Support Vector Machines for Protein Functional Classification

Abstract

We demonstrate that support vector machines (svms) with selective kernel scaling are an effective tool in discriminating between benign and pathologic proteins. initial results compare favorably against manual classification performed by experts and indicate the capability of svms to capture the underlying structure of the data. the data set consists of 70 proteins of human antibody k1 immunoglobulin light chains, each represented by aligned sequences of 120 amino acids. we perform feature selection based on a first-order adaptive scaling algorithm, which confirms the importance of changes in certain amino acid positions and identifies other positions that are key in the characterization of protein function.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2002
Accession Number
ADA616290

Entities

People

  • Fred J. Stevens
  • Jaques Reifman
  • Nela Zavaljevski

Organizations

  • United States Army Medical Research and Development Command

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Amino Acids
  • Applied Computer Science
  • Biomedical Research
  • Classification
  • Data Sets
  • Feature Selection
  • Information Operations
  • Machine Learning
  • Proteins
  • Standards
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Instructional Design and Training Evaluation.
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML