scholarly journals Working toward precision medicine: Predicting phenotypes from exomes in the Critical Assessment of Genome Interpretation (CAGI) challenges

2017 ◽  
Vol 38 (9) ◽  
pp. 1182-1192 ◽  
Author(s):  
Roxana Daneshjou ◽  
Yanran Wang ◽  
Yana Bromberg ◽  
Samuele Bovo ◽  
Pier L Martelli ◽  
...  
Keyword(s):  
Precision Medicine ◽  
Critical Assessment ◽  
Genome Interpretation

scholarly journals Reports from CAGI: The Critical Assessment of Genome Interpretation

2017 ◽  
Vol 38 (9) ◽  
pp. 1039-1041 ◽  
Author(s):  
Roger A Hoskins ◽  
Susanna Repo ◽  
Daniel Barsky ◽  
Gaia Andreoletti ◽  
John Moult ◽  
...  
Keyword(s):  
Critical Assessment ◽  
Genome Interpretation

scholarly journals Reports from the fifth edition of CAGI: The Critical Assessment of Genome Interpretation

2019 ◽  
Vol 40 (9) ◽  
pp. 1197-1201 ◽  
Author(s):  
Gaia Andreoletti ◽  
Lipika R. Pal ◽  
John Moult ◽  
Steven E. Brenner
Keyword(s):  
Critical Assessment ◽  
Genome Interpretation

scholarly journals Predicting venous thromboembolism risk from exomes in the Critical Assessment of Genome Interpretation (CAGI) challenges

2019 ◽  
Vol 40 (9) ◽  
pp. 1314-1320 ◽  
Author(s):  
Gregory McInnes ◽  
Roxana Daneshjou ◽  
Panagiostis Katsonis ◽  
Olivier Lichtarge ◽  
Rajgopal Srinivasan ◽  
...  
Keyword(s):  
Venous Thromboembolism ◽  
Critical Assessment ◽  
Genome Interpretation

scholarly journals Predicting Pathogenicity of Missense Variants with Weakly Supervised Regression

2019 ◽  
Author(s):  
Yue Cao ◽  
Yuanfei Sun ◽  
Mostafa Karimi ◽  
Haoran Chen ◽  
Oluwaseyi Moronfoye ◽  
...  
Keyword(s):  
Clinical Significance ◽  
Metal Binding ◽  
Molecular Mechanisms ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Critical Assessment ◽  
Model Interpretation ◽  
Genome Interpretation ◽  
Variation Data ◽  
Weakly Supervised

Quickly growing genetic variation data of unknown clinical significance demand computational methods that can reliably predict clinical phenotypes and deeply unravel molecular mechanisms. On the platform enabled by CAGI (Critical Assessment of Genome Interpretation), we develop a novel “weakly supervised” regression (WSR) model that not only predicts precise clinical significance (probability of pathogenicity) from inexact training annotations (class of pathogenicity) but also infers underlying molecular mechanisms in a variant-specific fashion. Compared to multi-class logistic regression, a representative multi-class classifier, our kernelized WSR improves the performance for the ENIGMA Challenge set from 0.72 to 0.97 in binary AUC (Area Under the receiver operating characteristic Curve) and from 0.64 to 0.80 in ordinal multi-class AUC. WSR model interpretation and protein structural interpretation reach consensus in corroborating the most probable molecular mechanisms by which some pathogenic BRCA1 variants confer clinical significance, namely metal-binding disruption for C44F and C47Y, protein-binding disruption for M18T, and structure destabilization for S1715N.

Sign in / Sign up

Export Citation Format

Share Document