Scientifically Speaking | How AI is paving the way for antibiotic discovery - Hindustan Times
close_game
close_game

Scientifically Speaking | How AI is paving the way for antibiotic discovery

ByAnirban Mahapatra
Jun 18, 2024 05:44 PM IST

Breakthroughs using machine learning have identified nearly 900,000 genetic sequences with antibiotic potential, providing a path forward in combating superbugs

Antibiotic resistance is one of the most urgent threats facing humanity today. If we do not act, superbugs — bacteria resistant to multiple antibiotics — could cause 10 million deaths globally per year by 2050, surpassing the current annual deaths from cancer. This crisis could also push 24 million people into poverty.

Antibiotic resistance is one of the most urgent threats facing humanity today (Yves Herman / REUTERS) PREMIUM
Antibiotic resistance is one of the most urgent threats facing humanity today (Yves Herman / REUTERS)

The misuse of antibiotics in health care and agriculture, especially in India where resistance rates to crucial antibiotics exceed 70%, has worsened the problem. India consumes the most antibiotics globally, accounting for 23% of the world's retail sales. The market is flooded with untested and unapproved antibiotic combinations, exacerbating the crisis.

In my new book, When the Drugs Don't Work, I explore the history of antibiotic discovery and the challenges we face today. The mid-20th century was a golden era for antibiotic discoveries, but this momentum has slowed significantly. No new major class of antibiotics has been introduced in decades.

Developing new antibiotics is expensive and slow. It costs about a billion dollars and over a decade to bring a new antibiotic to the market. Unlike other drugs, new antibiotics are used sparingly to prevent resistance, leading to lower sales. Insurers and governments are willing to pay much more for cancer treatments that extend life by a few months than they will for antibiotics that can cure patients completely. This makes it hard for pharmaceutical companies to justify the investment. Consequently, many large companies have abandoned antibiotic research.

At the same time, finding new antibiotics is getting harder. Most are derived from soil-dwelling bacteria that have developed antibiotics to outcompete their neighbours. Screening these bacteria is increasingly challenging. For instance, finding antibiotics like tetracycline or vancomycin is rare, and daptomycin, the last major class approved over two decades ago, was found in only one out of ten million samples.

Despite these obstacles, there is hope. Modern gene sequencing technologies have unearthed more antibiotic-producing genes, offering the potential to uncover new antibiotics. By understanding the genetic blueprints of these microorganisms, scientists can predict and identify new antibiotic molecules. This genomic insight is essential for reigniting antibiotic discovery.

One of the most promising developments is the use of Artificial Intelligence (AI) to accelerate antibiotic discovery. Since 2022, AI has been used to filter out promising compounds from the vast chemical universe quickly and in a cost-effective manner. AI can identify drug candidates that humans might overlook, offering a new path to discovery. I covered pioneering studies on this front in a science column last year.

Perhaps, the most revolutionary use of AI in antibiotic discovery is presented now in research published in the scientific journal, Cell, by César de la Fuente's team at the University of Pennsylvania. In their research, they used machine learning to analyse a vast dataset of 63,410 metagenomes and 87,920 prokaryotic genomes. Metagenomes are collections of genetic material from diverse environments, and genomes are the complete set of genes in an organism. This analysis is crucial for antibiotic discovery since it identifies potential sources of new drugs.

From this data, the researchers created a catalogue of antimicrobial peptides. Antimicrobial peptides are short proteins that can kill bacteria, making them valuable in the search for new antibiotics.

The AI-driven approach identified 863,498 genetic sequences corresponding to peptides, many with significant potential as new antibiotics. This catalogue represents the largest antibiotic discovery effort to date. Without AI, this process would have taken years.

To validate their findings, the researchers made 100 of the predicted molecules and tested them against 11 drug-resistant bacteria. Remarkably, 79 were active, and 63 specifically targeted disease-causing bacteria, demonstrating their potential as future antibiotics.

However, the journey from discovery to a marketable antibiotic is long. Before approval, new antibiotics must undergo extensive research and clinical trials, taking 10 to 20 years. Most leads will not become viable candidates, and even fewer will become marketable drugs.

According to the AMR Industry Alliance, only 3,000 researchers focus on antibiotic resistance worldwide, compared to 46,000 in cancer research. There are just 27 drug candidates in clinical development for priority bacteria, compared to 1,600 for cancer. Most of these candidate drugs will fail along the way.

The significance of the Cell study lies in streamlining the initial phase of discovery, providing new candidates for rigorous testing. This is the advance of AI: identifying more leads faster and cheaper.

This is critical in addressing the superbug crisis since generating more leads increases our chances of finding the new drugs that are needed.

Anirban Mahapatra is a scientist and author, most recently of the popular science book, When The Drugs Don’t Work: The Hidden Pandemic That Could End Medicine. The views expressed are personal.

Catch every big hit, every wicket with Crickit, a one stop destination for Live Scores, Match Stats, Infographics & much more. Explore now!

See more

Get Current Updates on India News, Elections 2024, Lok sabha election 2024 voting live , Karnataka election 2024 live in Bengaluru , Election 2024 Date along with Latest News and Top Headlines from India and around the world.

Continue reading with HT Premium Subscription

Daily E Paper I Premium Articles I Brunch E Magazine I Daily Infographics
freemium
SHARE THIS ARTICLE ON
Share this article
SHARE
Story Saved
Live Score
OPEN APP
Saved Articles
Following
My Reads
Sign out
New Delhi 0C
Saturday, July 13, 2024
Start 14 Days Free Trial Subscribe Now
Follow Us On