Secondary Protein Structure Prediction Using Neural Networks

TL;DR

This paper explores neural network approaches, including fully connected and recurrent models, for predicting protein secondary structures from amino acid sequences, with experiments on cross-species data, sequence length effects, and custom error functions.

Contribution

It introduces a neural network framework for secondary structure prediction and compares different architectures and input strategies.

Findings

Neural networks can predict protein secondary structures from primary sequences.

Sequence length impacts model accuracy.

Recurrent neural networks offer a promising alternative.

Abstract

In this paper we experiment with using neural network structures to predict a protein's secondary structure ({\alpha} helix positions) from only its primary structure (amino acid sequence). We implement a fully connected neural network (FCNN) and preform three experiments using that FCNN. Firstly, we do a cross-species comparison of models trained and tested on mouse and human datasets. Secondly, we test the impact of varying the length of protein sequence we input into the model. Thirdly, we compare custom error functions designed to focus on the center of the input window. At the end of paper we propose a alternative, recurrent neural network model which can be applied to the problem.