Proteomic Engineering
 

Automation, Engineering, and Science for Clinical Applications

People

Research

Publications

Downloads

Contact

 

 

 

 

Topic Menu

Home

Computation

Automation/Robot

 

 

 

 

 

Computation

Current research is examining machine learning techniques for proteomic classification and marker selection Using sample fractionation with SELDI-TOF MS.  Over the last couple of years, technologies such as surface-enhanced laser desorption/ionization (SELDI) time-of-flight mass spectrometry have dramatically changed the study of Proteomic.  Yet, as data is generated in an increasingly rapid and automated manner, novel and application-specific computational methods will be needed to deal with all this information.  This paper explores methods that can be used to glean informative marker and classification profiles from Proteomic and genomic data.  Then, these methods are applied to clonal hematological disorders in order to arrive at a diagnostic profile.  In doing so, novel proteomic markers, clustering, and classification profiles for these malignancies will be presented within the context of SELDI.

 

A SELDI-based procedure was developed to analyze serum from 74 patients with disease and 39 control patients from Harvard Medical School (USA) and University of Dusseldorf (Germany).  The serum was separated into pH5, pH9, organic, and whole serum fractions- and then analyzed by SELDI.  As part of this, novel methodologies were developed to facilitate the automation of the process both in computational methods and in robotic sample preparation.

 

Machine learning methods ranging from a Bayesian framework to support vector machines, k-nearest neighbors, logistic regression, decision trees, and others were used to find highly specific and sensitive profiles for prediction of these disorders and clinical subclasses.  Comparison between predictors that distinguish malignant samples from control is explored with regard to the orthogonal data it provides over current pre-bone biopsy information.  A high specificity might reduce the frequencies of biopsies.  Highest specificity was found using SVM and logistic regression (89%).  Using a decision tree approach and pruning, performance accuracy, sensitivity, and specificity were found to be 80%, 73%, and 85%.  This was accomplished by using only three simple decision rules with five protein markers, a fact that makes it much more clinically feasible than the current SELDI literature for any other disease currently explored (which usually includes profiles using over one hundred proteins).  Also, it is more feasible to test for proteins clinically from a blood draw than to do a large genetic profile.

 

In summary, protocols involving various novel SELDI sample preparation and machine learning techniques have been applied and compared for utilization in SELDI profile and marker discovery.  Evidence is provided for the first feasible protein profiles that can be exploited for these malignancies (and subtypes).  In addition, the power of Proteomic over genomic approaches both in terms of feasibility and performance is discussed.

 

Authors/contributors:
Gil Alterovitz, Manuel Aivado, Towia Libermann, Marco Ramoni, Isaac S. Kohane

 
 

Computation Links

Supplemental  Information

 

 

Copyright (c) 2004-2006. All Rights Reserved.