Saliency map on Cnns for protein secondary structure prediction
Saliency map on Cnns for protein secondary structure prediction
Deep learning, a powerful methodology for data-driven modelling, has been shown to be useful in tackling several problems in the biomedical domain. However, deep neural architectures lack interpretability of how predictions from them are made on any test input. While several approaches to "opening the black box" are being developed, their application to biological and medical data is very much as its infancy. Here, we consider the specific problem of protein secondary structure prediction using the techniques of saliency maps to explain decisions of a deep neural network. The analysis leads to two important observations: (a) one-hot-encoded amino-acids are irrelevant in the presence of PSSM values as extra features; and (b) in predicting α-helices at any position, amino-acids to the right are far more important than those to the left. The latter observation may have a biological basis relating to the synthesis of proteins by ribosome movement from left to right, sequentially adding amino-acids.
Interpretability, Saliency Maps, Protein Secondary Structure Prediction, Convolutional Neural Networks
1249-1253
Romero Moreno, Guillermo
8c2f32d6-b0b5-4563-af22-c08b410b867f
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
May 2019
Romero Moreno, Guillermo
8c2f32d6-b0b5-4563-af22-c08b410b867f
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Romero Moreno, Guillermo, Niranjan, Mahesan and Prugel-Bennett, Adam
(2019)
Saliency map on Cnns for protein secondary structure prediction.
In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
IEEE.
.
(doi:10.1109/ICASSP.2019.8683603).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Deep learning, a powerful methodology for data-driven modelling, has been shown to be useful in tackling several problems in the biomedical domain. However, deep neural architectures lack interpretability of how predictions from them are made on any test input. While several approaches to "opening the black box" are being developed, their application to biological and medical data is very much as its infancy. Here, we consider the specific problem of protein secondary structure prediction using the techniques of saliency maps to explain decisions of a deep neural network. The analysis leads to two important observations: (a) one-hot-encoded amino-acids are irrelevant in the presence of PSSM values as extra features; and (b) in predicting α-helices at any position, amino-acids to the right are far more important than those to the left. The latter observation may have a biological basis relating to the synthesis of proteins by ribosome movement from left to right, sequentially adding amino-acids.
Text
Saliency Maps On CNNs For Protein Secondary Structure Prediction
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
e-pub ahead of print date: 17 April 2019
Published date: May 2019
Venue - Dates:
ICASSP 2019: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton Conference Centre, Brighton, United Kingdom, 2019-05-12 - 2019-05-17
Keywords:
Interpretability, Saliency Maps, Protein Secondary Structure Prediction, Convolutional Neural Networks
Identifiers
Local EPrints ID: 430913
URI: http://eprints.soton.ac.uk/id/eprint/430913
ISSN: 2379-190X
PURE UUID: cc416c92-62a3-48e5-8a99-4a0a81d63747
Catalogue record
Date deposited: 17 May 2019 16:30
Last modified: 16 Mar 2024 04:38
Export record
Altmetrics
Contributors
Author:
Guillermo Romero Moreno
Author:
Mahesan Niranjan
Author:
Adam Prugel-Bennett
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics