Using artificial intelligence to discover new treatments for superbugs
Antimicrobial resistance is an to healthcare systems worldwide. As a consequence of the spread of , also called “superbugs,” medical treatments could become ineffective for an increasing number of people in the next years. To fix this huge problem, chemists are asked to find new effective antibiotics.

is an expensive and time-consuming process during which pharmaceutical chemists look for new candidate molecules to interact with a particular target protein or pathway causing the disease. Chemists screen large libraries of thousands to millions of molecules, looking for compounds with specific biological effects and low toxicity. However, these screenings are if chemical libraries don’t include molecules with enough structural diversity, chemists will fail to discover antibiotics with molecular structures different from the ones already tested in laboratories or clinical trials.
Now is flanking chemoinformatics through innovative approaches to find new drugs. An example of how this approach works can be seen in by James Collins and coworkers at MIT. First, researchers trained a neural network model to predict growth inhibition of Escherichia coli using a set of 2335 diverse molecules; then, they applied the optimized neural network model to screen large chemical libraries with more than 107 million molecules.
They ended up with a list of candidate molecules structurally different from known antibiotics, and ranked them based on their predicted biological activity. Among those candidates, they found that , a compound under investigation as a treatment for diabetes, displayed high efficacy against E. coli and a large spectrum of pathogens such as Acinetobacter baumanii, at the which urgently requires new antibiotics.
Research groups similar deep learning approaches to find new compounds that could fight the COVID-19 virus. This suggests how recent improvements in machine learning can assist chemists’ work to speed up and lower the costs of the drug discovery process.
This story originally appeared on , an editorial partner site that publishes science stories by scientists. to get even more science sent straight to you.

Enjoy reading ASBMB Today?
Become a member to receive the print edition four times a year and the digital edition monthly.
Learn moreGet the latest from ASBMB Today
Enter your email address, and we’ll send you a weekly email with recent articles, interviews and more.
Latest in Science
Science highlights or most popular articles

Mapping the placenta’s hormone network
Study uncovers how the placenta actively metabolizes not only glucocorticoids but also novel androgens and progesterones, reshaping our understanding of pregnancy and its complications.

Biochemists and molecular biologists sweep major 2025 honors
Recent Nobel, MacArthur and Kimberly Prize honorees highlight the power of biochemistry and molecular biology to drive discovery, including immune tolerance, vaccine design and metabolic disease, and to advance medicine and improve human health.

Spider-like proteins spin defenses to control immunity
Researchers from Utrecht University discovered two distinct binding modes of a spider-shaped immune inhibitor found in serum.

A biological camera: How AI is transforming retinal imaging
AI is helping clinicians see a more detailed view into the eye, allowing them to detect diabetic retinopathy earlier and expand access through tele-ophthalmology. These advances could help millions see a clearer future.

AI in the lab: The power of smarter questions
An assistant professor discusses AI's evolution from a buzzword to a trusted research partner. It helps streamline reviews, troubleshoot code, save time and spark ideas, but its success relies on combining AI with expertise and critical thinking.

Training AI to uncover novel antimicrobials
Antibiotic resistance kills millions, but César de la Fuente’s lab is fighting back. By pairing AI with human insight, researchers are uncovering hidden antimicrobial peptides across the tree of life with a 93% success rate against deadly pathogens.