Automated Microorganism Model Refinement via Experimental Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for simulating microorganism behavior are limited in accurately predicting responses to environmental conditions and genetic modifications, making it difficult to refine models and optimize microorganism performance for applications such as increased growth rates or substance production.

Innovation Solution

A system comprising an incubator, sensor, automated laboratory, and controller that subjects microorganisms to various environmental conditions, measures external and internal characteristics, and updates models based on measured data to adjust parameters and improve prediction accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If models are refined through extensive experimentation and parameter adjustment, then prediction accuracy improves, but time consumption and cost increase

Engineering Contradiction:
Improveprediction accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically designing and executing experiments to collect data on microorganism responses to environmental conditions and genetic modifications. This preliminary data collection enables subsequent model refinement without requiring extensive manual experimentation, thus improving prediction accuracy while reducing time consumption.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously comparing model predictions with actual experimental measurements of microorganism behavior. The controller automatically adjusts model parameters based on this feedback loop, enabling iterative refinement of prediction accuracy without requiring manual intervention for each adjustment, thereby reducing both time and cost.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If comprehensive measurements of internal characteristics are performed, then model parameter accuracy improves, but device complexity and operational difficulty increase

Engineering Contradiction:
Improvemodel parameter accuracyVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The controller serves multiple functions: it manages the incubator environment, operates sensors for measurements, controls the automated laboratory equipment, and performs model parameter adjustment. This multi-functionality consolidates what would otherwise require separate complex devices into a single integrated system, reducing overall device complexity while maintaining comprehensive measurement capabilities.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs self-service by automatically analyzing measurement data and adjusting model parameters without requiring manual intervention. The controller autonomously determines which internal characteristics need measurement and processes the results to refine model parameters, reducing operational difficulty while maintaining high measurement precision.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3443069B1Simulating living cell in silico
Publication Date: 2021.02.24 X DEVELOPMENT LLC
  • EP3443069B1 patent drawingFigure 1
  • EP3443069B1 patent drawingFigure 2
  • EP3443069B1 patent drawingFigure 3

AI summary

The behavior and/or internal activities of a microorganism can be simulated using a model of the microorganism. Such simulations can be used to determine the efficacy of treatments, disinfectants, antibiotics, chemotherapies, or other methods of interacting with the microorganism, or to provide some other information about the microorganism. Systems and methods are provided herein for fitting, refining, or otherwise improving such models in an automated fashion. Such systems and methods include performing whole-cell experiments to determine a correspondence between the predictions of such models and the actual behavior of samples of the microorganism. Such systems and methods also include, based on such determined correspondences, directly assessing determined discrete sets of properties of the microorganism and/or of constituents of the microorganism and updating parameters of the model corresponding to the properties of the discrete set such that the overall accuracy of the model is improved.