Yokogawa announces the acquisition of all shares in Insilico Biotechnology AG (“Insilico”), a Stuttgart-based developer and provider of bioprocess software and services. Promoting the development of the bioeconomy is one of the priority themes of Yokogawa’s sustainability goals, and in line with this, the company intends to use this acquisition to develop total bioprocessing solutions that support biopharmaceutical development through to manufacturing.
Driven by developments such as the COVID-19 pandemic, there is a growing demand for biopharmaceuticals that have fewer side effects and can be used to treat patients with rare and persistent diseases. In contrast to the production of chemically synthesized general-purpose pharmaceuticals, the total cost of biopharmaceuticals is higher and the complex cell cultivation process required to obtain the target proteins efficiently and stably requires strict quality controls, which pose significant challenges in mass production.
The number of cells cultivated in a bioreactor is immense. Since each of these cells produces the material for the active ingredients of drugs, it is necessary to monitor their individual metabolic reactions. Real-time visualization and analysis of environmental factors such as changes in pH and dissolved oxygen concentration are also very important. Therefore, it has been extremely difficult to carry out cell production by controlling the complex cell reaction systems with a large number of set parameters.
Insilico’s digital twin technology uses an advanced hybrid model consisting of a mechanistic model * 1 of the unique properties of an intracellular metabolic network and a data-driven model * 2 created from process data using machine learning. Prediction and simulation not only enable a drastic acceleration of the development process that has taken several years to date, but also a deep understanding of the metabolic process. And because this solution enables the construction of metabolic models for bacteria and many other types of cellular organisms, it can also be used in a wide variety of applications related to food, chemicals, and other biotechnological products.
In production, too, Insilico’s digital twin technology enables real-time analysis of process data, constant forecasting of cultivation performance, gentle recording of nutrient components that cannot be measured directly, as well as early detection of process anomalies and the provision of instructions for operators. By using this problem solving technology, product quality can be stabilized, which contributes to efficient mass production.
Klaus Mauch, CEO of Insilico Biotechnology AG, says:
High expectations are attached to this merger between our state-of-the-art digital twin software technology for bioprocesses and Yokogawa’s pharmaceutical production system solutions. I believe that through Yokogawa’s global network we can expand our sales channels and make a major contribution to the biopharmaceutical industry. “
Hiroshi Nakao, Vice President of Yokogawa and Head of the company’s Life Business Headquarters, said:
I firmly believe that Insilico’s innovative digital twin technology, which has proven itself in large biopharmaceutical companies, will accelerate the digital transformation in the bioprocess industry. We will use our engineering technology and develop our business with a view to commercializing bioprocesses. “
Overview of Insilico Biotechnology AG
- Founded: 2001
- Location: Stuttgart, Germany
- CEO: Klaus Mauch
- Number of employees: 29
- Business area: Development of digital twin-based software and provision of services for bioprocesses
- Website: https://www.insilico-biotechnology.com/
* 1 Mechanistic model: A model that is developed based on the basic principles of the relevant reaction or mechanism, so a deep knowledge and understanding of the process is required to construct the model. The model obtained as a result has physically interpretable variables and parameters and can be further generalized. However, a high-precision physical model requires high development and computing costs.
* 2 Data-driven model: In contrast to mechanistic models, no knowledge of the basic principles of the respective process is required. The advantages include the simple implementation and the relatively low development and computing effort. However, disadvantages include difficulty interpreting data after performing predictions or simulations and generalizing the results. Another disadvantage of this technique is that large amounts of process data are required to construct the model.