Model Zoo

Researchers develop DragoNN models for a wide range of genomics problems. To help share these models, we introduce the Model Zoo:

• Standard format for packaging DragoNN model info.
• Tools to upload and download trained DragoNN models.

To acquire a model:

1. download the model gist by ./scripts/download_model_from_gist.sh <gist_id> <dirname> to load the model metadata, architecture, solver configuration, and so on. (<dirname> is optional and defaults to ./models).
2. download the model weights by ./scripts/download_model_binary.py <model_dir> where <model_dir> is the gist directory from the first step.

Models in the DragoNN manuscript

We provide trained models, data, and code in (paper_supplement)[https://github.com/kundajelab/dragonn/tree/master/paper_supplement] to reproduce results in the DragoNN manuscript. Data files in (paper_supplement/simulation_data)[https://github.com/kundajelab/dragonn/tree/master/paper_supplement/simulation_data] are named based on parameters of (simulations functions)[https://github.com/kundajelab/simdna/blob/master/simdna/simulations.py] and contain training, validation, and test data for each simulation in the manuscript. We provide architecture and weights files for 139 models discussed in the manuscript in (paper_supplement/simulation_models)[https://github.com/kundajelab/dragonn/tree/master/paper_supplement/simulation_models]. Architecture and weights files of models based on simulations are prefixed with <simulation_function_name>.<model_architecture_parameters>.