molearn

molearn is a generative neural network learning protein conformational spaces from example protein conformations generated by molecular dynamics simulations, or experimentally.

AVAILABILITY

molearn is available for download on our Github page. For UNIX based systems, installation via conda-forge is also available.

Jupyter notebook tutorials showing how a trained molearn neural network can be used are available here.

REFERENCES

If you use molearn in your work, please cite:

S.C. Musson and M.T. Degiacomi (2023). Molearn: a Python package streamlining the design of generative models of biomolecular dynamics. Journal of Open Source Software, 8(89), 5523

Theory and benchmarks of neural networks trained on protein conformational ensembles are found here:

V.K. Ramaswamy, S.C. Musson, C.G. Willcocks, M.T. Degiacomi (2021). Learning protein conformational space with convolutions and latent interpolations, Physical Review X 11 (primary citation)

M.T. Degiacomi (2019). Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space, Structure