This presentation will cover case studies from upstream, downstream, analytical and formulation development to support diverse modalities.

Explore practical and successful applications of analytics and AI in manufacturing across small, medium, and large enterprises in the U.S. Learn where to invest to start and sustain a digital transformation journey, drawing on research and best practices from MIT and McKinsey. Discover impactful uses of Generative AI currently shaping the industry that will drive future investment.

Data analytics has become an important tool in the development and manufacture of biopharma products and has delivered speed in development, cost-efficiency in manufacture and has added important new capabilities to process science. Effective and successful implementation of data analytics into the business requires a strategic approach, clear goals and leadership buy-in. Prioritization of investment and sustained effective change management are necessary to harvests the benefits of this technology. A strategic, portfolio and network level view can maximise the realization of benefits. Enabling factors and potential barriers will be discussed and the results of a recent cross-company survey will be shared. The potential impact of AI on the CMC environment will be discussed and examples of AI capabilities will be reviewed.

The biopharma industry is poised to be transformed by deep-learning physical science models. These new AI tools are clearly powerful and entire companies have spun up around their capabilities, particularly in drug discovery. However, their use in process development poses some challenges around model training, validation, and accuracy. Limited datasets, incomplete model “exercising”, lack of appropriate controls, and complex non-linear behaviors all need to be considered and addressed - particularly as the application of the technology gets closer to filings and control uses. This presentation will flesh out some of those technical challenges, and how they might be mitigated by changes in staffing and directed skills development.

After the fold

The biopharmaceutical industry faces growing pressure to accelerate the development of new therapeutics while reducing production costs and ensuring product quality at scale. Despite advancements in cell line development, the traditional upstream bioprocessing workflows remain slow, repetitive and highly resource-intensive. These challenges contribute to long development timelines and low data throughput, making bioprocessing a critical bottleneck during R&D and production scale-up. Pow.bio has developed an intelligent continuous bioprocessing platform that addresses these limitations by significantly increasing the speed of bioprocess development. Our system enables rapid optimization of bioprocess conditions and generates data 5–10 times faster than the traditional processes. We developed real-time digital twin software, which predicts system outcomes, automatically detects abnormalities, and dynamically adapts process parameters to constantly search for the bioprocess optimum. This adaptive control approach improves both process reliability and volumetric productivity by enabling faster optimization cycles and reducing batch failures caused by suboptimal conditions. In a case study demonstrated in functional protein production with Pichia pastoris, our platform achieved nearly double the volumetric productivity compared to the baseline process. By accelerating bioprocess data generation velocity and increasing productivity, our approach aims to fundamentally reshape biomanufacturing and contribute to a more sustainable and efficient future for the bioeconomy.

After the fold

After the fold

Traditional biopharmaceutical production relies on one-size-fits-all expression vectors and iterative, empirical process optimization. This standard approach limits productivity and performance, hindering the commercial viability of increasingly complex modalities by causing development hurdles and extending time to clinic.

In this talk, we present a vision for the future of biopharmaceutical development, and discuss our progress toward end-to-end design of genetic systems, cell lines, and bioprocesses using a portfolio of mechanistic, AI-based, and hybrid models. We highlight case studies that demonstrate the power of this approach across multiple modalities, including monoclonal antibodies and viral vectors.