TY - JOUR T1 - SSCM: A method to analyze and predict the pathogenicity of sequence variants JF - bioRxiv DO - 10.1101/021527 SP - 021527 AU - Sharad Vikram AU - Matthew D. Rasmussen AU - Eric A. Evans AU - Imran S. Haque Y1 - 2015/01/01 UR - http://biorxiv.org/content/early/2015/06/26/021527.abstract N2 - The advent of cost-effective DNA sequencing has provided clinics with high-resolution information about patient’s genetic variants, which has resulted in the need for efficient interpretation of this genomic data. Traditionally, variant interpretation has been dominated by many manual, time-consuming processes due to the disparate forms of relevant information in clinical databases and literature. Computational techniques promise to automate much of this, and while they currently play only a supporting role, their continued improvement for variant interpretation is necessary to tackle the problem of scaling genetic sequencing to ever larger populations. Here, we present SSCM-Pathogenic, a genome-wide, allele-specific score for predicting variant pathogenicity. The score, generated by a semi-supervised clustering algorithm, shows predictive power on clinically relevant mutations, while also displaying predictive ability in noncoding regions of the genome. ER -