Subject: CASP-RNA-Sig: “RNA structure prediction with deep learning” by Dr. Yu Li
Dear RNA structure enthusiasts,
We would like to present you with our first RNA CASP Special Interest Group (SIG) speaker, Dr. Yu Li.
“RNA structure prediction with deep learning”
Zoom link Tuesday May 23 Pacific Time 8am / Eastern Time 11am / Central Europen Time: 5pm / China Standard Time: 11pm
Following the presentation and Q&A, we will engage in a discussion regarding the organization of our SIG for future meetings. If you have recommendations on topics of discussion or speakers, please feel free to email us as well.
See you!
Rachael Kretsch (Rhiju Das and Wah Chiu labs @Stanford)
Marcin Magnus (Elena Rivas lab @Harvard)
Zoom link: https://stanford.zoom.us/j/93445935624?pwd=K0VUWk0zaVNMZlU1U0xUMS8vSWUwZz09
TALK ABSTRACT
Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations. These are all among the core problems in the RNA field. With the rapid growth of sequencing technology, we have accumulated a massive amount of unannotated RNA sequences. On the other hand, expensive experimental observatory results in only limited numbers of annotated data and 3D structures. Hence, it is still challenging to design computational methods for predicting their structures and functions. The lack of annotated data and systematic study causes inferior performance. To resolve the issue, we proposed an RNA foundation model (RNA-FM) to take advantage of all the 23 million non-coding RNA sequences through self-supervised learning. Within this approach, we discovered that the pre-trained RNA-FM could infer sequential and evolutionary information of non-coding RNAs without using any labels. Building upon RNA-FM, we proposed a deep learning method, RhoFold, to predict the RNA 3D structure in an end-to-end fashion. We evaluated RhoFold using all the publicly available 3D structure data, on which it performs impressively. We will also discuss the limitations and potential improvement of RhoFold.
SPEAKER BIO
Yu Li joined the Department of Computer Science & Engineering at the Chinese University of Hong Kong in December 2020 as an assistant professor, leading the Artificial Intelligence in Healthcare (AIH) group. He is also the Visiting Assistant Professor at MIT/Harvard, working with Prof. James Collins. He works at the intersection between machine learning, healthcare and bioinformatics, developing new machine learning methods to resolve the computational problems in biology and healthcare. He has published over 50 papers in top venues, such as Nature Communications, PNAS, and Nature Computational Science. In 2022, he was selected to the Forbes 30 Under 30 Asia list, Healthcare & Science. He obtained his Ph.D. in computer science from KAUST in Saudi Arabia in 2020, after which he was nominated KAUST Alumni Change Makers Awards in 2022. Before that, he got the Bachelor degree in Biosciences from University of Science and Technology of China (USTC).
CASP RNA SIG:
Welcome to the Special Interest Group (SIG) focused different aspects of nucleic acid 3D structure prediction. We aim to meet virtually monthly to discuss the state of and new developments in our community. We hope also to foster an active Google group for email correspondence.
How to use google groups: