Improved classification of mass spectrometry database search results using newer machine learning approaches.

@article{citeulike:864592, abstract = {Manual analysis of mass spectrometry data is a current bottleneck in high throughput proteomics. In particular, the need to manually validate the results of mass spectrometry database searching algorithms can be prohibitively time-consuming. Development of software tools that attempt to quantify the confidence in the assignment of a protein or peptide identity to a mass spectrum is an area of active interest. We sought to extend work in this area by investigating the potential of recent machine learning algorithms to improve the accuracy of these approaches and as a flexible framework for accommodating new data features. Specifically we demonstrated the ability of boosting and random forest approaches to improve the discrimination of true hits from false positive identifications in the results of mass spectrometry database search engines compared with thresholding and other machine learning approaches. We accommodated additional attributes obtainable from database search results, including a factor addressing proton mobility. Performance was evaluated using publically available electrospray data and a new collection of MALDI data generated from purified human reference proteins.}, address = {National Resource for Proteomics and Pathways, School of Public Health, University of Michigan, Ann Arbor, Michigan 48109, USA. pulintz@umich.edu}, author = {Ulintz, P. J. and Zhu, J. and Qin, Z. S. and Andrews, P. C. }, citeulike-article-id = {864592}, doi = {10.1074/mcp.M500233-MCP200}, issn = {1535-9476}, journal = {Mol Cell Proteomics}, keywords = {machine-learning, peptide-identification, peptide-identification-statistics, proteomics, tandem-mass-spectrometry}, month = {March}, number = {3}, pages = {497--509}, posted-at = {2007-08-08 15:17:26}, priority = {2}, title = {Improved classification of mass spectrometry database search results using newer machine learning approaches.}, url = {http://dx.doi.org/10.1074/mcp.M500233-MCP200}, volume = {5}, year = {2006} }

TY - JOUR ID - citeulike:864592 L3 - citeulike-article-id:864592 TI - Improved classification of mass spectrometry database search results using newer machine learning approaches. JF - Mol Cell Proteomics VL - 5 IS - 3 SP - 497 EP - 509 AD - National Resource for Proteomics and Pathways, School of Public Health, University of Michigan, Ann Arbor, Michigan 48109, USA. pulintz@umich.edu SN - 1535-9476 N2 - Manual analysis of mass spectrometry data is a current bottleneck in high throughput proteomics. In particular, the need to manually validate the results of mass spectrometry database searching algorithms can be prohibitively time-consuming. Development of software tools that attempt to quantify the confidence in the assignment of a protein or peptide identity to a mass spectrum is an area of active interest. We sought to extend work in this area by investigating the potential of recent machine learning algorithms to improve the accuracy of these approaches and as a flexible framework for accommodating new data features. Specifically we demonstrated the ability of boosting and random forest approaches to improve the discrimination of true hits from false positive identifications in the results of mass spectrometry database search engines compared with thresholding and other machine learning approaches. We accommodated additional attributes obtainable from database search results, including a factor addressing proton mobility. Performance was evaluated using publically available electrospray data and a new collection of MALDI data generated from purified human reference proteins. KW - machine-learning KW - peptide-identification KW - peptide-identification-statistics KW - proteomics KW - tandem-mass-spectrometry AU - Ulintz, PJ AU - Zhu, J AU - Qin, ZS AU - Andrews, PC PY - 2006/03// UR - http://dx.doi.org/10.1074/mcp.M500233-MCP200 ER -