AI advances in drug and medicine development

[weatheriscool]

[weatheriscool]

AI-powered tool set to transform type 1 diabetes diagnosis and treatment
https://newatlas.com/chronic-pain/drug- ... lief-game/
by Ali Sardyga, Western Sydney University

Western Sydney University researchers have led a global team to pioneer a new AI-powered tool to assess the risk of developing type 1 diabetes (T1D) and predict treatment responses, potentially changing how the disease is diagnosed and managed.

This innovative risk score, based on microRNAs—small RNA molecules measured from blood—could help accurately capture the changing risk of T1D. The same microRNA markers used in the study were able to accurately predict early response to certain treatments, such as a cell therapy (islet transplantation), as well as a drug therapy (imatinib) for T1D.

In their article published in Nature Medicine, the research analyzed molecular data in 5,983 study samples from participants across Australia, Canada, Denmark, Hong Kong SAR China, India, New Zealand, and U.S., to develop a Dynamic Risk Score (DRS4C) that can classify people as having or not having T1D.

[weatheriscool]

AI helps researchers understand lung disease and proposes treatment
https://medicalxpress.com/news/2025-06- ... tment.html
by Gillian Dohrn, Yale School of Medicine

The secrets of idiopathic pulmonary fibrosis (IPF) are written in its very name. Idiopathic refers to a disease of unknown cause, and the condition, which turns healthy lung tissue into fibrous scar tissue, still raises many questions.

IPF originates at the periphery of the lung and progresses inward, compromising more and more tissue and, eventually, making it difficult for a person to breathe. There is no cure for IPF, and neither of the two drugs that are approved as treatments can reverse the scarring—they only slow it down.

In a new study published June 20 in Nature Biomedical Engineering, researchers at Yale School of Medicine and collaborators took a significant step toward understanding IPF—and numerous other complex diseases—with an algorithm that interprets disease data and proposes treatments.

[weatheriscool]

[weatheriscool]

New AI tool models protein dynamics, aiding drug discovery and protein research
https://phys.org/news/2025-07-ai-tool-p ... iding.html
by Free University of Berlin

A major scientific advance in protein modeling developed by Microsoft Research AI for Science, has been published in Science. The study introduces BioEmu, a generative deep learning system that emulates the equilibrium behavior of proteins with unprecedented speed and accuracy.

As the biological function of proteins depends on dynamical changes in their structure, the ability to predict these structural changes quickly and accurately opens the door to more rational design decisions in drug discovery, helping to reduce the failure rate of drugs in clinical trials.

[weatheriscool]

New AI tool accelerates mRNA-based treatments for viruses, cancers, genetic disorders
https://phys.org/news/2025-07-ai-tool-m ... ments.html
by University of Texas at Austin

Subtle differences in an mRNA sequence enables a ribosome to produce more or less of a certain protein. A new AI model called RiboNN predicts which sequences will be most efficiently produced and potentially, most effective for protein-based therapeutics. Credit: University of Texas at Austin

A new artificial intelligence model can improve the process of drug and vaccine discovery by predicting how efficiently specific mRNA sequences will produce proteins, both generally and in various cell types.

The new advance, developed through an academic-industrial partnership between The University of Texas at Austin and Sanofi, helps predict how much protein cells will produce, which can minimize the need for trial-and-error experimentation, accelerating the next generation of mRNA therapeutics.

Messenger RNA (mRNA) contains instructions for which proteins to make and how to make them, enabling our bodies to grow and carry out the day-to-day processes of life. Among the most promising areas of health and medicine, the ability to develop new mRNA vaccines and drugs—able to fight viruses, cancers and genetic disorders—involves the frequently challenging process of coaxing cells in a patient's body to produce enough protein from therapeutic mRNA to effectively combat disease.

[weatheriscool]

[wjfox]

AI-designed antibiotics pave way for defeating superbugs

3 minutes ago

Artificial intelligence has invented two new potential antibiotics that could kill drug-resistant gonorrhoea and MRSA, researchers have revealed.

The drugs were designed atom-by-atom by the AI and killed the superbugs in laboratory and animal tests.

The two compounds still need years of refinement and clinical trials before they could be prescribed.

But the Massachusetts Institute of Technology (MIT) team behind it say AI could start a "second golden age" in antibiotic discovery.

Antibiotics kill bacteria, but infections that resist treatment are now causing more than a million deaths a year.

https://www.bbc.co.uk/news/articles/cgr94xxye2lo

[weatheriscool]

[weatheriscool]

[weatheriscool]

[weatheriscool]

[weatheriscool]

[firestar464]

More on that by Reuters:

https://www.reuters.com/business/health ... 025-09-30/

Imagine mass firing scientists and then doing this lmao

[weatheriscool]

More on that by Reuters:

https://www.reuters.com/business/health ... 025-09-30/

Imagine mass firing scientists and then doing this lmao

I am thinking he wants to replace human scientist with a.i, but I doubt a.i is ready to replace human scientist yet but that is the kind of tight ass loserterian this fucker is.
I support using a.i to study cancer but we really shouldn't be defunding and firing human scientist.

[weatheriscool]

Collaborative AI passes U.S. medical exams
https://medicalxpress.com/news/2025-10- ... exams.html
by Public Library of Science

A council of five AI models working together, discussing their answers through an iterative process, achieved 97%, 93%, and 94% accuracy on 325 medical exam questions spanning the three stages of the U.S. Medical Licensing Examination (USMLE), according to a study published in PLOS Medicine by researcher Yahya Shaikh of Baltimore, U.S., and colleagues.

Over the past several years, many studies have evaluated the performance of large language models (LLMs) on medical knowledge and licensing exams. While scores have improved across LLMs, varying performance has been noted when the same question is asked to an LLM multiple times—a variety of responses are generated, some of which are incorrect or hallucinations.

[weatheriscool]

New Microsoft Team to Build Smarter-Than-Human AI for Medical Diagnostics
The company hopes to develop specialized AIs that perform at a superhuman level in specific fields without posing existential risks.
By Devesh Beri November 7, 2025
https://www.extremetech.com/computing/n ... iagnostics

Microsoft has announced the formation of a new research team, the MAI Superintelligence Team, to develop AI that outperforms humans in various areas, starting with medical diagnostics. Mustafa Suleyman, Microsoft's AI chief, told Reuters that the initiative will focus on creating what he calls "humanist superintelligence" that serves human interests and solves real-world problems.

Suleyman said Microsoft plans to invest heavily in the effort and staff it with both existing researchers and new recruits. Computer scientist and Google DeepMind researcher Karen Simonyan will serve as the team's chief scientist. The company has not disclosed whether it will use large financial incentives or hiring bonuses, such as those offered by Meta, to attract AI experts.

According to Suleyman, Microsoft does not plan to pursue an "infinitely capable generalist" AI. He said he doubts that fully autonomous, self-improving systems could be kept under control. Instead, the company hopes to develop specialized AIs that perform at a superhuman level in specific fields without posing existential risks. Suleyman said these systems could help solve major scientific problems, such as innovations in battery storage and molecule discovery.

[weatheriscool]

AI tool can analyze complex cancer images rapidly—offering potential to personalize treatment
https://medicalxpress.com/news/2025-11- ... mages.html
by University of Cambridge

Complex digital images of tissue samples that can take an experienced pathologist up to 20 minutes to annotate could be analyzed in just one minute using a new AI tool developed by researchers at the University of Cambridge.

SMMILe, a machine learning algorithm, is able not only to correctly detect the presence of cancer cells on slides taken from biopsies and surgical sections, but it can predict where the tumor lesions are located and even the proportion of regions with different levels of aggressiveness.

[firestar464]

Researchers diagnose disease with a drop of blood, a microscope and AI

https://medicalxpress.com/news/2025-11- ... pe-ai.html

[firestar464]

Studies suggest ambient AI saves time, reduces burnout and fosters patient connection

https://medicalxpress.com/news/2025-11- ... tient.html