A hybrid machine-learning approach for segmentation of protein localization data

Peter M. Kasson ¹^,2, Johannes B. Huppa ⁵^,6, Mark M. Davis ⁵^,6 and Axel T. Brunger ³^,4^,5^,*

¹Biophysics Program, Stanford Synchrotron Radiation Laboratory, Stanford University Stanford, CA 94305, USA
²Medical Scientist Training Program, Stanford Synchrotron Radiation Laboratory, Stanford University Stanford, CA 94305, USA
³Department of Molecular and Cellular Physiology, Stanford Synchrotron Radiation Laboratory, Stanford University Stanford, CA 94305, USA
⁴Department of Neurology and Neurological Sciences, Stanford Synchrotron Radiation Laboratory, Stanford University Stanford, CA 94305, USA
⁵Howard Hughes Medical Institute Stanford, CA 94305, USA
⁶Department of Microbiology and Immunology, Stanford University School of Medicine Stanford, CA 94305, USA

^*To whom correspondence should be addressed.

Motivation: Subcellular protein localization data are criticalto the quantitative understanding of cellular function and regulation.Such data are acquired via observation and quantitative analysisof fluorescently labeled proteins in living cells. Differentiationof labeled protein from cellular artifacts remains an obstacleto accurate quantification. We have developed a novel hybridmachine-learning-based method to differentiate signal from artifactin membrane protein localization data by deriving positionalinformation via surface fitting and combining this with fluorescence-intensity-baseddata to generate input for a support vector machine.

Results: We have employed this classifier to analyze signalingprotein localization in T-cell activation. Our classifier displayedincreased performance over previously available techniques,exhibiting both flexibility and adaptability: training on heterogeneousdata yielded a general classifier with good overall performance;training on more specific data cyielded an extremely high-performancespecific classifier. We also demonstrate accurate automatedlearning utilizing additional experimental data.

Availability: http://atb.slac.stanford.edu/~kasson/membraneclassifier.html

Contact: brunger{at}stanford.edu

Supplementary information: http://atb.slac.stanford.edu/~kasson/classifier_suppl.pdf

Received on March 2, 2005; revised on May 30, 2005; accepted on August 4, 2005

CiteULike

Connotea

Del.icio.us What's this?

Bioinformatics

A hybrid machine-learning approach for segmentation of protein localization data