Biomarker detection on Pancreatic cancer dataset using entropy based spectral clustering
(2017) 3rd IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2017 2017-December. p.208-212- Abstract
Pancreatic ductal adenocarcinoma (PDAC) is one of most aggressive malignancy. The identification of Biomarker for PDAC is an ongoing challenge. The high dimensional PDAC gene expression dataset in Gene Expression Omnibus(GEO) database, is analyzed in this work. To select those genes which are relevant as well as with least redundancy among them, we use successive approaches like Filter methods and Normalization phase. In this work, after pre-processing of the data, we have used three types of spectral clustering methods, Unnormalized, Ng-Jordan and proposed entropy based Shi-Malik spectral clustering algorithms to find important genetic and biological information. There we have applied new Shannon's Entropy based distance measure to... (More)
Pancreatic ductal adenocarcinoma (PDAC) is one of most aggressive malignancy. The identification of Biomarker for PDAC is an ongoing challenge. The high dimensional PDAC gene expression dataset in Gene Expression Omnibus(GEO) database, is analyzed in this work. To select those genes which are relevant as well as with least redundancy among them, we use successive approaches like Filter methods and Normalization phase. In this work, after pre-processing of the data, we have used three types of spectral clustering methods, Unnormalized, Ng-Jordan and proposed entropy based Shi-Malik spectral clustering algorithms to find important genetic and biological information. There we have applied new Shannon's Entropy based distance measure to identify the clusters on Pancreatic dataset. Some Biomarkers are identified through KEGG Pathway analysis. The Biological analysis and functional correlation of genes based on Gene Ontology(GO) terms show that the proposed method is helpful for the selection of Biomarkers.
(Less)
- author
- Pahari, Purbanka ; Basak, Piyali and Sarkar, Anasua LU
- publishing date
- 2017-12-21
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- keywords
- biomarker identification, gene expression dataset, Pancreatic cancer, Shannon entropy, spectral clustering
- host publication
- Proceedings - 2017 3rd IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2017
- volume
- 2017-December
- pages
- 5 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 3rd IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2017
- conference location
- Kolkata, India
- conference dates
- 2017-11-03 - 2017-11-05
- external identifiers
-
- scopus:85049011026
- ISBN
- 9781538619315
- DOI
- 10.1109/ICRCICN.2017.8234508
- language
- English
- LU publication?
- no
- id
- 77f97192-003f-41b5-a2bd-016b8d3575b2
- date added to LUP
- 2018-09-13 10:15:03
- date last changed
- 2022-04-25 17:11:16
@inproceedings{77f97192-003f-41b5-a2bd-016b8d3575b2, abstract = {{<p>Pancreatic ductal adenocarcinoma (PDAC) is one of most aggressive malignancy. The identification of Biomarker for PDAC is an ongoing challenge. The high dimensional PDAC gene expression dataset in Gene Expression Omnibus(GEO) database, is analyzed in this work. To select those genes which are relevant as well as with least redundancy among them, we use successive approaches like Filter methods and Normalization phase. In this work, after pre-processing of the data, we have used three types of spectral clustering methods, Unnormalized, Ng-Jordan and proposed entropy based Shi-Malik spectral clustering algorithms to find important genetic and biological information. There we have applied new Shannon's Entropy based distance measure to identify the clusters on Pancreatic dataset. Some Biomarkers are identified through KEGG Pathway analysis. The Biological analysis and functional correlation of genes based on Gene Ontology(GO) terms show that the proposed method is helpful for the selection of Biomarkers.</p>}}, author = {{Pahari, Purbanka and Basak, Piyali and Sarkar, Anasua}}, booktitle = {{Proceedings - 2017 3rd IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2017}}, isbn = {{9781538619315}}, keywords = {{biomarker identification; gene expression dataset; Pancreatic cancer; Shannon entropy; spectral clustering}}, language = {{eng}}, month = {{12}}, pages = {{208--212}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Biomarker detection on Pancreatic cancer dataset using entropy based spectral clustering}}, url = {{http://dx.doi.org/10.1109/ICRCICN.2017.8234508}}, doi = {{10.1109/ICRCICN.2017.8234508}}, volume = {{2017-December}}, year = {{2017}}, }