FactorNet: a deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data

By Daniel Quang, Xiaohui S. Xie. 2017

172 citations recorded by the source corpus.

Due to the large numbers of transcription factors (TFs) and cell types, querying binding profiles of all TF/cell type pairs is not experimentally feasible, owing to constraints in time and resources. To address this issue, we developed a convolutional-recurrent neural network model, called FactorNet, to computationally impute the missing binding data. FactorNet trains on binding data from reference cell types to make accurate predictions on testing cell types by leveraging a variety of features, including genomic sequences, genome annotations, gene expression, and single-nucleotide resolution sequential signals, such as DNase I cleavage. To the best of our knowledge, this is the first deep learning method to study the rules governing TF binding at such a fine resolution. With FactorNet, a researcher can perform a single sequencing assay, such as DNase-seq, on a cell type and computationally impute dozens of TF binding profiles. This is an integral step for reconstructing the complex networks underlying gene regulation. While neural networks can be computationally expensive to train, we introduce several novel strategies to significantly reduce the overhead. By visualizing the neural network models, we can interpret how the model predicts binding which in turn reveals additional insights into regulatory grammar. We also investigate the variables that affect cross-cell type predictive performance to explain why the model performs better on some TF/cell types than others, and offer insights to improve upon this field. Our method ranked among the top four teams in the ENCODE-DREAM in vivo Transcription Factor Binding Site Prediction Challenge.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “…binding maps.10 Prospective evaluation of top-performing models highlighted a significant drop in prediction performance across cellular contexts relative to cross-validation performance within training cell types (Keilwagen et al., 2019; Quang and Xie, 2019; Li et al., 2019; Li and Guan, 2019).”
Learning from mistakes: Accurate prediction of cell type-specific transcription factor binding (2017, background): “…et al. , 2012; Kumar and Bucher, 2016), (sparse) logistic regression (Natarajan et al. , 2012; Luo and Hartemink, 2012; K¨ah¨ar¨a and L¨ahdesm¨aki, 2015; Chen et al. , 2017), random forests (Liu et al. , 2017), or neural networks adapted by deep learning (Quang and Xie, 2017; Qin and Feng, 2017).”
An interpretable bimodal neural network characterizes the sequence and preexisting chromatin predictors of induced transcription factor binding (2021, methodology): “Our use of neural networks is motivated by their advantages in predicting genome-wide TF binding patterns [24, 28, 35], and the ability of multi-modal neural networks to integrate heterogeneous data types [36–38].”
Identifying viruses from metagenomic data using deep learning (2020, methodology): “That is, Similar techniques were used in Quang et al. and Wang et al. [22,23].”
Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities (2018, background): “FactorNet [115] applies a deep neural network to this problem.”