A major gap in diagnosis, classification, risk stratification, and prediction of therapeutic response exists in pulmonary arterial hypertension (PAH), driven in part by a lack of functional biomarkers that are also disease-specific. In this regard, leveraging big data-omics analyses using innovative approaches that integrate network medicine and machine learning correlated with clinically useful indices or risk stratification scores is an approach well-positioned to advance PAH precision medicine. For example, machine learning applied to a panel of 48 cytokines, chemokines, and growth factors could prognosticate PAH patients with immune-dominant subphenotypes at elevated or low-risk for mortality. Here, we discuss strengths and weaknesses of the most current studies evaluating omics-derived biomarkers in PAH. Progress in this field is offset by studies with small sample size, pervasive limitations in bioinformatics, and lack of standardized methods for data processing and interpretation. Future success in this field, in turn, is likely to hinge on mechanistic validation of data outputs in order to couple functional biomarker data with target-specific therapeutics in clinical practice.