Abstract
Background The growing availability of multi-omics data and machine learning methods creates both an opportunity and a challenge for the systems pharmacology community: the opportunity to model drug action at unprecedented mechanistic resolution, and the challenge of equipping a new generation of researchers with the computational literacy to do so. There is a particular need for training formats that bridge classical pharmacometrics with omics data science, and that foster interdisciplinary community building. Methods We organised a 4-day intensive hackathon on Predictive Modelling in Systems Pharmacology, bringing together 16 early-career researchers from the Horizon Europe CANVAS and French PEPR DIGPHAT consortia, spanning biology, bioinformatics, and computational science. The event pursued the dual aim of fostering a multidisciplinary consortium community and providing hands-on training that bridges classical pharmacometrics with omics data science. Three scientific tracks were delivered: (i) pharmacokinetic/pharmacodynamic (PK/PD) modelling, (ii) drug perturbation modelling through network diffusion in gene regulatory networks (GRN), and (iii) machine learning for pharmacogenomics. A theory-to-practice pedagogical framework structured each day, with morning workshops grounding participants in methodological foundations followed by afternoon coding sprints on real-world datasets. Results All three tracks produced working computational outputs within the hackathon timeframe. In the PK/PD track, all teams successfully identified a two-compartment structural model and key covariate effects. In the GRN track, participants implemented a network diffusion algorithm on gene regulatory networks, yielding patient-stratified therapy recommendations. In the pharmacogenomics track, four out of seven teams surpassed the logistic regression baseline in Matthews Correlation Coefficient on an external validation set. Conclusions The hackathon demonstrated that a structured multi-track format combining community-targeted outreach, theory-to-practice pedagogy, and real-world datasets constitutes a replicable model for interdisciplinary computational pharmacology training at the European level.