Genomic risk prediction of aromatase inhibitor-related arthralgia in patients with breast cancer using a novel machine-learning algorithm

AuthorsStephen Sonis, Raquel E. Reinbolt, Cynthia D. Timmers, Juan Luis Fernandez-Martinez, Ana Cernea, Enrique J. de Andres-Galiana, Sepehr Hashemi, Karin Miller, Robert Pilarski, Maryam B. Lustberg
PublishedOctober 13, 2017
JournalCancer Medicine


Many breast cancer (BC) patients treated with aromatase inhibitors (AIs) develop aromatase inhibitor-related arthralgia (AIA).  Candidate gene studies to identify AIA risk are limited in scope.  We evaluated the potential of a novel analytic algorithm (NAA) to predict AIA using germline single nucleotide polymorphisms (SNP) data obtained before treatment initiation.  Systematic chart review of 700 AI-treated patients with stage I-III BC identified asymptomatic patients (n = 39) and those with clinically significant AIA resulting in AI termination or therapy switch (n = 123).  Germline DNA was obtained and SNP genotyping performed using the Affymetrix UK BioBank Axiom Array to yield 695,277 SNPs.  SNP clusters that most closely defined AIA risk were discovered using an NAA that sequentially combined statistical filtering and a machine-learning algorithm.  NCBI PhenGenI and Ensemble databases defined gene attribution of the most discriminating SNPs.  Phenotype, pathway, and ontologic analyses assessed functional and mechanistic validity.  Demographics were similar in cases and controls.  A cluster of 70 SNPs, correlating to 57 genes, was identified.  This SNP group predicted AIA occurence with a maximum accuracy of 75.93%.  Strong associations with arthralgia, breast cancer, and estrogen phenotypes were seen in 19/57 genes (33%) and were functionally consistent.  Using a NAA, we identified a 70 SNP cluster that predicted AIA risk with fair accuracy.  Phenotype, functional, and pathway analysis of attributed genes was consistent with clinical phenotypes.  This study is the first to link a specific SNP/gene cluster to AIA risk independent of candidate gene bias.

Read full publication