Here you can find IPython notebooks and shell scripts that illustrate how to use DeepCpG.
To setup the required dependencies, execute setup.sh:
bash setup.sh./notebooks contains IPython notebooks, which can be executed interactively. They can be exported to shell scripts and executed in the terminal by selecting File -> Download as -> Bash (.sh). This is recommended for large-scale experiments, e.g. training models on the entire data set.
- DeepCpG basics: Pre-processing data, training models, and evaluating models.
- Fine-tuning: Fine-tuning a pre-trained model to speed-up training.
- Motif analysis: Visualizing and analyzing learned motifs.
- Mutations effects: Computing and visualizing mutations effects.
- Predicting statistics: Predicting statistics such as cell-to-cell variance.
./scripts contains shell scrips with recommended default parameters. They may help you to easily build a DeepCpG pipeline for creating data, training models, and evaluating models. Set test_mode variable in scripts to 1 for testing, and 0 otherwise.