Informing agent-based models with spatial data using convolutional autoencoders

Wang, B.R.; Liao, C.Y.; Danen, E.H.J.; Neubert, E.; Eduati, F.

doi:doi:10.1093/bioinformatics/btag444

MOTIVATION\nRESULTS\nAVAILABILITY AND IMPLEMENTATION\nSpatial 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.\nWe 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...Show moreMOTIVATION\nRESULTS\nAVAILABILITY AND IMPLEMENTATION\nSpatial 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.\nWe 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.\nSource 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.Show less

Leiden University Scholarly Publications

View statistics

Documents

In Collections

Informing agent-based models with spatial data using convolutional autoencoders