On preprocessing of protein sequences for neural network prediction of polyproline type II secondary structures
Siermala, M ; Juhola, M and Vihinen, Mauno LU
(2001)
In Computers in Biology and Medicine
31(5).
p.385-398
- Abstract
- Polyproline type II stretches are somewhat rare on proteins. The backbone of this secondary structural element folds to a triangular form instead of the normal alpha -helix with 3.6 residues per turn. It is a very challenging task to try to detect them computationally from protein sequence. Here, we have studied the preprocessing phase in particular, which is important for any machine learning method. Preprocessing included selection of relevant data from the Protein Data Bank and investigation of learnability properties. These properties show whether the material is suitable for neural network computing. The complexity of algorithms in connection with preprocessing was briefly considered. We found that feedforward perceptron neural... (More)
- Polyproline type II stretches are somewhat rare on proteins. The backbone of this secondary structural element folds to a triangular form instead of the normal alpha -helix with 3.6 residues per turn. It is a very challenging task to try to detect them computationally from protein sequence. Here, we have studied the preprocessing phase in particular, which is important for any machine learning method. Preprocessing included selection of relevant data from the Protein Data Bank and investigation of learnability properties. These properties show whether the material is suitable for neural network computing. The complexity of algorithms in connection with preprocessing was briefly considered. We found that feedforward perceptron neural networks were appropriate for the prediction of polyproline type II and also relatively efficient in this task. The problem is very difficult because of the great similarity of the two classes present in the classification. Nevertheless, neural networks were able to recognize and predict about 75% of secondary structures. (C) 2001 Elsevier Science Ltd. All rights reserved. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3851531
- author
- Siermala, M
; Juhola, M
and Vihinen, Mauno
LU
- publishing date
- 2001
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- neural networks, proteins, prediction of polyproline type II secondary, structures, polyproline type II structure, PPII
- in
- Computers in Biology and Medicine
- volume
- 31
- issue
- 5
- pages
- 385 - 398
- publisher
- Elsevier
- external identifiers
-
- wos:000170519300006
- scopus:0034870317
- ISSN
- 1879-0534
- DOI
- 10.1016/S0010-4825(01)00013-0
- language
- English
- LU publication?
- no
- id
- dc527074-9225-4553-b82c-7bea4fed3510 (old id 3851531)
- date added to LUP
- 2016-04-01 11:46:11
- date last changed
- 2022-01-26 17:56:47
@article{dc527074-9225-4553-b82c-7bea4fed3510,
abstract = {{Polyproline type II stretches are somewhat rare on proteins. The backbone of this secondary structural element folds to a triangular form instead of the normal alpha -helix with 3.6 residues per turn. It is a very challenging task to try to detect them computationally from protein sequence. Here, we have studied the preprocessing phase in particular, which is important for any machine learning method. Preprocessing included selection of relevant data from the Protein Data Bank and investigation of learnability properties. These properties show whether the material is suitable for neural network computing. The complexity of algorithms in connection with preprocessing was briefly considered. We found that feedforward perceptron neural networks were appropriate for the prediction of polyproline type II and also relatively efficient in this task. The problem is very difficult because of the great similarity of the two classes present in the classification. Nevertheless, neural networks were able to recognize and predict about 75% of secondary structures. (C) 2001 Elsevier Science Ltd. All rights reserved.}},
author = {{Siermala, M and Juhola, M and Vihinen, Mauno}},
issn = {{1879-0534}},
keywords = {{neural networks; proteins; prediction of polyproline type II secondary; structures; polyproline type II structure; PPII}},
language = {{eng}},
number = {{5}},
pages = {{385--398}},
publisher = {{Elsevier}},
series = {{Computers in Biology and Medicine}},
title = {{On preprocessing of protein sequences for neural network prediction of polyproline type II secondary structures}},
url = {{http://dx.doi.org/10.1016/S0010-4825(01)00013-0}},
doi = {{10.1016/S0010-4825(01)00013-0}},
volume = {{31}},
year = {{2001}},
}