Dataset Information

Identifying Crohn's disease signal from variome analysis.

ABSTRACT:

Background

After years of concentrated research efforts, the exact cause of Crohn's disease (CD) remains unknown. Its accurate diagnosis, however, helps in management and preventing the onset of disease. Genome-wide association studies have identified 241 CD loci, but these carry small log odds ratios and are thus diagnostically uninformative.

Methods

Here, we describe a machine learning method-AVA,Dx (Analysis of Variation for Association with Disease)-that uses exonic variants from whole exome or genome sequencing data to extract CD signal and predict CD status. Using the person-specific coding variation in genes from a panel of only 111 individuals, we built disease-prediction models informative of previously undiscovered disease genes. By additionally accounting for batch effects, we were able to accurately predict CD status for thousands of previously unseen individuals from other panels.

Results

AVA,Dx highlighted known CD genes including NOD2 and new potential CD genes. AVA,Dx identified 16% (at strict cutoff) of CD patients at 99% precision and 58% of the patients (at default cutoff) with 82% precision in over 3000 individuals from separately sequenced panels.

Conclusions

Larger training panels and additional features, including other types of genetic variants and environmental factors, e.g., human-associated microbiota, may improve model performance. However, the results presented here already position AVA,Dx as both an effective method for revealing pathogenesis pathways and as a CD risk analysis tool, which can improve clinical diagnostic time and accuracy. Links to the AVA,Dx Docker image and the BitBucket source code are at https://bromberglab.org/project/avadx/ .

SUBMITTER: Wang Y

PROVIDER: S-EPMC6767648 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying Crohn's disease signal from variome analysis.

Wang Yanran Y Miller Maximilian M Astrakhan Yuri Y Petersen Britt-Sabina BS Schreiber Stefan S Franke Andre A Bromberg Yana Y

Genome medicine 20190930 1

<h4>Background</h4>After years of concentrated research efforts, the exact cause of Crohn's disease (CD) remains unknown. Its accurate diagnosis, however, helps in management and preventing the onset of disease. Genome-wide association studies have identified 241 CD loci, but these carry small log odds ratios and are thus diagnostically uninformative.<h4>Methods</h4>Here, we describe a machine learning method-AVA,Dx (Analysis of Variation for Association with Disease)-that uses exonic variants f ...[more]

PMID: 31564248

Similar Datasets

Project description:BackgroundAlthough perianal fistulas occur commonly in pediatric Crohn's disease (CD), evaluations of health services have been limited since no validated claims-based methods exist for identifying cases.ObjectiveTo develop and validate accurate case definitions for perianal fistulas among pediatric patients with CD from administrative claims.MethodsRetrospective cohort study in which we developed and tested candidate case definitions for perianal fistula. Patients (age 5-21 years between 2005-2012) with CD enrolled in Michigan Medicaid with healthcare at University of Michigan were identified via claims. Medical records were obtained from all identified patients, whose entire records were abstracted. Medical record evidence for perianal fistula was considered the "gold standard" against which candidate case definitions were compared. The reference case definition of perianal fistula (ICD9 565.1) and candidate case definitions were evaluated.ResultsOf 843 patients identified via claims, 274 (33%) met CD criteria for inclusion. The true perianal fistula rate among CD patients was 18% (n = 49). The top-performing candidate case definition identified 15% (n = 42), had sensitivity of 77.6%, specificity of 98.2%, positive predictive value (PPV) 90.5%, negative predictive value (NPV) 95.3%, and area under receiver operator characteristic curve (ROC) of 0.88. In contrast, the reference case definition identified 9% (n = 26), sensitivity 51.0%, specificity 99.6%, PPV 96.2%, NPV 90.3%, and had an area under ROC of 0.75.ConclusionsWe demonstrated that it is feasible to use administrative claims data to accurately identify pediatric patients with perianal fistula complications. Claims-based case definitions were found to be highly accurate through medical record review, providing a high degree of confidence for future studies where chart review is not feasible. These claims-based methods can be applied to claims data in other settings for the evaluation of health services utilization as well as to assess the comparative effectiveness of prevention and treatment strategies.

Dataset Information

Identifying Crohn's disease signal from variome analysis.

Background

Methods

Results

Conclusions

Publications

Identifying Crohn's disease signal from variome analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure