MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction

Abstract

Predicting protein properties such as solvent accessibility and secondary structure from its primary amino acid sequence is an important task in bioinformatics. Recently, a few deep learning models have surpassed the traditional window based multilayer perceptron. Taking inspiration from the image classification domain we propose a deep convolutional neural network architecture, MUST-CNN, to predict protein properties. This architecture uses a novel multilayer shift-and-stitch (MUST) technique to generate fully dense per-position predictions on protein sequences. Our model is significantly simpler than the state-of-the-art, yet achieves better results. By combining MUST and the efficient convolution operation, we can consider far more parameters while retaining very fast prediction speeds. We beat the state-of-the-art performance on two large protein property prediction datasets.

8 pages ; 3 figures ; deep learning based sequence-sequence prediction. in AAAI 2016

References in corpus (9)

• Sequence to Sequence Learning with Neural Networks
• Practical Bayesian Optimization of Machine Learning Algorithms
• Natural Language Processing (almost) from Scratch
• Recurrent Neural Network Regularization
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Convolutional Neural Networks for Sentence Classification
• Protein Secondary Structure Prediction with Long Short Term Memory Networks
• Recurrent Convolutional Neural Networks for Scene Parsing
• Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction

Cited by in corpus (4)

• Deep Learning for Genomics: A Concise Overview
• Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction
• Protein Secondary Structure Prediction Using Deep Multi-scale Convolutional Neural Networks and Next-Step Conditioning
• EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation