Method for predicting outcome of an modelling of a process in a bioreactor

A method for modelling of a process used for manufacturing a sample in a bioreactor, the process belonging to a multi-level knowledge tree, wherein the method comprises:

• selecting a process model based on the multi-level knowledge tree, wherein each level of the knowledge tree corresponds to a category associated with a type of process;
• accessing historic data related to past process runs for manufacturing the sample;
• accessing current data obtained from a current process run of the process, wherein the current data, which is based on the selected process model, comprises:
• process strategy data, bioreactor instrument data, data from online sensors and/or data from offline sensors;
• monitoring at least one parameter selected from cell viability, cell count, product titre, and product quality of the current process run for manufacturing the sample;
• subselecting historic data of previous process runs similar to the current process run from the accessed historic data;
• automatically determining an updated model for predicting outcomes of future process runs, wherein the predicted outcome of future process runs comprises a prediction of the at least one parameter, and wherein the updated model is determined based at least in part on:
• the process model based on the multi-level knowledge tree;
• and
• additional data from the current process run;
• and
• applying the updated model to future process runs of other samples.

A control system for controlling a process used for manufacturing a sample in a bioreactor, the process belonging to a multi-level knowledge tree, wherein the control system is configured to model the process and is further configured to:

• select a process model based on the multi-level knowledge tree, wherein each level of the knowledge tree corresponds to a category associated with a type of process;
• access historic data related to past process runs for manufacturing the sample;
• access current data obtained from a current process run of the process, wherein the obtained data, which is based on the selected process model, comprises:
• process strategy data, bioreactor instrument data, data from online sensors and/or data from offline sensors;
• subselect historic data of previous process runs similar to the current process run from the accessed historic data;
• predict an outcome of at least one selected parameter selected from cell viability, cell count, product titre, and product quality of the current process run for manufacturing the sample;
• control the process used for manufacturing the sample in a bioreactor based on the predicted outcome of the at least one selected parameter of the current process run;
• automatically determine an updated model for predicting outcomes of future process runs, wherein the updated model is determined based at least in part on:
• the process model based on the multi-level knowledge tree;
• and
• additional data from the current process run;
• and
• applying the updated model to future process runs of other samples.

A method for predicting forecasts for a feature in a process used for manufacturing a sample in a bioreactor during a process run, the process belonging to a multi-level knowledge tree, wherein each level of the knowledge-tree corresponds to a category associated with a type of process, values related to the feature being continuously measured during a current process run, wherein the method comprises:

• creating a model for the current process run based on a selection of historic data;
• after a time period during the current process run, automatically selecting best fitting historic data related to the values related to the feature being continuously measured during the current process run by subselecting historic data of previous process runs similar to the current process run, and updating the model to produce an updated model, wherein the updated model is determined based on the best fitting historic data and the model;
• revising forecasts during the current process run of at least one process parameter selected from cell viability, cell count, product titre, and product quality from the updated model based on calculated errors between measured values and the updated model;
• and
• applying the updated model for future process runs of other samples.