Physiology-informed regularisation enables training of universal differential equation systems for biological applications.
Systems biology tackles the challenge of understanding the high complexity in the internal regulation of homeostasis in the human body through mathematical modelling. These models can aid in the discovery of disease mechanisms and potential drug targets. However, on one hand the development and vali...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1012198 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540315730313216 |
|---|---|
| author | Max de Rooij Balázs Erdős Natal A W van Riel Shauna D O'Donovan |
| author_facet | Max de Rooij Balázs Erdős Natal A W van Riel Shauna D O'Donovan |
| author_sort | Max de Rooij |
| collection | DOAJ |
| description | Systems biology tackles the challenge of understanding the high complexity in the internal regulation of homeostasis in the human body through mathematical modelling. These models can aid in the discovery of disease mechanisms and potential drug targets. However, on one hand the development and validation of knowledge-based mechanistic models is time-consuming and does not scale well with increasing features in medical data. On the other hand, data-driven approaches such as machine learning models require large volumes of data to produce generalisable models. The integration of neural networks and mechanistic models, forming universal differential equation (UDE) models, enables the automated learning of unknown model terms with less data than neural networks alone. Nevertheless, estimating parameters for these hybrid models remains difficult with sparse data and limited sampling durations that are common in biological applications. In this work, we propose the use of physiology-informed regularisation, penalising biologically implausible model behavior to guide the UDE towards more physiologically plausible regions of the solution space. In a simulation study we show that physiology-informed regularisation not only results in a more accurate forecasting of model behaviour, but also supports training with less data. We also applied this technique to learn a representation of the rate of glucose appearance in the glucose minimal model using meal response data measured in healthy people. In that case, the inclusion of regularisation reduces variability between UDE-embedded neural networks that were trained from different initial parameter guesses. |
| format | Article |
| id | doaj-art-433758913d3b42e8a955dc5ffb60dec3 |
| institution | Kabale University |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-433758913d3b42e8a955dc5ffb60dec32025-02-05T05:30:38ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-01-01211e101219810.1371/journal.pcbi.1012198Physiology-informed regularisation enables training of universal differential equation systems for biological applications.Max de RooijBalázs ErdősNatal A W van RielShauna D O'DonovanSystems biology tackles the challenge of understanding the high complexity in the internal regulation of homeostasis in the human body through mathematical modelling. These models can aid in the discovery of disease mechanisms and potential drug targets. However, on one hand the development and validation of knowledge-based mechanistic models is time-consuming and does not scale well with increasing features in medical data. On the other hand, data-driven approaches such as machine learning models require large volumes of data to produce generalisable models. The integration of neural networks and mechanistic models, forming universal differential equation (UDE) models, enables the automated learning of unknown model terms with less data than neural networks alone. Nevertheless, estimating parameters for these hybrid models remains difficult with sparse data and limited sampling durations that are common in biological applications. In this work, we propose the use of physiology-informed regularisation, penalising biologically implausible model behavior to guide the UDE towards more physiologically plausible regions of the solution space. In a simulation study we show that physiology-informed regularisation not only results in a more accurate forecasting of model behaviour, but also supports training with less data. We also applied this technique to learn a representation of the rate of glucose appearance in the glucose minimal model using meal response data measured in healthy people. In that case, the inclusion of regularisation reduces variability between UDE-embedded neural networks that were trained from different initial parameter guesses.https://doi.org/10.1371/journal.pcbi.1012198 |
| spellingShingle | Max de Rooij Balázs Erdős Natal A W van Riel Shauna D O'Donovan Physiology-informed regularisation enables training of universal differential equation systems for biological applications. PLoS Computational Biology |
| title | Physiology-informed regularisation enables training of universal differential equation systems for biological applications. |
| title_full | Physiology-informed regularisation enables training of universal differential equation systems for biological applications. |
| title_fullStr | Physiology-informed regularisation enables training of universal differential equation systems for biological applications. |
| title_full_unstemmed | Physiology-informed regularisation enables training of universal differential equation systems for biological applications. |
| title_short | Physiology-informed regularisation enables training of universal differential equation systems for biological applications. |
| title_sort | physiology informed regularisation enables training of universal differential equation systems for biological applications |
| url | https://doi.org/10.1371/journal.pcbi.1012198 |
| work_keys_str_mv | AT maxderooij physiologyinformedregularisationenablestrainingofuniversaldifferentialequationsystemsforbiologicalapplications AT balazserdos physiologyinformedregularisationenablestrainingofuniversaldifferentialequationsystemsforbiologicalapplications AT natalawvanriel physiologyinformedregularisationenablestrainingofuniversaldifferentialequationsystemsforbiologicalapplications AT shaunadodonovan physiologyinformedregularisationenablestrainingofuniversaldifferentialequationsystemsforbiologicalapplications |