Collins Lab, MIT
Collins Lab, MIT
Synthetic Biology | Systems Biology | Antibiotics

COLLINS LAB

 

SYNTHETIC biology

Antibiotics & AI

 
IMG_6725 2.jpeg
 
logo_cellfree.png
 
logo_antibio.png
 
 

Synthetic Biology

We are employing engineering principles to model, design and build synthetic gene circuits and programmable cells, in order to create novel classes of diagnostics & therapeutics.  We are also using deep learning approaches to discover new genetic parts and enhance the synthetic biology design process.

 

Antibiotics & AI

As part of the Antibiotics-AI Project, we are harnessing the power of artificial intelligence (AI) to discover novel classes of antibiotics and rapidly understand how they work. We are also using deep learning approaches for the de novo design of new antibiotics and the development of combination treatments.

 


RECENT PUBLICATIONS

 

Artificial intelligence for antibiotic discovery and design

Andreas Luttens, Melis N. Anahtar, Seyed Majed Modaresi, Aarti Krishnan and James J. Collins
Nature Reviews Microbiology (2026)

Antibiotic-resistant bacterial infections cause more than 1 million deaths worldwide each year. To effectively address this escalating global health crisis, there is a critical need for new classes of antibiotics, particularly those with novel mechanisms of action. In this Review, we focus on recent advances in small-molecule antibiotic discovery enabled by artificial intelligence. We present a range of innovative approaches that are substantially increasing the size and diversity of the explored chemical space. We highlight recent artificial intelligence-driven advancements in phenotypic antibiotic discovery, mechanism of action elucidation, target-based discovery, de novo molecular design and lead optimization, which promise to expand the repertoire of antibacterial agents and uncover bacterial pathways and vulnerabilities amenable to therapeutic intervention.

 
 

From code to cure: Harnessing AI for antibiotic discovery and design

Aarti Krishnan, Hanqun Cao, James J. Collins and Cesar de la Fuente-­Nunez
Science Translational Medicine (2026)

Artificial intelligence now enables the exploration of vast chemical and sequence spaces, the design of synthesizable antibiotics, and the prioritization of safe, mechanism-­diverse candidates through integrated modeling and accelerated testing. Here, we survey recent advances in AI for both small-­molecule and peptide antimicrobial drugs, highlight emerging data and reporting standards, and outline translational pathways and regulatory hurdles needed to bring these agents to patients.

 

Deep learning–enabled discovery of antibiotics effective against Neisseria gonorrhoeae

Melis N. Anahtar, Jacqueline A. Valeri, Seyed Majed Modaresi, Aarti Krishnan, Nina M. Donghia, Samantha G. Palace, Erica J. Zheng, Aakanksha Gulati, Alicia Jorgenson, Abidemi Junaid, Parijat Bandyopadhyay, Andreas Luttens, Krishna Suresh, Paige Edwards, Felix Wong, Yu Zhang, Danilo Ritz, Margaux Gaborieau, Edmund Loh, Massimiliano Gaetani, Marie-Stephanie Aschtgen, Amir Ata Saei, Yonatan H. Grad, Donald E. Ingber and James J. Collins
Science Translational Medicine (2026)

Neisseria gonorrhoeae is a common Gram-negative pathogen with increasing resistance to all recommended antibiotics. There is a critical need to improve the efficiency of the antibiotic hit discovery process to replenish the drug development pipeline. Here, we show that deep learning models can augment high-throughput screens to identify readily available molecules with narrow-spectrum activity against difficult-to-treat strains of N. gonorrhoeae. We phenotypically tested 38,650 small molecules for N. gonorrhoeae growth inhibition to train a predictive graph neural network (GNN) model. We benchmarked the model’s performance against other architectures, including a large language model, and found that GNNs more accurately identify active, drug-like molecules that are structurally distinct from the training set and known antibiotics. Using the model to virtually screen ~6 million compounds, we identified 213 compounds for experimental validation and found that 83 (39%) inhibited N. gonorrhoeae growth. Two of these compounds were structurally dissimilar to existing antibiotics, maintained potency against multidrug-resistant N. gonorrhoeae strains in vitro, exhibited promising selectivity indices, and were rapidly bactericidal with low frequencies of resistance. Proteomic studies revealed their distinct mechanisms of action, with one compound targeting alanine racemase, an enzyme involved in the essential process of peptidoglycan synthesis. Furthermore, the compounds showed early promise in reducing N. gonorrhoeae titers in a human vagina-on-a-chip infection model and a mouse vaginal infection model. Our work establishes the deep learning–enabled discovery of selective antibacterial compounds against N. gonorrhoeae as a much-needed hit discovery tool to address the growing crisis of antimicrobial resistance for this pathogen.

 

Generative AI for synthetic biology: Designing biological parts, circuits, and genomes

Nayoung Kim, Giuliano De Carluccio, Kehan Zhang and James J. Collins
Cell Systems (2026)

Synthetic biology aims to achieve predictable, programmable control over living systems by designing and engineering biological components and functions. Over the past 25 years, the field has advanced from foundational molecular tools to increasingly complex systems-level architectures. A new inflection point has emerged with the integration of generative artificial intelligence (AI), catalyzing a fundamental shift in how biological design is conceived and executed. Generative AI now enables the data-driven creation of novel designs with predictable functionality and context-aware precision. Here, we examine the convergence of synthetic biology and generative AI, highlighting key innovations at this emerging frontier of deep generative design across biological parts and systems. We discuss how design frameworks have evolved and outline the opportunities and challenges that lie ahead, spanning biomolecular elements, genetic circuits, and genomes. Finally, we propose a roadmap for how generative AI can unlock a new era of predictable, programmable synthetic biological systems.

 

A programmable microbial assembly line for plastic upcycling

Yuanchao Qian, James J. Collins and Ting Lu
Nature Sustainability (2026)

Biological upcycling is a promising strategy for handling end-of-life plastics. However, current practices, which predominantly focus on yielding fixed single outputs, face challenges in meeting diverse and evolving product demands. Here we present a programmable microbial assembly line that enables the efficient and versatile upcycling of plastic waste into various end products. The assembly line involves a deconstruction strain that catabolizes pretreated polyethylene terephthalate into pyruvate, serving as a universal building block, and a set of interchangeable production strains that transform this building block into tailorable outputs. Such a design allows a rapid, combinatorial assembly of microbial strains into diverse biomanufacturing systems. Accordingly, programmable upcycling is achieved, yielding successful production of a wide range of final products, including chemicals, fuels, enzymes, biopolymers and electricity. This work establishes a reconfigurable valorization platform, providing insights into biological treatment of plastic waste as well as into need-driven, sustainable biomanufacturing.