Presenter: Harmen Bussemaker, Ph. D (Columbia University)
Topic: Probing the DNA binding specificity of transcription factor complexes with deep sequencing and biophysically interpretable machine learning
Quantifying sequence-specific protein-ligand interactions is critical for understanding and exploiting numerous cellular processes, including gene regulation and signal transduction. Next-generation sequencing (NGS) based assays are increasingly being used to profile these interactions with high-throughput. However, these assays do not provide 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 define 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 in vivo data such as ChIP-seq without peak calling. When coupled with a new assay called Kd-seq, it determines the absolute affinity of protein-ligand interactions. It can also profile the kinetics of kinase-substrate interactions. By constructing a biophysically robust foundation for profiling sequence recognition, ProBound opens up new avenues for decoding biological networks and rationally engineering protein-ligand interactions.