Locating transcription factor binding sites by fully convolutional neural network

Zhang, Qinhu; Wang, Siguo; Chen, Zhanheng; He, Ying; Liu, Qi; Huang, De-Shuang

doi:10.1093/bib/bbaa435

“…To measure the performance of our proposed framework FCNsignal, several existing state-of-the-art methods were used, including MEME [12], STREME [13], DanQ [29], DeepCNN [53], FCNA * [31], FCNA, BPNet [33],…”

Section: Competing Methods and Evaluation Metricsmentioning

confidence: 99%

“…To remedy such problems, DESSO [30] used a CNN model for extracting motif patterns from given ChIP-seq peaks and a statistical model based on the binomial distribution for optimizing the identification of motif instances. FCNA * [31] predicted TFBSs and motifs on ChIP-seq data by using a fully convolutional neural network (FCN) and global average pooling (GAV). D-AEDNet [32] adopted an encoder-decoder architecture to identify the location of TF-DNA binding sites in DNA sequences.…”

Section: Introductionmentioning

confidence: 99%

Base-resolution prediction of transcription factor binding signals by a deep learning framework

Zhang

¹

,

He

²

,

Wang

³

et al. 2021

Preprint

Self Cite

1

0

View full text Add to dashboard Cite

Transcription factors (TFs) play an important role in regulating gene expression, thus the identification of the sites bound by them has become a fundamental step for molecular and cellular biology. In this paper, we developed a deep learning framework leveraging existing fully convolutional neural networks (FCN) to predict TF-DNA binding signals at the base-resolution level, called FCNsignal. The proposed FCNsignal can simultaneously achieve the following tasks: (i) modeling the base-resolution signals of binding regions; (ii) discriminating binding or non-binding regions; (iii) locating TF-DNA binding regions; (iv) predicting binding motifs. The experimental results on 53 TF ChIP-seq datasets and 6 chromatin accessibility ATAC-seq datasets show that our proposed framework outperforms some existing state-of-the-art methods. In addition, we explored to use the trained FCNsignal to locate all potential TF-DNA binding regions on a whole chromosome and predict DNA sequences of arbitrary length, and the results show that our framework can find most of the known binding regions and accept sequences of arbitrary length. Furthermore, we demonstrated the potential ability of our framework in discovering causal disease-associated single-nucleotide polymorphisms (SNPs) through a series of experiments.Author summaryIdentification of transcription factor binding sites (TFBSs) is fundamental to study gene regulatory networks in biological systems, as TFs activate or suppress the transcription of genes by binding to specific TFBSs. With the development of high-throughput sequencing technologies and deep learning (DL), several DL-based approaches have been developed for systematically studying TFBSs, achieving impressive performance. Nevertheless, these methods either excessively focus on discriminating binding or non-binding sequences or individually accomplish multiple TFBSs-associated tasks. In this work, we provide an integrated framework, which utilizes the FCN architecture to predict TF-DNA binding signals at the base-resolution level, to simultaneously study multiple TFBSs-associated tasks. More importantly, we also demonstrate that our proposed framework has the ability to locate all potential TF-DNA binding regions from DNA sequences of arbitrary length. We hope that our framework can provide a new perspective on studying the mechanism of TF-DNA binding and its related tasks.

show abstract

“…All the above has paved the way to deep neural network adoption in bioinformatics [95], e.g. for transcription factor binding sites prediction [96,97,98,99] or DNA/RNA motif mining [100,101,102,103]. However, since lots of training data are not always available, particularly in the medical field, this is also the main weakness of this type of algorithm [104,105].…”

Section: Neural Network Basedmentioning

confidence: 99%

A survey on data integration for multi-omics sample clustering

Lovino

¹

,

Randazzo

²

,

Ciravegna

³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To remedy such problems, DESSO [ 30 ] used a CNN model for extracting motif patterns from given ChIP-seq peaks and a statistical model based on the binomial distribution for optimizing the identification of motif instances. FCNA* [ 31 ] predicted TFBSs and motifs on ChIP-seq data by using a fully convolutional neural network (FCN) and global average pooling (GAV). D-AEDNet [ 32 ] adopted an encoder-decoder architecture to identify the location of TF-DNA binding sites in DNA sequences.…”

Section: Introductionmentioning

confidence: 99%

Base-resolution prediction of transcription factor binding signals by a deep learning framework

Zhang

¹

,

He

²

,

Wang

³

et al. 2022

Self Cite

View full text Add to dashboard Cite

Transcription factors (TFs) play an important role in regulating gene expression, thus the identification of the sites bound by them has become a fundamental step for molecular and cellular biology. In this paper, we developed a deep learning framework leveraging existing fully convolutional neural networks (FCN) to predict TF-DNA binding signals at the base-resolution level (named as FCNsignal). The proposed FCNsignal can simultaneously achieve the following tasks: (i) modeling the base-resolution signals of binding regions; (ii) discriminating binding or non-binding regions; (iii) locating TF-DNA binding regions; (iv) predicting binding motifs. Besides, FCNsignal can also be used to predict opening regions across the whole genome. The experimental results on 53 TF ChIP-seq datasets and 6 chromatin accessibility ATAC-seq datasets show that our proposed framework outperforms some existing state-of-the-art methods. In addition, we explored to use the trained FCNsignal to locate all potential TF-DNA binding regions on a whole chromosome and predict DNA sequences of arbitrary length, and the results show that our framework can find most of the known binding regions and accept sequences of arbitrary length. Furthermore, we demonstrated the potential ability of our framework in discovering causal disease-associated single-nucleotide polymorphisms (SNPs) through a series of experiments.

show abstract

Locating transcription factor binding sites by fully convolutional neural network

Cited by 43 publications

References 21 publications

Base-resolution prediction of transcription factor binding signals by a deep learning framework

Base-resolution prediction of transcription factor binding signals by a deep learning framework

A survey on data integration for multi-omics sample clustering

Base-resolution prediction of transcription factor binding signals by a deep learning framework

Contact Info

Product

Resources

About