UB research may offer a more streamlined approach to developing cancer drugs

What we're trying to do here at Benevolent is develop systems and processes that allow us to tap into the huge amount of public information and some propriety databases that we have paid to access and through that, generate hypotheses which our scientists can then triage. We've got over ten times the amount of information in our database at present (and it’s growing) than we believe that companies such as Watson have. Bringing that and filtering the signals from the ‘noise’ to our experienced drug discovery chemists and biologists, means, firstly, we can reduce the amount of time we take to triage new hypotheses, and secondly, we can develop more predictive chemical tools to allow us to make better molecules and also to reposition existing molecules for new indication.

There are no targeted treatments approved for pancreas cancer, and we haven't had any significant progress for a long time. We've only come up with different chemotherapy combinations, and those are only moderately effective. This new treatment is staggeringly better than chemotherapy. Usually, when we think of an improvement in pancreatic cancer survival, we think of 25% improvement. This medication actually doubled survival in patients with advanced disease. We have patients who participated in the trial who are still alive, which is unheard of because the five-year survival rate for pancreatic cancer patients is only 13%-14%. If the drug is approved by the FDA, it will most likely become the new standard of care for advanced pancreatic cancer and could replace chemotherapy as a first-line treatment.

For molecular design, classical machine learning with traditional fingerprints is not going to generate accurate 3D structures in the way modern graph-based, diffusion, and foundation models can. Where we have large, high-quality datasets, graph neural networks, language models, and foundation models can also outperform classical methods for property prediction. We even see some attempts at generating very large and widely applicable QSAR models, although bespoke models for specific target chemistries and properties remain the main form of QSAR model in use today. However, classical machine learning models are still very useful, especially for small datasets, which are common in early discovery. Classical machine learning models often have fewer parameters and can generalize better in small chemical spaces than larger deep learning models, which may overfit in such spaces. Classical models are also often much faster to train and perform inference with using modest compute infrastructure, such as a laptop. They can also be easier to interpret because many descriptors have a chemical or physical rationale. I do not think classical machine learning belongs in the past. The method pool is broader now, and the researcher's or engineer’s understanding of the data and desired outputs should guide the modeling decision.

Algae are photosynthetic aquatic creatures that grow through the consumption of nutrients, light, and carbon dioxide. They are a diverse group of creatures that include tiny single-celled algae and enormous kelp, as well as seaweed 1. Numerous prokaryotic and eukaryotic algae species are desirable food sources for humans due to their inherent qualities 2,3. Human intake of macroalgae such as seaweed and microalgae like phytoplankton dates back many years. Multicellular macroscopic aquatic plants, or macroalgae, are classified into three taxa: Phaeophyceae, or brown algae, Rhodophyta or red algae, and Chlorophyta or green algae. Microalgae, the unicellular counterpart of macroalgae, are categorized in a broader framework that includes prokaryotic cyanobacteria (blue-green algae), Euglenophyta, and Chlorophyta, which are genetically distinct from one another. The ancient populations of Chad and the Aztec culture were already familiar with the cyanobacteria spirulina, which is currently advertised as a superfood in the West 4. In Burma, Vietnam, and India, other cyanobacteria/microalgae, like Spirogyra and Oedogonium, were eaten as food or as a supplement 4. Seaweed is a staple of daily meals in many Asian and Pacific civilizations, including Korea, Japan, and Indonesia, as well as Hawaii and New Zealand 5.

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.