作者: Stephanie Hicks , David A. Wheeler , Sharon E. Plon , Marek Kimmel
DOI: 10.1002/HUMU.21490
关键词:
摘要: Multiple algorithms are used to predict the impact of missense mutations on protein structure and function using algorithm-generated sequence alignments or manually curated alignments. We compared accuracy with native alignment SIFT, Align-GVGD, PolyPhen-2, Xvar when generating functionality predictions well-characterized (n = 267) within BRCA1, MSH2, MLH1, TP53 genes. also evaluated employed from these (except Xvar) supplied same four including automatically generated by (1) (2) Polyphen-2, (3) Uniprot, (4) a tuned for Align-GVGD. Alignments differ in composition evolutionary depth. Data-based receiver operating characteristic curves employing each algorithm result area under curve 78-79% all algorithms. Predictions PolyPhen-2 were least dependent employed. In contrast, Align-GVGD predicts variants neutral provided large number sequences. Of note, make different even do not necessarily perform best their own alignment. Thus, researchers should consider optimizing both prediction.