Spotlight
in
Workshop: Generative AI and Biology (GenBio@NeurIPS2023)
Contributed talk | CodonBERT: Large Language Models for mRNA design and optimization
Sizhen Li · Saeed Moayedpour · Ruijiang Li · Michael Bailey · Saleh Riahi · Milad Miladi · Jacob Miner · Dinghai Zheng · Jun Wang · Akshay Balsubramani · Khang Tran · Minnie · Monica Wu · Xiaobo Gu · Ryan Clinton · Carla Asquith · Joseph Skaleski · Lianne Boeglin · Sudha Chivukula · Anusha Dias · Fernando Ulloa Montoya · Vikram Agarwal · Ziv Bar-Joseph · Sven Jager
Keywords: [ Deep codon representation ] [ Language language model ] [ Recombinant protein expression prediction ]
Sat 16 Dec 6:15 a.m. PST — 3:30 p.m. PST
mRNA based vaccines and therapeutics are gaining popularity and usage across a wide range of conditions. One of the critical issues when designing such mRNAs is sequence optimization. Even small proteins or peptides can be encoded by an enormously large number of mRNAs. The actual mRNA sequence can have a large impact on several properties including expression, stability, immunogenicity, and more. To enable the selection of an optimal sequence, we developed CodonBERT, a large language model (LLM) for mRNAs. Unlike prior models, CodonBERT uses codons as inputs which enables it to learn better representations. CodonBERT was trained using more than 10 million mRNA sequences from a diverse set of organisms. The resulting model captures important biological concepts. CodonBERT can also be extended to perform prediction tasks for various mRNA properties. CodonBERT outperforms previous mRNA prediction methods including on a new flu vaccine dataset.