hal-00643349, version 1

Learning predictive models for combinations of heterogeneous proteomic data sources

Michal Valko () ^1, 2, Richard Pelikan ¹, Milos Hauskrecht ¹

AMIA Summit on Translational Bioinformatics (2008)

• 1:  Department of Computer Science - University of Pittsburgh
• http://www.cs.pitt.edu/
  University of Pittsburgh Pittsburgh, PA 15260 United States
• 2:  SEQUEL (INRIA Lille - Nord Europe)
• http://www.inria.fr/equipes/sequel
  INRIA – CNRS : UMR8146 – Université Lille I - Sciences et technologies – Université Lille III - Sciences humaines et sociales – Ecole Centrale de Lille France

Bibliographic reference

• Type of document: Peer-reviewed conferences/proceedings
• Domain:

  Statistics/Machine Learning

  Life Sciences/Biotechnology

  Computer Science/Biotechnology

  Life Sciences/Human health and pathology

• Title: Learning predictive models for combinations of heterogeneous proteomic data sources
• Abstract: Multiple technologies that measure expression levels of protein mixtures in the human body offer a potential for detection and understanding the disease. The recent increase of these technologies prompts researchers to evaluate the individual and combined utility of data generated by the technologies. In this work, we study two data sources to measure the expression of protein mixtures in the human body: whole-sample MS profiling and multiplexed protein arrays. We investigate the individual and combined utility of these technologies by learning and testing a variety of classification models on the data from a pancreatic cancer study. We show that for the combination of these two (heterogeneous) datasets, classification models that work well on one of them individually fail on the combination of the two datasets. We study and propose a class of model fusion methods that acknowledge the differences and try to reap most of the benefits from their combination.
• Full text language: English
• Publication date: 2008
• Audience: international
• Conference title: AMIA Summit on Translational Bioinformatics
• Conference city: San Francisco
• Country: United States
• Conference date: 2008-03-10
• Conference date (end): 2008-03-12

Attached file list to this document: 

• hal-00643349, version 1
• http://hal.inria.fr/hal-00643349
• oai:hal.inria.fr:hal-00643349
• From: Michal Valko <>
• Submitted on: Monday, 21 November 2011 16:34:30
• Updated on: Thursday, 25 October 2012 15:06:02