DNAffinity: a machine-learning approach to predict DNA binding affinities of transcription factors
Sandro Barissi, Alba Sala, Miłosz Wieczór, Federica Battistini, Modesto Orozco
Abstract
We present a physics-based machine learning approach to predict in vitro transcription factor binding affinities from structural and mechanical DNA properties directly derived from atomistic molecular dynamics simulations. The method is able to predict affinities obtained with techniques as different as uPBM, gcPBM and HT-SELEX with an excellent performance, much better than existing algorithms. Due to its nature, the method can be extended to epigenetic variants, mismatches, mutations, or any non-coding nucleobases. When complemented with chromatin structure information, our in vitro trained method provides also good estimates of in vivo binding sites in yeast.
Topics & Concepts
BiologyAffinitiesComputational biologyEpigeneticsChromatinDNABinding affinitiesTranscription factorGeneticsBinding siteDNA binding siteSystematic evolution of ligands by exponential enrichmentBiophysicsEvolutionary biologyBiochemistryGenePromoterRNAGene expressionReceptorGenomics and Chromatin DynamicsRNA and protein synthesis mechanismsBacterial Genetics and Biotechnology