Simulations Plus and NVIDIA Collaborate to Scale GPU-Accelerated, AI-Assisted Modeling Workflows

Key Takeaways

• GPU‑optimized QSP and PK/PD engines cut runtimes up to 75%
• AI‑assisted workflows automate model building, fitting, and diagnostics
• Integrated NVIDIA BioNeMo platform expands Simulations Plus’ life‑science ecosystem
• Parallel parameter exploration enables larger virtual population studies
• Pilot programs target high‑complexity modeling use cases with pharma partners

Pulse Analysis

The drug‑development landscape is increasingly data‑driven, with model‑informed drug development (MIDD) becoming a cornerstone for reducing attrition and accelerating timelines. Traditional mechanistic models, such as physiologically‑based pharmacokinetics (PBPK) and quantitative systems pharmacology (QSP), demand extensive compute cycles, often limiting the scale of virtual experiments. As high‑performance computing moves from CPU‑centric clusters to GPU‑centric architectures, firms that harness this shift can unlock parallel processing power, shortening simulation loops and expanding the feasible design space for hypothesis testing.

Simulations Plus’ collaboration with NVIDIA directly addresses these bottlenecks. By porting its validated scientific engines to NVIDIA’s GPU infrastructure and leveraging the BioNeMo AI platform, the company reports up to a 75% cut in end‑to‑end QSP modeling time. AI‑assisted modules further streamline model construction, parameter fitting, and diagnostic checks, turning what once required days of expert labor into near‑real‑time iterations. This integration not only boosts computational efficiency but also democratizes advanced modeling, allowing scientists to focus on interpretation rather than manual tuning.

For the broader biopharma ecosystem, the partnership signals a move toward more iterative, data‑rich development cycles. Faster, larger‑scale simulations enable earlier identification of promising candidates and more robust risk assessments, potentially shaving months off clinical timelines and lowering overall R&D spend. As select pharmaceutical partners pilot these capabilities, successful outcomes could drive wider adoption, positioning GPU‑accelerated, AI‑enhanced modeling as a new industry standard. Companies that lag in adopting such technologies may face competitive disadvantages in speed and insight generation.