Article Dans Une Revue iScience Année : 2025

An AI-driven workflow for the accelerated optimization of cell-free protein synthesis

Un flux de travail guidé par l'IA pour une accélération de l'optimisation d'un système acellulaire de synthèse de protéines

Résumé

Cell-free protein synthesis (CFPS) is a versatile tool for rapid biological prototyping. However, exploring the large number of component combinations is a very time-consuming process. Active learning (AL) is known to reduce the number of experiments required, but is rarely integrated into routine laboratory workflows. To address this, we developed a fully automated Design-Build-Test-Learn (DBTL) pipeline that streamlines this optimization process with an improved AL strategy that selects informative and diverse experimental conditions. The Design phase was created entirely using ChatGPT-4 without manual code revisions, dramatically reducing coding time. This pipeline was implemented in a modular way within the Galaxy platform, following the Findable-Accessible-Interoperable-Reusable (FAIR) principles. When applied to the optimization of colicin M and E1 in both Escherichia coli and HeLa-based CFPS systems, a 2- to 9-fold increase in yield was achieved in just four cycles. This framework enables reliable, automated workflows for routine synthetic biology.

DOI

Est documentée par 10.5281/zenodo.14902238 Jeu de données Hérisson, J. (2025). Full sequences for DNA constructs expressing colicins M and E1 in CFPS systems [Data set]. Zenodo. https://doi.org/10.5281/ZENODO.14902238

Fully annotated DNA constructs
DOI

Est documentée par 10.5281/zenodo.14900104 Ouvrage Joan Hérisson, Yorgo El Moubayed, GuillaumeG, & Thomas Duigou. (2025). brsynth/icfree-ml: Release 2.9.1 (Version 2.9.1). Zenodo. https://doi.org/10.5281/ZENODO.14900104

Original code
DOI

Est documentée par 10.5281/zenodo.14893904 Article Microbiologie de l’alimentation au service de la santé. (2025). icfree conda package. Zenodo. https://doi.org/10.5281/ZENODO.14893904

Conda packages
DOI

Est documentée par 10.5281/zenodo.14893963 Article Microbiologie de l’alimentation au service de la santé. (2025). icfree-ml Galaxy wrappers suite. Zenodo. https://doi.org/10.5281/ZENODO.14893963

Galaxy wrappers
DOI

Est documentée par 10.5281/zenodo.14901023 Article Hérisson, J. (2025). AI-CellFree - Init. Zenodo. https://doi.org/10.5281/ZENODO.14901023

Galaxy workflow AI-CellFree - Init
DOI

Est documentée par 10.5281/zenodo.14899706 Article Hérisson, J. (2025). AI-CellFree - Core. Zenodo. https://doi.org/10.5281/ZENODO.14899706

Galaxy workflow AI-CellFree - Core

Dates et versions

hal-05315797 , version 1 (15-10-2025)

Identifiants

Citer

Mostafa Khalil, Aisha Elsawah, An Hoang, Jean-Loup Faulon, Baptiste Panthu, et al.. An AI-driven workflow for the accelerated optimization of cell-free protein synthesis. iScience, 2025, 28 (10), pp.113599. ⟨10.1016/j.isci.2025.113599⟩. ⟨hal-05315797⟩
155 Consultations
0 Téléchargements

Altmetric

Partager

  • More