Please use this identifier to cite or link to this item: http://hdl.handle.net/2381/40567
Title: DOMINO: Using Machine Learning to Predict Genes Associated with Dominant Disorders.
Authors: Quinodoz, Mathieu
Royer-Bertrand, Beryl
Cisarova, Katarina
Di Gioia, Silvio Alessandro
Superti-Furga, Andrea
Rivolta, Carlo
First Published: 5-Oct-2017
Publisher: Elsevier (Cell Press)
Citation: American Journal of Human Genetics, 2017, 101 (4), pp. 623-629
Abstract: In contrast to recessive conditions with biallelic inheritance, identification of dominant (monoallelic) mutations for Mendelian disorders is more difficult, because of the abundance of benign heterozygous variants that act as massive background noise (typically, in a 400:1 excess ratio). To reduce this overflow of false positives in next-generation sequencing (NGS) screens, we developed DOMINO, a tool assessing the likelihood for a gene to harbor dominant changes. Unlike commonly-used predictors of pathogenicity, DOMINO takes into consideration features that are the properties of genes, rather than of variants. It uses a machine-learning approach to extract discriminant information from a broad array of features (N = 432), including: genomic data, intra-, and interspecies conservation, gene expression, protein-protein interactions, protein structure, etc. DOMINO's iterative architecture includes a training process on 985 genes with well-established inheritance patterns for Mendelian conditions, and repeated cross-validation that optimizes its discriminant power. When validated on 99 newly-discovered genes with pathogenic mutations, the algorithm displays an excellent final performance, with an area under the curve (AUC) of 0.92. Furthermore, unsupervised analysis by DOMINO of real sets of NGS data from individuals with intellectual disability or epilepsy correctly recognizes known genes and predicts 9 new candidates, with very high confidence. In summary, DOMINO is a robust and reliable tool that can infer dominance of candidate genes with high sensitivity and specificity, making it a useful complement to any NGS pipeline dealing with the analysis of the morbid human genome.
DOI Link: 10.1016/j.ajhg.2017.09.001
ISSN: 0002-9297
eISSN: 1537-6605
Links: http://www.sciencedirect.com/science/article/pii/S0002929717303683?via%3Dihub
http://hdl.handle.net/2381/40567
Embargo on file until: 5-Apr-2018
Version: Post-print
Status: Peer-reviewed
Type: Journal Article
Rights: Copyright © 2017, Elsevier (Cell Press). Deposited with reference to the publisher’s open access archiving policy.
Description: Supplemental Information includes two figures and eight tables and can be found with this article online at http://dx.doi.org/10.1016/j.ajhg.2017.09.001.
The file associated with this record is under embargo until 6 months after publication, in accordance with the publisher's self-archiving policy. The full text may be available through the publisher links provided above.
Appears in Collections:Published Articles, Dept. of Genetics

Files in This Item:
File Description SizeFormat 
AJHG-D-17-00361_R3 (1).pdfPost-review (final submitted author manuscript)3.66 MBAdobe PDFView/Open
Rivolta_Supplementary_Figures.pdfPost-review (final submitted author manuscript)1.06 MBAdobe PDFView/Open
Table_S1.xlsxPost-review (final submitted author manuscript)42.89 kBUnknownView/Open
Table_S2.xlsxPost-review (final submitted author manuscript)19.53 kBUnknownView/Open
Table_S3.xlsxPost-review (final submitted author manuscript)10.3 kBUnknownView/Open
Table_S4.xlsxPost-review (final submitted author manuscript)13.9 kBUnknownView/Open
Table_S5.xlsxPost-review (final submitted author manuscript)12.13 kBUnknownView/Open
Table_S6.xlsxPost-review (final submitted author manuscript)22.73 kBUnknownView/Open
Table_S7.xlsxPost-review (final submitted author manuscript)15.6 kBUnknownView/Open
Table_S8.xlsxPost-review (final submitted author manuscript)11.06 kBUnknownView/Open


Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.