ACD/Labs, an informatics company that develops and commercialises software in support of digitalised R&D, has released a new two-part white paper series, AI-Digital-Physical Convergence: The Future of DMTA in Drug Discovery and Development.
Deemerwha studio Shutterstock
The series explores how pharmaceutical organisations can accelerate innovation by modernising the design-make-test-analyse (DMTA) cycle through AI applications and scientific software working in concert with scientists and the physical experiments they undertake.
The papers describe the transformative potential of an “AI-digital-physical DMTA cycle”— which can help organisations reduce data preparation time for predictive modelling and AI/ML applications from 80% to zero.
Part one focuses on drug discovery and outlines how digital twins and AI can accelerate lead optimisation, reduce the burden of manual synthesis design, and improve decision-making across exploratory and confirmatory experimentation. By unifying design, synthesis, testing, and analysis, researchers can shorten the path to identifying viable clinical candidates while maintaining scientific rigor.
Part two discusses the implementation of these principles in pharmaceutical development focusing on Chemistry, Manufacturing, and Controls (CMC). Innovations that accelerate pharmaceutical development can significantly reduce the cost of developing an API into a drug product. AI-augmented DMTA cycles enable organisations to implement quality by design (QbD) principles more effectively; leverage design of experiments (DoE) and Bayesian optimization for iterative and robust design; apply process digital twins for continuous optimisation and regulatory readiness; and improve drug substance characterisation and drug product formulation with higher reproducibility and compliance.
“The scientific method is being redefined,” said Andrew Anderson, white paper author and Vice President of Innovation and Informatics Strategy at ACD/Labs. “While many R&D organisations are well into their digitalisation journeys, most continue to operate in fragmented environments that rely heavily on manual data transfer between systems. This creates inefficiencies, increases the risk of errors, and slows down the transition from scientific insight to clinical reality.”
“We’re increasingly seeing machine-readable data being the work product of experiments to help shorten project timelines. Leaders in Pharmaceutical R&D are striving to enable collaborations with well-structured data—by their scientists, between scientists and machines, and machine-to-machine. In this white paper series, we’re highlighting best practices from the world’s most innovative R&D organisations.”
The white paper series “AI-Digital-Physical Convergence: The Future of DMTA in Drug Discovery and Development” is now available for download here.