The Antibiotics-AI Project at MIT pairs deep learning with experimental biology to discover and design entirely new classes of antibiotics against the world's deadliest bacterial pathogens.
Antibiotics are essential to modern medicine. The continuous evolution of antibiotic-resistant bacteria and a dwindling antibiotic discovery pipeline have resulted in an antimicrobial resistance (AMR) crisis. The United Nations estimates that by 2050, antibiotic resistance will lead to 10 million deaths annually, surpassing cancer. There is a critical need for new antibiotics, and yet pharmaceutical and biotechnology companies have largely abandoned the space in favor of more lucrative markets. Without immediate action to rapidly discover and develop new antibiotics, healthcare systems around the world are at risk of collapse.
To address this challenge, the Antibiotics-AI Project at MIT integrates world-class expertise and decades of experience in artificial intelligence (AI), bioengineering, and life sciences to rapidly discover and design entirely novel classes of antibiotics against the world's deadliest pathogens.
By setting our sights on the superbugs most likely to infect and kill humans over the next 30 years, we are paving the way for improvements in patients' lives and the prevention of an untold number of deaths. Our target pathogens include:
A closed loop where the lab and the model teach each other: experiments feed the AI, and the AI points back to the next experiment. Hits are discovered or designed and experimentally validated in vitro and in vivo.
Empirically test thousands of compounds for growth inhibition against priority pathogens.
Train deep neural networks to predict and explain antibacterial activity from structure.
Search 70B+ molecules, or generate de novo ones, for novel, non-toxic candidates.
Synthesize or procure top hits and confirm efficacy in vitro and in animal infection models.
A deep-learning screen finds readily available compounds active against drug-resistant gonorrhea, including an aminothiazole that inhibits alanine racemase.
Anahtar MN, Valeri JA, Modaresi SM, Krishnan A, … Ingber DE, Collins JJ
Generative models design brand-new antibacterial molecules from scratch; NG1 against gonorrhea and DN1 against MRSA; confirmed in animal models.
Krishnan A, Anahtar MN, Valeri JA, … Wong F, Collins JJ
Explainable graph neural networks uncover a new structural class of antibiotics active against MRSA and vancomycin-resistant enterococci.
Wong F, Zheng EJ, Valeri JA, Donghia NM, … Renner LD, Collins JJ
A screen for compounds that kill non-growing, metabolically dormant bacteria identifies semapimod and related outer-membrane disruptors.
Zheng EJ, Valeri JA, Andrews IW, Krishnan A, … Lourido S, Collins JJ
Deep learning predicts abaucin, a narrow-spectrum antibiotic that kills the hospital superbug Acinetobacter baumannii while sparing the microbiome.
Liu G, Catacutan DB, Rathod K, … Collins JJ, Stokes JM
The first deep-learning screen for antibiotics discovers halicin, a broad-spectrum compound that kills bacteria by collapsing their membrane potential.
Stokes JM, Yang K, Swanson K, Jin W, … Barzilay R, Collins JJ
An interpretable, white-box machine-learning model links antibiotic-induced metabolic disruption to bacterial killing, illuminating mechanisms of action.
Yang JH, Wright SN, Hamblin M, McCloskey D, … Walker GC, Collins JJ
A step-by-step, open-source platform for training explainable deep-learning models that discover and rationalize new non-toxic antibacterial molecules.
Wong F, Omori S, Li A, Krishnan A, … Wilson MZ, Collins JJ
A benchmark of AlphaFold-enabled molecular docking for antibiotic discovery, with datasets mapping where structure-based screening works.
Wong F, Krishnan A, Zheng EJ, Stark H, … Jaakkola T, Collins JJ
A perspective on how machine learning is reshaping antibiotic discovery, from large-scale screening to generative molecular design.
de la Fuente-Nunez C, Collins JJ
A review of machine-learning approaches for identifying and designing antimicrobial peptides.
Wan F, Wong F, Collins JJ, de la Fuente-Nunez C
A perspective on applying artificial intelligence across diagnostics, therapeutics, and surveillance to fight infectious diseases.
Wong F, de la Fuente-Nunez C, Collins JJ
Labeled growth inhibition data of 38K+ molecules across 7 bacterial pathogens for model training.
Download dataset ↗Viability readouts of 38K+ molecules against 3 human cell lines for the discovery of safe antibiotics.
Download dataset ↗Absorption, distribution, metabolism, and excretion data to prioritize candidates with drug-like properties.
An explainable deep learning platform to discover safe and structurally novel antibiotic classes.
github.com/felixjwong/antibioticsai ↗ github.com/felixjwong/protocol ↗Datasets and generative models (CReM and VAEs) for de novo antibiotic design.
github.com/aartikrish/de-novo-antibiotics ↗Paste SMILES or upload a CSV to instantly render structure tiles (RDKit), MW/logP, and SMARTS highlighting. Print or save as PDF.
yuzhang-io.github.io/mols2img ↗ Open-source modelMessage-passing neural networks for molecular property prediction; the D-MPNN framework behind our antibiotic-activity models.
github.com/chemprop/chemprop ↗ Open-source modelA parameter-efficient molecular fingerprinting foundation model, pre-trained on thousands of biological and quantum tasks.
github.com/graphcore-research/minimol ↗The Antibiotics-AI Project is made possible by several philanthropic initiatives and support from our U.S. federal research partners. We are grateful to all of our supporters.
An initiative of TED ↗
Flu Lab LLC ↗
Rosamund Zander and Hansjörg Wyss ↗
Sea Grape Foundation ↗
An anonymous donor
Mohammed Abdul Latif Jameel ↗
TARGET project 
Defense Threat Reduction Agency 
National Institutes of Health 
Phare Bio 
MIT Jameel Clinic