Improved modeling of RNA-binding protein motifs in an interpretable neural model of RNA splicing
Name
13059_2023_Article_3162.pdf
Size
5.33 MB
Format
Adobe PDF
Checksum (MD5)
549a61e93007f53f0f6f968e1bf67bfb
Author(s)
Gupta, Kavi
Yang, Chenxi
McCue, Kayla
Bastani, Osbert
Sharp, Phillip A.
Burge, Christopher B.
Solar-Lezama, Armando
Date Issued
January 16, 2024
Journal
Genome Biology
Publisher
BioMed Central
Citation
Genome Biology. 2024 Jan 16;25(1):23
Version
Final published version
Abstract
Sequence-specific RNA-binding proteins (RBPs) play central roles in splicing decisions. Here, we describe a modular splicing architecture that leverages in vitro-derived RNA affinity models for 79 human RBPs and the annotated human genome to produce improved models of RBP binding and activity. Binding and activity are modeled by separate Motif and Aggregator components that can be mixed and matched, enforcing sparsity to improve interpretability. Training a new Adjusted Motif (AM) architecture on the splicing task not only yields better splicing predictions but also improves prediction of RBP-binding sites in vivo and of splicing activity, assessed using independent data.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Biology
Koch Institute for Integrative Cancer Research at MIT
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1186/s13059-023-03162-x
