Protein Secondary Structure Prediction Research Articles

Prediction of Protein Secondary Structure Based on WS-BiLSTM Model

Protein secondary structure prediction is an important topic in bioinformatics. This paper proposed a novel model named WS-BiLSTM, which combined the wavelet scattering convolutional network and the long-short-term memory network for the first time to predict protein secondary structure. This model captures nonlocal interactions between amino acid sequences and remembers long-range interactions between amino acids. In our WS-BiLSTM model, the wavelet scattering convolutional network is used to extract protein features from the PSSM sliding window; the extracted features are combined with the original PSSM data as the input features of the long-short-term memory network to predict protein secondary structure. It is worth noting that the wavelet scattering convolutional network is asymmetric as a member of the continuous wavelet family. The Q3 accuracy on the test set CASP9, CASP10, CASP11, CASP12, CB513, and PDB25 reached 85.26%, 85.84%, 84.91%, 85.13%, 86.10%, and 85.52%, which were higher 2.15%, 2.16%, 3.5%, 3.19%, 4.22%, and 2.75%, respectively, than using the long-short-term memory network alone. Comparing our results with the state-of-art methods shows that our proposed model achieved better results on the CB513 and CASP12 data sets. The experimental results show that the features extracted from the wavelet scattering convolutional network can effectively improve the accuracy of protein secondary structure prediction.

Convolution-Bidirectional Temporal Convolutional Network for Protein Secondary Structure Prediction

As a basic feature extraction method, convolutional neural networks have some information loss problems when dealing with sequence problems, and a temporal convolutional network can compensate for this problem. Howerover, ordinary temporal convolutional networks can not deal well protein secondary structure prediction because of their one-way analysis. Therefore, we propose an integrated deep learning model called Convoluntional-Bidirectional Temporal Convolutional Network. for 3-state and 8-state protein secondary structure predictions based on a convolutional neural network and bidirectional temporal convolutional networks. Because the model combines the advantages of the convolutional neural network and bidirectional temporal convolution network, it can not only capture the local correlation in the amino acid sequence but also analyse the long-distance interaction in the amino acid sequence. Therefore, this model can effectively improve the accuracy of protein secondary structure predictions. The experimental results show that the combination of convolutional neural network and bidirectional temporal convolutional network is effective for predicting protein secondary structure.

A Deep Learning Approach for Prediction of Protein Secondary Structure

The secondary structure of a protein is critical for establishing a link between the protein primary and tertiary structures. For this reason, it is important to design methods for accurate protein secondary structure prediction. Most of the existing computational techniques for protein structural and functional prediction are based on machine learning with shallow frameworks. Different deep learning architectures have already been applied to tackle protein secondary structure prediction problem. In this study, deep learning based models, i.e., convolutional neural network and long short-term memory for protein secondary structure prediction were proposed. The input to proposed models is amino acid sequences which were derived from CulledPDB dataset. Hyperparameter tuning with cross validation was employed to attain best parameters for the proposed models. The proposed models enables effective processing of amino acids and attain approximately 87.05% and 87.47% Q3 accuracy of protein secondary structure prediction for convolutional neural network and long short-term memory models, respectively.

DLBLS_SS: protein secondary structure prediction using deep learning and broad learning system.

Protein secondary structure prediction (PSSP) is not only beneficial to the study of protein structure and function but also to the development of drugs. As a challenging task in computational biology, experimental methods for PSSP are time-consuming and expensive. In this paper, we propose a novel PSSP model DLBLS_SS based on deep learning and broad learning system (BLS) to predict 3-state and 8-state secondary structure. We first use a bidirectional long short-term memory (BLSTM) network to extract global features in residue sequences. Then, our proposed SEBTCN based on temporal convolutional networks (TCN) and channel attention can capture bidirectional key long-range dependencies in sequences. We also use BLS to rapidly optimize fused features while further capturing local interactions between residues. We conduct extensive experiments on public test sets including CASP10, CASP11, CASP12, CASP13, CASP14 and CB513 to evaluate the performance of the model. Experimental results show that our model exhibits better 3-state and 8-state PSSP performance compared to five state-of-the-art models.

Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules.

As an important task in bioinformatics, protein secondary structure prediction (PSSP) is not only beneficial to protein function research and tertiary structure prediction, but also to promote the design and development of new drugs. However, current PSSP methods cannot sufficiently extract effective features. In this study, we propose a novel deep learning model WGACSTCN, which combines Wasserstein generative adversarial network with gradient penalty (WGAN-GP), convolutional block attention module (CBAM) and temporal convolutional network (TCN) for 3-state and 8-state PSSP. In the proposed model, the mutual game of generator and discriminator in WGAN-GP module can effectively extract protein features, and our CBAM-TCN local extraction module can capture key deep local interactions in protein sequences segmented by sliding window technique, and the CBAM-TCN long-range extraction module can further capture the key deep long-range interactions in sequences. We evaluate the performance of the proposed model on seven benchmark datasets. Experimental results show that our model exhibits better prediction performance compared to the four state-of-the-art models. The proposed model has strong feature extraction ability, which can extract important information more comprehensively.

Ensemble Machine Learning to Enhance Q8 Protein Secondary Structure燩rediction

Protein structure prediction is one of the most essential objectives practiced by theoretical chemistry and bioinformatics as it is of a vital importance in medicine, biotechnology and more. Protein secondary structure prediction (PSSP) has a significant role in the prediction of protein tertiary structure, as it bridges the gap between the protein primary sequences and tertiary structure prediction. Protein secondary structures are classified into two categories: 3-state category and 8-state category. Predicting the 3 states and the 8 states of secondary structures from protein sequences are called the Q3 prediction and the Q8 prediction problems, respectively. The 8 classes of secondary structures reveal more precise structural information for a variety of applications than the 3 classes of secondary structures, however, Q8 prediction has been found to be very challenging, that is why all previous work done in PSSP have focused on Q3 prediction. In this paper, we develop an ensemble Machine Learning (ML) approach for Q8 PSSP to explore the performance of ensemble learning algorithms compared to that of individual ML algorithms in Q8 PSSP. The ensemble members considered for constructing the ensemble models are well known classifiers, namely SVM (Support Vector Machines), KNN (K-Nearest Neighbor), DT (Decision Tree), RF (Random Forest), and NB (Naïve Bayes), with two feature extraction techniques, namely LDA (Linear Discriminate Analysis) and PCA (Principal Component Analysis). Experiments have been conducted for evaluating the performance of single models and ensemble models, with PCA and LDA, in Q8 PSSP. The novelty of this paper lies in the introduction of ensemble learning in Q8 PSSP problem. The experimental results confirmed that ensemble ML models are more accurate than individual ML models. They also indicated that features extracted by LDA are more effective than those extracted by PCA.

Protein Secondary Structure Prediction based on CNN and Machine Learning Algorithms

One of the most important topics in computational biology is protein secondary structure prediction. Primary, secondary, tertiary, and quaternary structure are the four levels of complexity that can be used to characterize the entire structure of a protein that are totally ordered by the amino acid sequences. The polypeptide backbone of a protein's local configuration is referred to as a secondary structure. In this paper, three prediction algorithms have been proposed which will predict the protein secondary structure based on machine learning. These prediction methods have been improved by the model structure of convolutional neural networks (CNN). The Rectified Linear Units (ReLU) has been used as the activation function. The 2D CNN has been trained with machine learning algorithms, including Support Vector Machine, Naive Bays and Random Forest. The SVM is used to correctly classify the unseen data. Naïve Bays (NB) and Random Forest (RF) are also applied to solve the prediction problems for not only classification problems but also regression problems. The 2D CNN, hybrid of 2D CNN -SVM, CNN-RF and CNN-NB have been proposed in this experiment. These different methods are implemented with the RS126, 25PDB and CB513 dataset. Further, all prediction Q3 accuracy is compared and improved with their datasets.

Solving the Protein Secondary Structure Prediction Problem With the Hessian Free Optimization Algorithm

Trying to extract features from complex sequential data for classification and prediction problems is an extremely difficult task. This task is even more challenging when both the upstream and downstream information of a time-series is important to process the sequence at a specific time-step. One typical problem which falls in this category is Protein Secondary Structure Prediction (PSSP). Recurrent Neural Networks (RNNs) have been successful in handling sequential data. These methods are demanding in terms of time and space efficiency. On the other hand, simple Feed-Forward Neural Networks (FFNNs) can be trained really fast with the Backpropagation algorithm, but in practice they give poor results in this category of problems. The Hessian Free Optimization (HFO) algorithm is one of the latest developments in the field of Artificial Neural Network (ANN) training algorithms which can converge faster and more accurately. In this paper, we present the implementation of simple FFNNs trained with the powerful HFO second-order learning algorithm for the PSSP problem. In our approach, a single FFNN trained with the HFO learning algorithm can achieve an approximately 79.6% per residue ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q_{3}$ </tex-math></inline-formula> ) accuracy on the PISCES dataset. Despite the simplicity of our method, the results are comparable to some of the state of the art methods which have been designed for this problem. A majority voting ensemble method and filtering with Support Vector Machines have also been applied, which increase our results to 80.4% per residue ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q_{3}$ </tex-math></inline-formula> ) accuracy. Finally, our method has been tested on the CASP13 independent dataset and achieved 78.14% per residue ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q_{3}$ </tex-math></inline-formula> ) accuracy. Moreover, the HFO does not require tuning of any parameters which makes training much faster than other state of the art methods, a very important feature with big datasets and facilitates fast training of FFNN ensembles.

IPseU-TWSVM: Identification of RNA pseudouridine sites based on TWSVM.

Biological sequence analysis is an important basic research work in the field of bioinformatics. With the explosive growth of data, machine learning methods play an increasingly important role in biological sequence analysis. By constructing a classifier for prediction, the input sequence feature vector is predicted and evaluated, and the knowledge of gene structure, function and evolution is obtained from a large amount of sequence information, which lays a foundation for researchers to carry out in-depth research. At present, many machine learning methods have been applied to biological sequence analysis such as RNA gene recognition and protein secondary structure prediction. As a biological sequence, RNA plays an important biological role in the encoding, decoding, regulation and expression of genes. The analysis of RNA data is currently carried out from the aspects of structure and function, including secondary structure prediction, non-coding RNA identification and functional site prediction. Pseudouridine (У) is the most widespread and rich RNA modification and has been discovered in a variety of RNAs. It is highly essential for the study of related functional mechanisms and disease diagnosis to accurately identify У sites in RNA sequences. At present, several computational approaches have been suggested as an alternative to experimental methods to detect У sites, but there is still potential for improvement in their performance. In this study, we present a model based on twin support vector machine (TWSVM) for У site identification. The model combines a variety of feature representation techniques and uses the max-relevance and min-redundancy methods to obtain the optimum feature subset for training. The independent testing accuracy is improved by 3.4% in comparison to current advanced У site predictors. The outcomes demonstrate that our model has better generalization performance and improves the accuracy of У site identification. iPseU-TWSVM can be a helpful tool to identify У sites.

Dawn of a New Era for Membrane Protein Design.

A major advancement has recently occurred in the ability to predict protein secondary structure from sequence using artificial neural networks. This new accessibility to high-quality predicted structures provides a big opportunity for the protein design community. It is particularly welcome for membrane protein design, where the scarcity of solved structures has been a major limitation of the field for decades. Here, we review the work done to date on the membrane protein design and set out established and emerging tools that can be used to most effectively exploit this new access to structures.

In Silico Study of Secondary Structure of Hemoglobin Protein

Protein structure prediction is one of the important goals in the area of bioinformatics and biotechnology. Prediction methods include structure prediction of both secondary and tertiary structures of protein. Protein secondary structure prediction infers knowledge related to presence of helixes, sheets and coils in a polypeptide chain whereas protein tertiary structure prediction infers knowledge related to three dimensional structures of proteins. Protein secondary structures represent the possible motifs or regular expressions represented as patterns that are predicted from primary protein sequence in the form of alpha helix, betastr and and coils. The secondary structure prediction is useful as it infers information related to the structure and function of unknown protein sequence. There are various secondary structure prediction methods used to predict about helixes, sheets and coils. Based on these methods there are various prediction tools under study. This study includes prediction of hemoglobin using various tools. The results produced inferred knowledge with reference to percentage of amino acids participating to produce helices, sheets and coils. PHD and DSC produced the best of the results out of all the tools used.

Protein secondary structure prediction using a lightweight convolutional network and label distribution aware margin loss

Protein secondary structure prediction (PSSP) is an important task in computational molecular biology. Recently, deep neural networks have demonstrated great potential in improving the performance of eight-class PSSP. However, the existing deep predictors usually have higher model complexity and ignore the class imbalance of eight-class secondary structure data in training. In addition, the current methods cannot guarantee that the features corresponding to the padded residue positions are always zero during the forward propagation of the network, which will cause the prediction results of the same protein chain to be different under varied zero-padding numbers. To this end, we propose a novel lightweight convolutional network ShuffleNet_SS, which adopts modified 1-dimensional batch normalization to eliminate the impact of padded residue positions on nonpadded residue positions and uses the label distribution aware margin loss to enhance the network’s ability to learn rare classes. In particular, in order to enable ShuffleNet_SS to fully achieve cross-group information exchange, we further improve the standard channel shuffle operation. Experimental results on the benchmark datasets including CASP10, CASP11, CASP12, CASP13, CASP14 and CB513 show that the proposed method achieves state-of-the-art performance with much lower parameters compared to the five existing deep predictors.

Seq-SetNet: directly exploiting multiple sequence alignment for protein secondary structure prediction.

Accurate prediction of protein structure relies heavily on exploiting multiple sequence alignment (MSA) for residue mutations and correlations as this information specifies protein tertiary structure. The widely used prediction approaches usually transform MSA into inter-mediate models, say position-specific scoring matrix or profile hidden Markov model. These inter-mediate models, however, cannot fully represent residue mutations and correlations carried by MSA; hence, an effective way to directly exploit MSAs is highly desirable. Here, we report a novel sequence set network (called Seq-SetNet) to directly and effectively exploit MSA for protein structure prediction. Seq-SetNet uses an 'encoding and aggregation' strategy that consists of two key elements: (i) an encoding module that takes a component homologue in MSA as input, and encodes residue mutations and correlations into context-specific features for each residue; and (ii) an aggregation module to aggregate the features extracted from all component homologues, which are further transformed into structural properties for residues of the query protein. As Seq-SetNet encodes each homologue protein individually, it could consider both insertions and deletions, as well as long-distance correlations among residues, thus representing more information than the inter-mediate models. Moreover, the encoding module automatically learns effective features and thus avoids manual feature engineering. Using symmetric aggregation functions, Seq-SetNet processes the homologue proteins as a sequence set, making its prediction results invariable to the order of these proteins. On popular benchmark sets, we demonstrated the successful application of Seq-SetNet to predict secondary structure and torsion angles of residues with improved accuracy and efficiency. The code and datasets are available through https://github.com/fusong-ju/Seq-SetNet. Supplementary data are available at Bioinformatics online.

Discovering the Ultimate Limits of Protein Secondary Structure Prediction.

Secondary structure prediction (SSP) of proteins is an important structural biology technique with many applications. There have been ~300 algorithms published in the past seven decades with fierce competition in accuracy. In the first 60 years, the accuracy of three-state SSP rose from ~56% to 81%; after that, it has long stayed at 81–86%. In the 1990s, the theoretical limit of three-state SSP accuracy had been estimated to be 88%. Thus, SSP is now generally considered not challenging or too challenging to improve. However, we found that the limit of three-state SSP might be underestimated. Besides, there is still much room for improving segment-based and eight-state SSPs, but the limits of these emerging topics have not been determined. This work performs large-scale sequence and structural analyses to estimate SSP accuracy limits and assess state-of-the-art SSP methods. The limit of three-state SSP is re-estimated to be ~92%, 4–5% higher than previously expected, indicating that SSP is still challenging. The estimated limit of eight-state SSP is 84–87%. Several proposals for improving future SSP algorithms are made based on our results. We hope that these findings will help move forward the development of SSP and all its applications.

Q3 Accuracy and SOV Measure Analysis of Application of GA in Protein Secondary Structure Prediction

The protein secondary structure prediction (PSP) of the large biological molecule protein is an important task of bioinformatics and in the last decades many machines learning and soft computing methodologies play vital roles in achieving satisfactory results. The protein structural class determination is an important topic in protein science because an idea about protein structural class is quite useful to know about the changes and reaction of a living body in order to design new drugs and medicines. Though several hard computing techniques may be helpful in these areas but focusing upon the steady development and big data size in protein sequences that are entering into databanks, it is a challenge to do experiments with the hard computing techniques. Soft computing techniques like Artificial Neural Network, Fuzzy logic, Genetic Algorithm play a vital role for these types of genomic researches. To face these complex challenges, this article presents a novel method to predict the protein structure by using Genetic Algorithm. The Q3 accuracy and SOV measure analysis with SOVH, SOVE, SOVC value of respective α-helix (H), β-sheet (E) and coil/loop(C) structures are also discussed. The application of Genetic algorithm i.e. the proposed technique GApred provides better result than that of SPIDER2, JPred4, FSVM and SSpro5 for all the three datasets in the experiment. This method is helpful for distinct protein secondary structure prediction and a significant success rate was observed, which indicates that it can be used as a powerful tool in drug design and medicine research.

Ensemble of Template-Free and Template-Based Classifiers for Protein Secondary Structure Prediction.

Protein secondary structures are important in many biological processes and applications. Due to advances in sequencing methods, there are many proteins sequenced, but fewer proteins with secondary structures defined by laboratory methods. With the development of computer technology, computational methods have (started to) become the most important methodologies for predicting secondary structures. We evaluated two different approaches to this problem—driven by the recent results obtained by computational methods in this task—(i) template-free classifiers, based on machine learning techniques; and (ii) template-based classifiers, based on searching tools. Both approaches are formed by different sub-classifiers—six for template-free and two for template-based, each with a specific view of the protein. Our results show that these ensembles improve the results of each approach individually.

Cascading 1D-Convnet Bidirectional Long Short Term Memory Network with Modified COCOB Optimizer: A Novel Approach for Protein Secondary Structure Prediction

The functional properties of proteins play a key job in numerous organic procedures. These functional properties rely on the structure of the specific protein. Prediction of protein structure can be performed by experimental setup as well as by computational methods. In addition to statistics and probabilistic approaches, the computational methods also include artificial intelligence-based techniques. We designed a model which consists of 1D-Convnet and modified recurrent neural network with modified continuous coin betting optimizer for the prediction of protein structure. In the modified continuous coin betting (COCOB) algorithm the probability of getting a head or a tail is based on tossing the coin twice for getting the outcome of a coin flip. It shows significant improvement in gradient calculation. As per our knowledge this is the first approach to predict protein secondary structure using modified COCOB optimization in deep learning domain. We have performed this experiment on Nvidia DGX station having four GPU core. We have used bidirectional architecture of long short term memory for this research work. We designed a 1D-Convnet model and assessed it on CB513 and CullPDB dataset. Further we combined 1D-Convnet model with bidirectional long short term memory to assess CB513 and CullPDB dataset. Both the models are evaluated by Q8 and Q3 accuracy. We compared COCOB and modified COCOB on our model and found that modified COCOB performs better than COCOB. However, our 1D-Convnet-BLSTM model achieves 76.55% (Q3) and 74.45% (Q8) accuracy on CB513 dataset and 68.91% (Q3) and 75.04% (Q8) accuracy on CullPDB dataset.

Testing machine learning techniques for general application by using protein secondary structure prediction. A brief survey with studies of pitfalls and benefits using a simple progressive learning approach

Many researchers have recently used the prediction of protein secondary structure (local conformational states of amino acid residues) to test advances in predictive and machine learning technology such as Neural Net Deep Learning. Protein secondary structure prediction continues to be a helpful tool in research in biomedicine and the life sciences, but it is also extremely enticing for testing predictive methods such as neural nets that are intended for different or more general purposes. A complication is highlighted here for researchers testing their methods for other applications. Modern protein databases inevitably contain important clues to the answer, so-called "strong buried clues", though often obscurely; they are hard to avoid. This is because most proteins or parts of proteins in a modern protein data base are related to others by biological evolution. For researchers developing machine learning and predictive methods, this can overstate and so confuse understanding of the true quality of a predictive method. However, for researchers using the algorithms as tools, understanding strong buried clues is of great value, because they need to make maximum use of all information available. A simple method related to the GOR methods but with some features of neural nets in the sense of progressive learning of large numbers of weights, is used to explore this. It can acquire tens of millions and hence gigabytes of weights, but they are learned stably by exhaustive sampling. The significance of the findings is discussed in the light of promising recent results from AlphaFold using Google's DeepMind.

T1TAdb: the database of type I toxin-antitoxin systems.

Type I toxin–antitoxin (T1TA) systems constitute a large class of genetic modules with antisense RNA (asRNA)-mediated regulation of gene expression. They are widespread in bacteria and consist of an mRNA coding for a toxic protein and a noncoding asRNA that acts as an antitoxin preventing the synthesis of the toxin by directly base-pairing to its cognate mRNA. The co- and post-transcriptional regulation of T1TA systems is intimately linked to RNA sequence and structure, therefore it is essential to have an accurate annotation of the mRNA and asRNA molecules to understand this regulation. However, most T1TA systems have been identified by means of bioinformatic analyses solely based on the toxin protein sequences, and there is no central repository of information on their specific RNA features. Here we present the first database dedicated to type I TA systems, named T1TAdb. It is an open-access web database (https://d-lab.arna.cnrs.fr/t1tadb) with a collection of ∼1900 loci in ∼500 bacterial strains in which a toxin-coding sequence has been previously identified. RNA molecules were annotated with a bioinformatic procedure based on key determinants of the mRNA structure and the genetic organization of the T1TA loci. Besides RNA and protein secondary structure predictions, T1TAdb also identifies promoter, ribosome-binding, and mRNA-asRNA interaction sites. It also includes tools for comparative analysis, such as sequence similarity search and computation of structural multiple alignments, which are annotated with covariation information. To our knowledge, T1TAdb represents the largest collection of features, sequences, and structural annotations on this class of genetic modules.

CSI-LSTM: a web server to predict protein secondary structure using bidirectional long short term memory and NMR chemical shifts

Protein secondary structure provides rich structural information, hence the description and understanding of protein structure relies heavily on it. Identification or prediction of secondary structures therefore plays an important role in protein research. In protein NMR studies, it is more convenient to predict secondary structures from chemical shifts as compared to the traditional determination methods based on inter-nuclear distances provided by NOESY experiment. In recent years, there was a significant improvement observed in deep neural networks, which had been applied in many research fields. Here we proposed a deep neural network based on bidirectional long short term memory (biLSTM) to predict protein 3-state secondary structure using NMR chemical shifts of backbone nuclei. While comparing with the existing methods the proposed method showed better prediction accuracy. Based on the proposed method, a web server has been built to provide protein secondary structure prediction service.