinvinod/QeMFi
Scripts related to "CheMFi: A Multifidelity Dataset of Quantum Chemical Properties of Diverse Molecules". includes MFML learning curves, ORCA scripts etc.
SPP2363/QeMFi’s past year of commit activity - mlipx Public Forked from basf/mlipx
Machine-Learned Interatomic Potential eXploration (mlipx) is designed at BASF for evaluating machine-learned interatomic potentials (MLIPs). It offers a growing set of evaluation methods alongside powerful visualization and comparison tools.
SPP2363/mlipx’s past year of commit activity - MFDeltaML Public Forked from vivinvinod/MFDeltaML
Scripts for MFDeltaML and data efficiency benchmarks of DeltaML, MFML, o-MFML, MFDeltaML, o-MFDeltaML on the CheMFi dataset.
SPP2363/MFDeltaML’s past year of commit activity - MFML_DataHierarchy Public Forked from vivinvinod/MFML_DataHierarchy
Scripts for multifidelity models used to assess data hierarchy scaling for the prediction of excitation energies of molecules. This also includes scripts to generate the newly introduced Gamma curve.
SPP2363/MFML_DataHierarchy’s past year of commit activity - NonNestedMFML Public Forked from vivinvinod/NonNestedMFML
Non nested training data approach to multifidelity machine learning. Includes scripts run to test this on the CheMFi dataset.
SPP2363/NonNestedMFML’s past year of commit activity - apax Public Forked from apax-hub/apax
A flexible and performant framework for training machine learning potentials.
SPP2363/apax’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…