Simulations Plus

In drug development, trust in the models utilized is critical. Even when a model demonstrates acceptable predictive performance, certain recurring issues can significantly reduce reviewer confidence.

The question is not whether agentic AI is coming. It is this: can you stake a regulatory submission on it?

Model interpretability is not uniformly critical across all stages of model development; however, it becomes essential at key decision points where scientific understanding must support regulatory confidence.

In high-stakes decision-making, particularly within regulatory submissions to agencies such as the FDA, PMDA, EMA, Health Canada, MHRA, ANVISA, models serve as a weight of evidence approach rather than exploratory tools.

For decades, the pharmaceutical industry has pursued a reliable bridge between in vitro dissolution and in vivo performance.

Drug development is moving fast—and not everything deserves your attention.

In drug development, the science never stands still. Constant research means there is constantly more to know and understand to stay current—but how can you filter through to what is most impactful?

Drug discovery has always been a balancing act, with scientists constantly striving for ‘Goldilocks’ compounds – the search for molecules that achieve on-target activity, while also avoiding hidden liabilities such as toxicity, poor exposure, or unfavorable pharmacokinetics, can seem insurmountable at times.

As anyone who has worked in the pharmaceutical industry knows, there is a constant push to accelerate and optimize development processes.

As scientists working in pre-clinical drug development, we are constantly balancing the need for rigorous, mechanistic modeling with the realities of fast-moving project timelines.

Training is one of the most critical parts of study start-up and yet, we often treat it like a box to check rather than the foundation of trial quality.

Learn how AI-powered tools--specifically GastroPlusGPT--can help physiologically based pharmacokinetic (PBPK) modelers work more efficiently, focus on deeper analysis, and ultimately be better scientists.

Selecting the optimal first-in-human (FIH) dose is one of the most challenging steps in drug development.

Despite systemic lupus erythematosus (SLE) clinical trials being conducted for over half a century, there are only two biologic therapies that are approved by the FDA to treat SLE: belimumab and anifrolumab.

Today more than ever, the role of thought leaders—also referred to as key opinion leaders (KOLs), external experts, and other designations—is critical.

The co-administration of oral drug products with food can lead to marked alterations in bioavailability (BA) and plasma concentrations when compared to the fasted state.

In systems biology, we often speak of emergence—how complex systems yield behaviors not apparent from their individual parts.

As every researcher in early development knows, there is constant pressure to identify high-quality drug candidates—while also increasing the speed and efficiency of the discovery process.

As AI tools gain traction in drug development, there is growing enthusiasm around their potential to predict drug-induced liver injury (DILI).

Both the U.S. Food and Drug Administration (FDA) (1) and the European Medicines Agency (EMA) (2) have articulated clear regulatory expectations for the implementation and advancement of non-animal methods, known as new approach methodologies (NAMs).