High Resolution Models of Transcription Factor-DNA Affinities Improve In Vitro and In Vivo Binding Predictions

By Phaedra Agius, Aaron Arvey, William Chang, William Stafford Noble, Christina S. Leslie. 2010

67 citations recorded by the source corpus.

Accurately modeling the DNA sequence preferences of transcription factors (TFs), and using these models to predict in vivo genomic binding sites for TFs, are key pieces in deciphering the regulatory code. These efforts have been frustrated by the limited availability and accuracy of TF binding site motifs, usually represented as position-specific scoring matrices (PSSMs), which may match large numbers of sites and produce an unreliable list of target genes. Recently, protein binding microarray (PBM) experiments have emerged as a new source of high resolution data on in vitro TF binding specificities. PBM data has been analyzed either by estimating PSSMs or via rank statistics on probe intensities, so that individual sequence patterns are assigned enrichment scores (E-scores). This representation is informative but unwieldy because every TF is assigned a list of thousands of scored sequence patterns. Meanwhile, high-resolution in vivo TF occupancy data from ChIP-seq experiments is also increasingly available. We have developed a flexible discriminative framework for learning TF binding preferences from high resolution in vitro and in vivo data. We first trained support vector regression (SVR) models on PBM data to learn the mapping from probe sequences to binding intensities. We used a novel -mer based string kernel called the di-mismatch kernel to represent probe sequence similarities. The SVR models are more compact than E-scores, more expressive than PSSMs, and can be readily used to scan genomics regions to predict in vivo occupancy. Using a large data set of yeast and mouse TFs, we found that our SVR models can better predict probe intensity than the E-score method or PBM-derived PSSMs. Moreover, by using SVRs to score yeast, mouse, and human genomic regions, we were better able to predict genomic occupancy as measured by ChIP-chip and ChIP-seq experiments. Finally, we found that by training kernel-based models directly on ChIP-seq data, we greatly improved in vivo occupancy prediction, and by comparing a TF's in vitro and in vivo models, we could identify cofactors and disambiguate direct and indirect binding.

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

DNA-binding specificities of human transcription factors. (2013, unknown): “Several alternative models that do not make this independence assumption and, instead, use a larger set of parameters to describe TF-DNA binding have been developed (see, for example, Agius et al., 2010; Roulet et al., 2000; Sharon et al., 2008).”
Enhanced Regulatory Sequence Prediction Using Gapped k-mer Features (2014, methodology): “Mismatch kernel [8], Wildcard kernel [9], and Di-mismatch kernel [10,11], using the mouse forebrain EP300 data set.”
Sequence and chromatin determinants of cell-type–specific transcription factor binding (2012, methodology): “…into a feature space indexed by a set of informative k-mers, where each feature is a weighted count of the number of times the corresponding k-mer occurs in the input sequence with up to m mismatches in the alphabet of dinucleotides (for parameter choices, see Methods) (Agius et al. 2010).”
SeqGL Identifies Context-Dependent Binding Signals in Genome-Wide Regulatory Element Maps (2015, methodology): “SeqGL identifies TF sequence signals underlying ChIP-seq or DNase-seq/ATAC-seq peaks by training a discriminative model based on k-mer features on peaks (positive examples) versus their flanks (negative examples), building on our previous efforts in learning discriminative models of TF binding prefe”