Biomolecules, existing in high-order structural forms, are indispensable for the normal functioning of our bodies. To demystify those criticalbiological processes, we need to investigate biomolecular structures and functions. In this talk, we showcase our efforts in that research direction using deep learning. First, we proposed a deep lea rning guarded Bayesian inference framework for reconstructing super-resolved structure images from the super-resolved fluorescence microscopy data. This framework enables us to observe the overall biomolecular structures in living cells with super-resolution in almost rea l-time. Then, we zoom in on a particular biomolecule, RNA, predicting its secondary structure. For this one of the oldest problems in  bioinformatics,  we  proposed  an  unrolled  deep learning method, which can bring us w ith 20% performance improvement, regarding the Fl score. Finally, by leveraging the physioc hemica l features and deep  lea rning,   we   proposed   the   first-of-its­ kind framework to investigate the interaction between RNA and RNA-binding proteins (RBP). This framework can provide us w ith both the interaction deta ils and high-throughput binding prediction results. Extensive in vitro and in vivo biological experiments demonstrate the effectiveness of the proposed method.

Speaker: Mr Yu LI
Date: 19 May 2020 (Tue) 
Time: 3:30pm - 4:30pm
Poster: Click here