Quantifying Biopolymer Sequence Recognition using Biophysically Informed Machine Learning

Quantifying sequence-specific protein-ligand interactions is critical for understanding and exploiting numerous cellular processes, including gene expression regulation and signal transduction. Given their importance, next-generation sequencing (NGS) based assays that characterize such recognition with high-throughput are increasingly being used to profile a range of protein classes and interactions. However, these methods do not measure the biophysical parameters that have long been used to uncover the quantitative rules underlying sequence recognition. We developed a highly flexible machine learning framework, called ProBound, to quantify sequence recognition in terms of biophysical parameters based on NGS data. ProBound quantifies transcription factor (TF) behavior with models that accurately predict binding affinity over a range exceeding that of previous resources, captures the impact of DNA modifications and conformational flexibility of multi-TF complexes, and infers specificity directly from \textit{in vivo} data such as ChIP-seq without peak calling. When coupled with a new assay called Kd-seq, it quantifies the absolute affinity of protein-ligand interactions. Its applicability extends beyond thermodynamic equilibrium binding, to the kinetics of kinase-substrate interactions. Altogether, ProBound provides a versatile algorithmic framework for understanding sequence recognition in a wide variety of biological contexts. SELEX-seq was performed using the three homeodomain transcription factor Homothorax, Extradenticle and Ultrabithorax (Slattery, Cell, 2011). EpiSELEX-seq, generalize to assay 6mA and 5hMC modified DNA in addition to normal and meCpG, was performed for CEBPg and CEBPg together with ATF4 (Kribelbauer, Cell reports, 2017). K_D-seq was performed for Distal-less. Kinase-substrate sequencing was performed for SRC.