Published November 19, 2021
| Version v0.2.0
Software
Open
gitter-lab/nn4dms: Version 0.2.0
Authors/Creators
Description
- Add notebook with the number of trainable parameters in each model
- Add notebook showing how to visualize the latent space of a model with UMAP
- Add notebook and code for GB1 sequence design and corresponding outputs
- Add notebook and support for mutation- and position-based data splits
- Add additional data splits: main experiment replicates, reduced training set sizes, mutation extrapolation, position extrapolation
- Update conda environments
Files
gitter-lab/nn4dms-v0.2.0.zip
Additional details
Related works
- Is supplement to
- https://github.com/gitter-lab/nn4dms/tree/v0.2.0 (URL)
- Preprint: 10.1101/2020.10.25.353946 (DOI)
References
- Neural networks to learn protein sequence-function relationships from deep mutational scanning data. Sam Gelman, Sarah A Fahlberg, Pete Heinzelman, Philip A Romero, Anthony Gitter. bioRxiv 2021. doi:10.1101/2020.10.25.353946