DeepCCL#
The DeepCCL model is a peak regression model trained on an ATAC-seq dataset of cancer cell lines, using two ENCODE deeply-profiled-cell lines, namely HepG2 and GM12878; three melanoma cell lines (2 mesenchymal-like, MM029 and MM099, and one melanocytic-like, MM001); and three GBM cell lines (A172, M059J, and LN229).
The model was trained on a set of 415K consensus peaks and fine-tuned on 207K cell type-specific peaks, where peak heights were normalized across cell types with the normalize_peaks() function.
The model is a CNN multiclass regression model using the dilated_cnn() architecture.
Details of the data and the model can be found in the original publication.
Citation
Kempynck, N., De Winter, S., et al. CREsted: modeling genomic and synthetic cell type-specific enhancers across tissues and species. bioRxiv (2025). https://doi.org/10.1101/2025.04.02.646812
Usage#
1import crested
2import keras
3
4# download model
5model_path, output_names = crested.get_model("DeepCCL")
6
7# load model
8model = keras.models./load_model(model_path, compile=False)
9
10# make predictions
11sequence = "A" * 2114
12predictions = crested.tl.predict(sequence, model)
13print(predictions.shape)