CodonBERT: Large Language Models for mRNA design and optimization
Dec 15, 2023
Speakers
Saeed Moayedpour
Speaker · 0 followers
Ruijiang Li
Speaker · 0 followers
Michael Bailey
Speaker · 0 followers
Saleh Riahi
Speaker · 0 followers
Milad Miladi
Speaker · 0 followers
Jacob Miner
Speaker · 0 followers
Dinghai Zheng
Speaker · 0 followers
Akshay Balsubramani
Speaker · 0 followers
Khang Tran
Speaker · 0 followers
Ryan Clinton
Speaker · 0 followers
Carla Asquith
Speaker · 0 followers
Joseph Skaleski
Speaker · 0 followers
Lianne Boeglin
Speaker · 0 followers
Sudha Chivukula
Speaker · 0 followers
Anusha Dias
Speaker · 0 followers
Fernando Ulloa Montoya
Speaker · 0 followers
Vikram Agarwal
Speaker · 0 followers
Ziv Bar-Joseph
Speaker · 0 followers
Sven Jager
Speaker · 0 followers
About
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.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…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Refined Mechanism Design for Approximately Structured Priors via Active Regression
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem
Watch later
Jincheng Cao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost
Watch later
Vihan Shah, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
Watch later
Tianhe Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Exploring and Interacting with the Set of Good Sparse Generalized Additive Models
Watch later
Chudi Zhong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes
Watch later
Yulei Qin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%