Iterative design of training data to control intricate enzymatic reaction networks
Abstract Kinetic modeling of in vitro enzymatic reaction networks is vital to understand and control the complex behaviors emerging from the nonlinear interactions inside. However, modeling is severely hampered by the lack of training data. Here, we introduce a methodology that combines an active le...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-45886-9 |
| _version_ | 1797273914419707904 |
|---|---|
| author | Bob van Sluijs Tao Zhou Britta Helwig Mathieu G. Baltussen Frank H. T. Nelissen Hans A. Heus Wilhelm T. S. Huck |
| author_facet | Bob van Sluijs Tao Zhou Britta Helwig Mathieu G. Baltussen Frank H. T. Nelissen Hans A. Heus Wilhelm T. S. Huck |
| author_sort | Bob van Sluijs |
| collection | DOAJ |
| description | Abstract Kinetic modeling of in vitro enzymatic reaction networks is vital to understand and control the complex behaviors emerging from the nonlinear interactions inside. However, modeling is severely hampered by the lack of training data. Here, we introduce a methodology that combines an active learning-like approach and flow chemistry to efficiently create optimized datasets for a highly interconnected enzymatic reactions network with multiple sub-pathways. The optimal experimental design (OED) algorithm designs a sequence of out-of-equilibrium perturbations to maximize the information about the reaction kinetics, yielding a descriptive model that allows control of the output of the network towards any cost function. We experimentally validate the model by forcing the network to produce different product ratios while maintaining a minimum level of overall conversion efficiency. Our workflow scales with the complexity of the system and enables the optimization of previously unobtainable network outputs. |
| first_indexed | 2024-03-07T14:50:56Z |
| format | Article |
| id | doaj.art-d5a464a37bce4137a6e01321164f58f7 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-07T14:50:56Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-d5a464a37bce4137a6e01321164f58f72024-03-05T19:43:50ZengNature PortfolioNature Communications2041-17232024-02-0115111010.1038/s41467-024-45886-9Iterative design of training data to control intricate enzymatic reaction networksBob van Sluijs0Tao Zhou1Britta Helwig2Mathieu G. Baltussen3Frank H. T. Nelissen4Hans A. Heus5Wilhelm T. S. Huck6Institute for Molecules and Materials, Radboud UniversityInstitute for Molecules and Materials, Radboud UniversityInstitute for Molecules and Materials, Radboud UniversityInstitute for Molecules and Materials, Radboud UniversityInstitute for Molecules and Materials, Radboud UniversityInstitute for Molecules and Materials, Radboud UniversityInstitute for Molecules and Materials, Radboud UniversityAbstract Kinetic modeling of in vitro enzymatic reaction networks is vital to understand and control the complex behaviors emerging from the nonlinear interactions inside. However, modeling is severely hampered by the lack of training data. Here, we introduce a methodology that combines an active learning-like approach and flow chemistry to efficiently create optimized datasets for a highly interconnected enzymatic reactions network with multiple sub-pathways. The optimal experimental design (OED) algorithm designs a sequence of out-of-equilibrium perturbations to maximize the information about the reaction kinetics, yielding a descriptive model that allows control of the output of the network towards any cost function. We experimentally validate the model by forcing the network to produce different product ratios while maintaining a minimum level of overall conversion efficiency. Our workflow scales with the complexity of the system and enables the optimization of previously unobtainable network outputs.https://doi.org/10.1038/s41467-024-45886-9 |
| spellingShingle | Bob van Sluijs Tao Zhou Britta Helwig Mathieu G. Baltussen Frank H. T. Nelissen Hans A. Heus Wilhelm T. S. Huck Iterative design of training data to control intricate enzymatic reaction networks Nature Communications |
| title | Iterative design of training data to control intricate enzymatic reaction networks |
| title_full | Iterative design of training data to control intricate enzymatic reaction networks |
| title_fullStr | Iterative design of training data to control intricate enzymatic reaction networks |
| title_full_unstemmed | Iterative design of training data to control intricate enzymatic reaction networks |
| title_short | Iterative design of training data to control intricate enzymatic reaction networks |
| title_sort | iterative design of training data to control intricate enzymatic reaction networks |
| url | https://doi.org/10.1038/s41467-024-45886-9 |
| work_keys_str_mv | AT bobvansluijs iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks AT taozhou iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks AT brittahelwig iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks AT mathieugbaltussen iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks AT frankhtnelissen iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks AT hansaheus iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks AT wilhelmtshuck iterativedesignoftrainingdatatocontrolintricateenzymaticreactionnetworks |