Cross-Cell-Type Prediction of TF-Binding Site by Integrating Convolutional Neural Network and Adversarial Network

Transcription factor binding sites (TFBSs) play an important role in gene expression regulation. Many computational methods for TFBS prediction need sufficient labeled data. However, many transcription factors (TFs) lack labeled data in cell types. We propose a novel method, referred to as DANN_TF, for TFBS prediction. DANN_TF consists of a feature extractor, a label predictor, and a domain classifier. The feature extractor and the domain classifier constitute an Adversarial Network, which ensures that learned features are common features across different cell types. DANN_TF is evaluated on five TFs in five cell types with a total of 25 cell-type TF pairs and compared to a baseline method which does not use Adversarial Network. For both data augmentation and cross-cell-type prediction, DANN_TF performs better than the baseline method on most cell-type TF pairs. DANN_TF is further evaluated by an additional 13 TFs in the five cell types with a total of 65 cell-type TF pairs. Results show that DANN_TF achieves significantly higher AUC than the baseline method on 96.9% pairs of the 65 cell-type TF pairs. This is a strong indication that DANN_TF can indeed learn common features for cross-cell-type TFBS prediction.

Mocap: Large-scale inference of transcription factor binding sites from chromatin accessibility

Differential binding of transcription factors (TFs) atcis-regulatory loci drives the differentiation and function of diverse cellular lineages. Understanding the regulatory interactions that underlie cell fate decisions requires characterizing TF binding sites (TFBS) across multiple cell types and conditions. Techniques, e.g. ChIP-Seq can reveal genome-wide patterns of TF binding, but typically requires laborious and costly experiments for each TF-cell-type (TFCT) condition of interest. Chromosomal accessibility assays can connect accessible chromatin in one cell type to many TFs through sequence motif mapping. Such methods, however, rarely take into account that the genomic context preferred by each factor differs from TF to TF, and from cell type to cell type. To address the differences in TF behaviors, we developed Mocap, a method that integrates chromatin accessibility, motif scores, TF footprints, CpG/GC content, evolutionary conservation and other factors in an ensemble of TFCT-specific classifiers. We show that integration of genomic features, such as CpG islands improves TFBS prediction in some TFCT. Further, we describe a method for mapping new TFCT, for which no ChIP-seq data exists, onto our ensemble of classifiers and show that our cross-sample TFBS prediction method outperforms several previously described methods.

PREDICTION OF TRANSCRIPTION FACTOR BINDING SITES USING GENETICAL GENOMICS METHODS

In this paper, we wanted to test whether it is possible to use genetical genomics information such as expression quantitative trait loci (eQTL) mapping results as input to a transcription factor binding site (TFBS) prediction algorithm. Furthermore, this new approach was compared to the more traditional cluster based TFBS prediction. The results of eQTL mapping are used as input to one of the top ranking TFBS prediction algorithms. Genes with observed expression profiles showing the same eQTL region are collected into eQTL groups. The promoter sequences of all the genes within the same eQTL group are used as input in the transcription factor binding site search. This approach is tested with a real data set of a recombinant inbred line population of Arabidopsis thaliana. The predicted motifs are compared to results obtained from the conventional approach of first clustering the gene expression values and then using the promoter sequences of the genes within the same cluster as input for the transcription factor binding site prediction. Our eQTL based approach produced different motifs compared to the cluster based method. Furthermore the score of the eQTL based motifs was higher than the score of the cluster based motifs. In a comparison to already predicted motifs from the AtcisDB database, the eQTL based and the cluster based method produced about the same number of hits with binding sites from AtcisDB. In conclusion, the results of this study clearly demonstrate the usefulness of eQTL to predict transcription factor binding sites.