Jean‐Loup Faulon

This paper develops growth-coupled metabolic biosensors for disease detection and prognosis using COVID-19 as a proof-of-concept, achieving high diagnostic and prognostic accuracy.

This paper demonstrates using E. coli as a living reservoir computer to classify COVID-19 plasma samples and perform nonlinear computations through growth responses.

The paper develops a cell-free transcriptomics platform using active learning to optimize buffer conditions, significantly increasing mRNA yield and enabling deeper insights into genome regulation.

This paper introduces ChemProFlow, a framework that maps molecular transportability to microorganisms by predicting transport mechanisms and identifying relevant organisms.

dAMN predicts bacterial growth dynamics using a hybrid neural-mechanistic model, achieving high accuracy across diverse nutrient environments and capturing lag phase adaptation.

This paper uses large language models and active learning to optimize cell-free protein synthesis, achieving significant yield improvements for antimicrobial proteins.

This paper introduces a hybrid neural-mechanistic model that improves phenotype predictions for microorganisms by combining machine learning with constraint-based metabolic models.

Galaxy-SynBioCAD provides an automated pipeline for synthetic biology design and engineering, achieving an 83% success rate in retrieving validated pathways.

PeroxiHUB is a cell-free biosensing platform that detects metabolites by converting them into H2O2 using enzymatic transducers, enabling modular and scalable detection.

The paper introduces METIS, an active learning workflow for optimizing genetic and metabolic networks, demonstrating significant improvements in efficiency with minimal experiments.

This paper develops exonuclease-deficient cell-free extracts and optimized buffers to enable robust expression from unprotected linear DNA without additional protection strategies.

The paper uses active learning to explore a large combinatorial space of cell-free compositions to maximize protein production and identify critical parameters.

This paper introduces a reinforcement learning approach for bio-retrosynthesis to design metabolic pathways, validated on curated datasets and with media supplement suggestions.

The paper introduces metabolic perceptrons for binary classification of metabolite combinations using computational models and experimental validation in synthetic biological circuits.

This paper introduces hybrid cell-free biosensors that expand the range of detectable chemicals by combining synthetic metabolic cascades with transcription factor-based networks.

PartsGenie is a tool for designing and sharing synthetic biology parts, integrating optimization, data standards, and repository access.

Selenzyme is an online tool that helps select enzymes for metabolic pathway design by analyzing sequence, reaction, and organism-related data.

RetroPath2.0 is an open-source retrosynthesis workflow that streamlines pathway design for metabolic engineering by using generalized reaction rules and KNIME.

The paper demonstrates the use of RetroPath2.0 for molecular structure enumeration and virtual screening in chemical space, including applications for glass transition temperature prediction and antibacterial activity optimization.