Dataset Information

Enhancing the interpretability of transcription factor binding site prediction using attention mechanism.

ABSTRACT: Transcription factors (TFs) regulate the gene expression of their target genes by binding to the regulatory sequences of target genes (e.g., promoters and enhancers). To fully understand gene regulatory mechanisms, it is crucial to decipher the relationships between TFs and DNA sequences. Moreover, studies such as GWAS and eQTL have verified that most disease-related variants exist in non-coding regions, and highlighted the necessity to identify such variants that cause diseases by interrupting TF binding mechanisms. To do this, it is necessary to build a prediction model that precisely predicts the binding relationships between TFs and DNA sequences. Recently, deep learning based models have been proposed and have shown competitive results on a transcription factor binding site prediction task. However, it is difficult to interpret the prediction results obtained from the previous models. In addition, the previous models assumed all the sequence regions in the input DNA sequence have the same importance for predicting TF-binding, although sequence regions containing TF-binding-associated signals such as TF-binding motifs should be captured more than other regions. To address these challenges, we propose TBiNet, an attention based interpretable deep neural network for predicting transcription factor binding sites. Using the attention mechanism, our method is able to assign more importance on the actual TF binding sites in the input DNA sequence. TBiNet outperforms the current state-of-the-art methods (DeepSea and DanQ) quantitatively in the TF-DNA binding prediction task. Moreover, TBiNet is more effective than the previous models in discovering known TF-binding motifs.

SUBMITTER: Park S

PROVIDER: S-EPMC7414127 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Enhancing the interpretability of transcription factor binding site prediction using attention mechanism.

Park Sungjoon S Koh Yookyung Y Jeon Hwisang H Kim Hyunjae H Yeo Yoonsun Y Kang Jaewoo J

Scientific reports 20200807 1

Transcription factors (TFs) regulate the gene expression of their target genes by binding to the regulatory sequences of target genes (e.g., promoters and enhancers). To fully understand gene regulatory mechanisms, it is crucial to decipher the relationships between TFs and DNA sequences. Moreover, studies such as GWAS and eQTL have verified that most disease-related variants exist in non-coding regions, and highlighted the necessity to identify such variants that cause diseases by interrupting ...[more]

PMID: 32770026

Similar Datasets

Project description:Finding where transcription factors (TFs) bind to the DNA is of key importance to decipher gene regulation at a transcriptional level. Classically, computational prediction of TF binding sites (TFBSs) is based on basic position weight matrices (PWMs) which quantitatively score binding motifs based on the observed nucleotide patterns in a set of TFBSs for the corresponding TF. Such models make the strong assumption that each nucleotide participates independently in the corresponding DNA-protein interaction and do not account for flexible length motifs. We introduce transcription factor flexible models (TFFMs) to represent TF binding properties. Based on hidden Markov models, TFFMs are flexible, and can model both position interdependence within TFBSs and variable length motifs within a single dedicated framework. The availability of thousands of experimentally validated DNA-TF interaction sequences from ChIP-seq allows for the generation of models that perform as well as PWMs for stereotypical TFs and can improve performance for TFs with flexible binding characteristics. We present a new graphical representation of the motifs that convey properties of position interdependence. TFFMs have been assessed on ChIP-seq data sets coming from the ENCODE project, revealing that they can perform better than both PWMs and the dinucleotide weight matrix extension in discriminating ChIP-seq from background sequences. Under the assumption that ChIP-seq signal values are correlated with the affinity of the TF-DNA binding, we find that TFFM scores correlate with ChIP-seq peak signals. Moreover, using available TF-DNA affinity measurements for the Max TF, we demonstrate that TFFMs constructed from ChIP-seq data correlate with published experimentally measured DNA-binding affinities. Finally, TFFMs allow for the straightforward computation of an integrated TF occupancy score across a sequence. These results demonstrate the capacity of TFFMs to accurately model DNA-protein interactions, while providing a single unified framework suitable for the next generation of TFBS prediction.

Project description:BACKGROUND:The elucidation of mammalian transcriptional regulatory networks holds great promise for both basic and translational research and remains one the greatest challenges to systems biology. Recent reverse engineering methods deduce regulatory interactions from large-scale mRNA expression profiles and cross-species conserved regulatory regions in DNA. Technical challenges faced by these methods include distinguishing between direct and indirect interactions, associating transcription regulators with predicted transcription factor binding sites (TFBSs), identifying non-linearly conserved binding sites across species, and providing realistic accuracy estimates. METHODOLOGY/PRINCIPAL FINDINGS:We address these challenges by closely integrating proven methods for regulatory network reverse engineering from mRNA expression data, linearly and non-linearly conserved regulatory region discovery, and TFBS evaluation and discovery. Using an extensive test set of high-likelihood interactions, which we collected in order to provide realistic prediction-accuracy estimates, we show that a careful integration of these methods leads to significant improvements in prediction accuracy. To verify our methods, we biochemically validated TFBS predictions made for both transcription factors (TFs) and co-factors; we validated binding site predictions made using a known E2F1 DNA-binding motif on E2F1 predicted promoter targets, known E2F1 and JUND motifs on JUND predicted promoter targets, and a de novo discovered motif for BCL6 on BCL6 predicted promoter targets. Finally, to demonstrate accuracy of prediction using an external dataset, we showed that sites matching predicted motifs for ZNF263 are significantly enriched in recent ZNF263 ChIP-seq data. CONCLUSIONS/SIGNIFICANCE:Using an integrative framework, we were able to address technical challenges faced by state of the art network reverse engineering methods, leading to significant improvement in direct-interaction detection and TFBS-discovery accuracy. We estimated the accuracy of our framework on a human B-cell specific test set, which may help guide future methodological development.

Dataset Information

Enhancing the interpretability of transcription factor binding site prediction using attention mechanism.

Publications

Enhancing the interpretability of transcription factor binding site prediction using attention mechanism.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets