Multi-level machine learning for predictive and prescriptive applications

A non-transitory machine-readable storage medium storing instructions that, when executed by a processing device associated with a cell growth system, cause the processing device to perform operations comprising:

• generating training data for a machine learning model, wherein generating the training data comprises:
• identifying a first training input comprising:
• one or more first growth input parameter values indicative of a first growth rate of a first cell culture,
• output from a mechanistic model, wherein the output from the mechanistic model is based on model input comprising cell growth data of the cell growth system, and
• output from a statistical model, wherein the output from the statistical model is based on model input comprising cell growth data of the cell growth system;
• identifying a first target output for the first training input, wherein the first target output comprises a first prescriptive action that alters a first yield of a target product of the first cell culture, wherein the first prescriptive action modifies a first metabolism rate of the first cell culture;
• and
• providing the training data to train the machine learning model on (i) a set of training inputs comprising the first training input;
• and (ii) a set of target outputs comprising the first target output, wherein the machine learning model is to receive a new input having new cell growth data comprising one or more new growth input parameter values indicative of a new growth rate of a new cell culture and to produce a new output based on the new input, the new output indicating a new prescriptive action that alters a new yield of the target product of the new cell culture, based on at least the output from the mechanistic model and the output from the statistical model, wherein the new prescriptive action modifies a new metabolism rate of the new cell culture.

A system, comprising memory and a processing device coupled to the memory, wherein the processing device is to:

• receive cell growth data associated with a current cell culture of a cell growth system, the cell growth data comprising:
• growth input parameter values indicative of a growth rate of the current cell culture, and
• process analytical technology (PAT) sensor data comprising indications of one or more of cell count, density, or target product formation;
• provid the cell growth data to a mechanistic model as input;
• obtain, from the mechanistic model, mechanistic output comprising a prediction of future conditions of the current cell culture based on the cell growth data;
• provid the cell growth data to a statistical model;
• obtain, from the statistical model, statistical output comprising relationships in the cell growth data and historical cell growth data based on the cell growth data;
• identify, using a first machine learning model, a prescriptive action to alter a yield of a target product of the current cell culture based on the mechanistic output and the statistical output, wherein the prescriptive action modifies a metabolism rate of the current cell culture, the prescriptive action comprising an adjustment to at least one of feed flow rate, air flow rate, agitation rate, applied heat, applied pressure, or oxygen flow rate;
• identify, using the first machine learning model, a first level of confidence that the prescriptive action, when performed, alters the yield of the target product;
• and
• cause the cell growth system to perform the identified prescriptive action in view of the first level of confidence.