LecR1-antibodies

LecR1-antibodies - Learning from Diversity Epitope...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Learning from Diversity Epitope Prediction with Sequence and Structure Features using an Ensemble of Support Vector Machines Rob Patro and Carl Kingsford Center for Bioinformatics and Computational Biology University of Maryland Nov. 16, 2010 N Overview Challenge: epitope-antibody recognition Solution: ensemble of support vector machines I Trained with probabilistic extension I Variety of feature classes : physicochemical properties, string kernels, structure I Performance of individual methods and ensemble N Problem Overview The Challenge ht p:/ visualscience.ru, 2010 } Binding Site { Binding Site ? Binding with linear epitopes Simpler sequence affinity relation The Details Measure binding affinity aff ( p i ) [ , 65536 ] C + = { p i | aff ( p i ) [ 10000 , 65536 ] } 6 , 841 binders C- = { p i | aff ( p i ) [ , 1000 ] } 20 , 437 non-binders Learn a function to predict binding f : P [ , 1 ] f ( p i ) . 5 = p C + f ( p i ) < . 5 = p C- N System Overview ? C- f f 1 . . . f M 0.5 1.0 } } C + Individual classifiers trained on various features Decision Trees, Boosted / Bagged / Random Forests, Naive Bayes, Logistic Regression, Maximum Entropy Classification, (Balanced) Winnow Classifiers, etc. Support Vector Machines (SVM) Aggregate scores of classifiers Produces prediction for binding class Unlikely Binder Likely Binder N Probabilistic SVMs Ideally we want a confidence in each prediction ( Platt:1999 ) For each prediction, we obtain a posterior probability Allows ranking of predictions by posterior Aids in classifier combination C- 0.5 1.0 } } C + N Combining Predictions...
View Full Document

This note was uploaded on 01/13/2012 for the course CMSC 423 taught by Professor Staff during the Fall '07 term at Maryland.

Page1 / 20

LecR1-antibodies - Learning from Diversity Epitope...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online