Premium
Audio G ene: Predicting Hearing Loss Genotypes from Phenotypes to Guide Genetic Screening
Author(s) -
Taylor Kyle R.,
DeLuca Adam P.,
Shearer A. Eliot,
Hildebrand Michael S.,
BlackZiegelbein E. Ann,
Anand V. Nikhil,
Sloan Christina M.,
Eppsteiner Robert W.,
Scheetz Todd E.,
Huygen Patrick L. M.,
Smith Richard J. H.,
Braun Terry A.,
Casavant Thomas L.
Publication year - 2013
Publication title -
human mutation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.981
H-Index - 162
eISSN - 1098-1004
pISSN - 1059-7794
DOI - 10.1002/humu.22268
Subject(s) - biology , audiogram , hearing loss , genetics , locus (genetics) , phenotype , genetic heterogeneity , computational biology , gene , audiology , medicine
ABSTRACT Autosomal dominant nonsyndromic hearing loss ( ADNSHL ) is a common and often progressive sensory deficit. ADNSHL displays a high degree of genetic heterogeneity and varying rates of progression. Accurate, comprehensive, and cost‐effective genetic testing facilitates genetic counseling and provides valuable prognostic information to affected individuals. In this article, we describe the algorithm underlying A udio G ene, a software system employing machine‐learning techniques that utilizes phenotypic information derived from audiograms to predict the genetic cause of hearing loss in persons segregating ADNSHL . Our data show that A udio G ene has an accuracy of 68% in predicting the causative gene within its top three predictions, as compared with 44% for a majority classifier. We also show that A udio G ene remains effective for audiograms with high levels of clinical measurement noise. We identify audiometric outliers for each genetic locus and hypothesize that outliers may reflect modifying genetic effects. As personalized genomic medicine becomes more common, A udio G ene will be increasingly useful as a phenotypic filter to assess pathogenicity of variants identified by massively parallel sequencing.