Limits...
Causal graph-based analysis of genome-wide association data in rheumatoid arthritis.

Alekseyenko AV, Lytkin NI, Ai J, Ding B, Padyukov L, Aliferis CF, Statnikov A - Biol. Direct (2011)

Bottom Line: Anthony Almudevar, Dr. Eugene V.Koonin, and Prof.Marianthi Markatou.

View Article: PubMed Central - HTML - PubMed

Affiliation: Center for Health Informatics and Bioinformatics, New York University School of Medicine, New York, NY 10016, USA. alexander.alekseyenko@nyumc.org

ABSTRACT

Background: GWAS owe their popularity to the expectation that they will make a major impact on diagnosis, prognosis and management of disease by uncovering genetics underlying clinical phenotypes. The dominant paradigm in GWAS data analysis so far consists of extensive reliance on methods that emphasize contribution of individual SNPs to statistical association with phenotypes. Multivariate methods, however, can extract more information by considering associations of multiple SNPs simultaneously. Recent advances in other genomics domains pinpoint multivariate causal graph-based inference as a promising principled analysis framework for high-throughput data. Designed to discover biomarkers in the local causal pathway of the phenotype, these methods lead to accurate and highly parsimonious multivariate predictive models. In this paper, we investigate the applicability of causal graph-based method TIE* to analysis of GWAS data. To test the utility of TIE*, we focus on anti-CCP positive rheumatoid arthritis (RA) GWAS datasets, where there is a general consensus in the community about the major genetic determinants of the disease.

Results: Application of TIE* to the North American Rheumatoid Arthritis Cohort (NARAC) GWAS data results in six SNPs, mostly from the MHC locus. Using these SNPs we develop two predictive models that can classify cases and disease-free controls with an accuracy of 0.81 area under the ROC curve, as verified in independent testing data from the same cohort. The predictive performance of these models generalizes reasonably well to Swedish subjects from the closely related but not identical Epidemiological Investigation of Rheumatoid Arthritis (EIRA) cohort with 0.71-0.78 area under the ROC curve. Moreover, the SNPs identified by the TIE* method render many other previously known SNP associations conditionally independent of the phenotype.

Conclusions: Our experiments demonstrate that application of TIE* captures maximum amount of genetic information about RA in the data and recapitulates the major consensus findings about the genetic factors of this disease. In addition, TIE* yields reproducible markers and signatures of RA. This suggests that principled multivariate causal and predictive framework for GWAS analysis empowers the community with a new tool for high-quality and more efficient discovery.

Reviewers: This article was reviewed by Prof. Anthony Almudevar, Dr. Eugene V. Koonin, and Prof. Marianthi Markatou.

Show MeSH

Related in: MedlinePlus

Area under the ROC curve (AUC) for the causal graph-based predictive models developed in 1000 different random splits of NARAC data into training and testing sets.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3118953&req=5

Figure 3: Area under the ROC curve (AUC) for the causal graph-based predictive models developed in 1000 different random splits of NARAC data into training and testing sets.

Mentions: To assess statistical robustness of SNPs in the two Markov boundaries and of the associated predictive accuracies, we perform re-sampling analyses over 1000 different random splits of NARAC data into non-overlapping training and testing sets. Each training set is used for SNP selection by TIE* and fitting of predictive models with kernel ridge regression, while each testing set is only used for the final assessment of predictive accuracy. Over 1000 splits of the data, predictive models achieve an average accuracy of 0.82 AUC, with standard deviation 0.01 AUC (Figure 3). This demonstrates robustness of predictive accuracy of our models in the NARAC cohort. Similarly, five out of six SNPs reported in Table 1 show a high degree of statistical robustness and are selected in >50% of the training sets. Notably, 3 SNPs (rs660895, rs9275390, and rs9275374) are selected in all 1000 training sets. SNP rs12523624, which is not validated by the meta-analysis, also does not achieve significant robustness under re-sampling; it is selected in only the original training set. Table S2 in [Additional File 1] provides the list of all SNPs that are selected in at least 50 (5%) out of 1000 training sets in NARAC data.


Causal graph-based analysis of genome-wide association data in rheumatoid arthritis.

Alekseyenko AV, Lytkin NI, Ai J, Ding B, Padyukov L, Aliferis CF, Statnikov A - Biol. Direct (2011)

Area under the ROC curve (AUC) for the causal graph-based predictive models developed in 1000 different random splits of NARAC data into training and testing sets.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3118953&req=5

Figure 3: Area under the ROC curve (AUC) for the causal graph-based predictive models developed in 1000 different random splits of NARAC data into training and testing sets.
Mentions: To assess statistical robustness of SNPs in the two Markov boundaries and of the associated predictive accuracies, we perform re-sampling analyses over 1000 different random splits of NARAC data into non-overlapping training and testing sets. Each training set is used for SNP selection by TIE* and fitting of predictive models with kernel ridge regression, while each testing set is only used for the final assessment of predictive accuracy. Over 1000 splits of the data, predictive models achieve an average accuracy of 0.82 AUC, with standard deviation 0.01 AUC (Figure 3). This demonstrates robustness of predictive accuracy of our models in the NARAC cohort. Similarly, five out of six SNPs reported in Table 1 show a high degree of statistical robustness and are selected in >50% of the training sets. Notably, 3 SNPs (rs660895, rs9275390, and rs9275374) are selected in all 1000 training sets. SNP rs12523624, which is not validated by the meta-analysis, also does not achieve significant robustness under re-sampling; it is selected in only the original training set. Table S2 in [Additional File 1] provides the list of all SNPs that are selected in at least 50 (5%) out of 1000 training sets in NARAC data.

Bottom Line: Anthony Almudevar, Dr. Eugene V.Koonin, and Prof.Marianthi Markatou.

View Article: PubMed Central - HTML - PubMed

Affiliation: Center for Health Informatics and Bioinformatics, New York University School of Medicine, New York, NY 10016, USA. alexander.alekseyenko@nyumc.org

ABSTRACT

Background: GWAS owe their popularity to the expectation that they will make a major impact on diagnosis, prognosis and management of disease by uncovering genetics underlying clinical phenotypes. The dominant paradigm in GWAS data analysis so far consists of extensive reliance on methods that emphasize contribution of individual SNPs to statistical association with phenotypes. Multivariate methods, however, can extract more information by considering associations of multiple SNPs simultaneously. Recent advances in other genomics domains pinpoint multivariate causal graph-based inference as a promising principled analysis framework for high-throughput data. Designed to discover biomarkers in the local causal pathway of the phenotype, these methods lead to accurate and highly parsimonious multivariate predictive models. In this paper, we investigate the applicability of causal graph-based method TIE* to analysis of GWAS data. To test the utility of TIE*, we focus on anti-CCP positive rheumatoid arthritis (RA) GWAS datasets, where there is a general consensus in the community about the major genetic determinants of the disease.

Results: Application of TIE* to the North American Rheumatoid Arthritis Cohort (NARAC) GWAS data results in six SNPs, mostly from the MHC locus. Using these SNPs we develop two predictive models that can classify cases and disease-free controls with an accuracy of 0.81 area under the ROC curve, as verified in independent testing data from the same cohort. The predictive performance of these models generalizes reasonably well to Swedish subjects from the closely related but not identical Epidemiological Investigation of Rheumatoid Arthritis (EIRA) cohort with 0.71-0.78 area under the ROC curve. Moreover, the SNPs identified by the TIE* method render many other previously known SNP associations conditionally independent of the phenotype.

Conclusions: Our experiments demonstrate that application of TIE* captures maximum amount of genetic information about RA in the data and recapitulates the major consensus findings about the genetic factors of this disease. In addition, TIE* yields reproducible markers and signatures of RA. This suggests that principled multivariate causal and predictive framework for GWAS analysis empowers the community with a new tool for high-quality and more efficient discovery.

Reviewers: This article was reviewed by Prof. Anthony Almudevar, Dr. Eugene V. Koonin, and Prof. Marianthi Markatou.

Show MeSH
Related in: MedlinePlus