Predictive Biophysical Neural Network Modeling of a Compendium of in vivo Transcription Factor DNA Binding Profiles for Escherichia coli

The DNA binding of most Escherichia coli Transcription Factors (TFs) has not been comprehensively mapped, and few have models that can quantitatively predict binding affinity. We report the global mapping of in vivo DNA binding for 139 E. coli TFs using ChIP-Seq. We used these data to train BoltzNet, a novel neural network that predicts TF binding energy from DNA sequence. BoltzNet mirrors a quantitative biophysical model and provides directly interpretable predictions genome-wide at nucleotide resolution. We used BoltzNet to quantitatively design novel binding sites, which we validated with biophysical experiments on purified protein. We have generated models for 125 TFs that provide insight into global features of TF binding, including clustering of sites, the role of accessory bases, the relevance of weak sites, and the background affinity of the genome. Our paper provides new paradigms for studying TF-DNA binding and for the development of biophysically motivated neural networks. Overall design: Chromatin immunoprecipitation DNA-sequencing (ChIP-Seq) of 139 TFs from Escherichia coli K-12 MG1655 under native and inducible expression modes, plus in vitro ChIP-Seq of one TF, and Library-ChIP of 3 TFs.

绝大多数大肠杆菌（Escherichia coli）转录因子（Transcription Factors，TFs）的DNA结合特性尚未得到全面绘制，且目前鲜有可定量预测其结合亲和力的模型。本研究通过染色质免疫沉淀测序（ChIP-Seq）技术，完成了139个大肠杆菌转录因子的体内DNA结合谱全局绘制。我们利用这些数据训练了BoltzNet——一种全新的、可从DNA序列预测转录因子结合能量的神经网络。BoltzNet契合定量生物物理模型的逻辑，可在全基因组范围内以核苷酸分辨率提供直接可解释的预测结果。我们借助BoltzNet定量设计了全新的结合位点，并通过纯化蛋白的生物物理实验对其进行了验证。我们为125个转录因子构建了相关模型，可助力解析转录因子结合的全局特征，包括结合位点的聚类规律、辅助碱基的作用、弱结合位点的相关性以及基因组的本底亲和力。本研究为转录因子-DNA结合的研究以及基于生物物理原理的神经网络开发提供了全新范式。
实验整体设计：针对大肠杆菌K-12 MG1655的139个转录因子，在天然表达与诱导表达两种模式下开展染色质免疫沉淀测序（ChIP-Seq）；此外还完成了1个转录因子的体外ChIP-Seq实验，以及3个转录因子的文库免疫沉淀（Library-ChIP）实验。