An Enhanced Protein Fold Recognition for Low Similarity Datasets Using Convolutional and Skip-Gram Features With Deep Neural Network

PRFold-TNN: Protein Fold Recognition With an Ensemble Feature Selection Method Using PageRank Algorithm Based on Transformer

Understanding the tertiary structures of proteins is of great benefit to function in many aspects of human life. Protein fold recognition is a vital and salient means to know protein structure. Until now, researchers have successively proposed a variety of methods to realize protein fold recognition, but the novel and effective computational method is still needed to handle this problem with the continuous updating of protein structure databases. In this study, we develop a new protein structure dataset named AT and propose the PRFold-TNN model for protein fold recognition. First, different types of feature extraction methods including AAC, HMM, HMM-Bigram and ACC are selected to extract corresponding features for protein sequences. Then an ensemble feature selection method based on PageRank algorithm integrating various tree-based algorithms is used to screen the fusion features. Ultimately, the classifier based on the Transformer model achieves the final prediction. Experiments show that the prediction accuracy is 86.27% on the AT dataset and 88.91% on the independent test set, indicating that the model can demonstrate superior performance and generalization ability in the problem of protein fold recognition. Furthermore, we also carry out research on the DD, EDD and TG benchmark datasets, and make them achieve prediction accuracy of 88.41%, 97.91% and 95.16%, which are at least 3.0%, 0.8% and 2.5% higher than those of the state-of-the-art methods. It can be concluded that the PRFold-TNN model is more prominent.

ASFold-DNN: Protein Fold Recognition Based on Evolutionary Features With Variable Parameters Using Full Connected Neural Network

Protein fold recognition contribute to comprehend the function of proteins, which is of great help to the gene therapy of diseases and the development of new drugs. Researchers have been working in this direction and have made considerable achievements, but challenges still exist on low sequence similarity datasets. In this study, we propose the ASFold-DNN framework for protein fold recognition research. Above all, four groups of evolutionary features are extracted from the primary structures of proteins, and a preliminary selection of variable parameter is made for two groups of features including ACC _HMM and SXG _HMM, respectively. Then several feature selection algorithms are selected for comparison and the best feature selection scheme is obtained by changing their internal threshold values. Finally, multiple hyper-parameters of Full Connected Neural Network are fully optimized to construct the best model. DD, EDD and TG datasets with low sequence similarities are chosen to evaluate the performance of the models constructed by the framework, and the final prediction accuracy are 85.28, 95.00 and 88.84 percent, respectively. Furthermore, the ASTRAL186 and LE datasets are introduced to further verify the generalization ability of our proposed framework. Comprehensive experimental results prove that the ASFold-DNN framework is more prominent than the state-of-the-art studies on protein fold recognition. The source code and data of ASFold-DNN can be downloaded from https://github.com/Bioinformatics-Laboratory/project/tree/master/ASFold.

An Effective Multi-Label Protein Sub-Chloroplast Localization Prediction by Skipped-Grams of Evolutionary Profiles Using Deep Neural Network

Chloroplast is one of the most classic organelles in algae and plant cells. Identifying the locations of chloroplast proteins in the chloroplast organelle is an important as well as a challenging task in deciphering their functions. Biological-based experiments to identify the Protein Sub-Chloroplast Localization (PSCL) is time-consuming and cost-intensive. Over the last decade, a few computational methods have been developed to predict PSCL in which earlier works assumed to predict only single-location; whereas, recent works are able to predict multiple-locations of chloroplast organelle. However, the performances of all the state-of-the-art predictors are poor. This article proposes a novel skip-gram technique to extract highly discriminating patterns from evolutionary profiles and a multi-label deep neural network to predict the PSCL. The proposed model is assessed on two publicly available datasets, i.e., Benchmark and Novel. Experimental results demonstrate that the proposed work outperforms significantly when compared to the state-of-the-art multi-label PSCL predictors. A multi-label prediction accuracy (i.e., Overall Actual Accuracy) of the proposed model is enhanced by an absolute minimum margin of 6.7 percent on Benchmark dataset and 7.9 percent on Novel dataset when compared to the best PSCL predictor from the literature. Further, result of statistical t-test concludes that the performance of the proposed work is significantly improved and thus, the proposed work is an effective computational model to solve multi-label PSCL prediction. The proposed prediction model is hosted on web-server and available at https://nitkit-vgst727-nppsa.nitk.ac.in/deeplocpred/.

Recognition of Protein Network for Bioinformatics Knowledge Analysis Using Support Vector Machine

Protein is the material foundation of living things, and it directly takes part in and runs the process of living things itself. Predicting protein complexes helps us understand the structure and function of complexes, and it is an important foundation for studying how cells work. Genome-wide protein interaction (PPI) data is growing as high-throughput experiments become more common. The aim of this research is that it provides a dual-tree complex wavelet transform which is used to find out about the structure of proteins. It also identifies the secondary structure of protein network. Many computer-based methods for predicting protein complexes have also been developed in the field. Identifying the secondary structure of a protein is very important when you are studying protein characteristics and properties. This is how the protein sequence is added to the distance matrix. The scope of this research is that it can confidently predict certain protein complexes rapidly, which compensates for shortcomings in biological research. The three-dimensional coordinates of C atom are used to do this. According to the texture information in the distance matrix, the matrix is broken down into four levels by the double-tree complex wavelet transform because it has four levels. The subband energy and standard deviation in different directions are taken, and then, the two-dimensional feature vector is used to show the secondary structure features of the protein in a way that is easy to understand. Then, the KNN and SVM classifiers are used to classify the features that were found. Experiments show that a new feature called a dual-tree complex wavelet can improve the texture granularity and directionality of the traditional feature extraction method, which is called secondary structure.

An analysis of protein language model embeddings for fold prediction

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

FoldHSphere: deep hyperspherical embeddings for protein fold recognition

Background

Current state-of-the-art deep learning approaches for protein fold recognition learn protein embeddings that improve prediction performance at the fold level. However, there still exists aperformance gap at the fold level and the (relatively easier) family level, suggesting that it might be possible to learn an embedding space that better represents the protein folds.

Results

In this paper, we propose the FoldHSphere method to learn a better fold embedding space through a two-stage training procedure. We first obtain prototype vectors for each fold class that are maximally separated in hyperspherical space. We then train a neural network by minimizing the angular large margin cosine loss to learn protein embeddings clustered around the corresponding hyperspherical fold prototypes. Our network architectures, ResCNN-GRU and ResCNN-BGRU, process the input protein sequences by applying several residual-convolutional blocks followed by a gated recurrent unit-based recurrent layer. Evaluation results on the LINDAHL dataset indicate that the use of our hyperspherical embeddings effectively bridges the performance gap at the family and fold levels. Furthermore, our FoldHSpherePro ensemble method yields an accuracy of 81.3% at the fold level, outperforming all the state-of-the-art methods.

Conclusions

Our methodology is efficient in learning discriminative and fold-representative embeddings for the protein domains. The proposed hyperspherical embeddings are effective at identifying the protein fold class by pairwise comparison, even when amino acid sequence similarities are low.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04419-7.

Recent Advances in the Prediction of Protein Structural Classes: Feature Descriptors and Machine Learning Algorithms

In the postgenomic age, rapid growth in the number of sequence-known proteins has been accompanied by much slower growth in the number of structure-known proteins (as a result of experimental limitations), and a widening gap between the two is evident. Because protein function is linked to protein structure, successful prediction of protein structure is of significant importance in protein function identification. Foreknowledge of protein structural class can help improve protein structure prediction with significant medical and pharmaceutical implications. Thus, a fast, suitable, reliable, and reasonable computational method for protein structural class prediction has become pivotal in bioinformatics. Here, we review recent efforts in protein structural class prediction from protein sequence, with particular attention paid to new feature descriptors, which extract information from protein sequence, and the use of machine learning algorithms in both feature selection and the construction of new classification models. These new feature descriptors include amino acid composition, sequence order, physicochemical properties, multiprofile Bayes, and secondary structure-based features. Machine learning methods, such as artificial neural networks (ANNs), support vector machine (SVM), K-nearest neighbor (KNN), random forest, deep learning, and examples of their application are discussed in detail. We also present our view on possible future directions, challenges, and opportunities for the applications of machine learning algorithms for prediction of protein structural classes.