MoleculeAI Newsletter- September 2024

Discover the world of in silico drug discovery through MoleculeAI's monthly newsletter. Join our journey of learning and impactful discoveries in bringing life-saving medications to patients faster.

Can AI confront the rising threat of antimicrobial resistance?

With nearly 5 million deaths linked to antimicrobial resistance (AMR) globally every year, new ways to combat resistant bacterial strains are urgently needed. AMR also carries a hefty economic cost. The World Bank estimates that the economic impact of unmitigated AMR could decrease annual global gross domestic product (GDP) by 1.1- 3.8 per cent by 2050.

Since rising AMR has been documented over the past two decades, projections from the Organisation for Economic Co-operation and Development (OECD) for high-income countries predict resistance to third-line antibiotics, the last-resort drugs, could be 2·1 times higher in 2035 compared to 2005.

AMR is driven largely by the misuse and overuse of antimicrobials, yet, at the same time, many people around the world do not have access to essential antimicrobial medicines. According to reports, ESKAPE pathogens (Enterococcus faecium,?Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter?spp.) are the top priority pathogens as these have developed resistance against certain antibiotics.?

The World Health Organisation (WHO) has recently pointed out that pharmaceutical waste from antibiotic manufacturing can facilitate the emergence of new drug-resistant bacteria, which can spread globally and threaten our health.

As a result, a multifaceted problem like AMR requires a multidimensional approach, where technology must be a part of the solution. For instance, researchers at Stanford Medicine and McMaster University are tackling this problem with generative artificial intelligence (AI). A new model, dubbed SyntheMol, has 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.

Likewise, using an AI algorithm, researchers at MIT and McMaster University have identified a new antibiotic that can kill a type of bacteria that is responsible for many drug-resistant infections. If? approved for use in humans, the drug could help combat?Acinetobacter baumannii, that is often found in hospitals and can lead to pneumonia, meningitis, and other serious infections.?

Also, researchers from Broad Institute of the Massachusetts Institute of Technology (MIT) and Harvard University?are using AI to identify novel compounds effective against methicillin-resistant?Staphylococcus aureus?(MRSA) and vancomycin-resistant enterococci, some of the most stubbornly hard-to-kill pathogens.?

Further, researchers from the University of Manitoba, Canada, have deployed explainable AI (XAI), a branch of AI that provides a rationale for model judgments to develop antibiotics with less side effects.

Quoting another example of how technology can be best used to combat the growing health burden of AMR, scientists at Oxford University have shown that AI can detect antibiotic resistance in as little as 30 minutes. This method relies on training deep-learning models to analyse bacterial cell images and detect structural changes that may occur in cells when they are treated with antibiotics. The method was shown to be effective across multiple antibiotics, achieving at least 80 per cent accuracy on a per-cell basis.

Alongside the academicians, researchers within the pharma industry are also equally exploring the use of AI to fix this problem. ?Eli Lilly and Company?has recently announced a collaboration with?OpenAI?that will allow Lilly to leverage?OpenAI's generative AI to invent novel antimicrobials to treat drug-resistant pathogens.

Besides drug discovery, AI is also being deployed in the development of effective phage therapies to combat AMR, which includes identifying phages from metagenomic samples, annotating phage virion proteins from phage genome sequences, predicting phage hosts, and determining phage lifestyles.

With multiple developments taking shape across the globe, the significant increase in the use of AI platforms will hopefully result in the discovery of efficient antibiotic alternatives with lower chances of resistance generation.

MoleculeAI in News

Saurabh Singal, the founder of MoleculeAI and KnowDis, has been invited as a Guest Editor for the prestigious March edition of American Pharmaceutical Review's print magazine.