An unsupervised learning approach to identify novel signatures of health and disease from multimodal data

摘要

In the study, we collected multimodal data (  = 1385 features) from 1253 individuals. We analyzed the data by performing cross-modality associations between features after correcting for age, sex, and ancestry. Using the associations, we performed community detection analysis and found modules of densely connected features. To reduce the number of indirect associations and identify key biomarker features, we performed conditional independence network analysis (also referred to as a ). Using the identified key biomarkers, we clustered individuals into distinct groups with similar signatures that are consistent with different health statuses. We characterize the clusters and perform disease risk enrichment analysis