Predicting the DNA binding specificity of mutated transcription factors using family-level biophysically interpretable machine learning

Abstract

ABSTRACTSequence-specific interactions of transcription factors (TFs) with genomic DNA underlie many cellular processes. High-throughputin vitrobinding assays coupled with computational analysis have made it possible to accurately define such sequence recognition in a biophysically interpretable yet mechanism-agonistic way for individual TFs. The fact that such sequence-to-affinity models are now available for hundreds of TFs provides new avenues for predicting how the DNA binding specificity of a TF changes when its protein sequence is mutated. To this end, we developed an analytical framework based on a tetrahedron embedding that can be applied at the level of a given structural TF family. Using bHLH as a test case, we demonstrate that we can systematically map dependencies between the protein sequence of a TF and base preference within the DNA binding site. We also develop a regression approach to predict the quantitative energetic impact of mutations in the DNA binding domain of a TF on its DNA binding specificity, and perform SELEX-seq assays on mutated TFs to experimentally validate our results. Our results point to the feasibility of predicting the functional impact of disease mutations and allelic variation in the cell-wide TF repertoire by leveraging high-quality functional information across sets of homologous wild-type proteins.SIGNIFICANCE STATEMENTTranscription factors (TFs) are DNA binding proteins that play a key role in gene expression control. Genetic mutations in the protein sequence of TFs are increasingly found to be associated with disease. Being able to predict the functional impact of such mutations in terms the quantitative changes in DNA sequence preference they cause is therefore highly useful. TFs come in families that are structurally similar but vary in terms of their sequence and function. In this study, we show that by jointly analyzing high-throughput DNA binding data for the basic helix-loop-helix (bHLH) family of transcription factors, we can successfully build a model that predicts the impact of TF protein sequence mutations.