Journal article
DVPred: a disease-specific prediction tool for variant pathogenicity classification for hearing loss
Human genetics, Vol.141(3-4), pp.401-411
04/01/2022
DOI: 10.1007/s00439-022-02440-1
PMID: 35182233
Abstract
Numerous computational prediction tools have been introduced to estimate the functional impact of variants in the human genome based on evolutionary constraints and biochemical metrics. However, their implementation in diagnostic settings to classify variants faced challenges with accuracy and validity. Most existing tools are pan-genome and pan-diseases, which neglected gene- and disease-specific properties and limited the accessibility of curated data. As a proof-of-concept, we developed a disease-specific prediction tool named Deafness Variant deleteriousness Prediction tool (DVPred) that focused on the 157 genes reportedly causing genetic hearing loss (HL). DVPred applied the gradient boosting decision tree (GBDT) algorithm to the dataset consisting of expert-curated pathogenic and benign variants from a large in-house HL patient cohort and public databases. With the incorporation of variant-level and gene-level features, DVPred outperformed the existing universal tools. It boasts an area under the curve (AUC) of 0.98, and showed consistent performance (AUC = 0.985) in an independent assessment dataset. We further demonstrated that multiple gene-level metrics, including low complexity genomic regions and substitution intolerance scores, were the top features of the model. A comprehensive analysis of missense variants showed a gene-specific ratio of predicted deleterious and neutral variants, implying varied tolerance or intolerance to variation in different genes. DVPred explored the utility of disease-specific strategy in improving the deafness variant prediction tool. It can improve the prioritization of pathogenic variants among massive variants identified by high-throughput sequencing on HL genes. It also shed light on the development of variant prediction tools for other genetic disorders.
Details
- Title: Subtitle
- DVPred: a disease-specific prediction tool for variant pathogenicity classification for hearing loss
- Creators
- Fengxiao Bu - Sichuan UniversityMingjun Zhong - West China Hospital of Sichuan UniversityQinyi Chen - Medical Genetics CenterYumei Wang - GeneDock Co.Ltd., Beijing, 100083, China.Xia Zhao - GeneDock Co.Ltd., Beijing, 100083, China.Qian Zhang - West China Hospital of Sichuan UniversityXiarong Li - GeneDock Co Ltd, Beijing 100083, Peoples R ChinaKevin T Booth - Harvard Medical SchoolHela Azaiez - University of IowaYu Lu - West China Hospital of Sichuan UniversityJing Cheng - West China Hospital of Sichuan UniversityRichard J. H Smith - University of IowaHuijun Yuan - West China Hospital of Sichuan University
- Resource Type
- Journal article
- Publication Details
- Human genetics, Vol.141(3-4), pp.401-411
- Publisher
- Springer Nature
- DOI
- 10.1007/s00439-022-02440-1
- PMID
- 35182233
- ISSN
- 0340-6717
- eISSN
- 1432-1203
- Number of pages
- 11
- Grant note
- 2017YFC0907503 / National Key Research and Development Program of China ZYJC20002 / 1 3 5 project for disciplines of excellence West China Hospital of Sichuan University
- Language
- English
- Date published
- 04/01/2022
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Molecular Physiology and Biophysics; Anatomy and Cell Biology; Stead Family Department of Pediatrics; Iowa Neuroscience Institute; Otolaryngology; Internal Medicine
- Record Identifier
- 9984256841602771
Metrics
23 Record Views