{"id":21483,"date":"2024-06-20T13:45:44","date_gmt":"2024-06-20T13:45:44","guid":{"rendered":"https:\/\/clinlabint.com\/?p=21483"},"modified":"2024-06-27T12:37:05","modified_gmt":"2024-06-27T12:37:05","slug":"synthemol-ai-generates-25000-novel-antibiotics-and-their-recipes-in-9-hours","status":"publish","type":"post","link":"https:\/\/clinlabint.com\/synthemol-ai-generates-25000-novel-antibiotics-and-their-recipes-in-9-hours\/","title":{"rendered":"SyntheMol AI generates 25,000 novel antibiotics and their recipes in 9 hours"},"content":{"rendered":"
\n

\r\n\"Bio-Rad<\/a>\r\n<\/p>\n<\/div><\/section><\/div>

<\/p>\n<\/div><\/section>
\n

SyntheMol AI generates 25,000 novel antibiotics and their recipes in 9 hours<\/h1>\/ in Product News<\/a> <\/span><\/span><\/header>\n<\/div><\/section>
\n

Generative AI develops 6 new drugs that can kill resistant strains of A. baumannii<\/strong><\/h3>\n

With nearly 5 million deaths linked to antibiotic resistance globally every year, new ways to combat resistant bacterial strains are urgently needed.<\/strong><\/p>\n

<\/p>\n

Researchers at Stanford Medicine and McMaster University are tackling this problem with generative artificial intelligence. A new model, dubbed SyntheMol (for synthesizing molecules), created structures and chemical recipes for six novel drugs aimed at killing resistant strains of Acinetobacter baumannii, one of the leading pathogens responsible for antibacterial resistance-related deaths.<\/p>\n

The researchers described their model and experimental validation of these new compounds in a study [1] published March 22 in the journal Nature Machine Intelligence.<\/p>\n

\u201cThere\u2019s a huge public health need to develop new antibiotics quickly,\u201d said James Zou, PhD, an associate professor of biomedical data science and co-senior author on the study. \u201cOur hypothesis was that there are a lot of potential molecules out there that could be effective drugs, but we haven\u2019t made or tested them yet. That\u2019s why we wanted to use AI to design entirely new molecules that have never been seen in nature.\u201d<\/p>\n

Before the advent of generative AI, the same type of artificial intelligence technology that underlies large language models like ChatGPT, researchers had taken different computational approaches to antibiotic development. They used algorithms to scroll through existing drug libraries, identifying those compounds most likely to act against a given pathogen. This technique, which sifted through 100 million known compounds [2], yielded results but just scratched the surface in finding all the chemical compounds that could have antibacterial properties.<\/p>\n

\u201cChemical space is gigantic,\u201d said Kyle Swanson, a Stanford computational science doctoral student and co-lead author on the study. \u201cPeople have estimated that there are close to 1060 possible drug-like molecules. So, 100 million is nowhere close to covering that entire space.\u201d<\/p>\n

Hallucinating for drug development<\/h3>\n

Generative AI\u2019s tendency to \u201challucinate\u201d, or make up responses, could be a boon when it comes to drug discovery, but previous attempts to generate new drugs with this kind of AI resulted in compounds that would be impossible to make in the real world, Swanson said. The researchers needed to put guardrails around SyntheMol\u2019s activity \u2013 namely, to ensure that any molecules the model dreamed up could be synthesized in a lab.<\/p>\n

\u201cWe\u2019ve approached this problem by trying to bridge that gap between computational work and wet lab validation,\u201d Swanson said.<\/p>\n

Recipes to produce the drugs<\/p>\n

The model was trained to construct potential drugs using a library of more than 130,000 molecular building blocks and a set of validated chemical reactions. It generated not only the final compound but also the steps it took with those building blocks, giving the researchers a set of recipes to produce the drugs. The researchers also trained the model on existing data of different chemicals\u2019 antibacterial activity against A. baumannii. With these guidelines and its building block starting set, SyntheMol generated around 25,000 possible antibiotics and the recipes to make them in less than nine hours. To prevent the bacteria from quickly developing resistance to the new compounds, researchers then filtered the generated compounds to only those that were dissimilar from existing compounds.<\/p>\n

\u201cNow we have not just entirely new molecules but also explicit instructions for how to make those molecules,\u201d Zou said.<\/p>\n

A new chemical space<\/h4>\n

The researchers chose the 70 compounds with the highest potential to kill the bacterium and worked with the Ukrainian chemical company Enamine\u00a0 https:\/\/enamine.net<\/a>\u00a0 to synthesize them. The company was able to efficiently generate 58 of these compounds, six of which killed a resistant strain of A. baumannii when researchers tested them in the lab. These new compounds also showed antibacterial activity against other kinds of infectious bacteria prone to antibiotic resistance, including E. coli, Klebsiella pneumoniae and MRSA.<\/p>\n

The scientists were able to further test two of the six compounds for toxicity in mice, as the other four didn\u2019t dissolve in water. The two they tested seemed safe; the next step is to test the drugs in mice infected with A. baumannii to see if they work in a living body, Zou said.<\/p>\n

The six compounds are vastly different from each other and from existing antibiotics. The researchers don\u2019t know how their antibacterial properties work at the molecular level, but exploring those details could yield general principles relevant to other antibiotic development. \u201cThis AI is really designing and teaching us about this entirely new part of the chemical space that humans just haven\u2019t explored before,\u201d Zou said. Zou and Swanson are also refining SyntheMol and broadening its reach. They\u2019re collaborating with other research groups to use the model for drug discovery for heart disease and to create new fluorescent molecules for laboratory research.<\/p>\n

The study was funded by the Weston Family Foundation, the David Braley Centre for Antibiotic Discovery, the Canadian Institutes of Health Research, M. and M. Heersink, the Chan-Zuckerberg Biohub, and the Knight-Hennessy scholarship.<\/p>\n

References:<\/strong><\/em>
\n1. Swanson, K., Liu, G., Catacutan, D.B. et al. Generative AI for designing and validating easily synthesizable and structurally novel antibiotics. Nat Mach Intell 6, 338\u2013353 (2024). https:\/\/doi.org\/10.1038\/s42256-024-00809-7<\/a> <\/em>
\n2. doi: https:\/\/doi.org\/10.1016\/j.cell.2020.01.021<\/a><\/em><\/p>\n<\/div><\/section>
\n

\"\"<\/div><\/div><\/div>
\n

Illustration of Acinetobacter baumannii multi-drug resistant bacterium<\/em><\/p>\n<\/div><\/section>
\n