Predicting the Insurgence of Human Genetic Diseases Due to Single Point Protein Mutation using Machine Learning Approach.

Remo Calabrese, Emidio Capriotti, Rita Casadio

Abstract


The most common genetic variations in humans are related to single nucleotide polymorphisms (SNPs). The importance of SNPs in genetic studies is due to their association with genetic diseases. In this work we analyzed a particular class of SNPs that cause changes in the corresponding protein sequence.
We developed a new method that starting from the sequence information can predict if a new phenotype derived from a SNP is related to a genetic disease. Using a dataset of 21185 protein mutations (3587 human proteins) derived from Swiss-Prot Database, our predictor reaches 70% of accuracy for the specific task of predicting if a mutation can be related to a genetic disease.

[DOI: 10.1685/CSC06032] About DOI

Full Text:



[DOI: 10.1685/] About DOI

Url Resolver: : http://dx.doi.org/10.1685/





Creative Commons License   Except where otherwise noted, content on this site is
  licensed under a Creative Commons 2.5 Italy License