F. Hoffmann-La Roche. has filed a patent for a method to predict the metabolic state of a cell culture. The method involves using a metabolic model of a specific cell type, measuring concentrations of extracellular metabolites and cell density during cultivation, inputting these measurements into a machine learning program, predicting future extracellular fluxes, and calculating intracellular fluxes using metabolic flux analysis. GlobalData’s report on F. Hoffmann-La Roche gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData


Data Insights F. Hoffmann-La Roche Ltd - Company Profile

Buy the Report

Data Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on F. Hoffmann-La Roche, Cancer treatment biomarkers was a key innovation area identified from patents. F. Hoffmann-La Roche's grant share as of September 2023 was 52%. Grant share is based on the ratio of number of grants to total number of patents.

Method for predicting metabolic state of cell culture using machine learning

Source: United States Patent and Trademark Office (USPTO). Credit: F. Hoffmann-La Roche Ltd

A recently filed patent (Publication Number: US20230313113A1) describes a method for predicting the metabolic state of a cell culture of a specific cell type. The method involves providing a metabolic model of the cell type, which includes various intracellular and extracellular metabolites and fluxes. The model also includes stoichiometric equations that define the relationships between these metabolites.

During the cultivation of the cell culture, the method involves receiving measurement values at different points in time. These measurement values include concentrations of extracellular metabolites in the culture medium and the measured cell density of the cells in the culture. These measurement values are then used as input parameters for a trained machine learning program logic (MLP).

Using the received measurement values, the MLP predicts the extracellular fluxes of the metabolites at a future point in time. These extracellular fluxes represent the uptake or release rates of the metabolites into or from the cells. The future point in time is a time subsequent to the point at which the measurement values were received.

To calculate the intracellular fluxes at the future point in time, the method involves performing metabolic flux analysis. This analysis uses the predicted extracellular fluxes and the stoichiometric equations of the metabolic model.

In summary, this patent describes a method that combines a metabolic model, machine learning, and metabolic flux analysis to predict the metabolic state of a cell culture. By using measurement values and a trained MLP, the method can forecast the extracellular fluxes of metabolites at a future point in time. These predicted fluxes are then used in metabolic flux analysis to calculate the intracellular fluxes. This method has potential applications in various fields, including biotechnology and pharmaceutical research, where understanding and predicting the metabolic state of cell cultures is crucial.

To know more about GlobalData’s detailed insights on F. Hoffmann-La Roche, buy the report here.

Data Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies