Antibiotic resistance is a natural phenomenon, but overuse and misuse of antibiotics have exacerbated the problem – Copyright President Venezuelan/AFP Marcelo Garcia
Antibiotic resistance (AMR) is estimated to kill 10 million people a year by 2050, exceeding the death rates of some of the world's most deadly diseases, such as cancer. In 2021, 4.7 million deaths were associated with AMR, with 11.4 million of those deaths directly attributing this issue (according to the Medical Journal, Rancet).
Antibiotic resistance is a type of drug resistance that allows several subpopulations of microorganisms to survive after exposure to one or more antibiotics. Over the past 20 years, the proportion of bacteria being resistant to current antibiotic treatments has increased significantly.
The emergence of antibiotic resistance is a complex problem promoted by many interconnected factors, among which the use and misuse of antibiotics (antibiotics, preservatives, disinfectants, and preservatives) are the main drivers of resistance development.
Other factors affecting this phenomenon are that most clinically used antibiotics are broad-based and are known to rapidly increase resistance rates as 1) injure our intestinal bacteria and 2) the same antibiotics are used to treat many patients' illnesses.
MIT Jameel Clinic is conducting research to find solutions to combat this and has recently published a paper Nature. This study focuses on a family of drug-resistant bacteria known as enterobacteria. E. coli and Salmonellaamong other pathogens of concern. These organisms can exacerbate problems associated with the imbalanced gut microbiota.
Is artificial intelligence the answer?
Machine learning is considered a mechanism for finding new antibiotics. The best way to achieve success is to collect appropriate training data and use the best machine learning model architecture for predictive tasks. Finding new antibiotics.
By utilizing deep learning algorithms, researchers at Jameel Clinic have determined whether antibiotic binding can be predicted to protein targets, and whether it is a promising new drug candidate that can treat range conditions without harming intestinal bacteria.
This antibiotic provides alternative drug options for patients with chronic inflammatory bowel disease (IBD), such as Crohn's disease (CD).
“The discovery speaks to a central challenge in antibiotic development,” says Jon Stokes, McMaster's lead science professor of biochemistry and biomedical sciences and research affiliate at MIT's Abdul Latif Jameel Clinic, for machine learning in health.
“The problem was that, rather than finding molecules that kill bacteria in the dish, we were able to do that for a long time. Understanding what these molecules actually do within the bacteria. Without that detailed understanding, we cannot develop these early stage antibiotics into safe and effective treatments for patients.”
the study
Researchers screened 10,747 bioactive small molecules for antibacterial activity against adhesion invasion E. coli (AIEC) And they discovered a compound called enororin, an antibacterial compound with target activity against E. siblings.
Scientists hope that enterolin can overcome the endogenous and acquired resistance mechanisms of clinical isolates when combined with sub-inhibitory concentrations of SPR741, a polymyxin B analog used here to enhance outer membrane permeability of Gram-negative bacteria.
Subsequent investigations of molecular substrate structure and deep learning-inducing mechanisms revealed that enterolin revealed human trafficking of lipoproteins through a mechanism involving transporters called the Lolcde complex.
Importantly, when the compound becomes a human antibiotic, enterolin showed low mammalian cytotoxicity in mouse models. We also preserved the overall microbiome composition in terms of maintaining intestinal balance.
In terms of the general importance of the study, this study highlighted the usefulness of deep learning methods to predict molecular interactions and further identified promising enterobacterial specific antibacterial candidates for development.
This study is published in the Science Journal Natureentitled “Discovery of narrow spectral antibiotics and artificial intelligence-induced mechanical elucidation.”
