Knowledge-based variable selection for learning rules from proteomic data
<p>Abstract</p> <p>Background</p> <p>The incorporation of biological knowledge can enhance the analysis of biomedical data. We present a novel method that uses a proteomic knowledge base to enhance the performance of a rule-learning algorithm in identifying putative bio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2009-09-01
|
| Series: | BMC Bioinformatics |
| _version_ | 1818807498386178048 |
|---|---|
| author | Hogan William R Bowser Robert P Visweswaran Shyam Lustgarten Jonathan L Gopalakrishnan Vanathi |
| author_facet | Hogan William R Bowser Robert P Visweswaran Shyam Lustgarten Jonathan L Gopalakrishnan Vanathi |
| author_sort | Hogan William R |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>The incorporation of biological knowledge can enhance the analysis of biomedical data. We present a novel method that uses a proteomic knowledge base to enhance the performance of a rule-learning algorithm in identifying putative biomarkers of disease from high-dimensional proteomic mass spectral data. In particular, we use the Empirical Proteomics Ontology Knowledge Base (EPO-KB) that contains previously identified and validated proteomic biomarkers to select <it>m/z</it>s in a proteomic dataset prior to analysis to increase performance.</p> <p>Results</p> <p>We show that using EPO-KB as a pre-processing method, specifically selecting all biomarkers found only in the biofluid of the proteomic dataset, reduces the dimensionality by 95% and provides a statistically significantly greater increase in performance over no variable selection and random variable selection.</p> <p>Conclusion</p> <p>Knowledge-based variable selection even with a sparsely-populated resource such as the EPO-KB increases overall performance of rule-learning for disease classification from high-dimensional proteomic mass spectra.</p> |
| first_indexed | 2024-12-18T19:26:37Z |
| format | Article |
| id | doaj.art-08fef80e2ce04aff82af6b694c695a4e |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-18T19:26:37Z |
| publishDate | 2009-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-08fef80e2ce04aff82af6b694c695a4e2022-12-21T20:55:51ZengBMCBMC Bioinformatics1471-21052009-09-0110Suppl 9S1610.1186/1471-2105-10-S9-S16Knowledge-based variable selection for learning rules from proteomic dataHogan William RBowser Robert PVisweswaran ShyamLustgarten Jonathan LGopalakrishnan Vanathi<p>Abstract</p> <p>Background</p> <p>The incorporation of biological knowledge can enhance the analysis of biomedical data. We present a novel method that uses a proteomic knowledge base to enhance the performance of a rule-learning algorithm in identifying putative biomarkers of disease from high-dimensional proteomic mass spectral data. In particular, we use the Empirical Proteomics Ontology Knowledge Base (EPO-KB) that contains previously identified and validated proteomic biomarkers to select <it>m/z</it>s in a proteomic dataset prior to analysis to increase performance.</p> <p>Results</p> <p>We show that using EPO-KB as a pre-processing method, specifically selecting all biomarkers found only in the biofluid of the proteomic dataset, reduces the dimensionality by 95% and provides a statistically significantly greater increase in performance over no variable selection and random variable selection.</p> <p>Conclusion</p> <p>Knowledge-based variable selection even with a sparsely-populated resource such as the EPO-KB increases overall performance of rule-learning for disease classification from high-dimensional proteomic mass spectra.</p> |
| spellingShingle | Hogan William R Bowser Robert P Visweswaran Shyam Lustgarten Jonathan L Gopalakrishnan Vanathi Knowledge-based variable selection for learning rules from proteomic data BMC Bioinformatics |
| title | Knowledge-based variable selection for learning rules from proteomic data |
| title_full | Knowledge-based variable selection for learning rules from proteomic data |
| title_fullStr | Knowledge-based variable selection for learning rules from proteomic data |
| title_full_unstemmed | Knowledge-based variable selection for learning rules from proteomic data |
| title_short | Knowledge-based variable selection for learning rules from proteomic data |
| title_sort | knowledge based variable selection for learning rules from proteomic data |
| work_keys_str_mv | AT hoganwilliamr knowledgebasedvariableselectionforlearningrulesfromproteomicdata AT bowserrobertp knowledgebasedvariableselectionforlearningrulesfromproteomicdata AT visweswaranshyam knowledgebasedvariableselectionforlearningrulesfromproteomicdata AT lustgartenjonathanl knowledgebasedvariableselectionforlearningrulesfromproteomicdata AT gopalakrishnanvanathi knowledgebasedvariableselectionforlearningrulesfromproteomicdata |