Matching models across abstraction levels with Gaussian Processes

TL;DR

This paper introduces a statistical machine learning method using Gaussian Processes to reconcile and quantitatively compare predictions of biological models at different abstraction levels, ensuring their outputs are statistically aligned.

Contribution

The paper presents a novel correction map approach using Gaussian Processes to automatically align model predictions across abstraction levels in biological systems.

Findings

Method successfully reconciles model predictions in biological examples.

Provides a quantitative measure of agreement between models.

Demonstrates flexibility and potential for broader applications.

Abstract

Biological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study. Such different models often provide qualitatively concordant predictions over specific parametrisations, but it is generally unclear whether model predictions are quantitatively in agreement, and whether such agreement holds for different parametrisations. Here we present a generally applicable statistical machine learning methodology to automatically reconcile the predictions of different models across abstraction levels. Our approach is based on defining a correction map, a random function which modifies the output of a model in order to match the statistics of the output of a different model of the same system. We use two biological examples to give a proof-of-principle demonstration of the methodology, and discuss its advantages and potential further applications.