SeqEnhDL: sequence-based classification of cell type-specific enhancers using deep learning models.
SeqEnhDL: sequence-based classification of cell type-specific enhancers using deep learning models.
复制标题
DOI：
10.1186/s13104-021-05518-7
复制
发表时间：
2021-03-19
影响因子：
1.8
通讯作者：
Joseph PV
中科院分区：
文献类型：
--
作者：
Wang Y;Jaime-Lara RB;Roy A;Sun Y;Liu X;Joseph PV
解决在全基因组范围内计算识别细胞类型特异性调控元件的挑战。我们提出了 SeqEnhDL，这是一种深度学习框架，用于根据序列特征对细胞类型特异性增强子进行分类。从 ENCODE 项目中检索了九种细胞类型中“强增强子”染色质状态的 DNA 序列，以构建和测试增强子分类器。对于任何 DNA 序列，相对于每个核苷酸位置上随机选择的非编码序列，位置 k 聚体 (k = 5、7、9 和 11) 倍数变化被用作深度学习模型的特征。实现了三种深度学习模型，包括多层感知器（MLP）、卷积神经网络（CNN）和循环神经网络（RNN）。 SeqEnhDL 中的所有模型在区分细胞类型特异性增强子和随机选择的非编码序列方面均优于最先进的增强子分类器（包括 gkm-SVM 和 DanQ）。此外，SeqEnhDL可以直接区分来自不同细胞类型的增强子，这是其他增强子分类器尚未实现的。我们的分析表明，增强子及其组织特异性都可以根据其序列特征进行准确识别。 SeqEnhDL 可在 https://github.com/wyp1125/SeqEnhDL 上公开获取。在线版本包含可在 10.1186/s13104-021-05518-7 获取的补充材料。
To address the challenge of computational identification of cell type-specific regulatory elements on a genome-wide scale. We propose SeqEnhDL, a deep learning framework for classifying cell type-specific enhancers based on sequence features. DNA sequences of “strong enhancer” chromatin states in nine cell types from the ENCODE project were retrieved to build and test enhancer classifiers. For any DNA sequence, positional k-mer (k = 5, 7, 9 and 11) fold changes relative to randomly selected non-coding sequences across each nucleotide position were used as features for deep learning models. Three deep learning models were implemented, including multi-layer perceptron (MLP), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). All models in SeqEnhDL outperform state-of-the-art enhancer classifiers (including gkm-SVM and DanQ) in distinguishing cell type-specific enhancers from randomly selected non-coding sequences. Moreover, SeqEnhDL can directly discriminate enhancers from different cell types, which has not been achieved by other enhancer classifiers. Our analysis suggests that both enhancers and their tissue-specificity can be accurately identified based on their sequence features. SeqEnhDL is publicly available at https://github.com/wyp1125/SeqEnhDL. The online version contains supplementary material available at 10.1186/s13104-021-05518-7.
登录
查看更多内容
影响因子：
64.8
作者：
Ernst, Jason;Kheradpour, Pouya;Mikkelsen, Tarjei S.;Shoresh, Noam;Ward, Lucas D.;Epstein, Charles B.;Zhang, Xiaolan;Wang, Li;Issner, Robbyn;Coyne, Michael;Ku, Manching;Durham, Timothy;Kellis, Manolis;Bernstein, Bradley E.
通讯作者：
Bernstein, Bradley E.
影响因子：
7
作者：
Taher, Leila;McGaughey, David M.;Ovcharenko, Ivan
通讯作者：
Ovcharenko, Ivan
影响因子：
64.8
作者：
Emison, ES;McCallion, AS;Chakravarti, A
通讯作者：
Chakravarti, A
使用随机森林发现在顺式调节元素中发现细胞类型的特异性DNA基序语法。
影响因子：
4.4
作者：
Wang X;Lin P;Ho JWK
通讯作者：
Ho JWK
影响因子：
7
作者：
Birnbaum RY;Clowney EJ;Agamy O;Kim MJ;Zhao J;Yamanaka T;Pappalardo Z;Clarke SL;Wenger AM;Nguyen L;Gurrieri F;Everman DB;Schwartz CE;Birk OS;Bejerano G;Lomvardas S;Ahituv N
通讯作者：
Ahituv N