Learning Biomolecular Models using Signal Temporal Logic

Hanna Krasowski, Eric Palanques-Tost, Calin Belta, Murat Arcak
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:1365-1377, 2025.

Abstract

Modeling dynamical biological systems is key for understanding, predicting, and controlling complex biological behaviors. Traditional methods for identifying governing equations, such as ordinary differential equations (ODEs), typically require extensive quantitative data, which is often scarce in biological systems due to experimental limitations. To address this challenge, we introduce an approach that determines biomolecular models from qualitative system behaviors expressed as Signal Temporal Logic (STL) statements, which are naturally suited to translate expert knowledge into computationally tractable specifications. Our method represents the biological network as a graph, where edges represent interactions between species, and uses a genetic algorithm to identify the graph. To infer the parameters of the ODEs modeling the interactions, we propose a gradient-based algorithm. On a numerical example, we evaluate two loss functions using STL robustness and analyze different initialization techniques to improve the convergence of the approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-krasowski25a, title = {Learning Biomolecular Models using Signal Temporal Logic}, author = {Krasowski, Hanna and Palanques-Tost, Eric and Belta, Calin and Arcak, Murat}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {1365--1377}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/krasowski25a/krasowski25a.pdf}, url = {https://proceedings.mlr.press/v283/krasowski25a.html}, abstract = {Modeling dynamical biological systems is key for understanding, predicting, and controlling complex biological behaviors. Traditional methods for identifying governing equations, such as ordinary differential equations (ODEs), typically require extensive quantitative data, which is often scarce in biological systems due to experimental limitations. To address this challenge, we introduce an approach that determines biomolecular models from qualitative system behaviors expressed as Signal Temporal Logic (STL) statements, which are naturally suited to translate expert knowledge into computationally tractable specifications. Our method represents the biological network as a graph, where edges represent interactions between species, and uses a genetic algorithm to identify the graph. To infer the parameters of the ODEs modeling the interactions, we propose a gradient-based algorithm. On a numerical example, we evaluate two loss functions using STL robustness and analyze different initialization techniques to improve the convergence of the approach.} }
Endnote
%0 Conference Paper %T Learning Biomolecular Models using Signal Temporal Logic %A Hanna Krasowski %A Eric Palanques-Tost %A Calin Belta %A Murat Arcak %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-krasowski25a %I PMLR %P 1365--1377 %U https://proceedings.mlr.press/v283/krasowski25a.html %V 283 %X Modeling dynamical biological systems is key for understanding, predicting, and controlling complex biological behaviors. Traditional methods for identifying governing equations, such as ordinary differential equations (ODEs), typically require extensive quantitative data, which is often scarce in biological systems due to experimental limitations. To address this challenge, we introduce an approach that determines biomolecular models from qualitative system behaviors expressed as Signal Temporal Logic (STL) statements, which are naturally suited to translate expert knowledge into computationally tractable specifications. Our method represents the biological network as a graph, where edges represent interactions between species, and uses a genetic algorithm to identify the graph. To infer the parameters of the ODEs modeling the interactions, we propose a gradient-based algorithm. On a numerical example, we evaluate two loss functions using STL robustness and analyze different initialization techniques to improve the convergence of the approach.
APA
Krasowski, H., Palanques-Tost, E., Belta, C. & Arcak, M.. (2025). Learning Biomolecular Models using Signal Temporal Logic. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:1365-1377 Available from https://proceedings.mlr.press/v283/krasowski25a.html.

Related Material