For decades, the phrase “incurable disease” has been considered a cold, impenetrable and definitive wall in medical sciences. In the room where the word “incurable” enters, “hope” leaves through the window.
But as humanity moves through 2026, that wall is finally cracking under the sheer processing power of artificial intelligence (AI). Eventually, hope blooms through the ruined cracks of the wall.
In today’s AI-powered world, the researchers do not just treat symptoms; they are rewriting the rules of medical science.
From "folding" proteins in seconds to designing custom cures for rare cancers, to combating antibiotic resistance, AI is transforming the health laboratory from a trial and error place into the realm of “bio-digital certainty.”
AI tools are breaking a decades-long stalemate in drug discovery, particularly to combat antibiotic resistant superbugs.
For years, scientists have been grappling with the slow and expensive traditional drug development process.
As reported by BBC, between 2017 and 2022, just 12 new antibiotics were approved for use. The worst thing is that the majority of antibiotics have remained ineffective against bacterial resistance.
Antibiotic-resistance superbugs are responsible for 5 million annual deaths globally. It is also estimated that these infections could cause more than A$2.5 trillion economic disruption globally by 2050.
Here comes the groundbreaking role of AI models, which are now screening billions of compounds in days and identifying entirely new chemical structures.
Researchers from the Massachusetts Institute of Technology (MIT) have designed two new compounds by using the AI. According to Collin from MIT, these compounds could be highly effective against highly drug-resistant infections gonorrhoea (Neisseria gonorrhoeae) and methicillin-resistant (Staphylococcus aureus) MRSA.
AI can also perform “freestyle” molecular design or build upon existing molecules, narrowing down the millions of possibilities in hours rather than years.
Given its unprecedented efficiency, the generative AI tool used by Collin and his team screened more than 45 million different chemical structures for their ability to target Neisseria gonorrhoeae and Staphylococcus aureus.
Previously, AI has also been used to discover new and powerful antibiotic compounds against Clostridium difficile, a common bowel infection, and Mycobacterium tuberculosis, which causes tuberculosis.
Despite 200 years of research, the medical researchers have failed to find an effective treatment that slows down the progression of neurodegenerative disease.
Globally, 10 million people have developed Parkinson’s disease. In the US, up to 1 million people live with this disease.
Michele Vendruscolo, professor in biophysics and co-director of the Centre for Misfolding Diseases at the University of Cambridge in the UK"There are endless debates about the origin of the disorder. If you go to a Parkinson's conference, you will hear dozens of different hypotheses that are all actively investigated."
In 2024, AI came in handy. Vendruscolo and his colleagues from the University of Cambridge used machine learning, a form of AI, to target Lewy bodies (misfolded protein clumps) which play a role in the initial stages of neurodegeneration in Parkinson's patients.
Scientists are now using AI to find molecules that stabilize proteins before they misfold, so they can completely prevent the disease.
By using the AI, they use AI to screen billions of molecules for a few thousand pounds in mere days.
The AI-suggested compound proved to be more effective than conventional approaches when tested in the lab. Researchers are hopeful that one day AI can help to completely halt Parkinson’s disease.
"If we can stabilise the proteins in this form by binding to them, we have prevented Parkinson's – which is better than curing it,” Vendruscolo said.
David Fajgenbaum, an associate professor of medicine at the University of Pennsylvania in the US, demonstrated that many of thousands of already approved drugs can treat diseases they were not designed for. He saved his own life using a transplant drug to treat Castleman disease.
New AI models are being used to "map" the world's 8,000 approved drugs against 17,000 diseases.
The notable examples include the rare chromosomal disorder Pitt–Hopkins syndrome, the rare inflammatory disease sarcoidosis and a rare kidney cancer, where AI is used for repurposing existing treatments.
At McGill University, researchers created a "virtual disease system" for Idiopathic Pulmonary Fibrosis (IPF), a progressive lung disease.
By sequencing lung cells at various stages, AI simulates how a cell moves from healthy to diseased. Through this approach, the scientists can test virtual drug impacts on a subject.
Scientists spent decades mapping a single 3D protein structure. In 2022, AlphaFold 2, an AI tool developed by DeepMind, solved this protein mystery by predicting the 3D shapes of nearly all 200 million known proteins. It was largely limited to the proteins themselves.
AlphaFold 3 is now capable of modelling DNA, RNA, and ligands. It also predicts how a drug binds to a specific protein pocket.
Despite AI revolution in healthcare, certain challenges remain:
Much of the critical data on drug absorption and toxicity is locked away in biotech and pharmaceutical companies and not publicly available.
AI currently excels at the initial screening and target identification phases, but drugs still face years of mandatory, slow-moving human clinical trials.
“AI is revolutionising drug discovery. But only in very specific ways,” says Vendruscolo.