UVA scientists develop AI tools to accelerate new drug discovery

Picking the right target is absolutely fundamental. I mentioned that over half of failures of new medicines in development are due to us picking the wrong target. Even if we just doubled our success rate at picking the right target, it would have a huge impact on the development of new medicines for people. One of the reasons, and why I think artificial intelligence could be really important in helping us do that, is that, quite often, there may be some data buried in the literature that tells us a target is really good. Equally valuable is the fact that there may be something buried in the literature that tells you a target is not good. It's much harder to publish negative data than positive data. That target invalidation can be just as valuable as a target validation. It's really about being able to tap into all that knowledge and look up all the facts. That would mean that our systems and other people's AI systems can really be much more effective at picking the right target.

One major example is protein structure. Methods such as AlphaFold and Boltz-2 have transformed how we generate 3D structural data. Accurate protein structure prediction has been a decades-old challenge, and while there is still work to do on underrepresented protein classes, these models have opened an extraordinary pathway. We have also seen progress in multi-output models. Just over a decade ago (circa 2013), toxicology and property prediction models often focused on one endpoint at a time. Now, multi-output models, especially from methods such as graph neural networks (GNNs) and other deep learning methods, can predict multiple endpoints simultaneously. This allows for transfer learning between related properties. That creates opportunities across ADMET (absorption, distribution, metabolism, excretion, and toxicity) prediction and toxicology. Another exciting area is machine learning potentials. Molecular simulations traditionally rely on fixed mathematical functions to describe molecular interactions, but neural potentials can now replace or augment those functions. They can, in many cases, provide highly accurate simulations and structures at lower computational cost than quantum chemistry. However, its not just down to model architectures. The biggest blind spot behind all of these advances remains careful data curation, annotation, and collection. Open databases for example ChEMBL, PubChem and Chemspider together with data initiatives such as OpenADEMT and OpenBind to name but a few are making notable progress here. We still see some data for example on formulation chemistry often receiving less attention. Its is not just about data scale, but quality that is critical here to. Accessible high quality data sets are the fuel of AI methods. Architecture matters, but high-quality, accessible and abundant data is also absolutely critical.

RAS mutations are one of the most common cancer-causing genetic mutations, and the drug is now being studied in several cancer types. I think it's going to work especially well in tumors that are primarily RAS driven, including colon cancer and lung cancer. It might also work in other cancer types in combination with drugs targeting other genetic mutations, but further research is needed.

The bulk of vitamins and supplements containing fish oil, biotin, and vitamins A, C, and E can potentially promote nail and hair growth. You can find dietary supplements with higher concentrations of vitamins and minerals that aid skin, hair, and nail health. Fish oil supplements make nails and hair shiny. Fish oil also serves as an agent that can decrease signs of aging. If sun exposure damages the skin, the omega-3 fatty acids in fish oil can help. Biotin, also known as B7, increases hair density and strengthens it. It is found naturally in bananas, eggs, and milk. Vitamins are vital for skin health as well. Vitamin A reduces acne flairs and helps with changes due to aging like wrinkling. A vitamin A deficiency may increase the risk of acne because it becomes difficult for dead skin to slough off hair follicles, blocking pores. Vitamin B lowers the risk of precancerous growths and nonmelanoma skin cancer. Vitamin C is an antioxidant. It leads the fight against free radicals to help stimulate collagen and brighten skin. It also helps to prevent the formation of unneeded melanin that causes uneven skin pigmentation.

More specifically, the study showed that the female patient produced very few cathelicidins, which is a natural toxin found in the immune cells of the lungs needed to fight tuberculosis. In most people infected by tuberculosis, tuberculosis bacteria attack the immune cells of the lungs. The immune cells fight the bacteria by eating them. But the tuberculosis bacterium has developed various evasive mechanisms that reduce the immune cells’ ability to digest and thus to kill the Mtb. “You could say that the tuberculosis bacterium has developed a way to lull the immune cells to sleep. This enables the disease the hide inside the immune cells, making it invisible to other parts of the immune system,” Martin Kongsbak-Wismann explains. This is where vitamin D enters the picture. Because vitamin D is able to counteract the soporific effect of the tuberculosis bacteria by making the immune cells produce more of the cathelicidin toxin. “Cathelicidin is like a microscopic needle that is able to pierce the tuberculosis bacteria. And when it does, it weakens the bacteria’s soporific effect on the immune cells. This restores the immune cells’ ability to kill tuberculosis bacteria,” says Martin Kongsbak-Wismann and adds: “We were amazed by the effect of vitamin D. In immune cells from healthy control subjects, vitamin D improved the cells’ ability to fight Mtb, whereas in the female patient’s immune cells we saw no response to vitamin D. This shows that vitamin D is key to the immune system’s ability to fight Mtb and prevent tuberculosis.” Al-Jaberi, F.A.H., et al. (2022) Reduced vitamin D-induced cathelicidin production and killing of Mycobacterium tuberculosis in macrophages from a patient with a non-functional vitamin D receptor: A case report. Frontiers in Immunology. doi.org/10.3389/fimmu.2022.1038960.