genome-minimizer: Generative Models for Genomic Sequence Generation

Code developed by Stacy Shcherbakova and Chris P Barnes

Requirements

Libraries: PyTorch, numpy, seaborne, matplotlib, sklearn

The data folders: data These can be obtained from the Zenodo repository and should be placed in the top level directory of the package.

Some Acronyms/File names:

• Extras: Extra functions
• Training: Files which include training loops
• Directories: Directories paths
• BD: Horesh et. al. dataset (±7.5k samples)
• Final: Cut down Horesh et. al. dataset (±5k samples)
• GS: Gradient Clipping and Scheduling
• AHPT: After Hyperparameter Tuning

Usage