MouseCortexHydrop#
The MouseCortexHydrop model is a peak regression model fine-tuned to cell type-specific regions for cell types in the mouse cortex. It was trained in the same way and on the same cell types as the DeepBICCN model to show similarities between the HyDrop and 10x technologies.
After pretraining on all consensus peaks, the model was fine-tuned to specific peaks. Specific peaks were determined through the ratio of highest and second highest peak, and the ratio of the second and third highest peak. These sets of regions were then used as input to the model, where 2114bp one-hot encoded DNA sequences were used to per cell type predict the Tn5 cut-site counts over the center 1000 bp of the peak.
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
Dickmanken, H., Wojno, M., Theunis, K., Eksi, E. C., Mahieu, L., Christiaens, V., Kempynck, N., De Rop, F., Roels, N., Spanier, K. I., Vandepoel, R., Hulselmans, G., Poovathingal, S., Aerts, S. HyDrop v2: Scalable atlas construction for training sequence-to-function models. bioRxiv (2025). https://doi.org/10.1101/2025.04.02.646792
Usage#
1import crested
2import keras
3
4# download model
5model_path, output_names = crested.get_model("MouseCortexHydrop")
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)