COLLINS LAB

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.

Using Machine Learning for Antibiotic Discovery

Cesar de la Fuente-Nunez and James J. Collins

Physical Review Letters (2025)

Antimicrobial resistance is a critical global health challenge and one of the World Health Organization’s top ten public health threats. The alarming rise of drug-resistant pathogens threatens to usher in a postantibiotic era where common infections could once again become fatal. Despite the urgency, traditional discovery methods are time-consuming, expensive, and insufficient to keep pace with rapidly evolving resistance. Recent advances in machine learning (ML) and artificial intelligence (AI) present a transformative alternative, enabling the rapid identification of potential candidate antibiotics in a fraction of the time required by conventional methods. In this Essay, we discuss how ML and AI significantly accelerate antibiotic discovery, drawing on previous works and insights in this emerging field. We also consider the promises and challenges of this emerging area and speculate on its evolution in the coming years, highlighting the potential contributions from the physics community.

Optogenetics-enabled stress response modulators

Felix Wong, Alicia Li, Satotaka Omori, Ryan S. Lach, Jose Nunez, Yunke Ren, Sean P. Brown, Vipul Singhal, Brent R. Lyda, Taivan Batjargal, Ethan Dickson, Jose Roberto Rodrigues Reyes, Juan Manual Uruena Vargas, Shalaka Wahane, Hahn Kim, James J. Collins and Maxwell Z. Wilson
Cell (2025)

The integrated stress response (ISR) is a conserved stress response that maintains homeostasis in eukaryotic cells. Modulating the ISR holds therapeutic potential for diseases including viral infection, cancer, and neurodegeneration, but few known compounds can do so without toxicity. Here, we present an optogenetic platform for the discovery of compounds that selectively modulate the ISR. Optogenetic clustering of PKR induces ISR-mediated cell death, enabling the high-throughput screening of 370,830 compounds. We identify compounds that potentiate cell death without cytotoxicity across diverse cell types and stressors. Mechanistic studies reveal that these compounds upregulate activating transcription factor 4 (ATF4), sensitizing cells to stress and apoptosis, and identify GCN2 as a molecular target. Additionally, these compounds exhibit antiviral activity, and one compound reduced viral titers in a mouse model of herpesvirus infection. Structure activity and toxicology studies highlight opportunities to optimize therapeutic efficacy. This work demonstrates an optogenetic approach to drug discovery and introduces ISR potentiators with therapeutic potential.

Machine learning for synthetic gene circuit engineering 

Sebastian Palacios, James J. Collins, and Domitilla Del Vecchio
Current Opinion in Biotechnology (2025)

 Synthetic biology leverages engineering principles to program biology with new functions for applications in medicine, energy, food, and the environment. A central aspect of synthetic biology is the creation of synthetic gene circuits — engineered biological circuits capable of performing operations, detecting signals, and regulating cellular functions. Their development involves large design spaces with intricate interactions among circuit components and the host cellular machinery. Here, we discuss the emerging role of machine learning in addressing these challenges. We articulate how machine learning may enhance synthetic gene circuit engineering, from individual components to circuit-level aspects, while highlighting associated challenges. We discuss potential hybrid approaches that combine machine learning with mechanistic modeling to leverage the advantages of data-driven models with the prescriptive ability of mechanism-based models. Machine learning and its integration with mechanistic modeling are poised to advance synthetic biology, but challenges need to be overcome for such efforts to realize their potential. 

Engineering synthetic phosphorylation signaling
networks in human cells

Xiaoyu Yang, Jason W. Rocks, Kaiyi Jiang, Andrew J. Walters, Kshitij Rai, Jing Liu, Jason Nguyen, Scott D. Olson, Pankaj Mehta, James J. Collins, Nichole M. Daringer, and Caleb J. Bashor
Science (2025)

Protein phosphorylation signaling networks have a central role in how cells sense and respond to their environment. We engineered artificial phosphorylation networks in which reversible enzymatic phosphorylation cycles were assembled from modular protein domain parts and wired together to create synthetic phosphorylation circuits in human cells. Our design scheme enabled model-guided tuning of circuit function and the ability to make diverse network connections; synthetic phosphorylation circuits can be coupled to upstream cell surface receptors to enable fast-timescale sensing of extracellular ligands, and downstream connections can regulate gene expression. We engineered cell-based cytokine controllers that dynamically sense and suppress activated T cells. Our work introduces a generalizable approach that allows the design of signaling circuits that enable user-defined sense-and-respond function for diverse biosensing and therapeutic applications.

An explainable deep learning platform for molecular discovery

Felix Wong, Satotaka Omori, Alicia Li, Aarti Krishnan, Ryan S. Lach, Joseph Rufo, Maxwell Z. Wilson, and James J. Collins
Nature Protocols (2025)

Deep learning approaches have been increasingly applied to the discovery of novel chemical compounds. These predictive approaches can accurately model compounds and increase true discovery rates, but they are typically black box in nature and do not generate specifc chemical insights. Explainable deep learning aims to ‘open up’ the black box by providing generalizable and human-understandable reasoning for model predictions. These explanations can augment molecular discovery by identifying structural classes of compounds with desired activity in lieu of lone compounds. Additionally, these explanations can guide hypothesis generation and make searching large chemical spaces more efcient. Here we present an explainable deep learning platform that enables vast chemical spaces to be mined and the chemical substructures underlying predicted activity to be identifed. The platform relies on Chemprop, a software package implementing graph neural networks as a deep learning model architecture. In contrast to similar approaches, graph neural networks have been shown to be state of the art for molecular property prediction. Focusing on discovering structural classes of antibiotics, this protocol provides guidelines for experimental data generation, model implementation and model explainability and evaluation. This protocol does not require coding profciency or specialized hardware, and it can be executed in as little as 1–2 weeks, starting from data generation and ending in the testing of model predictions. The platform can be broadly applied to discover structural classes of other small molecules, including anticancer, antiviral and senolytic drugs, as well as to discover structural classes of inorganic molecules with desired physical and chemical properties.