Bridging the gap between mechanistic biological models and machine learning surrogates.
Mechanistic models have been used for centuries to describe complex interconnected processes, including biological ones. As the scope of these models has widened, so have their computational demands. This complexity can limit their suitability when running many simulations or when real-time results...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-04-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1010988 |
| _version_ | 1797829985192378368 |
|---|---|
| author | Ioana M Gherman Zahraa S Abdallah Wei Pang Thomas E Gorochowski Claire S Grierson Lucia Marucci |
| author_facet | Ioana M Gherman Zahraa S Abdallah Wei Pang Thomas E Gorochowski Claire S Grierson Lucia Marucci |
| author_sort | Ioana M Gherman |
| collection | DOAJ |
| description | Mechanistic models have been used for centuries to describe complex interconnected processes, including biological ones. As the scope of these models has widened, so have their computational demands. This complexity can limit their suitability when running many simulations or when real-time results are required. Surrogate machine learning (ML) models can be used to approximate the behaviour of complex mechanistic models, and once built, their computational demands are several orders of magnitude lower. This paper provides an overview of the relevant literature, both from an applicability and a theoretical perspective. For the latter, the paper focuses on the design and training of the underlying ML models. Application-wise, we show how ML surrogates have been used to approximate different mechanistic models. We present a perspective on how these approaches can be applied to models representing biological processes with potential industrial applications (e.g., metabolism and whole-cell modelling) and show why surrogate ML models may hold the key to making the simulation of complex biological systems possible using a typical desktop computer. |
| first_indexed | 2024-04-09T13:28:56Z |
| format | Article |
| id | doaj.art-c4c8a58fa00c4437b06968a41f641a69 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-04-09T13:28:56Z |
| publishDate | 2023-04-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-c4c8a58fa00c4437b06968a41f641a692023-05-10T05:30:50ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582023-04-01194e101098810.1371/journal.pcbi.1010988Bridging the gap between mechanistic biological models and machine learning surrogates.Ioana M GhermanZahraa S AbdallahWei PangThomas E GorochowskiClaire S GriersonLucia MarucciMechanistic models have been used for centuries to describe complex interconnected processes, including biological ones. As the scope of these models has widened, so have their computational demands. This complexity can limit their suitability when running many simulations or when real-time results are required. Surrogate machine learning (ML) models can be used to approximate the behaviour of complex mechanistic models, and once built, their computational demands are several orders of magnitude lower. This paper provides an overview of the relevant literature, both from an applicability and a theoretical perspective. For the latter, the paper focuses on the design and training of the underlying ML models. Application-wise, we show how ML surrogates have been used to approximate different mechanistic models. We present a perspective on how these approaches can be applied to models representing biological processes with potential industrial applications (e.g., metabolism and whole-cell modelling) and show why surrogate ML models may hold the key to making the simulation of complex biological systems possible using a typical desktop computer.https://doi.org/10.1371/journal.pcbi.1010988 |
| spellingShingle | Ioana M Gherman Zahraa S Abdallah Wei Pang Thomas E Gorochowski Claire S Grierson Lucia Marucci Bridging the gap between mechanistic biological models and machine learning surrogates. PLoS Computational Biology |
| title | Bridging the gap between mechanistic biological models and machine learning surrogates. |
| title_full | Bridging the gap between mechanistic biological models and machine learning surrogates. |
| title_fullStr | Bridging the gap between mechanistic biological models and machine learning surrogates. |
| title_full_unstemmed | Bridging the gap between mechanistic biological models and machine learning surrogates. |
| title_short | Bridging the gap between mechanistic biological models and machine learning surrogates. |
| title_sort | bridging the gap between mechanistic biological models and machine learning surrogates |
| url | https://doi.org/10.1371/journal.pcbi.1010988 |
| work_keys_str_mv | AT ioanamgherman bridgingthegapbetweenmechanisticbiologicalmodelsandmachinelearningsurrogates AT zahraasabdallah bridgingthegapbetweenmechanisticbiologicalmodelsandmachinelearningsurrogates AT weipang bridgingthegapbetweenmechanisticbiologicalmodelsandmachinelearningsurrogates AT thomasegorochowski bridgingthegapbetweenmechanisticbiologicalmodelsandmachinelearningsurrogates AT clairesgrierson bridgingthegapbetweenmechanisticbiologicalmodelsandmachinelearningsurrogates AT luciamarucci bridgingthegapbetweenmechanisticbiologicalmodelsandmachinelearningsurrogates |