Convolutional LSTM networks for subcellular localization of proteins

Søren Kaae Sønderby; Casper Kaae Sønderby; Henrik Nielsen; Ole Winther

doi:10.1007/978-3-319-21233-3_6

Convolutional LSTM networks for subcellular localization of proteins

Søren Kaae Sønderby^*, Casper Kaae Sønderby, Henrik Nielsen, Ole Winther

^*Corresponding author for this work

Computational and RNA Biology

57 Citations (Scopus)

Abstract

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 language	English
Title of host publication	Algorithms for Computational Biology
Editors	Adrian-Horia Dediu, Francisco Hernández-Quiroz, Carlos Martín-Vide, David A. Rosenblueth
Number of pages	13
Publisher	Springer
Publication date	2015
Pages	68-80
ISBN (Print)	978-3-319-21232-6
ISBN (Electronic)	978-3-319-21233-3
DOIs	https://doi.org/10.1007/978-3-319-21233-3_6
Publication status	Published - 2015
Event	2nd International Conference on Algorithms for Computational Biology, AlCoB 2015 - Mexico City, Mexico Duration: 4 Aug 2015 → 5 Aug 2015

Conference

Conference	2nd International Conference on Algorithms for Computational Biology, AlCoB 2015
Country/Territory	Mexico
City	Mexico City
Period	04/08/2015 → 05/08/2015

Series	Lecture notes in computer science
Volume	9199
ISSN	0302-9743

Keywords

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

Access to Document

10.1007/978-3-319-21233-3_6

Cite this

Convolutional LSTM networks for subcellular localization of proteins. / Sønderby, Søren Kaae; Sønderby, Casper Kaae; Nielsen, Henrik et al.
Algorithms for Computational Biology. ed. / Adrian-Horia Dediu; Francisco Hernández-Quiroz; Carlos Martín-Vide; David A. Rosenblueth. Springer, 2015. p. 68-80 (Lecture notes in computer science, Vol. 9199).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Sønderby, SK, Sønderby, CK, Nielsen, H & Winther, O 2015, Convolutional LSTM networks for subcellular localization of proteins. in A-H Dediu, F Hernández-Quiroz, C Martín-Vide & DA Rosenblueth (eds), Algorithms for Computational Biology. Springer, Lecture notes in computer science, vol. 9199, pp. 68-80, 2nd International Conference on Algorithms for Computational Biology, AlCoB 2015, Mexico City, Mexico, 04/08/2015. https://doi.org/10.1007/978-3-319-21233-3_6

@inproceedings{e86d47a1de3043589ed810d326efa3cc,

title = "Convolutional LSTM networks for subcellular localization of proteins",

abstract = "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.",

keywords = "Convolutional networks, Deep learning, LSTM, Machine learning, Neural networks, RNN, Subcellular location",

author = "S{\o}nderby, {S{\o}ren Kaae} and S{\o}nderby, {Casper Kaae} and Henrik Nielsen and Ole Winther",

year = "2015",

doi = "10.1007/978-3-319-21233-3_6",

language = "English",

isbn = "978-3-319-21232-6",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "68--80",

editor = "Dediu, {Adrian-Horia } and Francisco Hern{\'a}ndez-Quiroz and Mart{\'i}n-Vide, {Carlos } and Rosenblueth, {David A. }",

booktitle = "Algorithms for Computational Biology",

note = "2nd International Conference on Algorithms for Computational Biology, AlCoB 2015 ; Conference date: 04-08-2015 Through 05-08-2015",

}

TY - GEN

T1 - Convolutional LSTM networks for subcellular localization of proteins

AU - Sønderby, Søren Kaae

AU - Sønderby, Casper Kaae

AU - Nielsen, Henrik

AU - Winther, Ole

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - Convolutional networks

KW - Deep learning

KW - LSTM

KW - Machine learning

KW - Neural networks

KW - RNN

KW - Subcellular location

U2 - 10.1007/978-3-319-21233-3_6

DO - 10.1007/978-3-319-21233-3_6

M3 - Article in proceedings

AN - SCOPUS:84951119143

SN - 978-3-319-21232-6

T3 - Lecture notes in computer science

SP - 68

EP - 80

BT - Algorithms for Computational Biology

A2 - Dediu, Adrian-Horia

A2 - Hernández-Quiroz, Francisco

A2 - Martín-Vide, Carlos

A2 - Rosenblueth, David A.

PB - Springer

T2 - 2nd International Conference on Algorithms for Computational Biology, AlCoB 2015

Y2 - 4 August 2015 through 5 August 2015

ER -

Convolutional LSTM networks for subcellular localization of proteins

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this