ResidualBind: Uncovering Sequence-Structure Preferences of RNA-Binding Proteins with Deep Neural Networks

Overview

Journal Methods Mol Biol

Specialty Molecular Biology

Date 2023 Jan 27

PMID 36705906

Authors

Peter K Koo

Matt Ploenzke

Praveen Anand

Steffan Paul

Antonio Majdandzic

Affiliations

Soon will be listed here.

Abstract

Deep neural networks have demonstrated improved performance at predicting sequence specificities of DNA- and RNA-binding proteins. However, it remains unclear why they perform better than previous methods that rely on k-mers and position weight matrices. Here, we highlight a recent deep learning-based software package, called ResidualBind, that analyzes RNA-protein interactions using only RNA sequence as an input feature and performs global importance analysis for model interpretability. We discuss practical considerations for model interpretability to uncover learned sequence motifs and their secondary structure preferences.

References

Aviv T, Amborski A, Zhao X, Kwan J, Johnson P, Sicheri F . The NMR and X-ray structures of the Saccharomyces cerevisiae Vts1 SAM domain define a surface for the recognition of RNA hairpins. J Mol Biol. 2005; 356(2):274-9. DOI: 10.1016/j.jmb.2005.11.066. View

Wheeler E, Van Nostrand E, Yeo G . Advances and challenges in the detection of transcriptome-wide protein-RNA interactions. Wiley Interdiscip Rev RNA. 2017; 9(1). PMC: 5739989. DOI: 10.1002/wrna.1436. View

Maticzka D, Lange S, Costa F, Backofen R . GraphProt: modeling binding preferences of RNA-binding proteins. Genome Biol. 2014; 15(1):R17. PMC: 4053806. DOI: 10.1186/gb-2014-15-1-r17. View

Orenstein Y, Wang Y, Berger B . RCK: accurate and efficient inference of sequence- and structure-based protein-RNA binding models from RNAcompete data. Bioinformatics. 2016; 32(12):i351-i359. PMC: 4908343. DOI: 10.1093/bioinformatics/btw259. View

Alipanahi B, Delong A, Weirauch M, Frey B . Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat Biotechnol. 2015; 33(8):831-8. DOI: 10.1038/nbt.3300. View

Tareen A, Kinney J . Logomaker: beautiful sequence logos in Python. Bioinformatics. 2019; 36(7):2272-2274. PMC: 7141850. DOI: 10.1093/bioinformatics/btz921. View

Ray D, Kazan H, Cook K, Weirauch M, Najafabadi H, Li X . A compendium of RNA-binding motifs for decoding gene regulation. Nature. 2013; 499(7457):172-7. PMC: 3929597. DOI: 10.1038/nature12311. View

Gronning A, Doktor T, Larsen S, Spangsberg Petersen U, Holm L, Bruun G . DeepCLIP: predicting the effect of mutations on protein-RNA binding with deep learning. Nucleic Acids Res. 2020; 48(13):7099-7118. PMC: 7367176. DOI: 10.1093/nar/gkaa530. View

Weirauch M, Cote A, Norel R, Annala M, Zhao Y, Riley T . Evaluation of methods for modeling transcription factor sequence specificity. Nat Biotechnol. 2013; 31(2):126-34. PMC: 3687085. DOI: 10.1038/nbt.2486. View

10.

Ghanbari M, Ohler U . Deep neural networks for interpreting RNA-binding protein target preferences. Genome Res. 2020; 30(2):214-226. PMC: 7050519. DOI: 10.1101/gr.247494.118. View

11.

Ben-Bassat I, Chor B, Orenstein Y . A deep neural network approach for learning intrinsic protein-RNA binding preferences. Bioinformatics. 2018; 34(17):i638-i646. DOI: 10.1093/bioinformatics/bty600. View

12.

Pan X, Shen H . RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach. BMC Bioinformatics. 2017; 18(1):136. PMC: 5331642. DOI: 10.1186/s12859-017-1561-8. View

13.

Lorenz R, Bernhart S, Honer Zu Siederdissen C, Tafer H, Flamm C, Stadler P . ViennaRNA Package 2.0. Algorithms Mol Biol. 2011; 6:26. PMC: 3319429. DOI: 10.1186/1748-7188-6-26. View

14.

Foat B, Morozov A, Bussemaker H . Statistical mechanical modeling of genome-wide transcription factor occupancy data by MatrixREDUCE. Bioinformatics. 2006; 22(14):e141-9. DOI: 10.1093/bioinformatics/btl223. View

15.

Eraslan G, Avsec Z, Gagneur J, Theis F . Deep learning: new computational modelling techniques for genomics. Nat Rev Genet. 2019; 20(7):389-403. DOI: 10.1038/s41576-019-0122-6. View

16.

Koo P, Ploenzke M . Improving representations of genomic sequence motifs in convolutional networks with exponential activations. Nat Mach Intell. 2021; 3(3):258-266. PMC: 8315445. DOI: 10.1038/s42256-020-00291-x. View

17.

Aviv T, Lin Z, Ben-Ari G, Smibert C, Sicheri F . Sequence-specific recognition of RNA hairpins by the SAM domain of Vts1p. Nat Struct Mol Biol. 2006; 13(2):168-76. DOI: 10.1038/nsmb1053. View

18.

Friedersdorf M, Keene J . Advancing the functional utility of PAR-CLIP by quantifying background binding to mRNAs and lncRNAs. Genome Biol. 2014; 15(1):R2. PMC: 4053780. DOI: 10.1186/gb-2014-15-1-r2. View

19.

Kazan H, Ray D, Chan E, Hughes T, Morris Q . RNAcontext: a new method for learning the sequence and structure binding preferences of RNA-binding proteins. PLoS Comput Biol. 2010; 6:e1000832. PMC: 2895634. DOI: 10.1371/journal.pcbi.1000832. View

20.

Su Y, Luo Y, Zhao X, Liu Y, Peng J . Integrating thermodynamic and sequence contexts improves protein-RNA binding prediction. PLoS Comput Biol. 2019; 15(9):e1007283. PMC: 6752863. DOI: 10.1371/journal.pcbi.1007283. View