Comprehensive Study on Enhancing Low-Quality Position-Specific Scoring Matrix with Deep Learning for Accurate Protein Structure Property Prediction: Using Bagging Multiple Sequence Alignment Learning
Comprehensive Study on Enhancing Low-Quality Position-Specific Scoring Matrix with Deep Learning for Accurate Protein Structure Property Prediction: Using Bagging Multiple Sequence Alignment Learning
复制标题
DOI：
10.1089/cmb.2020.0416
复制
发表时间：
2021-02-22
影响因子：
1.7
通讯作者：
Huang，Junzhou
中科院分区：
文献类型：
--
作者：
Guo，Yuzhi;Wu，Jiaxiang;Huang，Junzhou
准确预测蛋白质的结构性质，例如二级结构和溶剂可及性，对于分析蛋白质的结构和功能至关重要。位置特异性评分矩阵（PSSM）特征在结构性质预测中得到了广泛的应用。然而，由于同源序列不足，一些蛋白质可能具有低质量的PSSM特征，导致预测精度有限。为了解决这一限制，我们提出了一种增强PSSM特征的方案。我们引入了“Bagging MSA”（多序列对齐）方法来计算用于训练模型的PSSM特征，采用卷积网络捕获局部上下文特征和长期依赖的双向长短期记忆，并将它们整合在无监督框架下。结构属性预测模型然后建立在这种增强的PSSM特征上，以获得更准确的预测。此外，我们开发了两个框架来评估增强的PSSM特征的有效性，并将所提出的方法带入了现实场景。对CB513、CASP11和CASP12数据集的实证评价表明，我们的无监督增强方案确实为结构性能预测生成了更有信息量的PSSM特征。
Accurate predictions of protein structure properties, for example, secondary structure and solvent accessibility, are essential in analyzing the structure and function of a protein. Position-specific scoring matrix (PSSM) features are widely used in the structure property prediction. However, some proteins may have low-quality PSSM features due to insufficient homologous sequences, leading to limited prediction accuracy. To address this limitation, we propose an enhancing scheme for PSSM features. We introduce the “Bagging MSA” (multiple sequence alignment) method to calculate PSSM features used to train our model, adopt a convolutional network to capture local context features and bidirectional long short-term memory for long-term dependencies, and integrate them under an unsupervised framework. Structure property prediction models are then built upon such enhanced PSSM features for more accurate predictions. Moreover, we develop two frameworks to evaluate the effectiveness of the enhanced PSSM features, which also bring proposed method into real-world scenarios. Empirical evaluation of CB513, CASP11, and CASP12 data sets indicates that our unsupervised enhancing scheme indeed generates more informative PSSM features for structure property prediction.