Learning from mistakes: Accurate prediction of cell type-specific transcription factor binding

Computational prediction of cell type-specific, in-vivo transcription factor binding sites is still one of the central challenges in regulatory genomics, and a variety of approaches has been proposed for this purpose. 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. This approach employs an extensive set of features derived from chromatin accessibility, binding motifs, gene expression, sequence and annotation to train classifiers using a supervised, discriminative learning principle. Two further key aspects of this approach is learning classifier parameters in an iterative training procedure that successively adds additional negative examples to the training set, and creating an ensemble prediction by averaging over classifiers obtained for different training cell types. In post-challenge analyses, we benchmark the influence of different feature sets and find that chromatin accessiblity and binding motifs are sufficient to yield state-of-the-art performance for in-vivo binding site predictions. We also show that the iterative training procedure and the ensemble prediction are pivotal for the final prediction performance. To make predictions of this approach readily accessible, we predict 682 peak lists for a total of 31 transcription factors in 22 primary cell types and tissues, which are available for download at http://www.synapse.Org/#!Synapse:syn11526239, and we demonstrate that these predictions may help to yield biological conclusions.

• Publication year

  2017

• Venue

  bioRxiv

• Publication date

  2017-12-06

• Fields of study

  Biology, Computer Science

• Identifiers
  DOI 10.1101/230011
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Imputation for transcription factor binding predictions based on deep learning

  2017influential reference
• Assessing the model transferability for prediction of transcription factor binding sites based on chromatin accessibility

  2017influential reference
• FactorNet: a deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data

  2017influential reference
• Dynamic decomposition of spatiotemporal neural signals

  2016cited by this paper
• Mocap: large-scale inference of transcription factor binding sites from chromatin accessibility

  2016influential reference
• Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction

  2016cited by this paper
• Predicting transcription factor site occupancy using DNA sequence intrinsic and cell-type specific chromatin features

  2016influential reference
• Romulus: robust multi-state identification of transcription factor binding sites from DNase-seq data

  2016cited by this paper
• ZNF143 is involved in CTCF-mediated chromatin interactions by cooperation with cohesin and other partners

  2016cited by this paper
• Predicting transcription factor site occupancy using DNA sequence intrinsic and cell-type specific chromatin features

  2016influential reference
• JASPAR 2016: a major expansion and update of the open-access database of transcription factor binding profiles

  2015cited by this paper
• The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets

  2015cited by this paper
• Motif clustering with implications for transcription factor interactions

  2015influential reference
• Biodiversity on the Rocks: Macrofauna Inhabiting Authigenic Carbonate at Costa Rica Methane Seeps

  2015cited by this paper
• PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R

  2015influential reference
• msCentipede: Modeling Heterogeneity across Genomic Sites and Replicates Improves Accuracy in the Inference of Transcription Factor Binding

  2015influential reference
• ZNF143 provides sequence specificity to secure chromatin interactions at gene promoters

  2015cited by this paper
• BinDNase: a discriminatory approach for transcription factor binding prediction using DNase I hypersensitivity data

  2015influential reference
• HOCOMOCO: expansion and enhancement of the collection of transcription factor binding sites models

  2015cited by this paper
• Varying levels of complexity in transcription factor binding motifs

  2015influential reference
• Sequence specificity incompletely defines the genome-wide occupancy of Myc

  2014cited by this paper
• Predicting the Human Epigenome from DNA Motifs

  2014cited by this paper
• Detection of active transcription factor binding sites with the combination of DNase hypersensitivity and histone modifications

  2014influential reference
• Area under Precision-Recall Curves for Weighted and Unweighted Data

  2014cited by this paper
• Determination and inference of eukaryotic transcription factor sequence specificity.

  2014cited by this paper
• Discovery of non-directional and directional pioneer transcription factors by modeling DNase profile magnitude and shape

  2014cited by this paper
• Systematic discovery and characterization of regulatory motifs in ENCODE TF binding experiments

  2013cited by this paper
• Transposition of native chromatin for fast and sensitive epigenomic profiling of open chromatin, DNA-binding proteins and nucleosome position

  2013cited by this paper
• Dynamic trans-acting factor colocalization in human cells.

  2013cited by this paper
• Wellington: a novel method for the accurate identification of digital genomic footprints from DNase-seq data

  2013cited by this paper
• A general approach for discriminative de novo motif discovery from high-throughput data

  2013cited by this paper
• Software for Computing and Annotating Genomic Ranges

  2013cited by this paper
• Sequence features and chromatin structure around the genomic regions bound by 119 human transcription factors

  2012cited by this paper
• GENCODE: The reference human genome annotation for The ENCODE Project

  2012cited by this paper
• Predicting cell-type–specific gene expression from regions of open chromatin

  2012cited by this paper
• Jstacs: A Java Framework for Statistical Analysis and Classification of Biological Sequences

  2012cited by this paper
• Sequence and chromatin determinants of cell-type–specific transcription factor binding

  2012influential reference
• Using DNase Digestion Data to Accurately Identify Transcription Factor Binding Sites

  2012influential reference
• RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome

  2011cited by this paper
• Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities.

  2010cited by this paper
• Apples and oranges: avoiding different priors in Bayesian DNA sequence analysis

  2010cited by this paper
• Supplementary material for “A dynamic Bayesian network for identifying protein binding footprints from single molecule based sequencing data”

  2010cited by this paper
• Discriminative Bayesian principles for predicting sequence signals of gene regulation

  2010cited by this paper
• Global mapping of protein-DNA interactions in vivo by digital genomic footprinting

  2009cited by this paper
• Differential binding and co-binding pattern of FOXA1 and FOXA3 and their relation to H3K4me3 in HepG2 cells revealed by ChIP-seq

  2009cited by this paper
• Design and analysis of ChIP-seq experiments for DNA-binding proteins

  2008cited by this paper
• E2F in vivo binding specificity: comparison of consensus versus nonconsensus binding sites.

  2008cited by this paper
• The role of transcription factors Sp1 and YY1 in proximal promoter region in initiation of transcription of the mu opioid receptor gene in human lymphocytes

  2008cited by this paper
• UniPROBE: an online database of protein binding microarray data on protein–DNA interactions

  2008cited by this paper
• Dynamic Bayesian Network

  2008cited by this paper
• Uniprobe: an Online Database of Protein Binding Microarray Data on Protein–dna Interactions

  2008cited by this paper
• Genome-Wide Mapping of in Vivo Protein-DNA Interactions

  2007cited by this paper
• ChIP-chip comes of age for genome-wide functional analysis.

  2006cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Genome-wide analysis of cAMP-response element binding protein occupancy, phosphorylation, and target gene activation in human tissues.

  2005cited by this paper
• On Discriminative Bayesian Network Classifiers and Logistic Regression

  2005cited by this paper
• TRANSFAC® and its module TRANSCompel®: transcriptional gene regulation in eukaryotes

  2005cited by this paper
• Computational prediction of transcription-factor binding site locations

  2003cited by this paper
• Specificity, free energy and information content in protein-DNA interactions.

  1998cited by this paper
• Experiments with a New Boosting Algorithm

  1996cited by this paper
• Selection of DNA binding sites by regulatory proteins. Statistical-mechanical theory and application to operators and promoters.

  1987cited by this paper
• Computer methods to locate signals in nucleic acid sequences

  1984cited by this paper
• footpHnnting: a simple method for the detection of protein-DNA binding specificity

  year unknowncited by this paper

• Revealing the transcription factor regulatory context of human specific cortical development using single-cell multi-omics

  2021cites this paper
• An interpretable bimodal neural network characterizes the sequence and preexisting chromatin predictors of induced TF binding

  2019cites this paper
• Informing disease modelling with brain-relevant functional genomic annotations

  2019cites this paper
• Virtual ChIP-seq: predicting transcription factor binding by learning from the transcriptome

  2018cites this paper
• Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities

  2018cites this paper
• Anchor: trans-cell type prediction of transcription factor binding sites

  2018cites this paper
• Opportunities and obstacles for deep learning in biology and medicine

  2017cites this paper
• Analysis, Visualization, and Machine Learning of Epigenomic Data

  2017cites this paper