Distilling identifiable and interpretable dynamic models from biological data.
Mechanistic dynamical models allow us to study the behavior of complex biological systems. They can provide an objective and quantitative understanding that would be difficult to achieve through other means. However, the systematic development of these models is a non-trivial exercise and an open pr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-10-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011014&type=printable |
| _version_ | 1797640246732521472 |
|---|---|
| author | Gemma Massonis Alejandro F Villaverde Julio R Banga |
| author_facet | Gemma Massonis Alejandro F Villaverde Julio R Banga |
| author_sort | Gemma Massonis |
| collection | DOAJ |
| description | Mechanistic dynamical models allow us to study the behavior of complex biological systems. They can provide an objective and quantitative understanding that would be difficult to achieve through other means. However, the systematic development of these models is a non-trivial exercise and an open problem in computational biology. Currently, many research efforts are focused on model discovery, i.e. automating the development of interpretable models from data. One of the main frameworks is sparse regression, where the sparse identification of nonlinear dynamics (SINDy) algorithm and its variants have enjoyed great success. SINDy-PI is an extension which allows the discovery of rational nonlinear terms, thus enabling the identification of kinetic functions common in biochemical networks, such as Michaelis-Menten. SINDy-PI also pays special attention to the recovery of parsimonious models (Occam's razor). Here we focus on biological models composed of sets of deterministic nonlinear ordinary differential equations. We present a methodology that, combined with SINDy-PI, allows the automatic discovery of structurally identifiable and observable models which are also mechanistically interpretable. The lack of structural identifiability and observability makes it impossible to uniquely infer parameter and state variables, which can compromise the usefulness of a model by distorting its mechanistic significance and hampering its ability to produce biological insights. We illustrate the performance of our method with six case studies. We find that, despite enforcing sparsity, SINDy-PI sometimes yields models that are unidentifiable. In these cases we show how our method transforms their equations in order to obtain a structurally identifiable and observable model which is also interpretable. |
| first_indexed | 2024-03-11T13:28:06Z |
| format | Article |
| id | doaj.art-1225c4bb0dd74c2c8a4a56f9d90b87f3 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-03-11T13:28:06Z |
| publishDate | 2023-10-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-1225c4bb0dd74c2c8a4a56f9d90b87f32023-11-03T05:31:43ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582023-10-011910e101101410.1371/journal.pcbi.1011014Distilling identifiable and interpretable dynamic models from biological data.Gemma MassonisAlejandro F VillaverdeJulio R BangaMechanistic dynamical models allow us to study the behavior of complex biological systems. They can provide an objective and quantitative understanding that would be difficult to achieve through other means. However, the systematic development of these models is a non-trivial exercise and an open problem in computational biology. Currently, many research efforts are focused on model discovery, i.e. automating the development of interpretable models from data. One of the main frameworks is sparse regression, where the sparse identification of nonlinear dynamics (SINDy) algorithm and its variants have enjoyed great success. SINDy-PI is an extension which allows the discovery of rational nonlinear terms, thus enabling the identification of kinetic functions common in biochemical networks, such as Michaelis-Menten. SINDy-PI also pays special attention to the recovery of parsimonious models (Occam's razor). Here we focus on biological models composed of sets of deterministic nonlinear ordinary differential equations. We present a methodology that, combined with SINDy-PI, allows the automatic discovery of structurally identifiable and observable models which are also mechanistically interpretable. The lack of structural identifiability and observability makes it impossible to uniquely infer parameter and state variables, which can compromise the usefulness of a model by distorting its mechanistic significance and hampering its ability to produce biological insights. We illustrate the performance of our method with six case studies. We find that, despite enforcing sparsity, SINDy-PI sometimes yields models that are unidentifiable. In these cases we show how our method transforms their equations in order to obtain a structurally identifiable and observable model which is also interpretable.https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011014&type=printable |
| spellingShingle | Gemma Massonis Alejandro F Villaverde Julio R Banga Distilling identifiable and interpretable dynamic models from biological data. PLoS Computational Biology |
| title | Distilling identifiable and interpretable dynamic models from biological data. |
| title_full | Distilling identifiable and interpretable dynamic models from biological data. |
| title_fullStr | Distilling identifiable and interpretable dynamic models from biological data. |
| title_full_unstemmed | Distilling identifiable and interpretable dynamic models from biological data. |
| title_short | Distilling identifiable and interpretable dynamic models from biological data. |
| title_sort | distilling identifiable and interpretable dynamic models from biological data |
| url | https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011014&type=printable |
| work_keys_str_mv | AT gemmamassonis distillingidentifiableandinterpretabledynamicmodelsfrombiologicaldata AT alejandrofvillaverde distillingidentifiableandinterpretabledynamicmodelsfrombiologicaldata AT juliorbanga distillingidentifiableandinterpretabledynamicmodelsfrombiologicaldata |