Lab-in-the-Loop
An iterative closed-loop method that combines machine learning models with high-throughput experimentation. The model proposes experimental points, the experimental side executes them rapidly and feeds data back to update the model, maximizing information gain under a limited experimental budget.
Timeline (last 90 days)
Leash Bio uses a Lab-in-the-Loop closed-loop approach, combining DEL experiments with iterative AI model updates to run the cycle of experimental design and data analysis at computational speed.
The Lab-in-the-Loop concept originates from active learning and Bayesian optimization and has mature applications in materials science and synthetic biology (such as Microsoft's MatterGen, A-Lab, and other robotic experiment platforms).
Under the Lab-in-the-Loop model, the difference between completing one iteration in a month versus one iteration in a week is an order of magnitude in model performance.
All Facts (3)
Leash Bio uses a Lab-in-the-Loop closed-loop approach, combining DEL experiments with iterative AI model updates to run the cycle of experimental design and data analysis at computational speed.
50%UnverifiedThe Lab-in-the-Loop concept originates from active learning and Bayesian optimization and has mature applications in materials science and synthetic biology (such as Microsoft's MatterGen, A-Lab, and other robotic experiment platforms).
50%UnverifiedUnder the Lab-in-the-Loop model, the difference between completing one iteration in a month versus one iteration in a week is an order of magnitude in model performance.
50%