Sophia Genetics rolled out a Digital Twins module inside its Sophia DDM cloud platform to simulate disease trajectories, treatment responses and survival outcomes using multimodal clinical, imaging and genomic data; the product is RUO for research applications with hopes to inform trial matching and clinical decisions over time. Jurgi Camblong, Sophia’s CEO, framed the tool as a way to evolve static patient snapshots into dynamic models that accelerate translational research. In parallel, KAIST researchers published a generative AI framework that predicts and assembles cellular drug responses like modular building blocks, enabling in silico decomposition of drug and genetic perturbations. Both announcements reflect the sector’s push to operationalize large multimodal datasets and generative models for target discovery, biomarker prioritization and virtual testing—though both groups caution substantial validation is required before clinical deployment. Clarification: a “digital twin” in biomedical research denotes a computational replica of an individual or cohort that integrates longitudinal clinical, molecular and imaging data to run simulated interventions or predict outcomes.