Protein Sequence Features Research Articles

BERT-PPII: The Polyproline Type II Helix Structure Prediction Model Based on BERT and Multichannel CNN.

Predicting the polyproline type II (PPII) helix structure is crucial important in many research areas, such as the protein folding mechanisms, the drug targets, and the protein functions. However, many existing PPII helix prediction algorithms encode the protein sequence information in a single way, which causes the insufficient learning of protein sequence feature information. To improve the protein sequence encoding performance, this paper proposes a BERT-based PPII helix structure prediction algorithm (BERT-PPII), which learns the protein sequence information based on the BERT model. The BERT model's CLS vector can fairly fuse sample's each amino acid residue information. Thus, we utilize the CLS vector as the global feature to represent the sample's global contextual information. As the interactions among the protein chains' local amino acid residues have an important influence on the formation of PPII helix, we utilize the CNN to extract local amino acid residues' features which can further enhance the information expression of protein sequence samples. In this paper, we fuse the CLS vectors with CNN local features to improve the performance of predicting PPII structure. Compared to the state-of-the-art PPIIPRED method, the experimental results on the unbalanced dataset show that the proposed method improves the accuracy value by 1% on the strict dataset and 2% on the less strict dataset. Correspondingly, the results on the balanced dataset show that the AUCs of the proposed method are 0.826 on the strict dataset and 0.785 on less strict datasets, respectively. For the independent test set, the proposed method has the AUC value of 0.827 on the strict dataset and 0.783 on the less strict dataset. The above experimental results have proved that the proposed BERT-PPII method can achieve a superior performance of predicting the PPII helix.

Prediction of post-translational modification cross-talk and mutation within proteins via imbalanced learning

Post-translational modification (PTM) is crucial for various cell signaling pathways and biological processes. However, the interactions between PTMs (PTM cross-talk) or PTMs and other sites (PTM mutation) are still in there infancy, with many challenges remaining unexplored. Since PTMs play a fundamental role in cell biology, many mutations cause abnormalities in many PTM sites and affect many human diseases. In this research, we propose an algorithm to improve PTM sites and PTM sites (PTM cross-talk) prediction and to study the interaction between PTM sites and mutation sites (PTM mutation). In addition to the primary network features of three-dimensional protein structure and sequence features, the dynamic features based on ENMs (elastic network models) are also used to improve model performance. Through feature selection, we reserved 48 features and developed a predictor for predicting PTM cross-talk and mutation. According to the evaluation based on PTM cross-talk, the area under the curve of our best prediction model reaches 0.911, which exceeds the state-of-art-model PCTpred. Based on the evaluation of PTM mutation, our prediction model is highly reliable, with an AUC score of 0.935. Even with the removal of the distance, the performance of our model (which is the most excellent model of the nine models, Random Forest model) is relatively stable.

DCSE:Double-Channel-Siamese-Ensemble model for protein protein interaction prediction

BackgroundProtein-protein interaction (PPI) is very important for many biochemical processes. Therefore, accurate prediction of PPI can help us better understand the role of proteins in biochemical processes. Although there are many methods to predict PPI in biology, they are time-consuming and lack accuracy, so it is necessary to build an efficiently and accurately computational model in the field of PPI prediction.ResultsWe present a novel sequence-based computational approach called DCSE (Double-Channel-Siamese-Ensemble) to predict potential PPI. In the encoding layer, we treat each amino acid as a word, and map it into an N-dimensional vector. In the feature extraction layer, we extract features from local and global perspectives by Multilayer Convolutional Neural Network (MCN) and Multilayer Bidirectional Gated Recurrent Unit with Convolutional Neural Networks (MBC). Finally, the output of the feature extraction layer is then fed into the prediction layer to output whether the input protein pair will interact each other. The MCN and MBC are siamese and ensemble based network, which can effectively improve the performance of the model. In order to demonstrate our model’s performance, we compare it with four machine learning based and three deep learning based models. The results show that our method outperforms other models in all evaluation criteria. The Accuracy, Precision, F_{1}, Recall and MCC of our model are 0.9303, 0.9091, 0.9268, 0.9452, 0.8609. For the other seven models, the highest Accuracy, Precision, F_{1}, Recall and MCC are 0.9288, 0.9243, 0.9246, 0.9250, 0.8572. We also test our model in the imbalanced dataset and transfer our model to another species. The results show our model is excellent.ConclusionOur model achieves the best performance by comparing it with seven other models. NLP-based coding method has a good effect on PPI prediction task. MCN and MBC extract protein sequence features from local and global perspectives and these two feature extraction layers are based on siamese and ensemble network structures. Siamese-based network structure can keep the features consistent and ensemble based network structure can effectively improve the accuracy of the model.

Detecting Drug-Target Interactions with Feature Similarity Fusion and Molecular Graphs.

Simple SummaryAccurate identification of potential targets for drugs to interact with can accelerate drug development. The identification of drug–target interactions can provide insights into hidden drug efficacy. This paper presents a prediction model based on feature similarity fusion that can identify crucial features of drugs and targets to help predict drug–target interactions.The key to drug discovery is the identification of a target and a corresponding drug compound. Effective identification of drug–target interactions facilitates the development of drug discovery. In this paper, drug similarity and target similarity are considered, and graphical representations are used to extract internal structural information and intermolecular interaction information about drugs and targets. First, drug similarity and target similarity are fused using the similarity network fusion (SNF) method. Then, the graph isomorphic network (GIN) is used to extract the features with information about the internal structure of drug molecules. For target proteins, feature extraction is carried out using TextCNN to efficiently capture the features of target protein sequences. Three different divisions (CVD, CVP, CVT) are used on the standard dataset, and experiments are carried out separately to validate the performance of the model for drug–target interaction prediction. The experimental results show that our method achieves better results on AUC and AUPR. The docking results also show the superiority of the proposed model in predicting drug–target interactions.

SDNN-PPI: self-attention with deep neural network effect on protein-protein interaction prediction

BackgroundProtein-protein interactions (PPIs) dominate intracellular molecules to perform a series of tasks such as transcriptional regulation, information transduction, and drug signalling. The traditional wet experiment method to obtain PPIs information is costly and time-consuming.ResultIn this paper, SDNN-PPI, a PPI prediction method based on self-attention and deep learning is proposed. The method adopts amino acid composition (AAC), conjoint triad (CT), and auto covariance (AC) to extract global and local features of protein sequences, and leverages self-attention to enhance DNN feature extraction to more effectively accomplish the prediction of PPIs. In order to verify the generalization ability of SDNN-PPI, a 5-fold cross-validation on the intraspecific interactions dataset of Saccharomyces cerevisiae (core subset) and human is used to measure our model in which the accuracy reaches 95.48% and 98.94% respectively. The accuracy of 93.15% and 88.33% are obtained in the interspecific interactions dataset of human-Bacillus Anthracis and Human-Yersinia pestis, respectively. In the independent data set Caenorhabditis elegans, Escherichia coli, Homo sapiens, and Mus musculus, all prediction accuracy is 100%, which is higher than the previous PPIs prediction methods. To further evaluate the advantages and disadvantages of the model, the one-core and crossover network are conducted to predict PPIs, and the data show that the model correctly predicts the interaction pairs in the network.ConclusionIn this paper, AAC, CT and AC methods are used to encode the sequence, and SDNN-PPI method is proposed to predict PPIs based on self-attention deep learning neural network. Satisfactory results are obtained on interspecific and intraspecific data sets, and good performance is also achieved in cross-species prediction. It can also correctly predict the protein interaction of cell and tumor information contained in one-core network and crossover network.The SDNN-PPI proposed in this paper not only explores the mechanism of protein-protein interaction, but also provides new ideas for drug design and disease prevention.

Functional characterization of unknown protein sequences using Neuro-Fuzzy based machine learning approach and sequence augmented feature

Functional characterization of the Unknown Protein Sequence (UPS) is significant for biological research such as disease diagnosis and drug design. In this work Neuro-Fuzzy based machine learning framework is proposed with two levels of predictions, for functional characterization of UPS using augmented features and subcellular localization of the protein sequences. In the first level, Neuro-Fuzzy Approach (NFA) is applied for the categorization of UPS as bacterial or non-bacterial protein sequence. While NFA is capable to overcome the likelihood prediction problem of supervised learning algorithms with untrained samples such as UPS. In the next level functions of bacterial protein sequences are characterized using Protein Subcellular Localization (PSL) model. Physicochemical and evolutionary informations of the protein sequences are extracted and augmented as a protein feature vector that preserves the protein-residue-property and sequence-order-information. Various individual and ensemble classifiers such as Decision-Tree (C-4.5), k-Nearest-Neighbor (k-NN), Multi-Layer-Perceptron (MLP), Naïve-Bayes (NB), AdaBoost, and Gradient-Boosting-Machine (GBM) are used for the formation of the PSL model. PSL model is trained with augmented features of known Gram-Negative Bacterial Protein Sequence (GN_BPS) dataset with 10-fold cross-validation and 97.94% accuracy is achieved through C-4.5 classifier. Validated PSL model is further utilized for the functional characterization of the Unknown G- Bacterial Protein Sequences (Unk_GN_BPS) such as Unk_GN_156 and Unk_GN_61 datasets. The accuracy achieved for Unk_GN_156 is 78.20% with C-4.5 and 79.32% for the Unk_GN_61 through k-NN.

Research on DNA-Binding Protein Identification Method Based on LSTM-CNN Feature Fusion.

Protein is closely related to life activities. As a kind of protein, DNA-binding protein plays an irreplaceable role in life activities. Therefore, it is very important to study DNA-binding protein, which is a subject worthy of study. Although traditional biotechnology has high precision, its cost and efficiency are increasingly unable to meet the needs of modern society. Machine learning methods can make up for the deficiencies of biological experimental techniques to a certain extent, but they are not as simple and fast as deep learning for data processing. In this paper, a deep learning framework based on parallel long and short-term memory(LSTM) and convolutional neural networks(CNN) was proposed to identify DNA-binding protein. This model can not only further extract the information and features of protein sequences, but also the features of evolutionary information. Finally, the two features are combined for training and testing. On the PDB2272 dataset, compared with PDBP_Fusion model, Accuracy(ACC) and Matthew's Correlation Coefficient (MCC) increased by 3.82% and 7.98% respectively. The experimental results of this model have certain advantages.

Prediction of Plant Resistance Proteins Based on Pairwise Energy Content and Stacking Framework.

Plant resistance proteins (R proteins) recognize effector proteins secreted by pathogenic microorganisms and trigger an immune response against pathogenic microbial infestation. Accurate identification of plant R proteins is an important research topic in plant pathology. Plant R protein prediction has achieved many research results. Recently, some machine learning-based methods have emerged to identify plant R proteins. Still, most of them only rely on protein sequence features, which ignore inter-amino acid features, thus limiting the further improvement of plant R protein prediction performance. In this manuscript, we propose a method called StackRPred to predict plant R proteins. Specifically, the StackRPred first obtains plant R protein feature information from the pairwise energy content of residues; then, the obtained feature information is fed into the stacking framework for training to construct a prediction model for plant R proteins. The results of both the five-fold cross-validation and independent test validation show that our proposed method outperforms other state-of-the-art methods, indicating that StackRPred is an effective tool for predicting plant R proteins. It is expected to bring some favorable contribution to the study of plant R proteins.

An automated multi-modal graph-based pipeline for mouse genetic discovery.

Our ability to identify causative genetic factors for mouse genetic models of human diseases and biomedical traits has been limited by the difficulties associated with identifying true causative factors, which are often obscured by the many false positive genetic associations produced by a GWAS. To accelerate the pace of genetic discovery, we developed a graph neural network (GNN)-based automated pipeline (GNNHap) that could rapidly analyze mouse genetic model data and identify high probability causal genetic factors for analyzed traits. After assessing the strength of allelic associations with the strain response pattern; this pipeline analyzes 29M published papers to assess candidate gene-phenotype relationships; and incorporates the information obtained from a protein-protein interaction network and protein sequence features into the analysis. The GNN model produces markedly improved results relative to that of a simple linear neural network. We demonstrate that GNNHap can identify novel causative genetic factors for murine models of diabetes/obesity and for cataract formation, which were validated by the phenotypes appearing in previously analyzed gene knockout mice. The diabetes/obesity results indicate how characterization of the underlying genetic architecture enables new therapies to be discovered and tested by applying 'precision medicine' principles to murine models. The GNNHap source code is freely available at https://github.com/zqfang/gnnhap, and the new version of the HBCGM program is available at https://github.com/zqfang/haplomap. Supplementary data are available at Bioinformatics online.

CHERRY: a Computational metHod for accuratE pRediction of virus-pRokarYotic interactions using a graph encoder-decoder model.

Prokaryotic viruses, which infect bacteria and archaea, are key players in microbial communities. Predicting the hosts of prokaryotic viruses helps decipher the dynamic relationship between microbes. Experimental methods for host prediction cannot keep pace with the fast accumulation of sequenced phages. Thus, there is a need for computational host prediction. Despite some promising results, computational host prediction remains a challenge because of the limited known interactions and the sheer amount of sequenced phages by high-throughput sequencing technologies. The state-of-the-art methods can only achieve 43% accuracy at the species level. In this work, we formulate host prediction as link prediction in a knowledge graph that integrates multiple protein and DNA-based sequence features. Our implementation named CHERRY can be applied to predict hosts for newly discovered viruses and to identify viruses infecting targeted bacteria. We demonstrated the utility of CHERRY for both applications and compared its performance with 11 popular host prediction methods. To our best knowledge, CHERRY has the highest accuracy in identifying virus–prokaryote interactions. It outperforms all the existing methods at the species level with an accuracy increase of 37%. In addition, CHERRY’s performance on short contigs is more stable than other tools.

Identifying Functions of Proteins in Mice With Functional Embedding Features.

In current biology, exploring the biological functions of proteins is important. Given the large number of proteins in some organisms, exploring their functions one by one through traditional experiments is impossible. Therefore, developing quick and reliable methods for identifying protein functions is necessary. Considerable accumulation of protein knowledge and recent developments on computer science provide an alternative way to complete this task, that is, designing computational methods. Several efforts have been made in this field. Most previous methods have adopted the protein sequence features or directly used the linkage from a protein–protein interaction (PPI) network. In this study, we proposed some novel multi-label classifiers, which adopted new embedding features to represent proteins. These features were derived from functional domains and a PPI network via word embedding and network embedding, respectively. The minimum redundancy maximum relevance method was used to assess the features, generating a feature list. Incremental feature selection, incorporating RAndom k-labELsets to construct multi-label classifiers, used such list to construct two optimum classifiers, corresponding to two key measurements: accuracy and exact match. These two classifiers had good performance, and they were superior to classifiers that used features extracted by traditional methods.

RCSB Protein Data Bank 1D3D module: displaying positional features on macromolecular assemblies.

MotivationMapping positional features from one-dimensional (1D) sequences onto three-dimensional (3D) structures of biological macromolecules is a powerful tool to show geometric patterns of biochemical annotations and provide a better understanding of the mechanisms underpinning protein and nucleic acid function at the atomic level.ResultsWe present a new library designed to display fully customizable interactive views between 1D positional features of protein and/or nucleic acid sequences and their 3D structures as isolated chains or components of macromolecular assemblies.Availability and implementation https://github.com/rcsb/rcsb-saguaro-3d.Supplementary information Supplementary data are available at Bioinformatics online.

Identifying Pupylation Proteins and Sites by Incorporating Multiple Methods.

Pupylation is an important posttranslational modification in proteins and plays a key role in the cell function of microorganisms; an accurate prediction of pupylation proteins and specified sites is of great significance for the study of basic biological processes and development of related drugs since it would greatly save experimental costs and improve work efficiency. In this work, we first constructed a model for identifying pupylation proteins. To improve the pupylation protein prediction model, the KNN scoring matrix model based on functional domain GO annotation and the Word Embedding model were used to extract the features and Random Under-sampling (RUS) and Synthetic Minority Over-sampling Technique (SMOTE) were applied to balance the dataset. Finally, the balanced data sets were input into Extreme Gradient Boosting (XGBoost). The performance of 10-fold cross-validation shows that accuracy (ACC), Matthew’s correlation coefficient (MCC), and area under the ROC curve (AUC) are 95.23%, 0.8100, and 0.9864, respectively. For the pupylation site prediction model, six feature extraction codes (i.e., TPC, AAI, One-hot, PseAAC, CKSAAP, and Word Embedding) served to extract protein sequence features, and the chi-square test was employed for feature selection. Rigorous 10-fold cross-validations indicated that the accuracies are very high and outperformed its existing counterparts. Finally, for the convenience of researchers, PUP-PS-Fuse has been established at https://bioinfo.jcu.edu.cn/PUP-PS-Fuse and http://121.36.221.79/PUP-PS-Fuse/as a backup.

GLSTM-DTA: Application of Prediction Improvement Model Based on GNN and LSTM

Abstract Most prediction models of drug-target binding affinity (DTA) treated drugs and targets as sequences, and feature extraction networks could not sufficiently extract features. Inspired by DeepDTA and GraphDTA, we proposed an improved model named GLSTM-DTA for DTA prediction, which combined Graph Neural Network (GNN) and Long Short-Term Memory Network (LSTM). The feature extraction block consists of two parts: GNN block and LSTM block, which extract drug features and protein features respectively. The novelty of our work is using LSTM, instead of Convolutional neural network (CNN) to extract protein sequence features, which is facilitating to capture long-term dependencies in sequence. In addition, we also converted drugs into graph structures and use GNN for feature extraction. The improved model performs better than DeepDTA and GraphDTA. The comprehensive results prove the advantages of our model in accurately predicting the binding affinity of drug-targets.

DeepNEC: a novel alignment-free tool for the identification and classification of nitrogen biochemical network-related enzymes using deep learning.

Nitrogen is essential for life and its transformations are an important part of the global biogeochemical cycle. Being an essential nutrient, nitrogen exists in a range of oxidation states from +5 (nitrate) to -3 (ammonium and amino-nitrogen), and its oxidation and reduction reactions catalyzed by microbial enzymes determine its environmental fate. The functional annotation of the genes encoding the core nitrogen network enzymes has a broad range of applications in metagenomics, agriculture, wastewater treatment and industrial biotechnology. This study developed an alignment-free computational approach to determine the predicted nitrogen biochemical network-related enzymes from the sequence itself. We propose deepNEC, a novel end-to-end feature selection and classification model training approach for nitrogen biochemical network-related enzyme prediction. The algorithm was developed using Deep Learning, a class of machine learning algorithms that uses multiple layers to extract higher-level features from the raw input data. The derived protein sequence is used as an input, extracting sequential and convolutional features from raw encoded protein sequences based on classification rather than traditional alignment-based methods for enzyme prediction. Two large datasets of protein sequences, enzymes and non-enzymes were used to train the models with protein sequence features like amino acid composition, dipeptide composition (DPC), conformation transition and distribution, normalized Moreau-Broto (NMBroto), conjoint and quasi order, etc. The k-fold cross-validation and independent testing were performed to validate our model training. deepNEC uses a four-tier approach for prediction; in the first phase, it will predict a query sequence as enzyme or non-enzyme; in the second phase, it will further predict and classify enzymes into nitrogen biochemical network-related enzymes or non-nitrogen metabolism enzymes; in the third phase, it classifies predicted enzymes into nine nitrogen metabolism classes; and in the fourth phase, it predicts the enzyme commission number out of 20 classes for nitrogen metabolism. Among all, the DPC + NMBroto hybrid feature gave the best prediction performance (accuracy of 96.15% in k-fold training and 93.43% in independent testing) with an Matthews correlation coefficient (0.92 training and 0.87 independent testing) in phase I; phase II (accuracy of 99.71% in k-fold training and 98.30% in independent testing); phase III (overall accuracy of 99.03% in k-fold training and 98.98% in independent testing); phase IV (overall accuracy of 99.05% in k-fold training and 98.18% in independent testing), the DPC feature gave the best prediction performance. We have also implemented a homology-based method to remove false negatives. All the models have been implemented on a web server (prediction tool), which is freely available at http://bioinfo.usu.edu/deepNEC/.

SIP: A computational prediction of S-Adenosyl methionine (SAM) interacting proteins and their interaction sites through primary structures

S-Adenosyl methionine (SAM), a universal methyl group donor, plays a vital role in biosynthesis and acts as an inhibitor to many enzymes. Due to protein interaction-dependent biological role, SAM has become a favorite target in various therapeutical and clinical studies such as treating cancer, Alzheimer’s, epilepsy, and neurological disorders. Therefore, the identification of the SAM interacting proteins and their interaction sites is a biologically significant problem. However, wet-lab techniques, though accurate, to identify SAM interactions and interaction sites are tedious and costly. Therefore, efficient and accurate computational methods for this purpose are vital to the design and assist such wet-lab experiments. In this study, we present machine learning-based models to predict SAM interacting proteins and their interaction sites by using only primary structures of proteins. Here we modeled SAM interaction prediction through whole protein sequence features along with different classifiers. Whereas, we modeled SAM interaction site prediction through overlapping sequence windows and ranking with multiple instance learning that allows handling imprecisely annotated SAM interaction sites. Through a series of simulation studies along with biological significant evaluation, we showed that our proposed models give a state-of-the-art performance for both SAM interaction and interaction site prediction. Through data mining in this study, we have also identified various characteristics of amino acid sub-sequences and their relative position to effectively locate interaction sites in a SAM interacting protein. Python code for training and evaluating our proposed models together with a webserver implementation as SIP (Sam Interaction Predictor) is available at the URL: https://sites.google.com/view/wajidarshad/software.

Machine Learning Approaches for Discriminating Bacterial and Viral Targeted Human Proteins

Infectious diseases are one of the core biological complications for public health. It is important to recognize the pathogen-specific mechanisms to improve our understanding of infectious diseases. Differentiations between bacterial- and viral-targeted human proteins are important for improving both prognosis and treatment for the patient. Here, we introduce machine learning-based classifiers to discriminate between the two groups of human proteins. We used the sequence, network, and gene ontology features of human proteins. Among different classifiers and features, the deep neural network (DNN) classifier with amino acid composition (AAC), dipeptide composition (DC), and pseudo-amino acid composition (PAAC) (445 features) achieved the best area under the curve (AUC) value (0.939), F1-score (94.9%), and Matthews correlation coefficient (MCC) value (0.81). We found that each of the selected top 100 of the bacteria- and virus-targeted human proteins from a candidate pool of 1618 and 3916 proteins, respectively, were part of distinct enriched biological processes and pathways. Our proposed method will help to differentiate between the bacterial and viral infections based on the targeted human proteins on a global scale. Furthermore, identification of the crucial pathogen targets in the human proteome would help us to better understand the pathogen-specific infection strategies and develop novel therapeutics.

Prediksi interaksi protein-protein berbasis sekuens protein menggunakan fitur autocorrelation dan machine learning

Protein-protein interaction (PPI) can define a protein's function by knowing the protein's position in a complex network of protein interactions. The number of PPIs that have been identified is relatively small. Therefore, several studies were conducted to predict PPI using protein sequence information. This research compares the performance of three autocorrelation methods: Moran, Geary, and Moreau-Broto, in extracting protein sequence features to predict PPI. The results of the three extractions are then applied to three machine learning algorithms, namely k-Nearest Neighbor (KNN), Random Forest, and Support Vector Machine (SVM). The prediction models with the three autocorrelation methods can produce predictions with high average accuracy, which is 95.34% for Geary in KNN, 97.43% for Geary in RF, and 97.11% for Geary and Moran in SVM. In addition, the interacting protein pairs tend to have similar autocorrelation characteristics. Thus, the autocorrelation method can be used to predict PPI well.

Research on protein solubility prediction based on ensemble learning and feature fusion

Protein solubility is one of the momentous properties of a protein that can effectively participate in and inhibit the physiological and biochemical processes of cancer cells in the human body. Therefore, understanding the solubility of proteins may be significant to find the mechanism of diseases caused by the solubility of proteins. In this paper, to improve the protein solubility prediction performance and address the inadequacy of existing protein solubility prediction methods that more feature information about protein sequences is difficult to be obtained. A protein solubility prediction model named EL-FFsol is proposed, which is based on the CatBoost ensemble learning framework and multiple feature fusion of protein sequences. First of all, protein sequence features were introduced to build fusion representation, including the Physicochemical Properties, One-hot Feature Encoding, Amino Acid Composition and Statistical Features. Additionally, the CatBoost was employed to construct an ensemble learning model to predict protein solubility. Finally, EL-FFsol was tested on the benchmark dataset to predict the solubility of proteins. In terms of accuracy, matthews correlation coefficient, sensitivity, specificity, area under ROC curve and area under P-R curve, EL-FFsol achieved 0.7679, 0.5480, 0.6630, 0.8729, 0.8540 and 0.8440 performances. Compared with the DeepSOL and DDcCNN, the matthews correlation coefficient was increased by 1.68% and 0.79%, the area under ROC curve was increased by 1.60% and 2.20% and the area under P-R curve was increased by 1.70% and 2.40%, respectively.

Potential of deep representative learning features to interpret the sequence information in proteomics.

In molecular biology and proteomics, accurately predicting functions of proteins is a very critical step. However, it sinks a lot of time and resources to detect the protein functions through biological experiments. Therefore, it is necessary to develop an accurate and reliable computational method for this prediction purpose. Since a growing number of deep learning and natural language processing (NLP) models have been developed recently, they hold potential to assist in protein function problems. Therefore, Wang etal. applied them to extract the hidden features of protein sequences and improve the performance of protein function prediction. As a case study, they used their approach to develop a web-server namely prPred-DRLF to predict plant resistance proteins, which play important roles in the detection of pathogen invasion. Cross-validation and independent test results indicate that prPred-DRLF outperformed current state-of-the-art prediction methods on the same datasets. The excellent performance then shows that deep representative learning (using deep learning and NLP) is an accurate and reliable method for protein function prediction. This article is protected by copyright. All rights reserved.