TAMC: A deep-learning approach to predict motif-centric transcriptional factor binding activity based on ATAC-seq profile

Determining transcriptional factor binding sites (TFBSs) is critical for understanding the molecular mechanisms regulating gene expression in different biological conditions. Biological assays designed to directly mapping TFBSs require large sample size and intensive resources. As an alternative, ATAC-seq assay is simple to conduct and provides genomic cleavage profiles that contain rich information for imputing TFBSs indirectly. Previous footprint-based tools are inheritably limited by the accuracy of their bias correction algorithms and the efficiency of their feature extraction models. Here we introduce TAMC (Transcriptional factor binding prediction from ATAC-seq profile at Motif-predicted binding sites using Convolutional neural networks), a deep-learning approach for predicting motif-centric TF binding activity from paired-end ATAC-seq data. TAMC does not require bias correction during signal processing. By leveraging a one-dimensional convolutional neural network (1D-CNN) model, TAMC make predictions based on both footprint and non-footprint features at binding sites for each TF and outperforms existing footprinting tools in TFBS prediction particularly for ATAC-seq data with limited sequencing depth.

Profiling the quantitative occupancy of myriad transcription factors across conditions by modeling chromatin accessibility data

Over a thousand different transcription factors (TFs) bind with varying occupancy across the human genome. Chromatin immunoprecipitation (ChIP) can assay occupancy genome-wide, but only one TF at a time, limiting our ability to comprehensively observe the TF occupancy landscape, let alone quantify how it changes across conditions. We developed TF occupancy profiler (TOP), a Bayesian hierarchical regression framework, to profile genome-wide quantitative occupancy of numerous TFs using data from a single chromatin accessibility experiment (DNase- or ATAC-seq). TOP is supervised, and its hierarchical structure allows it to predict the occupancy of any sequence-specific TF, even those never assayed with ChIP. We used TOP to profile the quantitative occupancy of hundreds of sequence-specific TFs at sites throughout the genome and examined how their occupancies changed in multiple contexts: in approximately 200 human cell types, through 12 h of exposure to different hormones, and across the genetic backgrounds of 70 individuals. TOP enables cost-effective exploration of quantitative changes in the landscape of TF binding.

A novel convolution attention model for predicting transcription factor binding sites by combination of sequence and shape

The discovery of putative transcription factor binding sites (TFBSs) is important for understanding the underlying binding mechanism and cellular functions. Recently, many computational methods have been proposed to jointly account for DNA sequence and shape properties in TFBSs prediction. However, these methods fail to fully utilize the latent features derived from both sequence and shape profiles and have limitation in interpretability and knowledge discovery. To this end, we present a novel Deep Convolution Attention network combining Sequence and Shape, dubbed as D-SSCA, for precisely predicting putative TFBSs. Experiments conducted on 165 ENCODE ChIP-seq datasets reveal that D-SSCA significantly outperforms several state-of-the-art methods in predicting TFBSs, and justify the utility of channel attention module for feature refinements. Besides, the thorough analysis about the contribution of five shapes to TFBSs prediction demonstrates that shape features can improve the predictive power for transcription factors-DNA binding. Furthermore, D-SSCA can realize the cross-cell line prediction of TFBSs, indicating the occupancy of common interplay patterns concerning both sequence and shape across various cell lines. The source code of D-SSCA can be found at https://github.com/MoonLord0525/.

Constructing gene regulatory networks using epigenetic data

The biological processes that drive cellular function can be represented by a complex network of interactions between regulators (transcription factors) and their targets (genes). A cell's epigenetic state plays an important role in mediating these interactions, primarily by influencing chromatin accessibility. However, how to effectively use epigenetic data when constructing a gene regulatory network remains an open question. Almost all existing network reconstruction approaches focus on estimating transcription factor to gene connections using transcriptomic data. In contrast, computational approaches for analyzing epigenetic data generally focus on improving transcription factor binding site predictions rather than deducing regulatory network relationships. We bridged this gap by developing SPIDER, a network reconstruction approach that incorporates epigenetic data into a message-passing framework to estimate gene regulatory networks. We validated SPIDER's predictions using ChIP-seq data from ENCODE and found that SPIDER networks are both highly accurate and include cell-line-specific regulatory interactions. Notably, SPIDER can recover ChIP-seq verified transcription factor binding events in the regulatory regions of genes that do not have a corresponding sequence motif. The networks estimated by SPIDER have the potential to identify novel hypotheses that will allow us to better characterize cell-type and phenotype specific regulatory mechanisms.

Epitome: predicting epigenetic events in novel cell types with multi-cell deep ensemble learning

The accumulation of large epigenomics data consortiums provides us with the opportunity to extrapolate existing knowledge to new cell types and conditions. We propose Epitome, a deep neural network that learns similarities of chromatin accessibility between well characterized reference cell types and a query cellular context, and copies over signal of transcription factor binding and modification of histones from reference cell types when chromatin profiles are similar to the query. Epitome achieves state-of-the-art accuracy when predicting transcription factor binding sites on novel cellular contexts and can further improve predictions as more epigenetic signals are collected from both reference cell types and the query cellular context of interest.

High-resolution transcription factor binding sites prediction improved performance and interpretability by deep learning method

Transcription factors (TFs) are essential proteins in regulating the spatiotemporal expression of genes. It is crucial to infer the potential transcription factor binding sites (TFBSs) with high resolution to promote biology and realize precision medicine. Recently, deep learning-based models have shown exemplary performance in the prediction of TFBSs at the base-pair level. However, the previous models fail to integrate nucleotide position information and semantic information without noisy responses. Thus, there is still room for improvement. Moreover, both the inner mechanism and prediction results of these models are challenging to interpret. To this end, the Deep Attentive Encoder-Decoder Neural Network (D-AEDNet) is developed to identify the location of TFs-DNA binding sites in DNA sequences. In particular, our model adopts Skip Architecture to leverage the nucleotide position information in the encoder and removes noisy responses in the information fusion process by Attention Gate. Simultaneously, the Transcription Factor Motif Discovery based on Sliding Window (TF-MoDSW), an approach to discover TFs-DNA binding motifs by utilizing the output of neural networks, is proposed to understand the biological meaning of the predicted result. On ChIP-exo datasets, experimental results show that D-AEDNet has better performance than competing methods. Besides, we authenticate that Attention Gate can improve the interpretability of our model by ways of visualization analysis. Furthermore, we confirm that ability of D-AEDNet to learn TFs-DNA binding motifs outperform the state-of-the-art methods and availability of TF-MoDSW to discover biological sequence motifs in TFs-DNA interaction by conducting experiment on ChIP-seq datasets.

An Integrative Framework for Combining Sequence and Epigenomic Data to Predict Transcription Factor Binding Sites Using Deep Learning

Knowing the transcription factor binding sites (TFBSs) is essential for modeling the underlying binding mechanisms and follow-up cellular functions. Convolutional neural networks (CNNs) have outperformed methods in predicting TFBSs from the primary DNA sequence. In addition to DNA sequences, histone modifications and chromatin accessibility are also important factors influencing their activity. They have been explored to predict TFBSs recently. However, current methods rarely take into account histone modifications and chromatin accessibility using CNN in an integrative framework. To this end, we developed a general CNN model to integrate these data for predicting TFBSs. We systematically benchmarked a series of architecture variants by changing network structure in terms of width and depth, and explored the effects of sample length at flanking regions. We evaluated the performance of the three types of data and their combinations using 256 ChIP-seq experiments and also compared it with competing machine learning methods. We find that contributions from these three types of data are complementary to each other. Moreover, the integrative CNN framework is superior to traditional machine learning methods with significant improvements.

Atlas of Transcription Factor Binding Sites from ENCODE DNase Hypersensitivity Data across 27 Tissue Types

Characterizing the tissue-specific binding sites of transcription factors (TFs) is essential to reconstruct gene regulatory networks and predict functions for non-coding genetic variation. DNase-seq footprinting enables the prediction of genome-wide binding sites for hundreds of TFs simultaneously. Despite the public availability of high-quality DNase-seq data from hundreds of samples, a comprehensive, up-to-date resource for the locations of genomic footprints is lacking. Here, we develop a scalable footprinting workflow using two state-of-the-art algorithms: Wellington and HINT. We apply our workflow to detect footprints in 192 ENCODE DNase-seq experiments and predict the genomic occupancy of 1,515 human TFs in 27 human tissues. We validate that these footprints overlap true-positive TF binding sites from ChIP-seq. We demonstrate that the locations, depth, and tissue specificity of footprints predict effects of genetic variants on gene expression and capture a substantial proportion of genetic risk for complex traits.

A practical guide for DNase-seq data analysis: from data management to common applications

Deoxyribonuclease I (DNase I)-hypersensitive site sequencing (DNase-seq) has been widely used to determine chromatin accessibility and its underlying regulatory lexicon. However, exploring DNase-seq data requires sophisticated downstream bioinformatics analyses. In this study, we first review computational methods for all of the major steps in DNase-seq data analysis, including experimental design, quality control, read alignment, peak calling, annotation of cis-regulatory elements, genomic footprinting and visualization. The challenges associated with each step are highlighted. Next, we provide a practical guideline and a computational pipeline for DNase-seq data analysis by integrating some of these tools. We also discuss the competing techniques and the potential applications of this pipeline for the analysis of analogous experimental data. Finally, we discuss the integration of DNase-seq with other functional genomics techniques.

TRACE: transcription factor footprinting using chromatin accessibility data and DNA sequence

Transcription is tightly regulated by cis-regulatory DNA elements where transcription factors (TFs) can bind. Thus, identification of TF binding sites (TFBSs) is key to understanding gene expression and whole regulatory networks within a cell. The standard approaches used for TFBS prediction, such as position weight matrices (PWMs) and chromatin immunoprecipitation followed by sequencing (ChIP-seq), are widely used but have their drawbacks, including high false-positive rates and limited antibody availability, respectively. Several computational footprinting algorithms have been developed to detect TFBSs by investigating chromatin accessibility patterns; however, these also have limitations. We have developed a footprinting method to predict TF footprints in active chromatin elements (TRACE) to improve the prediction of TFBS footprints. TRACE incorporates DNase-seq data and PWMs within a multivariate hidden Markov model (HMM) to detect footprint-like regions with matching motifs. TRACE is an unsupervised method that accurately annotates binding sites for specific TFs automatically with no requirement for pregenerated candidate binding sites or ChIP-seq training data. Compared with published footprinting algorithms, TRACE has the best overall performance with the distinct advantage of targeting multiple motifs in a single model.

Analytical Approaches for ATAC-seq Data Analysis

ATAC-seq, the assay for transposase-accessible chromatin using sequencing, is a quick and efficient approach to investigating the chromatin accessibility landscape. Investigating chromatin accessibility has broad utility for answering many biological questions, such as mapping nucleosomes, identifying transcription factor binding sites, and measuring differential activity of DNA regulatory elements. Because the ATAC-seq protocol is both simple and relatively inexpensive, there has been a rapid increase in the availability of chromatin accessibility data. Furthermore, advances in ATAC-seq protocols are rapidly extending its breadth to additional experimental conditions, cell types, and species. Accompanying the increase in data, there has also been an explosion of new tools and analytical approaches for analyzing it. Here, we explain the fundamentals of ATAC-seq data processing, summarize common analysis approaches, and review computational tools to provide recommendations for different research questions. This primer provides a starting point and a reference for analysis of ATAC-seq data. © 2020 Wiley Periodicals LLC.

GTRD: a database on gene transcription regulation-2019 update

The current version of the Gene Transcription Regulation Database (GTRD; http://gtrd.biouml.org) contains information about: (i) transcription factor binding sites (TFBSs) and transcription coactivators identified by ChIP-seq experiments for Homo sapiens, Mus musculus, Rattus norvegicus, Danio rerio, Caenorhabditis elegans, Drosophila melanogaster, Saccharomyces cerevisiae, Schizosaccharomyces pombe and Arabidopsis thaliana; (ii) regions of open chromatin and TFBSs (DNase footprints) identified by DNase-seq; (iii) unmappable regions where TFBSs cannot be identified due to repeats; (iv) potential TFBSs for both human and mouse using position weight matrices from the HOCOMOCO database. Raw ChIP-seq and DNase-seq data were obtained from ENCODE and SRA, and uniformly processed. ChIP-seq peaks were called using four different methods: MACS, SISSRs, GEM and PICS. Moreover, peaks for the same factor and peak calling method, albeit using different experiment conditions (cell line, treatment, etc.), were merged into clusters. To reduce noise, such clusters for different peak calling methods were merged into meta-clusters; these were considered to be non-redundant TFBS sets. Moreover, extended quality control was applied to all ChIP-seq data. Web interface to access GTRD was developed using the BioUML platform. It provides browsing and displaying information, advanced search possibilities and an integrated genome browser.

From reads to insight: a hitchhiker's guide to ATAC-seq data analysis

Assay of Transposase Accessible Chromatin sequencing (ATAC-seq) is widely used in studying chromatin biology, but a comprehensive review of the analysis tools has not been completed yet. Here, we discuss the major steps in ATAC-seq data analysis, including pre-analysis (quality check and alignment), core analysis (peak calling), and advanced analysis (peak differential analysis and annotation, motif enrichment, footprinting, and nucleosome position analysis). We also review the reconstruction of transcriptional regulatory networks with multiomics data and highlight the current challenges of each step. Finally, we describe the potential of single-cell ATAC-seq and highlight the necessity of developing ATAC-seq specific analysis tools to obtain biologically meaningful insights.

Predicting transcription factor binding using ensemble random forest models

Background: Understanding the location and cell-type specific binding of Transcription Factors (TFs) is important in the study of gene regulation. Computational prediction of TF binding sites is challenging, because TFs often bind only to short DNA motifs and cell-type specific co-factors may work together with the same TF to determine binding. Here, we consider the problem of learning a general model for the prediction of TF binding using DNase1-seq data and TF motif description in form of position specific energy matrices (PSEMs).

Methods: We use TF ChIP-seq data as a gold-standard for model training and evaluation. Our contribution is a novel ensemble learning approach using random forest classifiers. In the context of the ENCODE-DREAM in vivo TF binding site prediction challenge we consider different learning setups.

Results: Our results indicate that the ensemble learning approach is able to better generalize across tissues and cell-types compared to individual tissue-specific classifiers or a classifier built based upon data aggregated across tissues. Furthermore, we show that incorporating DNase1-seq peaks is essential to reduce the false positive rate of TF binding predictions compared to considering the raw DNase1 signal.

Conclusions: Analysis of important features reveals that the models preferentially select motifs of other TFs that are close interaction partners in existing protein protein-interaction networks. Code generated in the scope of this project is available on GitHub: https://github.com/SchulzLab/TFAnalysis (DOI: 10.5281/zenodo.1409697).

BiFET: sequencing Bias-free transcription factor Footprint Enrichment Test

Transcription factor (TF) footprinting uncovers putative protein–DNA binding via combined analyses of chromatin accessibility patterns and their underlying TF sequence motifs. TF footprints are frequently used to identify TFs that regulate activities of cell/condition-specific genomic regions (target loci) in comparison to control regions (background loci) using standard enrichment tests. However, there is a strong association between the chromatin accessibility level and the GC content of a locus and the number and types of TF footprints that can be detected at this site. Traditional enrichment tests (e.g. hypergeometric) do not account for this bias and inflate false positive associations. Therefore, we developed a novel post-processing method, Bias-free Footprint Enrichment Test (BiFET), that corrects for the biases arising from the differences in chromatin accessibility levels and GC contents between target and background loci in footprint enrichment analyses. We applied BiFET on TF footprint calls obtained from EndoC-βH1 ATAC-seq samples using three different algorithms (CENTIPEDE, HINT-BC and PIQ) and showed BiFET’s ability to increase power and reduce false positive rate when compared to hypergeometric test. Furthermore, we used BiFET to study TF footprints from human PBMC and pancreatic islet ATAC-seq samples to show its utility to identify putative TFs associated with cell-type-specific loci.

Dynamic motif occupancy (DynaMO) analysis identifies transcription factors and their binding sites driving dynamic biological processes

Biological processes are usually associated with genome-wide remodeling of transcription driven by transcription factors (TFs). Identifying key TFs and their spatiotemporal binding patterns are indispensable to understanding how dynamic processes are programmed. However, most methods are designed to predict TF binding sites only. We present a computational method, dynamic motif occupancy analysis (DynaMO), to infer important TFs and their spatiotemporal binding activities in dynamic biological processes using chromatin profiling data from multiple biological conditions such as time-course histone modification ChIP-seq data. In the first step, DynaMO predicts TF binding sites with a random forests approach. Next and uniquely, DynaMO infers dynamic TF binding activities at predicted binding sites using their local chromatin profiles from multiple biological conditions. Another landmark of DynaMO is to identify key TFs in a dynamic process using a clustering and enrichment analysis of dynamic TF binding patterns. Application of DynaMO to the yeast ultradian cycle, mouse circadian clock and human neural differentiation exhibits its accuracy and versatility. We anticipate DynaMO will be generally useful for elucidating transcriptional programs in dynamic processes.

XL-DNase-seq: improved footprinting of dynamic transcription factors

Background

As the cost of high-throughput sequencing technologies decreases, genome-wide chromatin accessibility profiling methods such as the assay of transposase-accessible chromatin using sequencing (ATAC-seq) are employed widely, with data accumulating at an unprecedented rate. However, accurate inference of protein occupancy requires higher-resolution footprinting analysis where major hurdles exist, including the sequence bias of nucleases and the short-lived chromatin binding of many transcription factors (TFs) with consequent lack of footprints.

Results

Here we introduce an assay termed cross-link (XL)-DNase-seq, designed to capture chromatin interactions of dynamic TFs. Mild cross-linking improved the detection of DNase-based footprints of dynamic TFs but interfered with ATAC-based footprinting of the same TFs.

Conclusions

XL-DNase-seq may help extract novel gene regulatory circuits involving previously undetectable TFs. The DNase-seq and ATAC-seq data generated in our systematic comparison of various cross-linking conditions also represent an unprecedented-scale resource derived from activated mouse macrophage-like cells which share many features of inflammatory macrophages.

Electronic supplementary material

The online version of this article (10.1186/s13072-019-0277-6) contains supplementary material, which is available to authorized users.

Reproducible inference of transcription factor footprints in ATAC-seq and DNase-seq datasets using protocol-specific bias modeling

BACKGROUND

DNase-seq and ATAC-seq are broadly used methods to assay open chromatin regions genome-wide. The single nucleotide resolution of DNase-seq has been further exploited to infer transcription factor binding sites (TFBSs) in regulatory regions through footprinting. Recent studies have demonstrated the sequence bias of DNase I and its adverse effects on footprinting efficiency. However, footprinting and the impact of sequence bias have not been extensively studied for ATAC-seq.

RESULTS

Here, we undertake a systematic comparison of the two methods and show that a modification to the ATAC-seq protocol increases its yield and its agreement with DNase-seq data from the same cell line. We demonstrate that the two methods have distinct sequence biases and correct for these protocol-specific biases when performing footprinting. Despite the differences in footprint shapes, the locations of the inferred footprints in ATAC-seq and DNase-seq are largely concordant. However, the protocol-specific sequence biases in conjunction with the sequence content of TFBSs impact the discrimination of footprint from the background, which leads to one method outperforming the other for some TFs. Finally, we address the depth required for reproducible identification of open chromatin regions and TF footprints.

CONCLUSIONS

We demonstrate that the impact of bias correction on footprinting performance is greater for DNase-seq than for ATAC-seq and that DNase-seq footprinting leads to better performance. It is possible to infer concordant footprints by using replicates, highlighting the importance of reproducibility assessment. The results presented here provide an overview of the advantages and limitations of footprinting analyses using ATAC-seq and DNase-seq.

Anchor: trans-cell type prediction of transcription factor binding sites

The ENCyclopedia of DNA Elements (ENCODE) consortium has generated transcription factor (TF) binding ChIP-seq data covering hundreds of TF proteins and cell types; however, due to limits on time and resources, only a small fraction of all possible TF-cell type pairs have been profiled. One solution is to build machine learning models trained on currently available epigenomic data sets that can be applied to the remaining missing pairs. A major challenge is that TF binding sites are cell-type-specific, which can be attributed to cellular contexts such as chromatin accessibility. Meanwhile, indirect TF-DNA binding and interactions between TFs complicate this regulatory process. Technical issues such as sequencing biases and batch effects render the prediction task even more challenging. Many pioneering efforts have been made to predict TF binding profiles based on DNA sequence and DNase-seq footprints, but to what extent a model can be generalized to completely untested cell conditions remains unknown. In this study, we describe our first place solution to the 2017 ENCODE-DREAM in vivo TF binding site prediction challenge. By carefully addressing multisource biases and information imbalance across cell types, we created a pipeline that significantly outperforms the current state-of-the-art methods. The proposed method is sufficiently complex enough to model nonlinear interactions between TF binding motifs and chromatin accessibility information up to 1500 bp from the genomic region of interest.

Accurate prediction of cell type-specific transcription factor binding

Prediction of cell type-specific, in vivo transcription factor binding sites is one of the central challenges in regulatory genomics. Here, we present our approach that earned a shared first rank in the "ENCODE-DREAM in vivo Transcription Factor Binding Site Prediction Challenge" in 2017. In post-challenge analyses, we benchmark the influence of different feature sets and find that chromatin accessibility and binding motifs are sufficient to yield state-of-the-art performance. Finally, we provide 682 lists of predicted peaks for a total of 31 transcription factors in 22 primary cell types and tissues and a user-friendly version of our approach, Catchitt, for download.

An efficient method to transcription factor binding sites imputation via simultaneous completion of multiple matrices with positional consistency

Transcription factors (TFs) are DNA-binding proteins that have a central role in regulating gene expression. Identification of DNA-binding sites of TFs is a key task in understanding transcriptional regulation, cellular processes and disease. Chromatin immunoprecipitation followed by high-throughput sequencing (ChIP-seq) enables genome-wide identification of in vivo TF binding sites. However, it is still difficult to map every TF in every cell line owing to cost and biological material availability, which poses an enormous obstacle for integrated analysis of gene regulation. To address this problem, we propose a novel computational approach, TFBSImpute, for predicting additional TF binding profiles by leveraging information from available ChIP-seq TF binding data. TFBSImpute fuses the dataset to a 3-mode tensor and imputes missing TF binding signals via simultaneous completion of multiple TF binding matrices with positional consistency. We show that signals predicted by our method achieve overall similarity with experimental data and that TFBSImpute significantly outperforms baseline approaches, by assessing the performance of imputation methods against observed ChIP-seq TF binding profiles. Besides, motif analysis shows that TFBSImpute preforms better in capturing binding motifs enriched in observed data compared with baselines, indicating that the higher performance of TFBSImpute is not simply due to averaging related samples. We anticipate that our approach will constitute a useful complement to experimental mapping of TF binding, which is beneficial for further study of regulation mechanisms and disease.

Integrated analysis of motif activity and gene expression changes of transcription factors

The ability to predict transcription factors based on sequence information in regulatory elements is a key step in systems-level investigation of transcriptional regulation. Here, we have developed a novel tool, IMAGE, for precise prediction of causal transcription factors based on transcriptome profiling and genome-wide maps of enhancer activity. High precision is obtained by combining a near-complete database of position weight matrices (PWMs), generated by compiling public databases and systematic prediction of PWMs for uncharacterized transcription factors, with a state-of-the-art method for PWM scoring and a novel machine learning strategy, based on both enhancers and promoters, to predict the contribution of motifs to transcriptional activity. We applied IMAGE to published data obtained during 3T3-L1 adipocyte differentiation and showed that IMAGE predicts causal transcriptional regulators of this process with higher confidence than existing methods. Furthermore, we generated genome-wide maps of enhancer activity and transcripts during human mesenchymal stem cell commitment and adipocyte differentiation and used IMAGE to identify positive and negative transcriptional regulators of this process. Collectively, our results demonstrate that IMAGE is a powerful and precise method for prediction of regulators of gene expression.

Universal correction of enzymatic sequence bias reveals molecular signatures of protein/DNA interactions

Coupling molecular biology to high-throughput sequencing has revolutionized the study of biology. Molecular genomics techniques are continually refined to provide higher resolution mapping of nucleic acid interactions and structure. Sequence preferences of enzymes can interfere with the accurate interpretation of these data. We developed seqOutBias to characterize enzymatic sequence bias from experimental data and scale individual sequence reads to correct intrinsic enzymatic sequence biases. SeqOutBias efficiently corrects DNase-seq, TACh-seq, ATAC-seq, MNase-seq and PRO-seq data. We show that seqOutBias correction facilitates identification of true molecular signatures resulting from transcription factors and RNA polymerase interacting with DNA.

Deconvolving sequence features that discriminate between overlapping regulatory annotations

Genomic loci with regulatory potential can be annotated with various properties. For example, genomic sites bound by a given transcription factor (TF) can be divided according to whether they are proximal or distal to known promoters. Sites can be further labeled according to the cell types and conditions in which they are active. Given such a collection of labeled sites, it is natural to ask what sequence features are associated with each annotation label. However, discovering such label-specific sequence features is often confounded by overlaps between the labels; e.g. if regulatory sites specific to a given cell type are also more likely to be promoter-proximal, it is difficult to assess whether motifs identified in that set of sites are associated with the cell type or associated with promoters. In order to meet this challenge, we developed SeqUnwinder, a principled approach to deconvolving interpretable discriminative sequence features associated with overlapping annotation labels. We demonstrate the novel analysis abilities of SeqUnwinder using three examples. Firstly, SeqUnwinder is able to unravel sequence features associated with the dynamic binding behavior of TFs during motor neuron programming from features associated with chromatin state in the initial embryonic stem cells. Secondly, we characterize distinct sequence properties of multi-condition and cell-specific TF binding sites after controlling for uneven associations with promoter proximity. Finally, we demonstrate the scalability of SeqUnwinder to discover cell-specific sequence features from over one hundred thousand genomic loci that display DNase I hypersensitivity in one or more ENCODE cell lines.

Transcription factor proteins control gene expression by recognizing and interacting with short DNA sequence patterns in regulatory regions on the genome. Current genomics experiments allow us to find regulatory regions associated with a particular biochemical activity over the entire genome; for example, all regions where a particular transcription factor interacts with the genome in a given cell type. Given a collection of regulatory regions, we often aim to discover short DNA sequence patterns that are more common in the collection than in other regions. Performing such “DNA motif-finding” analysis can give us hints about the patterns that determine gene regulation in the analyzed cell type.

Here we describe a new method for DNA motif-finding called SeqUnwinder. Our approach analyzes collections of regulatory regions where each has been labeled according to various biological properties. For example, the labels could correspond to various cell types in which the regulatory region is active. SeqUnwinder then performs machine-learning analysis to unravel DNA sequence features that are characteristic of each label (e.g. features that distinguish regulatory regions in each cell type from other cell types). SeqUnwinder is the first method to enable analysis of regulatory region collections that contain several overlapping labels.

Assessing the model transferability for prediction of transcription factor binding sites based on chromatin accessibility

Background

Computational prediction of transcription factor (TF) binding sites in different cell types is challenging. Recent technology development allows us to determine the genome-wide chromatin accessibility in various cellular and developmental contexts. The chromatin accessibility profiles provide useful information in prediction of TF binding events in various physiological conditions. Furthermore, ChIP-Seq analysis was used to determine genome-wide binding sites for a range of different TFs in multiple cell types. Integration of these two types of genomic information can improve the prediction of TF binding events.

Results

We assessed to what extent a model built upon on other TFs and/or other cell types could be used to predict the binding sites of TFs of interest. A random forest model was built using a set of cell type-independent features such as specific sequences recognized by the TFs and evolutionary conservation, as well as cell type-specific features derived from chromatin accessibility data. Our analysis suggested that the models learned from other TFs and/or cell lines performed almost as well as the model learned from the target TF in the cell type of interest. Interestingly, models based on multiple TFs performed better than single-TF models. Finally, we proposed a universal model, BPAC, which was generated using ChIP-Seq data from multiple TFs in various cell types.

Conclusion

Integrating chromatin accessibility information with sequence information improves prediction of TF binding.The prediction of TF binding is transferable across TFs and/or cell lines suggesting there are a set of universal “rules”. A computational tool was developed to predict TF binding sites based on the universal “rules”.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1769-7) contains supplementary material, which is available to authorized users.

RegulatorTrail: a web service for the identification of key transcriptional regulators

Transcriptional regulators such as transcription factors and chromatin modifiers play a central role in most biological processes. Alterations in their activities have been observed in many diseases, e.g. cancer. Hence, it is of utmost importance to evaluate and assess the effects of transcriptional regulators on natural and pathogenic processes. Here, we present RegulatorTrail, a web service that provides rich functionality for the identification and prioritization of key transcriptional regulators that have a strong impact on, e.g. pathological processes. RegulatorTrail offers eight methods that use regulator binding information in combination with transcriptomic or epigenomic data to infer the most influential regulators. Our web service not only provides an intuitive web interface, but also a well-documented RESTful API that allows for a straightforward integration into third-party workflows. The presented case studies highlight the capabilities of our web service and demonstrate its potential for the identification of influential regulators: we successfully identified regulators that might explain the increased malignancy in metastatic melanoma compared to primary tumors, as well as important regulators in macrophages. RegulatorTrail is freely accessible at: https://regulatortrail.bioinf.uni-sb.de/.

DeFCoM: analysis and modeling of transcription factor binding sites using a motif-centric genomic footprinter

Motivation

Identifying the locations of transcription factor binding sites is critical for understanding how gene transcription is regulated across different cell types and conditions. Chromatin accessibility experiments such as DNaseI sequencing (DNase-seq) and Assay for Transposase Accessible Chromatin sequencing (ATAC-seq) produce genome-wide data that include distinct 'footprint' patterns at binding sites. Nearly all existing computational methods to detect footprints from these data assume that footprint signals are highly homogeneous across footprint sites. Additionally, a comprehensive and systematic comparison of footprinting methods for specifically identifying which motif sites for a specific factor are bound has not been performed.

Results

Using DNase-seq data from the ENCODE project, we show that a large degree of previously uncharacterized site-to-site variability exists in footprint signal across motif sites for a transcription factor. To model this heterogeneity in the data, we introduce a novel, supervised learning footprinter called Detecting Footprints Containing Motifs (DeFCoM). We compare DeFCoM to nine existing methods using evaluation sets from four human cell-lines and eighteen transcription factors and show that DeFCoM outperforms current methods in determining bound and unbound motif sites. We also analyze the impact of several biological and technical factors on the quality of footprint predictions to highlight important considerations when conducting footprint analyses and assessing the performance of footprint prediction methods. Finally, we show that DeFCoM can detect footprints using ATAC-seq data with similar accuracy as when using DNase-seq data.

Availability and Implementation

Python code available at https://bitbucket.org/bryancquach/defcom.

Contact

bquach@email.unc.edu or tsfurey@email.unc.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

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

Differential binding of transcription factors (TFs) at cis-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.

Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction

The binding and contribution of transcription factors (TF) to cell specific gene expression is often deduced from open-chromatin measurements to avoid costly TF ChIP-seq assays. Thus, it is important to develop computational methods for accurate TF binding prediction in open-chromatin regions (OCRs). Here, we report a novel segmentation-based method, TEPIC, to predict TF binding by combining sets of OCRs with position weight matrices. TEPIC can be applied to various open-chromatin data, e.g. DNaseI-seq and NOMe-seq. Additionally, Histone-Marks (HMs) can be used to identify candidate TF binding sites. TEPIC computes TF affinities and uses open-chromatin/HM signal intensity as quantitative measures of TF binding strength. Using machine learning, we find low affinity binding sites to improve our ability to explain gene expression variability compared to the standard presence/absence classification of binding sites. Further, we show that both footprints and peaks capture essential TF binding events and lead to a good prediction performance. In our application, gene-based scores computed by TEPIC with one open-chromatin assay nearly reach the quality of several TF ChIP-seq data sets. Finally, these scores correctly predict known transcriptional regulators as illustrated by the application to novel DNaseI-seq and NOMe-seq data for primary human hepatocytes and CD4+ T-cells, respectively.

Identification of DNA-binding proteins by combining auto-cross covariance transformation and ensemble learning

DNA-binding proteins play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. With the rapid development of next generation of sequencing technique, the number of protein sequences is unprecedentedly increasing. Thus it is necessary to develop computational methods to identify the DNA-binding proteins only based on the protein sequence information. In this study, a novel method called iDNA-KACC is presented, which combines the Support Vector Machine (SVM) and the auto-cross covariance transformation. The protein sequences are first converted into profile-based protein representation, and then converted into a series of fixed-length vectors by the auto-cross covariance transformation with Kmer composition. The sequence order effect can be effectively captured by this scheme. These vectors are then fed into Support Vector Machine (SVM) to discriminate the DNA-binding proteins from the non DNA-binding ones. iDNA-KACC achieves an overall accuracy of 75.16% and Matthew correlation coefficient of 0.5 by a rigorous jackknife test. Its performance is further improved by employing an ensemble learning approach, and the improved predictor is called iDNA-KACC-EL. Experimental results on an independent dataset shows that iDNA-KACC-EL outperforms all the other state-of-the-art predictors, indicating that it would be a useful computational tool for DNA binding protein identification. .

Romulus: robust multi-state identification of transcription factor binding sites from DNase-seq data

Motivation: Computational prediction of transcription factor (TF) binding sites in the genome remains a challenging task. Here, we present Romulus, a novel computational method for identifying individual TF binding sites from genome sequence information and cell-type–specific experimental data, such as DNase-seq. It combines the strengths of previous approaches, and improves robustness by reducing the number of free parameters in the model by an order of magnitude.

Results: We show that Romulus significantly outperforms existing methods across three sources of DNase-seq data, by assessing the performance of these tools against ChIP-seq profiles. The difference was particularly significant when applied to binding site prediction for low-information-content motifs. Our method is capable of inferring multiple binding modes for a single TF, which differ in their DNase I cut profile. Finally, using the model learned by Romulus and ChIP-seq data, we introduce Binding in Closed Chromatin (BCC) as a quantitative measure of TF pioneer factor activity. Uniquely, our measure quantifies a defining feature of pioneer factors, namely their ability to bind closed chromatin.

Availability and Implementation: Romulus is freely available as an R package at http://github.com/ajank/Romulus.

Contact:ajank@mimuw.edu.pl

Supplementary information:Supplementary data are available at Bioinformatics online.

Analysis of computational footprinting methods for DNase sequencing experiments

DNase-seq allows nucleotide-level identification of transcription factor binding sites on the basis of a computational search of footprint-like DNase I cleavage patterns on the DNA. Frequently in high-throughput methods, experimental artifacts such as DNase I cleavage bias affect the computational analysis of DNase-seq experiments. Here we performed a comprehensive and systematic study on the performance of computational footprinting methods. We evaluated ten footprinting methods in a panel of DNase-seq experiments for their ability to recover cell-specific transcription factor binding sites. We show that three methods--HINT, DNase2TF and PIQ--consistently outperformed the other evaluated methods and that correcting the DNase-seq signal for experimental artifacts significantly improved the accuracy of computational footprints. We also propose a score that can be used to detect footprints arising from transcription factors with potentially short residence times.

Predicting transcription factor site occupancy using DNA sequence intrinsic and cell-type specific chromatin features

Background

Understanding the mechanisms by which transcription factors (TF) are recruited to their physiological target sites is crucial for understanding gene regulation. DNA sequence intrinsic features such as predicted binding affinity are often not very effective in predicting in vivo site occupancy and in any case could not explain cell-type specific binding events. Recent reports show that chromatin accessibility, nucleosome occupancy and specific histone post-translational modifications greatly influence TF site occupancy in vivo. In this work, we use machine-learning methods to build predictive models and assess the relative importance of different sequence-intrinsic and chromatin features in the TF-to-target-site recruitment process.

Methods

Our study primarily relies on recent data published by the ENCODE consortium. Five dissimilar TFs assayed in multiple cell-types were selected as examples: CTCF, JunD, REST, GABP and USF2. We used two types of candidate target sites: (a) predicted sites obtained by scanning the whole genome with a position weight matrix, and (b) cell-type specific peak lists provided by ENCODE. Quantitative in vivo occupancy levels in different cell-types were based on ChIP-seq data for the corresponding TFs. In parallel, we computed a number of associated sequence-intrinsic and experimental features (histone modification, DNase I hypersensitivity, etc.) for each site. Machine learning algorithms were then used in a binary classification and regression framework to predict site occupancy and binding strength, for the purpose of assessing the relative importance of different contextual features.

Results

We observed striking differences in the feature importance rankings between the five factors tested. PWM-scores were amongst the most important features only for CTCF and REST but of little value for JunD and USF2. Chromatin accessibility and active histone marks are potent predictors for all factors except REST. Structural DNA parameters, repressive and gene body associated histone marks are generally of little or no predictive value.

Conclusions

We define a general and extensible computational framework for analyzing the importance of various DNA-intrinsic and chromatin-associated features in determining cell-type specific TF binding to target sites. The application of our methodology to ENCODE data has led to new insights on transcription regulatory processes and may serve as example for future studies encompassing even larger datasets.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0846-z) contains supplementary material, which is available to authorized users.