Uncovering genetic associations in the human diseasome using an endophenotype-augmented disease network.

MOTIVATION: Many diseases, particularly cardiometabolic disorders, exhibit complex multimorbidities with one another. An intuitive way to model the connections between phenotypes is with a disease-disease network (DDN), where nodes represent diseases and edges represent associations, such as shared single-nucleotide polymorphisms (SNPs), between pairs of diseases. To gain further genetic understanding of molecular contributors to disease associations, we propose a novel version of the shared-SNP DDN (ssDDN), denoted as ssDDN+, which includes connections between diseases derived from genetic correlations with intermediate endophenotypes. We hypothesize that a ssDDN+ can provide complementary information to the disease connections in a ssDDN, yielding insight into the role of clinical laboratory measurements in disease interactions. RESULTS: Using PheWAS summary statistics from the UK Biobank, we constructed a ssDDN+ revealing hundreds of genetic correlations between diseases and quantitative traits. Our augmented network uncovers genetic associations across different disease categories, connects relevant cardiometabolic diseases, and highlights specific biomarkers that are associated with cross-phenotype associations. Out of the 31 clinical measurements under consideration, HDL-C connects the greatest number of diseases and is strongly associated with both type 2 diabetes and heart failure. Triglycerides, another blood lipid with known genetic causes in non-mendelian diseases, also adds a substantial number of edges to the ssDDN. This work demonstrates how association with clinical biomarkers can better explain the shared genetics between cardiometabolic disorders. Our study can facilitate future network-based investigations of cross-phenotype associations involving pleiotropy and genetic heterogeneity, potentially uncovering sources of missing heritability in multimorbidities. AVAILABILITY AND IMPLEMENTATION: The generated ssDDN+ can be explored at https://hdpm.biomedinfolab.com/ddn/biomarkerDDN.

Uncovering genetic associations in the human diseasome using an endophenotype-augmented disease network.

Many diseases exhibit complex multimorbidities with one another. An intuitive way to model the connections between phenotypes is with a disease-disease network (DDN), where nodes represent diseases and edges represent associations, such as shared single-nucleotide polymorphisms (SNPs), between pairs of diseases. To gain further genetic understanding of molecular contributors to disease associations, we propose a novel version of the shared-SNP DDN (ssDDN), denoted as ssDDN+, which includes connections between diseases derived from genetic correlations with endophenotypes. We hypothesize that a ssDDN+ can provide complementary information to the disease connections in a ssDDN, yielding insight into the role of clinical laboratory measurements in disease interactions. Using PheWAS summary statistics from the UK Biobank, we constructed a ssDDN+ revealing hundreds of genetic correlations between disease phenotypes and quantitative traits. Our augmented network uncovers genetic associations across different disease categories, connects relevant cardiometabolic diseases, and highlights specific biomarkers that are associated with cross-phenotype associations. Out of the 31 clinical measurements under consideration, HDL-C connects the greatest number of diseases and is strongly associated with both type 2 diabetes and diabetic retinopathy. Triglycerides, another blood lipid with known genetics causes in non-mendelian diseases, also adds a substantial number of edges to the ssDDN. Our study can facilitate future network-based investigations of cross-phenotype associations involving pleiotropy and genetic heterogeneity, potentially uncovering sources of missing heritability in multimorbidities.

Discovering comorbid diseases using an inter-disease interactivity network based on biobank-scale PheWAS data.

MOTIVATION: Understanding comorbidity is essential for disease prevention, treatment and prognosis. In particular, insight into which pairs of diseases are likely or unlikely to co-occur may help elucidate the potential relationships between complex diseases. Here, we introduce the use of an inter-disease interactivity network to discover/prioritize comorbidities. Specifically, we determine disease associations by accounting for the direction of effects of genetic components shared between diseases, and categorize those associations as synergistic or antagonistic. We further develop a comorbidity scoring algorithm to predict whether diseases are more or less likely to co-occur in the presence of a given index disease. This algorithm can handle networks that incorporate relationships with opposite signs. RESULTS: We finally investigate inter-disease associations among 427 phenotypes in UK Biobank PheWAS data and predict the priority of comorbid diseases. The predicted comorbidities were verified using the UK Biobank inpatient electronic health records. Our findings demonstrate that considering the interaction of phenotype associations might be helpful in better predicting comorbidity. AVAILABILITY AND IMPLEMENTATION: The source code and data of this study are available at https://github.com/dokyoonkimlab/DiseaseInteractiveNetwork. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Development of early prediction model for pregnancy-associated hypertension with graph-based semi-supervised learning.

Clinical guidelines recommend several risk factors to identify women in early pregnancy at high risk of developing pregnancy-associated hypertension. However, these variables result in low predictive accuracy. Here, we developed a prediction model for pregnancy-associated hypertension using graph-based semi-supervised learning. This is a secondary analysis of a prospective study of healthy pregnant women. To develop the prediction model, we compared the prediction performances across five machine learning methods (semi-supervised learning with both labeled and unlabeled data, semi-supervised learning with labeled data only, logistic regression, support vector machine, and random forest) using three different variable sets: [a] variables from clinical guidelines, [b] selected important variables from the feature selection, and [c] all routine variables. Additionally, the proposed prediction model was compared with placental growth factor, a predictive biomarker for pregnancy-associated hypertension. The study population consisted of 1404 women, including 1347 women with complete follow-up (labeled data) and 57 women with incomplete follow-up (unlabeled data). Among the 1347 with complete follow-up, 2.4% (33/1347) developed pregnancy-associated HTN. Graph-based semi-supervised learning using top 11 variables achieved the best average prediction performance (mean area under the curve (AUC) of 0.89 in training set and 0.81 in test set), with higher sensitivity (72.7% vs 45.5% in test set) and similar specificity (80.0% vs 80.5% in test set) compared to risk factors from clinical guidelines. In addition, our proposed model with graph-based SSL had a higher performance than that of placental growth factor for total study population (AUC, 0.71 vs. 0.80, p < 0.001). In conclusion, we could accurately predict the development pregnancy-associated hypertension in early pregnancy through the use of routine clinical variables with the help of graph-based SSL.

NETMAGE: A human disease phenotype map generator for the network-based visualization of phenome-wide association study results.

BACKGROUND: Disease complications, the onset of secondary phenotypes given a primary condition, can exacerbate the long-term severity of outcomes. However, the exact cause of many of these cross-phenotype associations is still unknown. One potential reason is shared genetic etiology-common genetic drivers may lead to the onset of multiple phenotypes. Disease-disease networks (DDNs), where nodes represent diseases and edges represent associations between diseases, can provide an intuitive way of understanding the relationships between phenotypes. Using summary statistics from a phenome-wide association study (PheWAS), we can generate a corresponding DDN where edges represent shared genetic variants between diseases. Such a network can help us analyze genetic associations across the diseasome, the landscape of all human diseases, and identify potential genetic influences for disease complications. RESULTS: To improve the ease of network-based analysis of shared genetic components across phenotypes, we developed the humaN disEase phenoType MAp GEnerator (NETMAGE), a web-based tool that produces interactive DDN visualizations from PheWAS summary statistics. Users can search the map by various attributes and select nodes to view related phenotypes, associated variants, and various network statistics. As a test case, we used NETMAGE to construct a network from UK BioBank (UKBB) PheWAS summary statistic data. Our map correctly displayed previously identified disease comorbidities from the UKBB and identified concentrations of hub diseases in the endocrine/metabolic and circulatory disease categories. By examining the associations between phenotypes in our map, we can identify potential genetic explanations for the relationships between diseases and better understand the underlying architecture of the human diseasome. Our tool thus provides researchers with a means to identify prospective genetic targets for drug design, using network medicine to contribute to the exploration of personalized medicine.

netCRS: Network-based comorbidity risk score for prediction of myocardial infarction using biobank-scaled PheWAS data.

The polygenic risk score (PRS) can help to identify individuals' genetic susceptibility for various diseases by combining patient genetic profiles and identified single-nucleotide polymorphisms (SNPs) from genome-wide association studies. Although multiple diseases will usually afflict patients at once or in succession, conventional PRSs fail to consider genetic relationships across multiple diseases. Even multi-trait PRSs, which take into account genetic effects for more than one disease at a time, fail to consider a sufficient number of phenotypes to accurately reflect the state of disease comorbidity in a patient, or are biased in terms of the traits that are selected. Thus, we developed novel network-based comorbidity risk scores to quantify associations among multiple phenotypes from phenome-wide association studies (PheWAS). We first constructed a disease-SNP heterogeneous multi-layered network (DS-Net), which consists of a disease network (disease-layer) and SNP network (SNP-layer). The disease-layer describes the population-level interactome from PheWAS data. The SNP-layer was constructed according to linkage disequilibrium. Both layers were attached to transform the information from a population-level interactome to individual-level inferences. Then, graph-based semi-supervised learning was applied to predict possible comorbidity scores on disease-layer for each subject. The SNP-layer serves as receiving individual genotyping data in the scoring process, and the disease-layer serves as the propagated output for an individual's multiple disease comorbidity scores. The possible comorbidity scores were combined by logistic regression, and it is denoted as netCRS. The DS-Net was constructed from UK Biobank PheWAS data, and the individual genetic profiles were collected from the Penn Medicine Biobank. As a proof-of-concept study, myocardial infarction (MI) was selected to compare netCRS with the PRS with pruning and thresholding (PRS-PT). The combined model (netCRS + PRS-PT + covariates) achieved an AUC improvement of 6.26% compared to the (PRS-PT + covariates) model. In terms of risk stratification, the combined model was able to capture the risk of MI up to approximately eight-fold higher than that of the low-risk group. The netCRS and PRS-PT complement each other in predicting high-risk groups of patients with MI. We expect that using these risk prediction models will allow for the development of prevention strategies and reduction of MI morbidity and mortality.

A Network-Based Analysis of Disease Complication Associations for Obstetric Disorders in the UK Biobank.

BACKGROUND: Recent studies have found that women with obstetric disorders are at increased risk for a variety of long-term complications. However, the underlying pathophysiology of these connections remains undetermined. A network-based view incorporating knowledge of other diseases and genetic associations will aid our understanding of the role of genetics in pregnancy-related disease complications. METHODS: We built a disease-disease network (DDN) using UK Biobank (UKBB) summary data from a phenome-wide association study (PheWAS) to elaborate multiple disease associations. We also constructed egocentric DDNs, where each network focuses on a pregnancy-related disorder and its neighboring diseases. We then applied graph-based semi-supervised learning (GSSL) to translate the connections in the egocentric DDNs to pathologic knowledge. RESULTS: A total of 26 egocentric DDNs were constructed for each pregnancy-related phenotype in the UKBB. Applying GSSL to each DDN, we obtained complication risk scores for additional phenotypes given the pregnancy-related disease of interest. Predictions were validated using co-occurrences derived from UKBB electronic health records. Our proposed method achieved an increase in average area under the receiver operating characteristic curve (AUC) by a factor of 1.35 from 55.0% to 74.4% compared to the use of the full DDN. CONCLUSION: Egocentric DDNs hold promise as a clinical tool for the network-based identification of potential disease complications for a variety of phenotypes.