Base-resolution models of transcription factor binding reveal soft motif syntax

By Žiga Avsec, Melanie Weilert, Avanti Shrikumar, S. Krueger, Amr M. Alexandari, Khyati Dalal, Robin Fropf, Charles E. McAnany, J. Gagneur, Anshul B Kundaje and 1 more. Nature Genetics, 2021

562 citations recorded by the source corpus.

The arrangement (syntax) of transcription factor (TF) binding motifs is an important part of the cis-regulatory code, yet remains elusive. We introduce a deep learning model, BPNet, that uses DNA sequence to predict base-resolution chromatin immunoprecipitation (ChIP)–nexus binding profiles of pluripotency TFs. We develop interpretation tools to learn predictive motif representations and identify soft syntax rules for cooperative TF binding interactions. Strikingly, Nanog preferentially binds with helical periodicity, and TFs often cooperate in a directional manner, which we validate using clustered regularly interspaced short palindromic repeat (CRISPR)-induced point mutations. Our model represents a powerful general approach to uncover the motifs and syntax of cis-regulatory sequences in genomics data. BPNet is an interpretable deep learning tool that predicts transcription-factor binding profiles from DNA sequence at base-pair resolution, enabling the identification of motifs and the regulatory syntax underlying transcription-factor binding.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/31ee7d41146cb7a0abcb23b1e0a6e207744fb4f5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human Genomics (2024, background): “In this context, specialized deep learning (DL) models have been trained to uncover meaningful patterns of DNA [9, 10, 11, 12].”
JASPAR 2024: 20th anniversary of the open-access database of transcription factor binding profiles (2023, methodology): “Mostly based on convolutional neural networks, deep learning models are now considered state-of-the-art to accurately model data generated from genomic assays such as ChIP-seq, ChIP-nexus, or A T AC-seq ( 47– 49 ).”
JASPAR 2022: the 9th release of the open-access database of transcription factor binding profiles (2021, background): “A novel generation of computational models based on machine learning approaches such as deep learning are arising (68,69).”
Transcription factors interact with RNA to regulate genes (2022, background): “TFs typically contain DNA-binding domains that recognize specific sequences and multiple TFs collectively bind to enhancers and promoter-proximal regions of genes (Avsec et al., 2021; Panne et al., 2007).”
Effective gene expression prediction from sequence by integrating long-range interactions (2021, background): “Machine learning success depends on the training data, so increasing the resolution and quality of the target tracks 14 , and curating data from additional organisms 2 , would likely boost performance.”