/multimodal-k562-cell-line-prediction

Project for the Bioinformatic course, focusing on the development of deep neural network models for the prediction of active regulatory regions in K562 cell line.

Primary LanguageJupyter NotebookBSD 2-Clause "Simplified" LicenseBSD-2-Clause

Bioinformatic project

Predict active regulatory regions in K562 cell line. The considered tasks are

- AEvsIE: active enanchers vs incative enanchers;
- APvsIP: active promoters vs incative promoters.

The neural network models used to predict such tasks are:

- Feed-Forward Neural Network;
- Convolutional Neural Network;
- Multi-Modal Neural Network;

Files

File k562_prediction.ipynb contains the Jupyter notebook developed for the project, while file relazione.pdf is the final written report.