leero-ady/cap5510fa18

CAP5510 - Bioinformatics Project Proposal

Project Title:

Protein Secondary Structure Prediction with Long Short Term Memory Networks

Team Members:

Aditya Nalluri UFID: 64153915
Sai Madhav Kasam UFID: 17351683
Harish Jayanti UFID: 11552570

Abstract:

Prediction of protein secondary structure from the amino acid sequence is a classical bioinformatics problem. Common methods use feed forward neural networks or SVM’s combined with a sliding window, as these models does not naturally handle sequential data. Recurrent neural networks are an generalization of the feed forward neural network that naturally handle sequential data. We use a bidirectional recurrent neural network with long short term memory cells for prediction of secondary structure and evaluate using the Protein Data Bank dataset.

Plan of action:

Understanding the paper and do some background work on implementing Neural Networks.
Primary amino acids sequences of proteins would be collected from Protein Data Bank, WWPDB.
Implement the Neural Network with Long Short Term cells.
Train the neural network using Primary sequences.
The model is evaluted based on the Q8 class ouput predictions.

Work load:

The work load will be divided among the three of us equally in all aspects like reading research papers and Implementation.

References:

[1] SØNDERBY, S. K., AND WINTHER, O. Protein secondary structure prediction with long short term memory networks. arXiv preprint arXiv:1412.7828 (2014).
[2] Bordoloi H., Sarma K.K. (2012) Protein Structure Prediction Using Multiple Artificial Neural Network Classifier. In: Patnaik S., Yang [3] YM. (eds) Soft Computing Techniques in Vision Science. Studies in Computational Intelligence, vol 395. Springer, Berlin, Heidelberg.
Jian Zhou, Olga G. Troyanskaya Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction. arXiv:1403.134