Believe it or not, linguistics and biology are two sides of the same coin, and language AI can be used not only to understand but also to design de novo biological systems. For example, our recent Nature (2023) paper designed highly stable and efficient messenger RNA (mRNA) vaccines using natural language processing techniques. Experiments on COVID and another virus show that our designs dramatically improves mRNA half-life, protein expression, and in vivo antibody response, compared to the standard method used by Pfizer and Moderna. Nature News reported our work as a “remarkable AI tool” for mRNA design. On the other hand, in order to find conserved structures across SARS-CoV-2 variants, our PNAS (2021) paper showed that aligning and folding related genomes can be viewed as “synchronous parsing” for multiple languages. This work stood the test of time with the arrival of Omicron and can be used to design variant-insensitive test kits and drugs.
Liang Huang (PhD, Penn, 2008) is a Professor of Computer Science (AI) and (by courtesy) Biochemistry & Biophysics at Oregon State University. He was known for algorithms and theory in natural language processing (NLP), but recently he has shifted his attention to applying NLP algorithms to computational biology, esp. RNA folding and RNA design. This line of interdisciplinary work eventually led to PNAS (2021) and Nature (2023) papers, and is widely covered in the media.