Convolutional LSTM networks for subcellular localization of proteins

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

  • Søren Kaae Sønderby
  • Casper Kaae Sønderby
  • Henrik Nielsen
  • Winther, Ole

Machine learning is widely used to analyze biological sequence data. Non-sequential models such as SVMs or feed-forward neural networks are often used although they have no natural way of handling sequences of varying length. Recurrent neural networks such as the long short term memory (LSTM) model on the other hand are designed to handle sequences. In this study we demonstrate that LSTM networks predict the subcellular location of proteins given only the protein sequence with high accuracy (0.902) outperforming current state of the art algorithms. We further improve the performance by introducing convolutional filters and experiment with an attention mechanism which lets the LSTM focus on specific parts of the protein. Lastly we introduce new visualizations of both the convolutional filters and the attention mechanisms and show how they can be used to extract biologically relevant knowledge from the LSTM networks.

Original languageEnglish
Title of host publicationAlgorithms for Computational Biology
EditorsAdrian-Horia Dediu, Francisco Hernández-Quiroz, Carlos Martín-Vide, David A. Rosenblueth
Number of pages13
Publication date2015
ISBN (Print)978-3-319-21232-6
ISBN (Electronic)978-3-319-21233-3
Publication statusPublished - 2015
Event2nd International Conference on Algorithms for Computational Biology, AlCoB 2015 - Mexico City, Mexico
Duration: 4 Aug 20155 Aug 2015


Conference2nd International Conference on Algorithms for Computational Biology, AlCoB 2015
ByMexico City
SeriesLecture notes in computer science

    Research areas

  • Convolutional networks, Deep learning, LSTM, Machine learning, Neural networks, RNN, Subcellular location

ID: 153446256