EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Informing agent-based models with spatial data using convolutional autoencoders

Bi-Rong Wang iD, Chen-Yi Liao iD, Erik H J Danen iD, Elsa Neubert iD, Federica Eduati iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag444 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Bi-Rong Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven 5600MB, The Netherlands. Hauptthemen laut MEDLINE: Models, Biological, Computational Biology, Image Processing, Computer-Assisted. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Netherlands Organization for Scientific Research, NWO Aspasia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, BiologicalComputational BiologyImage Processing, Computer-AssistedAutoencoderHumansConvolutional Neural NetworksMelanomaComputer Simulation

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven 5600MB, The Netherlands.
  • Institute for Complex Molecular Systems, Eindhoven University of Technology, Eindhoven 5600MB, The Netherlands.
  • Leiden Academic Center for Drug Research, Leiden University, Leiden, the Netherlands.

ORCID-Profile: Bi-Rong Wang, Chen-Yi Liao, Erik H J Danen, Elsa Neubert, Federica Eduati

Förderung

  • Netherlands Organization for Scientific Research
  • NWO Aspasia

Zitieren

APA

Wang, B. R., Liao, C. Y., Danen, E. H. J., Neubert, E., & Eduati, F. (2026). Informing agent-based models with spatial data using convolutional autoencoders. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag444

Vancouver

Wang BR, Liao CY, Danen EHJ, Neubert E, Eduati F. Informing agent-based models with spatial data using convolutional autoencoders. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag444

BibTeX
@article{Wang2026,
  author = {Wang, Bi-Rong and Liao, Chen-Yi and Danen, Erik H J and Neubert, Elsa and Eduati, Federica},
  title = {Informing agent-based models with spatial data using convolutional autoencoders},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag444}
}
Kostenlos starten →