Deep Learning Models (RNN, LSTM, GRU, RBM, DBN, AE) for Saccharomyces Cerevisiae

Download .zip Download .tar.gz View on GitHub

Confirming DNA Replication Origins of Saccharomyces Cerevisiae

A Deep Learning Approach

In the past, the study of medicine used to focus on observing biological processes that take place in organisms, and based on these observations, biologists would make conclusions that translate into a better understanding of how organisms systems work. Recently, the approach has changed to a computational paradigm, where scientists try to model these biological processes as mathematical equations or statistical models. In this study, we have modeled an important activity of cell replication in a type of bacteria genome using different deep learning network models. Results from this research suggest that deep learning models have the potential to learn representations of DNA sequences, hence predicting cell behavior.

Models Trained

  • Basic Recurrent Neural Network
  • Long Short Term Memory
  • Gated Recurrent Unit
  • Restricted Boltzmann Machine
  • Deep Belief Network
  • Auto-encoder

Tools Used

  • Tensorflow
  • Numpy Package
  • BioPython Package

Experimental Results

See the source code on the repository. Research report can be read here

Authors and Contributors

This research is part of Big Data class (Spring 2016) at University of Connecticut instructed by Prof. Fei Wang. Main contributors: