Rapid advances in molecular profiling and the expanding availability of digitally captured healthcare data are reshaping the study, diagnosis, and management of human disease. Genomic, transcriptomic, proteomic, and metabolomic measurements can reveal biological processes underlying disease development and progression, while electronic health records, medical reports, and other clinical data provide information on patient characteristics, diagnoses, treatments, outcomes, and disease trajectories. Converting these diverse sources into clinically meaningful knowledge, however, remains challenging because of differences in data structure and scale, limited or inconsistent annotation, high dimensionality, and the need to meet rigorous standards for interpretability, privacy, reproducibility, and clinical relevance. This Special Issue focuses on the use of artificial intelligence to bridge molecular-level information and patient-centered clinical data, with the goal of accelerating translational research and precision medicine. Contributions are invited on computational strategies for identifying, evaluating, contextualizing, and translating biomarkers into clinically relevant applications. Relevant approaches include machine learning, natural language processing, compact and large language models, retrieval-augmented generation, knowledge-graph technologies, and multimodal AI frameworks. Topics of particular interest include AI-enabled extraction, harmonization, and interpretation of biomedical information contained in clinical text; joint analysis of molecular measurements and electronic health records; computational interpretation of genomic, transcriptomic, proteomic, and metabolomic datasets; molecular and clinical characterization of disease; identification of patient subgroups; prediction of diagnostic, prognostic, and therapeutic outcomes; biomarker-informed clinical decision support; and temporal modeling of molecular and clinical changes across the course of disease. The Special Issue welcomes both experimental and computational contributions. Potential submissions may address molecular and cellular processes, identification and validation of candidate biomarkers, predictive and mechanistic modeling, analysis of clinical datasets, or the design and assessment of artificial intelligence methods for biomedical applications. Review articles examining methodological developments, translational opportunities, current limitations, and future directions are also encouraged. Particular interest will be given to research that connects computational findings with experimental evidence or clinical validation.