A deep learning method for recovering missing signals in transcriptome-wide RNA structure profiles from probing experiments

Sequencing-based RNA structure probing can generate transcriptome-wide profiles of RNA secondary structures. Sufficient structural coverage is needed to obtain unbiased insights about RNA structures and functions, yet probing methods often yield uneven coverage, with missing structural scores across many transcripts. To overcome this barrier, we developed StructureImpute, a deep learning framework inspired by depth completion from computer vision that integrates an RNA sequence with available RNA structural information of neighbouring nucleotides to infer missing structure scores. We demonstrate the strong imputation performance of StructureImpute, with accuracy much superior to predictions based on RNA sequence alone. We also show that StructureImpute reliably reconstructs RNA structural patterns at biologically impactful RNA regulation regions, including protein-binding and RNA-modification sites. Strikingly, StructureImpute can use transfer learning to apply a model trained on one dataset to accurately infer missing structural scores in other datasets, even if they were generated with different technologies (for example, icSHAPE and DMS-seq). RNA structure profiling methods suffer from missing values in RNA structurome data. Inspired by a computer vision approach, Gong and colleagues develop a deep learning method that imputes missing RNA structure scores and increases the structural coverage of the transcriptome.