Pseudo Amino Acid Composition Research Articles

IGPred-HDnet: Prediction of Immunoglobulin Proteins Using Graphical Features and the Hierarchal Deep Learning-Based Approach.

Motivation. Immunoglobulin proteins (IGP) (also called antibodies) are glycoproteins that act as B-cell receptors against external or internal antigens like viruses and bacteria. IGPs play a significant role in diverse cellular processes ranging from adhesion to cell recognition. IGP identifications via the in-silico approach are faster and more cost-effective than wet-lab technological methods. Methods. In this study, we developed an intelligent theoretical deep learning framework, "IGPred-HDnet" for the discrimination of IGPs and non-IGPs. Three types of promising descriptors are feature extraction based on graphical and statistical features (FEGS), amphiphilic pseudo-amino acid composition (Amp-PseAAC), and dipeptide composition (DPC) to extract the graphical, physicochemical, and sequential features. Next, the extracted attributes are evaluated through machine learning, i.e., decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), and hierarchical deep network (HDnet) classifiers. The proposed predictor IGPred-HDnet was trained and tested using a 10-fold cross-validation and independent test. Results and Conclusion. The success rates in terms of accuracy (ACC) and Matthew's correlation coefficient (MCC) of IGPred-HDnet on training and independent dataset (Dtrain Dtest) are ACC = 98.00%, 99.10%, and MCC = 0.958, and 0.980 points, respectively. The empirical outcomes demonstrate that the IGPred-HDnet model efficacy on both datasets using the novel FEGS feature and HDnet algorithm achieved superior predictions to other existing computational models. We hope this research will provide great insights into the large-scale identification of IGPs and pharmaceutical companies in new drug design.

Using several pseudo amino acid composition types and different machine learning algorithms to classify and predict archaeal phospholipases.

Phospholipases, as important lipolytic enzymes, have diverse industrial applications. Regarding the stability of extremophilic archaea's proteins in harsh conditions, analyses of unusual features of their proteins are significantly important for their utilization. This research was accomplished to in silico study of archaeal phospholipases' properties and to develop a pioneering method for distinguishing these enzymes from other archaeal enzymes via machine learning algorithms and Chou's pseudo-amino acid composition concept. The non-redundant sequences of archaeal phospholipases were collected. BioSeq-Analysis sever was used with Support Vector Machine (SVM), Random Forests (RF), Covariance Discrimination (CD), and Optimized Evidence-Theoretic K-nearest Neighbor (OET-KNN) as powerful machine learnings algorithms. Also, different Chou's pseudo-amino acid composition modes were performed and then, 5-fold cross-validation was applied to the sequences. Based on our results, the OET-KNN predictor, with 96% accuracy, yields the best performance in SC-PseAAC mode by 5-fold cross-validation. This predictor also achieved very high values of specificity (95%), sensitivity (96%), Matthews's correlation coefficient (0.92), and accuracy (96%). The present investigation yielded a robust anticipatory model for the archaeal phospholipase prediction utilizing the tenets PseAAC and OET-KNN machine learning algorithm.

Rapid, accurate and serotype independent pipeline for in silico epitope mapping of SARS-CoV-2 antigens: a combined machine learning and Chou’s pseudo amino acid composition method

Rapid, accurate and serotype independent pipeline for in silico epitope mapping of SARS-CoV-2 antigens: a combined machine learning and Chou’s pseudo amino acid composition method

Prediction of protein-protein interactions based on ensemble residual convolutional neural network

With the development of bio-medical big data, the prediction of protein-protein interactions (PPIs) with the help of deep learning (DL) has attracted much attention for the study of intermolecular mechanism, drug design, human disease treatment. Given that the experiment-based methods can be difficult, reliable and DL-based approaches are needed. In this paper, we develop the EResCNN, an effective predictor to predict PPIs based on ensemble residual convolutional neural network. First, the fused feature representation is captured by concatenating the vectors obtained via pseudo amino acid composition (PseAAC), auto covariance descriptor (AC), pseudo position-specific scoring matrix (PsePSSM), encoding based on grouped weight (EBGW), multivariate mutual information (MMI) and conjoint triad (CT). Then the high-level information can be obtained using the convolution and pooling of the residual convolutional neural network (RCNN) via layer-by-layer learning. At last, we ensemble RCNN, XGBoost, random forest, LightGBM and extremely randomized trees to build the EResCNN model. The predictive results indicate that EResCNN achieves better performance with the ACC values of 95.34%, 87.89% and 98.61% on S. cerevisiae, H. pylori and Human-Y. pestis datasets, respectively. We also apply EResCNN to the datasets of H. sapiens, M. musculus, C. elegans and E. coli for cross-species prediction. Especially, we find EResCNN can infer significant PPIs network on one-core network, Wnt-related signal pathway network, cancer-specific network and multi-core network, which could provide some references for signal pathway research, disease-related gene mining, and interaction network topology.

MARPPI: boosting prediction of protein-protein interactions with multi-scale architecture residual network.

Protein-protein interactions (PPIs) are a major component of the cellular biochemical reaction network. Rich sequence information and machine learning techniques reduce the dependence of exploring PPIs on wet experiments, which are costly and time-consuming. This paper proposes a PPI prediction model, multi-scale architecture residual network for PPIs (MARPPI), based on dual-channel and multi-feature. Multi-feature leverages Res2vec to obtain the association information between residues, and utilizes pseudo amino acid composition, autocorrelation descriptors and multivariate mutual information to achieve the amino acid composition and order information, physicochemical properties and information entropy, respectively. Dual channel utilizes multi-scale architecture improved ResNet network which extracts protein sequence features to reduce protein feature loss. Compared with other advanced methods, MARPPI achieves 96.03%, 99.01% and 91.80% accuracy in the intraspecific datasets of Saccharomyces cerevisiae, Human and Helicobacter pylori, respectively. The accuracy on the two interspecific datasets of Human-Bacillus anthracis and Human-Yersinia pestis is 97.29%, and 95.30%, respectively. In addition, results on specific datasets of disease (neurodegenerative and metabolic disorders) demonstrate the ability to detect hidden interactions. To better illustrate the performance of MARPPI, evaluations on independent datasets and PPIs network suggest that MARPPI can be used to predict cross-species interactions. The above shows that MARPPI can be regarded as a concise, efficient and accurate tool for PPI datasets.

Target-AMP: Computational prediction of antimicrobial peptides by coupling sequential information with evolutionary profile

Antimicrobial peptides (AMPs) are gaining a lot of attention as cutting-edge treatments for many infectious disorders. The effectiveness of AMPs against bacteria, fungi, and viruses has persisted for a long period, making them the greatest option for addressing the growing problem of antibiotic resistance. Due to their wide-ranging actions, AMPs have become more prominent, particularly in therapeutic applications. The prediction of AMPs has become a difficult task for academics due to the explosive increase of AMPs documented in databases. Wet-lab investigations to find anti-microbial peptides are exceedingly costly, time-consuming, and even impossible for some species. Therefore, in order to choose the optimal AMPs candidate before to the in-vitro trials, an efficient computational method must be developed. In this study, an effort was made to develop a machine learning-based classification system that is effective, accurate, and can distinguish between anti-microbial peptides. The position-specific-scoring-matrix (PSSM), Pseudo Amino acid composition, di-peptide composition, and combination of these three were utilized in the suggested scheme to extract salient aspects from AMPs sequences. The classification techniques K-nearest neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM) were employed. On the independent dataset and training dataset, the accuracy levels achieved by the suggested predictor (Target-AMP) are 97.07% and 95.71%, respectively. The results show that, when compared to other techniques currently used in the literature, our Target-AMP had the best success rate.

MP-VHPPI: Meta predictor for viral host protein-protein interaction prediction in multiple hosts and viruses.

Viral-host protein-protein interaction (VHPPI) prediction is essential to decoding molecular mechanisms of viral pathogens and host immunity processes that eventually help to control the propagation of viral diseases and to design optimized therapeutics. Multiple AI-based predictors have been developed to predict diverse VHPPIs across a wide range of viruses and hosts, however, these predictors produce better performance only for specific types of hosts and viruses. The prime objective of this research is to develop a robust meta predictor (MP-VHPPI) capable of more accurately predicting VHPPI across multiple hosts and viruses. The proposed meta predictor makes use of two well-known encoding methods Amphiphilic Pseudo-Amino Acid Composition (APAAC) and Quasi-sequence (QS) Order that capture amino acids sequence order and distributional information to most effectively generate the numerical representation of complete viral-host raw protein sequences. Feature agglomeration method is utilized to transform the original feature space into a more informative feature space. Random forest (RF) and Extra tree (ET) classifiers are trained on optimized feature space of both APAAC and QS order separate encoders and by combining both encodings. Further predictions of both classifiers are utilized to feed the Support Vector Machine (SVM) classifier that makes final predictions. The proposed meta predictor is evaluated over 7 different benchmark datasets, where it outperforms existing VHPPI predictors with an average performance of 3.07, 6.07, 2.95, and 2.85% in terms of accuracy, Mathews correlation coefficient, precision, and sensitivity, respectively. To facilitate the scientific community, the MP-VHPPI web server is available at https://sds_genetic_analysis.opendfki.de/MP-VHPPI/.

Machine learning-based approach for prediction of ion channels and their subclasses.

Ion channels are ion-permeable protein pores that are found in all cell lipid membranes. Distinct ion channels play multiple roles in biological processes. Proteomic data is fast accumulating as a result of the fast growth of mass spectrometry and giving us the chance to comprehensively explore ion channel classes along with their subclasses. This paper proposes an eXtreme Gradient Boosting(XGBoost)-based method to estimate the ion channel classes and their subclasses. Here, 12feature vectors are applied to better characterize protein sequences like amino acid composition, pseudo-amino acid composition, normalized moreau-broto autocorrelation, amphiphilic pseudo-amino acid composition, dipeptide composition, Geary autocorrelation, tripeptide composition, sequence-order-coupling number, composition/transition/distribution, conjoint triad, moran autocorrelation, quasi-sequence-order descriptors. Here, a total of 9920 features are extracted from the protein sequence. The principal component analysis is applied to determine the optimal number of features to optimize the performance. In 10-fold cross-validation the proposed XGBoost based approach with optimal 50 features achieved accuracy of 100%, 98.70%, 98.77%, 97.26%, 87.40%, 97.39%, 98.03%, 96.42%, and F1-Score of 100%, 99%, 99%, 97%, 87%, 97%, 98%, 97%, for prediction of ion channel and nonion channel, voltage-gated and ligand-gated ion channels, subclasses of voltage-gated ion channels (VGICs), subclasses of ligand-gated ion channels (LGICs), subclasses of voltage-gated calcium channels (VGCCs), subclasses of voltage-gated potassium channels (VGKCs), subclasses of voltage-gated sodium channels (VGSCs), and subclasses of voltage-gated chloride channels, respectively. Here the proposed approach also compares with the other approaches such as support vector machine, k-nearest neighbor, Gaussian Naïve Bayes,and random forest and also compares with existing methods such as support vector machine(SVM) with maximum relevance maximum distancewith an accuracy of 86.6%, 83.7%, and 85.1%, for ion channels, non-ion channels and overall respectively and SVM with radial basis functionkernel-based method with an accuracy of 100%, 97% and 99.9% for ion channels, nonion channels, and overall accuracy, respectively.

DEEPStack-RBP: Accurate identification of RNA-binding proteins based on autoencoder feature selection and deep stacking ensemble classifier

RNA-binding proteins (RBPs) are involved in a number of biological processes such as RNA synthesis, protein folding, alternative splicing, etc. Predicting RBPs can facilitate the discovery and treatment of human diseases, such as muscle atrophy, nervous system diseases, and cancer. However, there are still various challenges in identifying RBPs using experimental methods. Computational methods, and in particular Deep Learning, are being deployed to alleviate some of these challenges and provide new avenues of investigation in the field of RBPs prediction. Here, we propose DEEPStack-RBP, a novel RBPs prediction tool based on deep learning and ensemble learning. First, conjoint triad (CT), local descriptors (LD), pseudo amino acid composition (PseAAC), multivariate mutual information (MMI) and position specific scoring matrix-transition probability composition (PSSM-TPC) are applied to extract multiple features from the proteins. Subsequently, autoencoder (AE) is used to eliminate redundancy in features, and SMOTE-ENN is employed to balance the samples by minimizing the number difference between positive and negative cases. Finally, the stacked ensemble classifier composed of bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU), and support vector machine (SVM) is used for prediction. On the training dataset RBP9873, the ACC value of DEEPStack-RBP reaches 98.76% with a MCC value of 0.9508. For the three independent test datasets of Human, S. cerevisiae and A. thaliana, the accuracy of the model is 97.16%, 97.67% and 99.57% respectively, and the MCC is 0.9405, 0.9499 and 0.9906 respectively. These results show that DEEPStack-RBP can be used as a powerful tool for RBPs prediction.

PseAraUbi: predicting arabidopsis ubiquitination sites by incorporating the physico-chemical and structural features.

We makes three kinds of important features from Arabidopsis thaliana: protein secondary structure based on the Chou-Fasman parameter, amino acids hydrophobicity and polarity information, and analyze their properties. Ubiquitination modification is an important post-translational modification of proteins, which participates in the regulation of many important life activities in cells. At present, ubiquitination proteomics research is mostly concentrated in animals and yeasts, while relatively few studies have been carried out in plants. It can be said that the calculation and prediction of Arabidopsis thaliana ubiquitination sites is still in its infancy. Based on this, we describe a calculation method, PseAraUbi (Prediction of Arabidopsis thaliana ubiquitination sites using pseudo amino acid composition), that can effectively detect ubiquitination sites on Arabidopsis thaliana using support vector machine learning classifiers. Based on protein sequence information, extract features from the Chou-Fasman parameter, amino acids hydrophobicity features, polarity information and selected for classification with the Boruta algorithm. PseAraUbi achieves promising performances with an AUC score of 0.953 with fivefold cross-validation on the training dataset, which are significantly better than that of the pioneer Arabidopsis thaliana ubiquitination sites method. We also proved the ability of our proposed method on independent test sets, thus gaining a competitive advantage. In addition, we also in-depth analyzed the physicochemical properties of amino acids in the region adjacent to the ubiquitination site. To facilitate the community, the source code, optimal feature subset, ubiquitination sites dataset in the Arbidopsis proteome are available at GitHub ( https://github.com/HNUBioinformatics/PseAraUbi.git ) for interest users.

Deep-GHBP: Improving prediction of Growth Hormone-binding proteins using deep learning model

Growth hormone-binding proteins (GHBPs) are carrier proteins that interact with other growth hormone proteins in a selective and non-covalent fashion. GHBPs perform significant roles in various biological activities including cell growth, granular cellular mechanism, and therapeutic approaches. Considering these crucial functions, an accurate prediction of GHBPs is indispensable. In this connection, wet-laboratory and machine learning (ML) models have been developed. However, these methods have a limited amount of performance, including less informative features or inefficient learning models. This study presents an innovative approach by employing a Position Specific Scoring Matrix (PSSM), Composition Transition Distribution (CTD), Geary, Moran, and Pseudo Amino Acid Composition (PseAAC). The important features of these were selected by a novel Multi-Model Consensus (MMC) feature selection algorithm. The most appropriate feature set was then provided to four classifiers: Deep Neural Network (DNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The DNN on the optimal feature set achieved the highest accuracies of 88.09% and 83.33% on the training and testing datasets, respectively. The achieved results were also superior to existing predictors for the identification of GHBPs. Thus, GHBP-Pred will be significantly helpful for large scale prediction of GHBPs with high precision.

To Assist Oncologists: An Efficient Machine Learning-Based Approach for Anti-Cancer Peptides Classification.

In the modern technological era, Anti-cancer peptides (ACPs) have been considered a promising cancer treatment. It’s critical to find new ACPs to ensure a better knowledge of their functioning processes and vaccine development. Thus, timely and efficient ACPs using a computational technique are highly needed because of the enormous peptide sequences generated in the post-genomic era. Recently, numerous adaptive statistical algorithms have been developed for separating ACPs and NACPs. Despite great advancements, existing approaches still have insufficient feature descriptors and learning methods, limiting predictive performance. To address this, a trustworthy framework is developed for the precise identification of ACPs. Particularly, the presented approach incorporates four hypothetical feature encoding mechanisms namely: amino acid, dipeptide, tripeptide, and an improved version of pseudo amino acid composition are applied to indicate the motif of the target class. Moreover, principal component analysis (PCA) is employed for feature pruning, while selecting optimal, deep, and highly variated features. Due to the diverse nature of learning, experiments are performed over numerous algorithms to select the optimum operating method. After investigating the empirical outcomes, the support vector machine with hybrid feature space shows better performance. The proposed framework achieved an accuracy of 97.09% and 98.25% over the benchmark and independent datasets, respectively. The comparative analysis demonstrates that our proposed model outperforms as compared to the existing methods and is beneficial in drug development, and oncology.

DeepHPI: a comprehensive deep learning platform for accurate prediction and visualization of host-pathogen protein-protein interactions.

Host-pathogen protein interactions (HPPIs) play vital roles in many biological processes and are directly involved in infectious diseases. With the outbreak of more frequent pandemics in the last couple of decades, such as the recent outburst of Covid-19 causing millions of deaths, it has become more critical to develop advanced methods to accurately predict pathogen interactions with their respective hosts. During the last decade, experimental methods to identify HPIs have been used to decipher host-pathogen systems with the caveat that those techniques are labor-intensive, expensive and time-consuming. Alternatively, accurate prediction of HPIs can be performed by the use of data-driven machine learning. To provide a more robust and accurate solution for the HPI prediction problem, we have developed a deepHPI tool based on deep learning. The web server delivers four host-pathogen model types: plant-pathogen, human-bacteria, human-virus and animal-pathogen, leveraging its operability to a wide range of analyses and cases of use. The deepHPI web tool is the first to use convolutional neural network models for HPI prediction. These models have been selected based on a comprehensive evaluation of protein features and neural network architectures. The best prediction models have been tested on independent validation datasets, which achieved an overall Matthews correlation coefficient value of 0.87 for animal-pathogen using the combined pseudo-amino acid composition and conjoint triad (PAAC_CT) features, 0.75 for human-bacteria using the combined pseudo-amino acid composition, conjoint triad and normalized Moreau-Broto feature (PAAC_CT_NMBroto), 0.96 for human-virus using PAAC_CT_NMBroto and 0.94 values for plant-pathogen interactions using the combined pseudo-amino acid composition, composition and transition feature (PAAC_CTDC_CTDT). Our server running deepHPI is deployed on a high-performance computing cluster that enables large and multiple user requests, and it provides more information about interactions discovered. It presents an enriched visualization of the resulting host-pathogen networks that is augmented with external links to various protein annotation resources. We believe that the deepHPI web server will be very useful to researchers, particularly those working on infectious diseases. Additionally, many novel and known host-pathogen systems can be further investigated to significantly advance our understanding of complex disease-causing agents. The developed models are established on a web server, which is freely accessible at http://bioinfo.usu.edu/deepHPI/.

HGDTI: predicting drug\u2013target interaction by using information aggregation based on heterogeneous graph neural network

BackgroundIn research on new drug discovery, the traditional wet experiment has a long period. Predicting drug–target interaction (DTI) in silico can greatly narrow the scope of search of candidate medications. Excellent algorithm model may be more effective in revealing the potential connection between drug and target in the bioinformatics network composed of drugs, proteins and other related data.ResultsIn this work, we have developed a heterogeneous graph neural network model, named as HGDTI, which includes a learning phase of network node embedding and a training phase of DTI classification. This method first obtains the molecular fingerprint information of drugs and the pseudo amino acid composition information of proteins, then extracts the initial features of nodes through Bi-LSTM, and uses the attention mechanism to aggregate heterogeneous neighbors. In several comparative experiments, the overall performance of HGDTI significantly outperforms other state-of-the-art DTI prediction models, and the negative sampling technology is employed to further optimize the prediction power of model. In addition, we have proved the robustness of HGDTI through heterogeneous network content reduction tests, and proved the rationality of HGDTI through other comparative experiments. These results indicate that HGDTI can utilize heterogeneous information to capture the embedding of drugs and targets, and provide assistance for drug development.ConclusionsThe HGDTI based on heterogeneous graph neural network model, can utilize heterogeneous information to capture the embedding of drugs and targets, and provide assistance for drug development. For the convenience of related researchers, a user-friendly web-server has been established at http://bioinfo.jcu.edu.cn/hgdti.

XGB-DrugPred: computational prediction of druggable proteins using eXtreme gradient boosting and optimized features set

Accurate identification of drug-targets in human body has great significance for designing novel drugs. Compared with traditional experimental methods, prediction of drug-targets via machine learning algorithms has enhanced the attention of many researchers due to fast and accurate prediction. In this study, we propose a machine learning-based method, namely XGB-DrugPred for accurate prediction of druggable proteins. The features from primary protein sequences are extracted by group dipeptide composition, reduced amino acid alphabet, and novel encoder pseudo amino acid composition segmentation. To select the best feature set, eXtreme Gradient Boosting-recursive feature elimination is implemented. The best feature set is provided to eXtreme Gradient Boosting (XGB), Random Forest, and Extremely Randomized Tree classifiers for model training and prediction. The performance of these classifiers is evaluated by tenfold cross-validation. The empirical results show that XGB-based predictor achieves the best results compared with other classifiers and existing methods in the literature.

DeepDNAbP: A deep learning-based hybrid approach to improve the identification of deoxyribonucleic acid-binding proteins

Accurate identification of DNA-binding proteins (DBPs) is critical for both understanding protein function and drug design. DBPs also play essential roles in different kinds of biological activities such as DNA replication, repair, transcription, and splicing. As experimental identification of DBPs is time-consuming and sometimes biased toward prediction, constructing an effective DBP model represents an urgent need, and computational methods that can accurately predict potential DBPs based on sequence information are highly desirable. In this paper, a novel predictor called DeepDNAbP has been developed to accurately predict DBPs from sequences using a convolutional neural network (CNN) model. First, we perform three feature extraction methods, namely position-specific scoring matrix (PSSM), pseudo-amino acid composition (PseAAC) and tripeptide composition (TPC), to represent protein sequence patterns. Secondly, SHapley Additive exPlanations (SHAP) are employed to remove the redundant and irrelevant features for predicting DBPs. Finally, the best features are provided to the CNN classifier to construct the DeepDNAbP model for identifying DBPs. The final DeepDNAbP predictor achieves superior prediction performance in K-fold cross-validation tests and outperforms other existing predictors of DNA–protein binding methods. DeepDNAbP is poised to be a powerful computational resource for the prediction of DBPs. The web application and curated datasets in this study are freely available at: http://deepdbp.sblog360.blog/.

Predicting the function of rice proteins through Multi-instance Multi-label Learning based on multiple features fusion.

There are a large number of unannotated proteins with unknown functions in rice, which are difficult to be verified by biological experiments. Therefore, computational method is one of the mainstream methods for rice proteins function prediction. Two representative rice proteins, indica protein and japonica protein, are selected as the experimental dataset. In this paper, two feature extraction methods (the residue couple model method and the pseudo amino acid composition method) and the Principal Component Analysis method are combined to design protein descriptive features. Moreover, based on the state-of-the-art MIML algorithm EnMIMLNN, a novel MIML learning framework MK-EnMIMLNN is proposed. And the MK-EnMIMLNN algorithm is designed by learning multiple kernel fusion function neural network. The experimental results show that the hybrid feature extraction method is better than the single feature extraction method. More importantly, the MK-EnMIMLNN algorithm is superior to most classic MIML learning algorithms, which proves the effectiveness of the MK-EnMIMLNN algorithm in rice proteins function prediction.

Comprehensive Prediction of Lipocalin Proteins Using Artificial Intelligence Strategy.

Lipocalin belongs to the calcyin family, and its sequence length is generally between 165 and 200 residues. They are mainly stable and multifunctional extracellular proteins. Lipocalin plays an important role in several stress responses and allergic inflammations. Because the accurate identification of lipocalins could provide significant evidences for the study of their function, it is necessary to develop a machine learning-based model to recognize lipocalin. In this study, we constructed a prediction model to identify lipocalin. Their sequences were encoded by six types of features, namely amino acid composition (AAC), composition of k-spaced amino acid pairs (CKSAAP), pseudo amino acid composition (PseAAC), Geary correlation (GD), normalized Moreau-Broto autocorrelation (NMBroto) and composition/transition/distribution (CTD). Subsequently, these features were optimized by using feature selection techniques. A classifier based on random forest was trained according to the optimal features. The results of 10-fold cross-validation showed that our computational model would classify lipocalins with accuracy of 95.03% and area under the curve of 0.987. On the independent dataset, our computational model could produce the accuracy of 89.90% which was 4.17% higher than the existing model. In this work, we developed an advanced computational model to discriminate lipocalin proteins from non-lipocalin proteins. In the proposed model, protein sequences were encoded by six descriptors. Then, feature selection was performed to pick out the best features which could produce the maximum accuracy. On the basis of the best feature subset, the RF-based classifier can obtained the best prediction results.

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.

Computational identification of 4-carboxyglutamate sites to supplement physiological studies using deep learning

In biological systems, Glutamic acid is a crucial amino acid which is used in protein biosynthesis. Carboxylation of glutamic acid is a significant post-translational modification which plays important role in blood coagulation by activating prothrombin to thrombin. Contrariwise, 4-carboxy-glutamate is also found to be involved in diseases including plaque atherosclerosis, osteoporosis, mineralized heart valves, bone resorption and serves as biomarker for onset of these diseases. Owing to the pathophysiological significance of 4-carboxyglutamate, its identification is important to better understand pathophysiological systems. The wet lab identification of prospective 4-carboxyglutamate sites is costly, laborious and time consuming due to inherent difficulties of in-vivo, ex-vivo and in vitro experiments. To supplement these experiments, we proposed, implemented, and evaluated a different approach to develop 4-carboxyglutamate site predictors using pseudo amino acid compositions (PseAAC) and deep neural networks (DNNs). Our approach does not require any feature extraction and employs deep neural networks to learn feature representation of peptide sequences and performing classification thereof. Proposed approach is validated using standard performance evaluation metrics. Among different deep neural networks, convolutional neural network-based predictor achieved best scores on independent dataset with accuracy of 94.7%, AuC score of 0.91 and F1-score of 0.874 which shows the promise of proposed approach. The iCarboxE-Deep server is deployed at https://share.streamlit.io/sheraz-n/carboxyglutamate/app.py.