Informing agent-based models with spatial data using convolutional autoencoders

Bioinformatics, vol. 42

Abstract

MOTIVATION: Spatial computational models such as agent-based models (ABMs) offer powerful in silico tools to study tumor dynamics, yet imaging data are still rarely used to inform these models directly. RESULTS: We present an ABM optimization framework that leverages convolutional encoders to compare spatial patterns between experimental imaging data and ABM-generated outputs within a shared latent space. This quantitative comparison was used to estimate ABM parameters across three datasets, ranging from synthetic data to 3D tumoroid-T cell co-culture microscopy and histopathology images from The Cancer Genome Atlas skin cutaneous melanoma samples. Estimated parameters were evaluated using data-derived features and experimental knowledge, including experimental conditions and gene expressions. Simulations using optimized parameters reproduced key spatial features of the training images, such as tumor boundary complexity and tumor-tumor neighborhood structure. Together, these results demonstrate a flexible framework for ABM parameter optimization using spatial data across modalities, enabling systematic investigation of how spatial architecture influences tumor progression and immune interactions. AVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/SysBioOncology/ AutoencoderABM under the GPL-3.0 license, with corresponding data sets at https://zenodo.org/records/19022344.

Authors 5

1. Bi-rong Wang

   Eindhoven University of Technology

   Affiliation as printed

   Department of Biomedical Engineering, Eindhoven University of Technology , Eindhoven 5600MB,

   Institute for Complex Molecular Systems, Eindhoven University of Technology , Eindhoven 5600MB,

2. Chen-yi Anita Liao Aachen Leiden Academic Centre for Drug Research

   Leiden University

   Affiliation as printed

   Leiden Academic Center for Drug Research, Leiden University , Leiden,

3. Erik H.J. Danen Aachen Leiden Academic Centre for Drug Research

   Leiden University

   Affiliation as printed

   Leiden Academic Center for Drug Research, Leiden University , Leiden,

4. Elsa Neubert Aachen Leiden Academic Centre for Drug Research

   Leiden University

   Affiliation as printed

   Leiden Academic Center for Drug Research, Leiden University , Leiden,

5. Federica Eduati

   Eindhoven University of Technology

   Affiliation as printed

   Department of Biomedical Engineering, Eindhoven University of Technology , Eindhoven 5600MB,

   Institute for Complex Molecular Systems, Eindhoven University of Technology , Eindhoven 5600MB,