TAMC: A deep-learning approach to predict motif-centric transcriptional factor binding activity based on ATAC-seq profile.
TAMC: A deep-learning approach to predict motif-centric transcriptional factor binding activity based on ATAC-seq profile.
复制标题
DOI：
10.1371/journal.pcbi.1009921
复制
发表时间：
2022-09
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
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. Applications of deep learning models are rapidly gaining popularity in recent biological studies because of their efficiency in analyzing non-linear patterns from feature-rich data. In this study, we developed a deep learning method to predict transcription factor binding sites based on chromatin accessibility profiles. Compared to previous methods using scoring functions and classical machine learning algorithms, our method forgoes the need for bias correction during signal processing and significantly increases the efficiency in extracting features at transcription factor binding sites. In addition, we showed that our method outperforms previous methods particularly for chromatin accessibility data with shallow sequencing depth. In this study, we applied our method to prediction of changes in binding sites of a transcription factor, CTCF, during early embryonic development based on bulk chromatin accessibility profiles. We then discussed about the potential application of our method to transcription factor binding site prediction using single-cell chromatin accessibility profiles as well as possible strategies to further improve the performance of our method in the future.
登录
查看更多内容
DOI：
10.1093/bioinformatics/btr064
发表时间：
2011-04-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Grant CE;Bailey TL;Noble WS
通讯作者：
Noble WS
影响因子：
48
作者：
Langmead, Ben;Salzberg, Steven L.
通讯作者：
Salzberg, Steven L.
影响因子：
3.7
作者：
Raj A;Shim H;Gilad Y;Pritchard JK;Stephens M
通讯作者：
Stephens M
影响因子：
7
作者：
Ouyang, Ningxin;Boyle, Alan P.
通讯作者：
Boyle, Alan P.
影响因子：
7
作者：
Pique-Regi, Roger;Degner, Jacob F.;Pritchard, Jonathan K.
通讯作者：
Pritchard, Jonathan K.