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.

Cite

Text

Lin et al. "MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-Based Protein Structure Prediction." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10007

Markdown

[Lin et al. "MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-Based Protein Structure Prediction." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/lin2016aaai-cnn/) doi:10.1609/AAAI.V30I1.10007

BibTeX

@inproceedings{lin2016aaai-cnn,
  title     = {{MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-Based Protein Structure Prediction}},
  author    = {Lin, Zeming and Lanchantin, Jack and Qi, Yanjun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {27-34},
  doi       = {10.1609/AAAI.V30I1.10007},
  url       = {https://mlanthology.org/aaai/2016/lin2016aaai-cnn/}
}