RNAglib: A Python Package for RNA 2.5D Graphs

Abstract

RNA 3D architectures are stabilized by sophisticated networks of (non-canonical) base pair interactions, which can be conveniently encoded as multi-relational graphs and efficiently exploited by graph theoretical approaches and recent progresses in machine learning techniques. RNAglib is a library that eases the use of this representation, by providing clean data, methods to load it in machine learning pipelines and graph-based deep learning models suited for this representation. RNAglib also offers other utilities to model RNA with 2.5D graphs, such as drawing tools, comparison functions or baseline performances on RNA applications. The method and data is distributed as a fully documented pip package. A full description for installation and usage is available as a README.

Edge-similarity-aware Graph Neural Networks

“…We use the rnaglib [9] benchmark to test our layers. This benchmark tries to predict three node-level tasks : whether a node was chemically modified (a proxy for its accessibility) or binds to a protein or a small molecule.…”

“…To capture the tertiary structure of RNA in a computationally feasible manner, a growing number of algorithms make use of 2.5D graph networks, whose nodes are nucleotides and whose edge types are structural categories of interactions [9]. This representation carries a strong prior and has shown to be efficient for machine learning.…”