A new disease-specific machine learning approach for the prediction of cancer-causing missense variants

Genomics. 2011 Oct;98(4):310-7. doi: 10.1016/j.ygeno.2011.06.010. Epub 2011 Jul 7.


High-throughput genotyping and sequencing techniques are rapidly and inexpensively providing large amounts of human genetic variation data. Single Nucleotide Polymorphisms (SNPs) are an important source of human genome variability and have been implicated in several human diseases, including cancer. Amino acid mutations resulting from non-synonymous SNPs in coding regions may generate protein functional changes that affect cell proliferation. In this study, we developed a machine learning approach to predict cancer-causing missense variants. We present a Support Vector Machine (SVM) classifier trained on a set of 3163 cancer-causing variants and an equal number of neutral polymorphisms. The method achieve 93% overall accuracy, a correlation coefficient of 0.86, and area under ROC curve of 0.98. When compared with other previously developed algorithms such as SIFT and CHASM our method results in higher prediction accuracy and correlation coefficient in identifying cancer-causing variants.

Publication types

  • Evaluation Study
  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Artificial Intelligence*
  • Computational Biology / methods
  • Genetic Predisposition to Disease
  • Genome, Human
  • Humans
  • Mutation, Missense / genetics*
  • Neoplasms / genetics*
  • Polymorphism, Single Nucleotide / genetics
  • Predictive Value of Tests
  • Support Vector Machine*