Deep learning identifies new compounds against antibiotic-resistant gonorrhea

With tens of millions of annual cases, gonorrhea is the second most frequently reported sexually transmitted infection (STI). In the United States alone, more than 600,000 cases are reported each year. If gonorrhea is left untreated, it can lead to serious reproductive health problems, including infertility in both women and men and pelvic inflammatory disease. The infection also increases the risk of transmitting HIV, and if the pathogen spreads from the genitals or throat to other parts of the body, it can damage the heart and cause meningitis and sepsis. The main challenge in controlling the disease more effectively lies in the ability of the pathogen responsible, Neisseria gonorrhoeaeto rapidly develop resistance against newly available antibiotics.

Along with zoleflodacin and gipotidacin, two new oral antibiotics have recently been approved for the treatment of uncomplicated genitourinary gonorrhea. These are the first completely new classes of antibiotics developed to fight infections in more than thirty years. But if these two antibiotics are widely used, the pathogen will almost certainly eventually develop significant resistance to them. We have seen the cycle of resistance development occur within just five to ten years after first-line administration, and it has happened over and over again. “To be able to win this ongoing arms race, we will be using new antibiotics to fill the pipeline.”

Melis Anahtar, MD, PhD, physician-scientist, associate director, Clinical Microbiology Laboratory, Massachusetts General Hospital (MGH)

Now, a new study published in Science Translational Medicine Led by Wyss Institute core faculty member James Collins, Ph.D. The Wyss Institute at Harvard, MIT, and the Broad Institute of MIT and Harvard, led by Anahtar, Jacqueline Valéry, and Majid Madarisi, presents an exciting new strategy capable of identifying new chemical compounds that can be further developed into highly selective antibiotic therapeutics for the treatment of diseases. n. Gonorrhea. Initially, the researchers hypothesized that entirely new chemical structures with antimicrobial activity could significantly reduce the chances of antimicrobial resistance occurring because they might also target cellular pathways uncommon in the pathogen, and that to identify those structures, deep learning-guided antimicrobial discovery approaches could lead the way.

Lead researcher Collins said: “We have reached a very important point in time where a vast chemical field has opened up in which billions of chemical compounds with clearly defined structures can be synthesized. This is converging with the rapidly evolving capabilities of machine learning that allow us to explore this space with very specific biological activities, such as novel antimicrobial activities, being much needed.” “This study builds on a body of work in our lab that leverages artificial intelligence to fight infectious diseases and brings this focus to… n. Gonorrhea “To help address the growing crisis of antimicrobial resistance to this rapidly evolving pathogen.” Termeer is a professor of medical engineering and science at the Massachusetts Institute of TechnologyHe is a member of the Broad Institute at MIT and Harvard University.

Building a machine learning pipeline

To build the foundation for their approach, the team first tested 38,650 small molecules for their ability to inhibit bacterial growth. n. Gonorrhea In lab tests, they then used this data set to train a deep learning predictive model. They demonstrated that the model was able to identify potential antibacterial and drug-like molecules with a chemical structure that differed from those found in common antibiotics.

After gaining confidence in the model’s ability to find “hidden gems” with anti-gonococcal activity, they used their AI model to screen a much larger library of about 6 million compounds. This yielded 213 candidates that were further validated. After a series of growth inhibition and antimicrobial resistance assays, as well as cell biological assays to exclude compounds with unwanted toxicities, they were able to identify two compounds with promising selectivity for and Strong potency against multi-drug resistance n. Gonorrhea Strains that themselves have caused resistance at very low frequencies.

“Using proteomic approaches, we have successfully identified the target for our promising compound called A1, a so-called aminothiazole compound with previously undescribed anti-gonococcal activity. It specifically binds to and inhibits the critical alanine racemase enzyme, which n. Gonorrhea “It needs to build its cell wall,” Anahtar said, adding, “We have validated the alanine racemization specificity of A1 using genetic tools and are now in the process of investigating how A1 inhibits enzyme activity.” Multiple existing antibiotics inhibit the cell wall biosynthesis of pathogenic bacteria, however, specifically targeting the alanine racemase with a small molecule is a new mechanism uncovered by the team.

from In silico to alive

In a next translational step, the team investigated whether their compounds could exhibit anti-gonococcal activity in the physiological tissue environment of the vagina where infection n. Gonorrhea It often happens. In collaboration with the group of Wyss Founding Director and co-author Donald Ingber, MD, PhD, who had previously developed a microfluidic organ chip model for the human vagina, they demonstrated that their first compound, MP20, significantly reduced pathogen titers after introduction into the device and interaction with vaginal epithelial cells. Also, in a murine vaginal infection model where they were inoculated intravaginally n. Gonorrhea Bacteria: Five treatments with its second compound, A1, over a 24-hour period significantly reduced the concentration of pathogens compared to the no antibiotic control.

“Although our observations on A1 are promising, it requires further validation and improved results through medicinal chemistry and other efforts in order to become a clinically relevant antimicrobial drug for the treatment of gonorrhea,” Anahtar said. “However, our deep learning-enabled discovery pipeline has the potential to screen more comprehensive and very large chemical libraries on demand to identify unexpected chemical compounds as new starting points in gonorrhea-focused antibiotic development programs.”

“This study by Jim Collins and his team once again demonstrates the tremendous power of artificial intelligence combined with high-quality biological datasets in discovering potential therapeutic compounds that would otherwise be completely out of reach. It also demonstrates how we, at the Wyss Institute, are seamlessly integrating important advances in artificial intelligence with human-relevant models, in this case the human vaginal chip,” said co-author Ingber, MD, Ph.D. Who is he too Judah Folkman, Professor of Vascular Biology At Harvard Medical School and Boston Children’s Hospital, and Hansjörg Weiss, Professor of Biologically Inspired Engineering At John A. College Paulson School of Engineering and Applied Science at Harvard University.

Other authors on the study include Aarti Krishnan, Nina Donghia, Samantha Ballas, Erika Cheng, Akanksha Gulati, Alicia Jorgenson, Abedimi Junaid, Parijat Bandyopadhyay, Andreas Lutens, Krishna Suresh, Paige Edwards, Felix Wong, Yu Zhang, Danilo Ritz, Margot Gaborio, Edmund Loh, Massimiliano Gaetani, Mary Stephanie Eshtegen, Amir Atta Saei, and Jonathan Jarrad.