High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures

TL;DR

This paper introduces diverse neural network architectures for protein Q8 secondary structure prediction, achieving state-of-the-art accuracy with a focus on reproducibility and unbiased performance evaluation.

Contribution

It presents novel neural architectures and a principled machine learning framework for unbiased, reproducible protein secondary structure prediction at Q8 resolution.

Findings

Achieved 70.7% accuracy on CB513 test set

Used ensemble of predictors for improved performance

Provided open data, models, and code for reproducibility

Abstract

We tackle the problem of protein secondary structure prediction using a common task framework. This lead to the introduction of multiple ideas for neural architectures based on state of the art building blocks, used in this task for the first time. We take a principled machine learning approach, which provides genuine, unbiased performance measures, correcting longstanding errors in the application domain. We focus on the Q8 resolution of secondary structure, an active area for continuously improving methods. We use an ensemble of strong predictors to achieve accuracy of 70.7% (on the CB513 test set using the CB6133filtered training set). These results are statistically indistinguishable from those of the top existing predictors. In the spirit of reproducible research we make our data, models and code available, aiming to set a gold standard for purity of training and testing sets. Such good practices lower entry barriers to this domain and facilitate reproducible, extendable research.