Logo image
De novo inference of thermodynamic binding energies using deep learning models of in vivo transcription factor binding
Dataset   Open access

De novo inference of thermodynamic binding energies using deep learning models of in vivo transcription factor binding

Amr Alexandari, Connor Horton, Avanti Shrikumar, Nilay Shah, Eileen Li, Melanie Weilert, Miles Pufall, Julia Zeitlinger, Polly Fordyce and Anshul Kundaje
Zenodo
06/27/2022
DOI: 10.5281/zenodo.6762262
url
https://doi.org/10.5281/zenodo.6762262View
Open Access

Abstract

We introduce Affinity Distillation (AD), a method for extracting thermodynamic affinities de-novo from in-vivo immunoprecipitation experiments using deep learning. We show that neural networks modeling base-resolution in-vivo binding profiles of yeast and mammalian TFs can accurately predict energetic impacts of varying underlying DNA sequence on TF binding. Systematic comparisons between Affinity Distillation predictions and other predictive algorithms consistently show that Affinity Distillation more accurately predicts affinities across a wide range of TF structural classes and DNA sequences. Affinity Distillation relies on in-silico marginalization against many sequence backgrounds, resulting in a higher dynamic range and more accurate predictions than motif discovery algorithms. Moreover, we show that Affinity Distillation can learn differential paralog-specific affinities, thereby making it possible to more accurately reconstruct regulatory networks in cells.
Gene Regulation deep learning protein-DNA binding Transcription factors binding specificity high-throughput binding assays

Details

Metrics

22 Record Views
Logo image