Ruengsrichaiya Bhukrit, Nukoolkit Chakarida, Kalapanulak Saowalak, Saithong Treenut
Bioinformatics and Systems Biology Program, School of Bioresources and Technology and School of Information Technology, King Mongkut's University of Technology Thonburi (Bang KhunThian), Bangkok, Thailand.
School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok, Thailand.
Front Plant Sci. 2022 Aug 23;13:970018. doi: 10.3389/fpls.2022.970018. eCollection 2022.
As a sessile organism, plants hold elaborate transcriptional regulatory systems that allow them to adapt to variable surrounding environments. Current understanding of plant regulatory mechanisms is greatly constrained by limited knowledge of transcription factor (TF)-DNA interactions. To mitigate this problem, a Plant-DTI predictor (BD-FBS nteraction) was developed here as the first machine-learning model that covered the largest experimental datasets of 30 plant TF families, including 7 plant-specific DNA binding domain (DBD) types, and their transcription factor binding sites (TFBSs). Plant-DTI introduced a novel TFBS feature construction, called TFBS base-preference, which enhanced the specificity of TFBS to DBD types. The proposed model showed better predictive performance with the TFBS base-preference than the simple binary representation. Plant-DTI was validated with 22 independent ChIP-seq datasets. It accurately predicted the measured DBD-TFBS pairs along with their TFBS motifs, and effectively predicted interactions of other TFs containing similar DBD types. Comparing to the existing state-of-art methods, Plant-DTI prediction showed a figure of merit in sensitivity and specificity with respect to the position weight matrix (PWM) and TSPTFBS methods. Finally, the proposed Plant-DTI model helped to fill the knowledge gap in the regulatory mechanisms of the cassava sucrose synthase 1 gene (MeSUS1). Plant-DTI predicted MeERF72 as a regulator of MeSUS1 in consistence with the yeast one-hybrid (Y1H) experiment. Taken together, Plant-DTI would help facilitate the prediction of TF-TFBS and TF-target gene (TG) interactions, thereby accelerating the study of transcriptional regulatory systems in plant species.
作为固着生物，植物拥有复杂的转录调控系统，使其能够适应多变的周围环境。目前对植物调控机制的理解受到转录因子（TF）与DNA相互作用相关知识有限的极大限制。为缓解这一问题，本文开发了一种植物DTI预测器（BD - FBS相互作用），这是首个涵盖30个植物TF家族最大实验数据集的机器学习模型，包括7种植物特有的DNA结合域（DBD）类型及其转录因子结合位点（TFBS）。植物DTI引入了一种名为TFBS碱基偏好的新型TFBS特征构建方法，增强了TFBS对DBD类型的特异性。与简单的二进制表示相比，所提出的模型在具有TFBS碱基偏好时表现出更好的预测性能。植物DTI用22个独立的ChIP - seq数据集进行了验证。它准确地预测了测量的DBD - TFBS对及其TFBS基序，并有效地预测了包含相似DBD类型的其他TF的相互作用。与现有的先进方法相比，植物DTI预测在关于位置权重矩阵（PWM）和TSPTFBS方法的灵敏度和特异性方面表现出优异的品质因数。最后，所提出的植物DTI模型有助于填补木薯蔗糖合酶1基因（MeSUS1）调控机制方面的知识空白。植物DTI预测MeERF72是MeSUS1的调节因子，这与酵母单杂交（Y1H）实验结果一致。综上所述，植物DTI将有助于促进TF - TFBS和TF - 靶基因（TG）相互作用的预测，从而加速植物物种转录调控系统的研究。
