news

한어Русский языкEnglishFrançaisIndonesianSanskrit日本語DeutschPortuguêsΕλληνικάespañolItalianoSuomalainenLatina

it home reported on september 6 that google published a blog post yesterday (september 5) to showcase its latest alphaproteo ai model, which is mainly used to design proteins that can successfully bind to target molecules, thereby promoting development in drug design, disease understanding and other aspects.

background

from cell growth to immune responses, every biological process in the human body relies on the interaction of protein molecules. like a key fitting into a lock, one protein can bind to another to help regulate critical cellular processes.

current challenges

protein structure prediction tools such as alphafold can help scientists gain a deeper understanding of how proteins interact to perform their functions, but these tools cannot create new proteins to directly manipulate these interactions.

about alphaproteo

to this end, google launched alphaproteo, its first artificial intelligence system for designing new high-strength protein binders, which can serve as the cornerstone of biological and health research. this technology has the potential to accelerate human understanding of biological processes, help discover new drugs, develop biosensors, etc.

it home quoted a press release as saying that alphaproteo can generate new protein binders for a variety of target proteins, including vascular endothelial growth factor-a (vegf-a), which is related to cancer and diabetic complications. this is the first time that an ai tool has successfully designed a protein binder for vascular endothelial growth factor-a.

the bar graph shows the in vitro success rate of alphaproteo for seven target proteins compared to other design methods. a higher success rate means that fewer designs must be tested to find a successful binder.

to test alphaproteo, google designed binders of multiple target proteins, including two viral proteins involved in infection, bhrf1 and sars-cov-2 spike protein receptor binding domain sc2rbd, as well as five proteins involved in cancer, inflammation and autoimmune diseases, il-7rɑ, pd-l1, trka, il-17a and vegf-a.