Baidu AI Milestone to Improve Covid-19 mRNA Vaccine Published in Nature
BEIJING, May 3 (TMTPOST)— Baidu achieves another milestone at artificial intelligence (AI) sector.
Source: TMTPOST
The leading scientific journal Nature published the paper titled Algorithm for Optimized mRNA Design Improves Stability and Immunogenicity through Accelerted Article Preview (AAP) on Wednesday, unveiling a groundbreaking methodology to significantly improve stability of the Covid-19 mRNA vaccine and its antibody response. The publication marks Baidu becomes the first Chinese tech company that was credited as the first affiliation on a paper published in Nature.
The paper involves an AI algorithm, developed by scientists at Baidu Research, for rapidly design of highly stable Covid mRNA vaccine sequences that were previously unattainable. It showed how a complex biology problem can be tackled by taking a classic approach from natural language processing (NLP), using an elegantly simple solution that has been employed to understand words and grammar. The algorithm, named LinearDesign, was said to deliver a 128-fold increase in the Covid vaccine’s antibody response.
Specifically, Baidu researchers used a technique in language processing called lattice parsing to enhance stability and efficacy of the vaccine. The tech represents potential word connections in a lattice graph and selects the most plausible option based on grammar. With deterministic finite-state automaton (DFA), they created a graph that compactly represents all mRNA candidates, and then applied lattice parsing to mRNA, to make finding the optimal mRNA similar as identifying the most likely sentence among a range of similar-sounding alternatives. By this means, LinearDesign takes a mere 11 minutes to generate the most stable mRNA sequence that encodes Spike protein.
“This research can apply mRNA medicine encoding to a wider range of therapeutic proteins, such as monoclonal antibodies and anti-cancer drugs, promising broad applications and far-reaching impact,” said Dr. He Zhang, Staff Software Engineer at Baidu Research. Zhang added that Baidu’s method to design vaccines would greatly reduce the research and development (R&D) cost for biopharmaceutical companies while improving the outcomes.
Calling the new methodology a “remarkable” one, Dave Mauger, a computational RNA biologist and former staff at Moderna, a biotech company to make mRNA vaccines, commented the computational efficiency is “really impressive and more sophisticated” than ever.
The study is also an AI achievement made by Baidu following its ChatGPT-like chatbot Ernie Bot, and knowledge-enhanced LLM. Baidu officially launched Ernie Bot on March 16, a day after OpenAI released the multimodal pre-training large model GPT-4. The generative AI product enables to generate texts and integrate other capabilities of Baidu in the field of AI, such as the ability to create pictures, and the ability to automatically generate videos according to the copywriting, which can generate content with pictures. Baidu CEO Robin Li said in February that his company planned to integrate the bot with search and other major businesses.
At a blog released on Wednesday, Baidu said Ernie Bot is part the Ernie Big Model family, which has developed a comprehensive big model technology system, covering NLP, vision, cross-modal, and biocomputing. The Chinese tech giant has created a biocomputing platform based on PaddlePaddle called PaddleHelix, which encompasses the ERNIE-Biocomputing Big Models, including LinearDesign. It vows to continue the exploration of AI application in life sciences, and broadening the scope and depth of inclusive technology.
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.
