Learning Distance-Dependent Motif Interactions: An Explicitly Interpretable Neural Model of Genomic Events

Quinn, Thomas P.; Nguyen, Dang; Nguyen, Phuoc; Gupta, Sunil; Venkatesh, Svetha

doi:10.1101/2020.08.27.270967

Cited by 3 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In line with this, RBPs have been shown by spaced k -mer counting approaches to often bind with multiple RBDs two separated cores with usually similar or identical motifs ( Dominguez et al , 2018 ; Jolma et al , 2020 ). Transcription factor motif discovery tools have been developed to learn co-occurrence of motif pairs in genomic sequences ( Toivonen et al , 2018 , 2020 ), and more recently, it was shown that distance dependent RNA motif pairs can be inferred from neural networks ( Koo et al , 2020 ; Quinn et al , 2020 ). However, transcription factor binding fundamentally differs from RBP binding as DNA can mediate cooperativity by propagating structural deformations induced by binding of proteins along the helix.…”

Section: Introductionmentioning

confidence: 99%

Thermodynamic modeling reveals widespread multivalent binding by RNA-binding proteins

Sohrabi-Jahromi

Söding

2021

Bioinformatics

View full text Add to dashboard Cite

Motivation Understanding how proteins recognize their RNA targets is essential to elucidate regulatory processes in the cell. Many RNA-binding proteins (RBPs) form complexes or have multiple domains that allow them to bind to RNA in a multivalent, cooperative manner. They can thereby achieve higher specificity and affinity than proteins with a single RNA-binding domain. However, current approaches to de novo discovery of RNA binding motifs do not take multivalent binding into account. Results We present Bipartite Motif Finder (BMF), which is based on a thermodynamic model of RBPs with two cooperatively binding RNA-binding domains. We show that bivalent binding is a common strategy among RBPs, yielding higher affinity and sequence specificity. We furthermore illustrate that the spatial geometry between the binding sites can be learned from bound RNA sequences. These discovered bipartite motifs are consistent with previously known motifs and binding behaviors. Our results demonstrate the importance of multivalent binding for RNA-binding proteins and highlight the value of bipartite motif models in representing the multivalency of protein-RNA interactions. Availability and implementation BMF source code is available at https://github.com/soedinglab/bipartite_motif_finder under a GPL license. The BMF web server is accessible at https://bmf.soedinglab.org. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Introductionmentioning

confidence: 99%

Thermodynamic modeling reveals widespread multivalent binding by RNA-binding proteins

Sohrabi-Jahromi

Söding

2021

Bioinformatics

View full text Add to dashboard Cite

show abstract

“…RBPs have further been shown by spaced k-mer counting approaches to often bind with multiple RNA-binding domains two separated cores with usually similar or identical motifs (6,13). A recent deep learning software is the only available one capable of learning distance dependent motif pairs (29).…”

Section: Introductionmentioning

confidence: 99%

Thermodynamic modeling reveals widespread multivalent binding by RNA-binding proteins

Sohrabi-Jahromi

Soeding

2021

Preprint

View full text Add to dashboard Cite

MotivationUnderstanding how proteins recognize their RNA targets is essential to elucidate regulatory processes in the cell. Many RNA-binding proteins (RBPs) form complexes or have multiple domains that allow them to bind to RNA in a multivalent, cooperative manner. They can thereby achieve higher specificity and affinity than proteins with a single RNA-binding domain. However, current approaches to de-novo discovery of RNA binding motifs do not take multivalent binding into account.ResultsWe present Bipartite Motif Finder (BMF), which is based on a thermodynamic model of RBPs with two cooperatively binding RNA-binding domains. We show that bivalent binding is a common strategy among RBPs, yielding higher affinity and sequence specificity. We furthermore illustrate that the spatial geometry between the binding sites can be learned from bound RNA sequences. These discovered bipartite motifs are consistent with previously known motifs and binding behaviors. Our results demonstrate the importance of multivalent binding for RNA-binding proteins and highlight the value of bipartite motif models in representing the multivalency of protein-RNA interactions.AvailabilityBMF source code is available at https://github.com/soedinglab/bipartite_motif_finder under a GPL license. The BMF web server is accessible at https://bmf.soedinglab.org.

show abstract

A Neural Model of RNA Splicing: Learning Motif Distances with Self-Attention and Toeplitz Max Pooling

Quinn

Nguyen

Gupta

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Alternative RNA splicing is an important regulator of tissue development and specificity, and a relevant mechanism in cancer progression. There exists a strong motivation to disentangle the rules that govern RNA splicing, in part because this knowledge may one day yield new clinically relevant diagnostic tools and therapeutics. It is no easy to task to reverse engineer how the splicesome machinery choreographs the removal and addition of RNA elements following transcription. Here, we propose an interpretable neural network called the Toeplitz ATtention Architecture (TATA), which learns distance-dependent motif interactions through a novel Toeplitz max pool layer that captures the relative distance between interacting CNN filters. TATA is a completely transparent ``clear-box'' solution: every model parameter is human-interpretable. We validate TATA on simulated data, then apply it to real data to identify putative cis-regulatory elements that interact with primary RNA splice sites.

show abstract

Learning Distance-Dependent Motif Interactions: An Explicitly Interpretable Neural Model of Genomic Events

Cited by 3 publications

References 35 publications

Thermodynamic modeling reveals widespread multivalent binding by RNA-binding proteins

Thermodynamic modeling reveals widespread multivalent binding by RNA-binding proteins

Thermodynamic modeling reveals widespread multivalent binding by RNA-binding proteins

A Neural Model of RNA Splicing: Learning Motif Distances with Self-Attention and Toeplitz Max Pooling

Contact Info

Product

Resources

About