Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence
We have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-01-01
|
| Series: | Scientifica |
| Online Access: | http://dx.doi.org/10.1155/2016/1060843 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563674965868544 |
|---|---|
| author | Abhinandan Khan Sudip Mandal Rajat Kumar Pal Goutam Saha |
| author_facet | Abhinandan Khan Sudip Mandal Rajat Kumar Pal Goutam Saha |
| author_sort | Abhinandan Khan |
| collection | DOAJ |
| description | We have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism to extract the underlying dynamics present in the time series expression data accurately. We have introduced a new hybrid swarm intelligence framework for the accurate training of the model parameters. The proposed methodology has been first applied to a small artificial network, and the results obtained suggest that it can produce the best results available in the contemporary literature, to the best of our knowledge. Subsequently, we have implemented our proposed framework on experimental (in vivo) datasets. Finally, we have investigated two medium sized genetic networks (in silico) extracted from GeneNetWeaver, to understand how the proposed algorithm scales up with network size. Additionally, we have implemented our proposed algorithm with half the number of time points. The results indicate that a reduction of 50% in the number of time points does not have an effect on the accuracy of the proposed methodology significantly, with a maximum of just over 15% deterioration in the worst case. |
| format | Article |
| id | doaj-art-f6a25e867d364f1ca4518d00bb1bdcf7 |
| institution | Kabale University |
| issn | 2090-908X |
| language | English |
| publishDate | 2016-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Scientifica |
| spelling | doaj-art-f6a25e867d364f1ca4518d00bb1bdcf72025-02-03T01:12:57ZengWileyScientifica2090-908X2016-01-01201610.1155/2016/10608431060843Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm IntelligenceAbhinandan Khan0Sudip Mandal1Rajat Kumar Pal2Goutam Saha3Department of Computer Science and Engineering, University of Calcutta, Acharya Prafulla Chandra Roy Siksha Prangan, JD-2, Sector III, Salt Lake City, Kolkata, West Bengal 700 098, IndiaDepartment of Computer Science and Engineering, University of Calcutta, Acharya Prafulla Chandra Roy Siksha Prangan, JD-2, Sector III, Salt Lake City, Kolkata, West Bengal 700 098, IndiaDepartment of Computer Science and Engineering, University of Calcutta, Acharya Prafulla Chandra Roy Siksha Prangan, JD-2, Sector III, Salt Lake City, Kolkata, West Bengal 700 098, IndiaDepartment of Information Technology, North Eastern Hill University, Umshing-Mawkynroh, Shillong, Meghalaya 793 022, IndiaWe have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism to extract the underlying dynamics present in the time series expression data accurately. We have introduced a new hybrid swarm intelligence framework for the accurate training of the model parameters. The proposed methodology has been first applied to a small artificial network, and the results obtained suggest that it can produce the best results available in the contemporary literature, to the best of our knowledge. Subsequently, we have implemented our proposed framework on experimental (in vivo) datasets. Finally, we have investigated two medium sized genetic networks (in silico) extracted from GeneNetWeaver, to understand how the proposed algorithm scales up with network size. Additionally, we have implemented our proposed algorithm with half the number of time points. The results indicate that a reduction of 50% in the number of time points does not have an effect on the accuracy of the proposed methodology significantly, with a maximum of just over 15% deterioration in the worst case.http://dx.doi.org/10.1155/2016/1060843 |
| spellingShingle | Abhinandan Khan Sudip Mandal Rajat Kumar Pal Goutam Saha Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence Scientifica |
| title | Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence |
| title_full | Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence |
| title_fullStr | Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence |
| title_full_unstemmed | Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence |
| title_short | Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence |
| title_sort | construction of gene regulatory networks using recurrent neural networks and swarm intelligence |
| url | http://dx.doi.org/10.1155/2016/1060843 |
| work_keys_str_mv | AT abhinandankhan constructionofgeneregulatorynetworksusingrecurrentneuralnetworksandswarmintelligence AT sudipmandal constructionofgeneregulatorynetworksusingrecurrentneuralnetworksandswarmintelligence AT rajatkumarpal constructionofgeneregulatorynetworksusingrecurrentneuralnetworksandswarmintelligence AT goutamsaha constructionofgeneregulatorynetworksusingrecurrentneuralnetworksandswarmintelligence |