New drugs can take 10-14 years and cost on average $1.8 bn to develop before entering the market. Consecutively, the net effect is that the price per dose easily exceeds $10,000.
The pressure downstream on the patients, the healthcare systems and insurance is intense with an aging and growing population.
This is why we need novel biopharmaceuticals earlier, and therefore cheaper, on the market.
Drug Life Cycle
We believe that every day & dollar saved, and every data insight gained, benefits the society and business.
We achieve a reduced time to market by an accelerated bioprocess development.
Advantages of increased process understanding
- Faster development timelines
- A higher return of investment
- Fewer required experiments, i.e., saving on experimental time, energy and materials
- Deeper process understanding of how critical process parameters impact the products’ critical quality attributes in a time-resolved manner
- Higher transparency for regulatory bodies
- Straightforward process know-how transfer between different products
We are meeting your needs if you
- are under pressure to reduce development timelines for new drugs, biosimilars and other biologically derived molecules (in red and white biotech)
- have growing needs for tools to better understand processes with the goal of achieving higher yields or a more stable process
- are seeking to fulfill the FDA’s QbD and PAT guidelines in a timely and cost-effective manner
Process Modeling Consulting
We create process models and thereby process understanding based on the data we receive. For best results, preferably starting projects before data creation.
Contract Research (CRO)
Advanced hybrid modeling toolbox for process modeling. Together with model-based and intensified Design of Experiments processes development timelines can be reduced significantly.
We also build the (hybrid) modeling knowledge within your company.
Combining our expertise with your data, we provide tailored support for the digital transformation of bioprocess modeling and control. From developing process models to implementing model-based process control (MPC), we work closely with our data scientists to find the best solution for your process.
Our approach starts by understanding your process and modeling goals. Through collaborative discussions, we iterate on your process to identify the optimal solution. Our team of data scientists analyzes your data using advanced techniques to uncover insights that drive process optimization.
If you recorded process data and would like to build the first model, describing the process or to make first predictions, we support you with initial data import (basic process on-line data, data from advanced sensors, and off-line analytics), data pre-processing, visualization and to find the best-suited model structure for your application.
Advanced process modeling
You already use statistical modeling tools, such as design of experiments, or mechanistic approaches and understand the basic influences, but want to know if hybrid modeling would increase your time-resolved process knowledge? We evaluate the accuracy, predictive capabilities and possible implementations of existing and suggested models.
Digital twin application
Once a suitable model structure is established and properly trained, we offer in-silico process optimization for upstream and downstream steps. Our digital process twins enable the replacement of laboratory experiments with virtual experiments, saving money and time in the long-term.
Model-based process control strategies
With well-trained hybrid models and predictive digital twin applications in hand, we help you tackle the last part of the digital transformation – model predictive control (MPC). Together with our partners, we set up model-based controllers that detect deviations of critical quality attributes on-line to adapt critical process parameter settings in real-time, thereby reducing deviations in production processes.