An eScience-Bayes strategy for analyzing omics data
<p>Abstract</p> <p>Background</p> <p>The omics fields promise to revolutionize our understanding of biology and biomedicine. However, their potential is compromised by the challenge to analyze the huge datasets produced. Analysis of omics data is plagued by the curse of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2010-05-01
|
| Series: | BMC Bioinformatics |
| Online Access: | http://www.biomedcentral.com/1471-2105/11/282 |
| _version_ | 1818792156437938176 |
|---|---|
| author | Spjuth Ola Eklund Martin Wikberg Jarl ES |
| author_facet | Spjuth Ola Eklund Martin Wikberg Jarl ES |
| author_sort | Spjuth Ola |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>The omics fields promise to revolutionize our understanding of biology and biomedicine. However, their potential is compromised by the challenge to analyze the huge datasets produced. Analysis of omics data is plagued by the curse of dimensionality, resulting in imprecise estimates of model parameters and performance. Moreover, the integration of omics data with other data sources is difficult to shoehorn into classical statistical models. This has resulted in <it>ad hoc </it>approaches to address specific problems.</p> <p>Results</p> <p>We present a general approach to omics data analysis that alleviates these problems. By combining eScience and Bayesian methods, we retrieve scientific information and data from multiple sources and coherently incorporate them into large models. These models improve the accuracy of predictions and offer new insights into the underlying mechanisms. This "eScience-Bayes" approach is demonstrated in two proof-of-principle applications, one for breast cancer prognosis prediction from transcriptomic data and one for protein-protein interaction studies based on proteomic data.</p> <p>Conclusions</p> <p>Bayesian statistics provide the flexibility to tailor statistical models to the complex data structures in omics biology as well as permitting coherent integration of multiple data sources. However, Bayesian methods are in general computationally demanding and require specification of possibly thousands of prior distributions. eScience can help us overcome these difficulties. The eScience-Bayes thus approach permits us to fully leverage on the advantages of Bayesian methods, resulting in models with improved predictive performance that gives more information about the underlying biological system.</p> |
| first_indexed | 2024-12-18T15:22:46Z |
| format | Article |
| id | doaj.art-de5daf48967947ffa1f9b7c55906e066 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-18T15:22:46Z |
| publishDate | 2010-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-de5daf48967947ffa1f9b7c55906e0662022-12-21T21:03:21ZengBMCBMC Bioinformatics1471-21052010-05-0111128210.1186/1471-2105-11-282An eScience-Bayes strategy for analyzing omics dataSpjuth OlaEklund MartinWikberg Jarl ES<p>Abstract</p> <p>Background</p> <p>The omics fields promise to revolutionize our understanding of biology and biomedicine. However, their potential is compromised by the challenge to analyze the huge datasets produced. Analysis of omics data is plagued by the curse of dimensionality, resulting in imprecise estimates of model parameters and performance. Moreover, the integration of omics data with other data sources is difficult to shoehorn into classical statistical models. This has resulted in <it>ad hoc </it>approaches to address specific problems.</p> <p>Results</p> <p>We present a general approach to omics data analysis that alleviates these problems. By combining eScience and Bayesian methods, we retrieve scientific information and data from multiple sources and coherently incorporate them into large models. These models improve the accuracy of predictions and offer new insights into the underlying mechanisms. This "eScience-Bayes" approach is demonstrated in two proof-of-principle applications, one for breast cancer prognosis prediction from transcriptomic data and one for protein-protein interaction studies based on proteomic data.</p> <p>Conclusions</p> <p>Bayesian statistics provide the flexibility to tailor statistical models to the complex data structures in omics biology as well as permitting coherent integration of multiple data sources. However, Bayesian methods are in general computationally demanding and require specification of possibly thousands of prior distributions. eScience can help us overcome these difficulties. The eScience-Bayes thus approach permits us to fully leverage on the advantages of Bayesian methods, resulting in models with improved predictive performance that gives more information about the underlying biological system.</p>http://www.biomedcentral.com/1471-2105/11/282 |
| spellingShingle | Spjuth Ola Eklund Martin Wikberg Jarl ES An eScience-Bayes strategy for analyzing omics data BMC Bioinformatics |
| title | An eScience-Bayes strategy for analyzing omics data |
| title_full | An eScience-Bayes strategy for analyzing omics data |
| title_fullStr | An eScience-Bayes strategy for analyzing omics data |
| title_full_unstemmed | An eScience-Bayes strategy for analyzing omics data |
| title_short | An eScience-Bayes strategy for analyzing omics data |
| title_sort | escience bayes strategy for analyzing omics data |
| url | http://www.biomedcentral.com/1471-2105/11/282 |
| work_keys_str_mv | AT spjuthola anesciencebayesstrategyforanalyzingomicsdata AT eklundmartin anesciencebayesstrategyforanalyzingomicsdata AT wikbergjarles anesciencebayesstrategyforanalyzingomicsdata AT spjuthola esciencebayesstrategyforanalyzingomicsdata AT eklundmartin esciencebayesstrategyforanalyzingomicsdata AT wikbergjarles esciencebayesstrategyforanalyzingomicsdata |