Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida
Abstract Although synthetic biology can produce valuable chemicals in a renewable manner, its progress is still hindered by a lack of predictive capabilities. Media optimization is a critical, and often overlooked, process which is essential to obtain the titers, rates and yields needed for commerci...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Communications Biology |
| Online Access: | https://doi.org/10.1038/s42003-025-08039-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725145315278848 |
|---|---|
| author | Apostolos Zournas Matthew R. Incha Tijana Radivojevic Vincent Blay Jose Manuel Martí Zak Costello Matthias Schmidt Tan Chung Mitchell G. Thompson Allison Pearson Patrick C. Kinnunen Thomas Eng Christopher E. Lawson Stephen Tan Tadeusz Ogorzalek Nurgul Kaplan Mark Forrer Tyler Backman Aindrila Mukhopadhyay Nathan J. Hillson Jay D. Keasling Hector Garcia Martin |
| author_facet | Apostolos Zournas Matthew R. Incha Tijana Radivojevic Vincent Blay Jose Manuel Martí Zak Costello Matthias Schmidt Tan Chung Mitchell G. Thompson Allison Pearson Patrick C. Kinnunen Thomas Eng Christopher E. Lawson Stephen Tan Tadeusz Ogorzalek Nurgul Kaplan Mark Forrer Tyler Backman Aindrila Mukhopadhyay Nathan J. Hillson Jay D. Keasling Hector Garcia Martin |
| author_sort | Apostolos Zournas |
| collection | DOAJ |
| description | Abstract Although synthetic biology can produce valuable chemicals in a renewable manner, its progress is still hindered by a lack of predictive capabilities. Media optimization is a critical, and often overlooked, process which is essential to obtain the titers, rates and yields needed for commercial viability. Here, we present a molecule- and host-agnostic active learning process for media optimization that is enabled by a fast and highly repeatable semi-automated pipeline. Its application yielded 60% and 70% increases in titer, and 350% increase in process yield in three different campaigns for flaviolin production in Pseudomonas putida KT2440. Explainable Artificial Intelligence techniques pinpointed that, surprisingly, common salt (NaCl) is the most important component influencing production. The optimal salt concentration is very high, comparable to seawater and close to the limits that P. putida can tolerate. The availability of fast Design-Build-Test-Learn (DBTL) cycles allowed us to show that performance improvements for active learning are rarely monotonous. This work illustrates how machine learning and automation can change the paradigm of current synthetic biology research to make it more effective and informative, and suggests a cost-effective and underexploited strategy to facilitate the high titers, rates and yields essential for commercial viability. |
| format | Article |
| id | doaj-art-bfd6f58132da4ec2b154977df7a953d2 |
| institution | DOAJ |
| issn | 2399-3642 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Biology |
| spelling | doaj-art-bfd6f58132da4ec2b154977df7a953d22025-08-20T03:10:32ZengNature PortfolioCommunications Biology2399-36422025-04-018111410.1038/s42003-025-08039-2Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putidaApostolos Zournas0Matthew R. Incha1Tijana Radivojevic2Vincent Blay3Jose Manuel Martí4Zak Costello5Matthias Schmidt6Tan Chung7Mitchell G. Thompson8Allison Pearson9Patrick C. Kinnunen10Thomas Eng11Christopher E. Lawson12Stephen Tan13Tadeusz Ogorzalek14Nurgul Kaplan15Mark Forrer16Tyler Backman17Aindrila Mukhopadhyay18Nathan J. Hillson19Jay D. Keasling20Hector Garcia Martin21Biological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryDepartment of Energy Agile BioFoundryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryBiological Systems and Engineering Division, Lawrence Berkeley National LaboratoryAbstract Although synthetic biology can produce valuable chemicals in a renewable manner, its progress is still hindered by a lack of predictive capabilities. Media optimization is a critical, and often overlooked, process which is essential to obtain the titers, rates and yields needed for commercial viability. Here, we present a molecule- and host-agnostic active learning process for media optimization that is enabled by a fast and highly repeatable semi-automated pipeline. Its application yielded 60% and 70% increases in titer, and 350% increase in process yield in three different campaigns for flaviolin production in Pseudomonas putida KT2440. Explainable Artificial Intelligence techniques pinpointed that, surprisingly, common salt (NaCl) is the most important component influencing production. The optimal salt concentration is very high, comparable to seawater and close to the limits that P. putida can tolerate. The availability of fast Design-Build-Test-Learn (DBTL) cycles allowed us to show that performance improvements for active learning are rarely monotonous. This work illustrates how machine learning and automation can change the paradigm of current synthetic biology research to make it more effective and informative, and suggests a cost-effective and underexploited strategy to facilitate the high titers, rates and yields essential for commercial viability.https://doi.org/10.1038/s42003-025-08039-2 |
| spellingShingle | Apostolos Zournas Matthew R. Incha Tijana Radivojevic Vincent Blay Jose Manuel Martí Zak Costello Matthias Schmidt Tan Chung Mitchell G. Thompson Allison Pearson Patrick C. Kinnunen Thomas Eng Christopher E. Lawson Stephen Tan Tadeusz Ogorzalek Nurgul Kaplan Mark Forrer Tyler Backman Aindrila Mukhopadhyay Nathan J. Hillson Jay D. Keasling Hector Garcia Martin Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida Communications Biology |
| title | Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida |
| title_full | Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida |
| title_fullStr | Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida |
| title_full_unstemmed | Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida |
| title_short | Machine learning-led semi-automated medium optimization reveals salt as key for flaviolin production in Pseudomonas putida |
| title_sort | machine learning led semi automated medium optimization reveals salt as key for flaviolin production in pseudomonas putida |
| url | https://doi.org/10.1038/s42003-025-08039-2 |
| work_keys_str_mv | AT apostoloszournas machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT matthewrincha machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT tijanaradivojevic machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT vincentblay machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT josemanuelmarti machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT zakcostello machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT matthiasschmidt machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT tanchung machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT mitchellgthompson machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT allisonpearson machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT patrickckinnunen machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT thomaseng machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT christopherelawson machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT stephentan machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT tadeuszogorzalek machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT nurgulkaplan machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT markforrer machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT tylerbackman machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT aindrilamukhopadhyay machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT nathanjhillson machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT jaydkeasling machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida AT hectorgarciamartin machinelearningledsemiautomatedmediumoptimizationrevealssaltaskeyforflaviolinproductioninpseudomonasputida |