Reference News Network, July 13 report. According to the US Science Daily website on July 11, in the past year, the number of proteins developed by artificial intelligence (AI) has surged, and they will eventually be used to treat a variety of diseases from snake bites to cancer. Scientists once took decades to develop, but now custom proteins targeting specific diseases can be completed in just seconds.

Australian scientists have for the first time used AI to generate a ready-to-use biological protein that can kill bacteria such as E. coli, which are resistant to antibiotics.

The study, published in the UK's Nature Communications, offers a new approach to address the increasingly severe crisis caused by superbugs with antibiotic resistance. By using AI technology in this way, the Australian scientific community has joined the ranks of countries such as the United States and China - which have developed AI platforms capable of rapidly generating thousands of ready-to-use proteins, paving the way for faster, more economical drug development and diagnostic technologies that could change the landscape of biomedical research and patient care.

This research was jointly led by Dr. Liese Grint and Associate Professor Gavin Nott from Snow Medical Research. Their new "AI Protein Design Program" has workstations at the Bio21 Institute of the University of Melbourne and the Monash Biomedical Discovery Institute.

According to Grint and Nott, the AI protein design platform used in this study is the first of its kind in Australia, emulating the end-to-end research workflow developed by David Baker (the 2024 Nobel Prize winner in Chemistry) for generating various proteins. Nott said, "These proteins will now be developed as drugs, vaccines, nanomaterials, and micro-sensors, and there are many other applications to be tested."

In this study, the AI protein design platform uses an AI protein design tool that is freely available to scientists around the world. Daniel Fox, a doctoral student who carried out most of the experimental work in the study, said, "Democratizing protein design so that people around the world can use these tools is extremely important. By using these tools and our own developed tools, we can design proteins that bind to specific targets or ligands as inhibitors, agonists, antagonists, or engineered enzymes with better activity and stability."

According to Grint, proteins currently used to treat diseases such as cancer and infections usually come from nature and achieve functional re-direction through rational design or in vitro evolution and screening. He said, "These new methods using deep learning technology make it possible to efficiently design proteins with specific properties and functions from scratch, thereby reducing costs and accelerating the development of new protein binders and engineered enzymes." (Translated by Cao Weiguo)

Original: https://www.toutiao.com/article/7526488818816451099/

Statement: This article represents the views of the author. Please express your opinion by clicking the [upvote/downvote] button below.