Applied AI Therapeutics.
Hang-On Therapeutics. Because "All Things Do Come To Pass".
A Free Placeholder For You. Herbals, Therapeutics, & Biologics.
A Cool, Catchy, & Fun Name Is Important.
Makes It Memorable (See/Hear Once, Remembers),
Cool (Attractive, Fun, Pleasing, Interesting), And
Attention-Grabbing (Catches Attention, Separates From The Crowd).
You Catch A Bug/Virus. It Comes In, Wreaks You Havoc, And Leaves You Stronger. Coming Back Banging. So Until It Passes Through, Hang On With The Herbals & Therapeutics. To Restore Health & Function.
The Secrets of Life: The Words That Matter Most Now And Forever.
Love & Laughter.
Joy & Peace.
Good & Grace.
Faith & Hope.
Add Your Choice: Grain, Pasta, Meat, Potatoes:
Applied AI Therapeutics:
Accelerating Drug Discovery. Screening And Generating Candidate Molecules/Compounds. Guided, Generated, Powered, And Based-On AI.
The Power Of AI Can Be Used To Search, Screen, Sift, Generate, And Suggest Drug Molecules And Compounds. AI Can Screen Billions Of Molecules/Compounds In Just A Few Days That No Traditional Method Can.
AI Can Generate/Suggest Candidate Compounds. Lab Makes It. Tests It. Feed Back The Real Results Into The AI. The AI Learns From Itself. So Then The AI Can Suggest Better Compounds. Repeating The Learning Feedback Loop.
_________________________________________________________________________
These Diseases Were Thought To Be Incurable.
Now AI Is Unlocking New Treatments.
Laurie Clarke
10 March 2026
Applied AI. Case Study 1: Antibiotic-Resistant Superbugs.
"We can – in a matter of days or hours – look at massive libraries" of chemical compounds to identify those that display antibacterial activity, says James Collins.
Collins and his team trained a generative AI model to recognise the chemical structures of known antibiotics. This allowed the algorithm to learn what it takes to kill bacteria. The researchers then used the AI to screen more than 45 million different chemical structures for their [antibacterial] ability to target Neisseria gonorrhoeae, the bacteria that cause gonorrhoea, and Staphylococcus aureus, a significant source of infections in the form of MRSA.
Collins' method [also] used AI to create entirely new compounds to target the bugs. In one approach, he selected a molecule as a starting point and used a combination of generative AI techniques to build it out, "adding bonds, atoms, substructures", he says. At each critical stage, the compound was scored by his trained AI model: "Is this looking like an antibiotic? Is it getting closer to a potential antibiotic?" In another approach involved dispensing with the starting compound and letting the AI freestyle [build it] from the beginning.
Collins and his colleagues designed 36 million compounds in this way with potential to work against the bacteria. The team selected 24 to synthesize in a laboratory. Seven proved to have some antimicrobial activity, and two were highly effective at killing strains of both bacteria that were resistant to other types of antibiotics.The two candidates are currently undergoing further testing.
Applied AI. Case Study 2: Parkinson’s Disease.
The aggregations of proteins, known as Lewy bodies [in brain tissue], are thought to play a role in the initial stages of neurodegeneration in Parkinson's patients, eventually leading to symptoms including tremors, slowness of movement and muscle stiffness.
Right now, the most effective treatment for Parkinson's is Levodopa, a drug that helps to improve the symptoms of the disease but can also cause side-effects such as involuntary movements.
Vendruscolo is focused on halting the progression of the disease itself. He and his team started with a set of compounds that had already been identified as potentially effective in the treatment of Lewy bodies. He fed these [compounds] into a machine learning program, [let the program learn the compounds’ chemical structures, their patterns, similarities, etc], which [the program then] extrapolated from their chemical structures to [generate, suggest] propose new compounds that might also be effective.
The power of AI is that it can very quickly narrow down that search.
"We can analyse this data and can make very accurate predictions about ‘the way candidate molecules will bind to the target’, at a scale that was unthinkable until a few years ago," says Vendruscolo. With more traditional methods, scientists could screen around one million molecules in six months at the cost of several million pounds. "Now, you can do the same in a few days but screen billions of molecules, for the cost of a few thousand pounds."
Vendruscolo's AI-suggested compounds were then tested in the lab. "We measured which of the candidates were actually binding [to the Lewy bodies], and we fed this information back into the machine learning program, so it could learn from its own mistakes," he says. [Generate, Make, Test, Feed Back Actual Results into the program, Let It Learn from it, So Then Can Generate Better Compounds. Repeat The Learning Feedback Loop.]
They ended up identifying five promising new compounds more quickly and effectively than conventional approaches. The compounds identified by the AI were also far more novel than would have been found using more traditional drug development methods, says Vendruscolo. They are now undergoing further testing to assess whether they could one day be offered as a therapeutic to Parkinson's patients.
Vendruscolo hopes that one day, AI could help to halt Parkinson's before it begins. He is now using the technology to find small molecules that bind to the individual proteins that [will later] form Lewy bodies while [the proteins are] still in their normal state.
"If we can stabilise the proteins in this form by binding to them, we have prevented Parkinson's – which is better than curing it."
Applied AI. Case Study 3: Repurpose Existing Drugs For New Uses.
[Fajgenbaum] His experience opened his eyes to the potential that exists in the many thousands of drugs that have already been through the extensive safety testing required to make it to market. By repurposing these drugs to treat other conditions, patients get treatments they would not have otherwise.
In 2022, Fajgenbaum set up a nonprofit called Every Cure, using machine learning ‘to compare thousands of drugs against thousands of diseases’ [to repurposing existing drugs to treat other diseases]. The most promising are tested in laboratories or sent to doctors who are willing to experiment.
At Harvard Medical School, an AI model found nearly 8,000 approved drugs that could potentially be repurposed to treat 17,000 different diseases.
Applied AI: Case Study 4: In Silico Disease Progression Modelling With AI.
Idiopathic Pulmonary Fibrosis (IPF), a rare, progressive lung disease characterised by the scarring and thickening of lung tissue.
Their approach involved modelling the progression of the disease with an AI model.
"Most complex diseases are driven by abnormal cell state change," says one of the researchers, Jun Ding, assistant professor in the department of medicine at McGill University. "If we can figure out how the cell went from healthy to abnormal, maybe we can reverse it, or slow it down."
First, the researchers extracted lung cells from healthy participants and [then] patients at different stages of the disease progression. Using high-resolution DNA sequencing, they generate a lot of data [from it]. This allowed them to see how the cells changed over the course of the illness.
They then built a generative AI model that would simulate this, mapping the transitions of ‘various cell states and populations’ as the disease advanced. Along the way it would also highlight any biomarkers that could be used to diagnose the disease and potential therapeutic targets.
"We call it the virtual disease system," says Ding. Traditionally, drugs have been tested on animals or on isolated human cells. They wanted to apply the same paradigm with AI – essentially simulating the effects of IPF on virtual cells. [In silico]
"Researchers can then test the impacts of applying different drugs in the model without too much cost," says Ding.
In the McGill study, the AI suggested eight candidate treatment options for IPF. One promising candidate is a drug that is typically prescribed for hypertension, offering a low-cost option that is already proven as safe.
Ding says that the AI he and his colleagues developed could also be used on other diseases including cancers and lung conditions. His team is continuing to improve the model and diversify it across different conditions.
IPF saw another recent breakthrough thanks to AI. Insilico Medicine, an AI drug-discovery company, has produced a drug candidate called Rentosertib. In phase two clinical trials, it has shown promise against IPF. The company used AI to ‘both identify a potential weakness in the disease and [also] design a drug that could target it’. It hopes that if the trials are successful, the drug could be available by the end of the decade.
"My belief is, in the next five to 10 years, the majority of new drug development could be guided by AI, or even entirely based on AI," says Ding.
At present, AI is most useful in the initial screening part of the drug development process: in [disease] target identification and finding the molecules to bind to the target.
These are just two steps in the long process it takes to develop new medicines, meaning it could be some time before any of these potential treatments find their way to patients, if at all.
"AI is revolutionising drug discovery, says Vendruscolo. "But only in very specific ways."
Comments