Protein Sequences Classification Using Modular RBF Neural Networks
A protein super-family consists of proteins which share amino acid sequence homology and which may therefore be functionally and structurally related. One of the benefits from this category grouping is that some hint of function may be deduced for individual members from information on other member...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Book Chapter |
| Language: | English |
| Published: |
Springer Berlin/Heidelberg
2002
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/11921/ http://ir.unimas.my/id/eprint/11921/1/Protein%20Sequences%20Classification_abstract.pdf |
| _version_ | 1848837088853622784 |
|---|---|
| author | Wang, Dianhui Lee, Nung Kion Dillon, Tharam S. Hoogenraad, Nicholas J. |
| author2 | McKay, Bob |
| author_facet | McKay, Bob Wang, Dianhui Lee, Nung Kion Dillon, Tharam S. Hoogenraad, Nicholas J. |
| author_sort | Wang, Dianhui |
| building | UNIMAS Institutional Repository |
| collection | Online Access |
| description | A protein super-family consists of proteins which share amino acid sequence homology and which may therefore be functionally and structurally related. One of the benefits from this category grouping is that some hint of function
may be deduced for individual members from information on other members of the family. Traditionally, two protein sequences are classified into the same class if they have high homology in terms of feature patterns extracted through sequence alignment algorithms. These algorithms compare an unseen protein sequence with all the identified protein sequences and returned the higher scored protein sequences. As the sizes of the protein sequence databases are very large, it is a very time consuming job to perform exhaustive comparison of existing protein sequence. Therefore, there is a need to build an improved classification system for effectively identifying protein sequences. This paper presents a modular neural classifier for protein sequences with improved classification criteria. The intelligent classification techniques described in this paper aims to enhance the performance of single neural classifiers based on a centralized information structure in terms of recognition rate, generalization and reliability. The architecture of the proposed model is a modular RBF neural network with a
compensational combination at the transition output layer. The connection weights between the final output layer and the transition output layer are optimized by delta rule, which serve as an integrator of the local neural classifiers. To enhance the classification reliability, we present two heuristic rules to apply to decision-making. Two sets of protein sequences with ten classes of superfamilies downloaded from a public domain database, Protein Information Resources (PIR), are used in our simulation study. Experimental results with performance
comparisons are carried out between single neural classifiers and the proposed modular neural classifier. |
| first_indexed | 2025-11-15T06:34:06Z |
| format | Book Chapter |
| id | unimas-11921 |
| institution | Universiti Malaysia Sarawak |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T06:34:06Z |
| publishDate | 2002 |
| publisher | Springer Berlin/Heidelberg |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | unimas-119212016-05-12T04:01:57Z http://ir.unimas.my/id/eprint/11921/ Protein Sequences Classification Using Modular RBF Neural Networks Wang, Dianhui Lee, Nung Kion Dillon, Tharam S. Hoogenraad, Nicholas J. QA Mathematics T Technology (General) A protein super-family consists of proteins which share amino acid sequence homology and which may therefore be functionally and structurally related. One of the benefits from this category grouping is that some hint of function may be deduced for individual members from information on other members of the family. Traditionally, two protein sequences are classified into the same class if they have high homology in terms of feature patterns extracted through sequence alignment algorithms. These algorithms compare an unseen protein sequence with all the identified protein sequences and returned the higher scored protein sequences. As the sizes of the protein sequence databases are very large, it is a very time consuming job to perform exhaustive comparison of existing protein sequence. Therefore, there is a need to build an improved classification system for effectively identifying protein sequences. This paper presents a modular neural classifier for protein sequences with improved classification criteria. The intelligent classification techniques described in this paper aims to enhance the performance of single neural classifiers based on a centralized information structure in terms of recognition rate, generalization and reliability. The architecture of the proposed model is a modular RBF neural network with a compensational combination at the transition output layer. The connection weights between the final output layer and the transition output layer are optimized by delta rule, which serve as an integrator of the local neural classifiers. To enhance the classification reliability, we present two heuristic rules to apply to decision-making. Two sets of protein sequences with ten classes of superfamilies downloaded from a public domain database, Protein Information Resources (PIR), are used in our simulation study. Experimental results with performance comparisons are carried out between single neural classifiers and the proposed modular neural classifier. Springer Berlin/Heidelberg McKay, Bob Slaney, John 2002 Book Chapter PeerReviewed text en http://ir.unimas.my/id/eprint/11921/1/Protein%20Sequences%20Classification_abstract.pdf Wang, Dianhui and Lee, Nung Kion and Dillon, Tharam S. and Hoogenraad, Nicholas J. (2002) Protein Sequences Classification Using Modular RBF Neural Networks. In: AI 2002: Advances in Artificial Intelligence. Lecture Notes in Computer Science, 2557 . Springer Berlin/Heidelberg, pp. 477-486. ISBN 978-3-540-36187-9 http://download.springer.com/static/pdf/433/chp%253A10.1007%252F3-540-36187-1_42.pdf?originUrl=http%3A%2F%2Flink.springer.com%2Fchapter%2F10.1007%2F3-540-36187-1_42&token2=exp=1462500353~acl=%2Fstatic%2Fpdf%2F433%2Fchp%25253A10.1007%25252F3-540-36187-1_42 10.1007/3-540-36187-1_42 |
| spellingShingle | QA Mathematics T Technology (General) Wang, Dianhui Lee, Nung Kion Dillon, Tharam S. Hoogenraad, Nicholas J. Protein Sequences Classification Using Modular RBF Neural Networks |
| title | Protein Sequences Classification Using Modular RBF Neural Networks |
| title_full | Protein Sequences Classification Using Modular RBF Neural Networks |
| title_fullStr | Protein Sequences Classification Using Modular RBF Neural Networks |
| title_full_unstemmed | Protein Sequences Classification Using Modular RBF Neural Networks |
| title_short | Protein Sequences Classification Using Modular RBF Neural Networks |
| title_sort | protein sequences classification using modular rbf neural networks |
| topic | QA Mathematics T Technology (General) |
| url | http://ir.unimas.my/id/eprint/11921/ http://ir.unimas.my/id/eprint/11921/ http://ir.unimas.my/id/eprint/11921/ http://ir.unimas.my/id/eprint/11921/1/Protein%20Sequences%20Classification_abstract.pdf |