NAGbinder: An approach for identifying N-acetylglucosamine interacting residues of a protein from its primary sequence

A hybrid method for discovering interferon-gamma inducing peptides in human and mouse

Interferon-gamma (IFN-γ) is a versatile pleiotropic cytokine essential for both innate and adaptive immune responses. It exhibits both pro-inflammatory and anti-inflammatory properties, making it a promising therapeutic candidate for treating various infectious diseases and cancers. We present IFNepitope2, a host-specific technique to annotate IFN-γ inducing peptides, it is an updated version of IFNepitope introduced by Dhanda et al. In this study, dataset used for developing prediction method contain experimentally validated 25,492 and 7983 IFN-γ inducing peptides in human and mouse host, respectively. In initial phase, machine learning techniques have been exploited to develop classification model using wide range of peptide features. Further, to improve machine learning based models or alignment free models, we explore potential of similarity-based technique BLAST. Finally, a hybrid model has been developed that combine best machine learning based model with BLAST. In most of the case, models based on extra tree perform better than other machine learning techniques. In case of peptide features, compositional feature particularly dipeptide composition performs better than one-hot encoding or binary profile. Our best machine learning based models achieved AUROC 0.89 and 0.83 for human and mouse host, respectively. The hybrid model achieved the AUROC 0.90 and 0.85 for human and mouse host, respectively. All models have been evaluated on an independent/validation dataset not used for training or testing these models. Newly developed method performs better than existing method on independent dataset. The major objective of this study is to predict, design and scan IFN-γ inducing peptides, thus server/software have been developed ( https://webs.iiitd.edu.in/raghava/ifnepitope2/ ). This method is also available as standalone at https://github.com/raghavagps/ifnepitope2 and python package index at https://pypi.org/project/ifnepitope2/ .

A hybrid approach for predicting transcription factors

Transcription factors are essential DNA-binding proteins that regulate the transcription rate of several genes and control the expression of genes inside a cell. The prediction of transcription factors with high precision is important for understanding biological processes such as cell differentiation, intracellular signaling, and cell-cycle control. In this study, we developed a hybrid method that combines alignment-based and alignment-free methods for predicting transcription factors with higher accuracy. All models have been trained, tested, and evaluated on a large dataset that contains 19,406 transcription factors and 523,560 non-transcription factor protein sequences. To avoid biases in evaluation, the datasets were divided into training and validation/independent datasets, where 80% of the data was used for training, and the remaining 20% was used for external validation. In the case of alignment-free methods, models were developed using machine learning techniques and the composition-based features of a protein. Our best alignment-free model obtained an AUC of 0.97 on an independent dataset. In the case of the alignment-based method, we used BLAST at different cut-offs to predict the transcription factors. Although the alignment-based method demonstrated excellent performance, it was unable to cover all transcription factors due to instances of no hits. To combine the strengths of both methods, we developed a hybrid method that combines alignment-free and alignment-based methods. In the hybrid method, we added the scores of the alignment-free and alignment-based methods and achieved a maximum AUC of 0.99 on the independent dataset. The method proposed in this study performs better than existing methods. We incorporated the best models in the webserver/Python Package Index/standalone package of "TransFacPred" (https://webs.iiitd.edu.in/raghava/transfacpred).

TNFepitope: A webserver for the prediction of TNF-α inducing epitopes

Tumor Necrosis Factor alpha (TNF-α) is a pleiotropic pro-inflammatory cytokine that is crucial in controlling the signaling pathways within the immune cells. Recent studies reported that higher expression levels of TNF-α are associated with the progression of several diseases, including cancers, cytokine release syndrome in COVID-19, and autoimmune disorders. Thus, it is the need of the hour to develop immunotherapies or subunit vaccines to manage TNF-α progression in various disease conditions. In the pilot study, we proposed a host-specific in-silico tool for predicting, designing, and scanning TNF-α inducing epitopes. The prediction models were trained and validated on the experimentally validated TNF-α inducing/non-inducing epitopes from human and mouse hosts. Firstly, we developed alignment-free (machine learning based models using composition-based features of peptides) methods for predicting TNF-α inducing peptides and achieved maximum AUROC of 0.79 and 0.74 for human and mouse hosts, respectively. Secondly, an alignment-based (using BLAST) method has been used for predicting TNF-α inducing epitopes. Finally, a hybrid method (combination of alignment-free and alignment-based method) has been developed for predicting epitopes. Hybrid approach achieved maximum AUROC of 0.83 and 0.77 on an independent dataset for human and mouse hosts, respectively. We have also identified potential TNF-α inducing peptides in different proteins of HIV-1, HIV-2, SARS-CoV-2, and human insulin. The best models developed in this study has been incorporated in the webserver TNFepitope (https://webs.iiitd.edu.in/raghava/tnfepitope/), standalone package and GitLab (https://gitlab.com/raghavalab/tnfepitope).

Pfeature: A Tool for Computing Wide Range of Protein Features and Building Prediction Models

In the last three decades, a wide range of protein features have been discovered to annotate a protein. Numerous attempts have been made to integrate these features in a software package/platform so that the user may compute a wide range of features from a single source. To complement the existing methods, we developed a method, Pfeature, for computing a wide range of protein features. Pfeature allows to compute more than 200,000 features required for predicting the overall function of a protein, residue-level annotation of a protein, and function of chemically modified peptides. It has six major modules, namely, composition, binary profiles, evolutionary information, structural features, patterns, and model building. Composition module facilitates to compute most of the existing compositional features, plus novel features. The binary profile of amino acid sequences allows to compute the fraction of each type of residue as well as its position. The evolutionary information module allows to compute evolutionary information of a protein in the form of a position-specific scoring matrix profile generated using Position-Specific Iterative Basic Local Alignment Search Tool (PSI-BLAST); fit for annotation of a protein and its residues. A structural module was developed for computing of structural features/descriptors from a tertiary structure of a protein. These features are suitable to predict the therapeutic potential of a protein containing non-natural or chemically modified residues. The model-building module allows to implement various machine learning techniques for developing classification and regression models as well as feature selection. Pfeature also allows the generation of overlapping patterns and features from a protein. A user-friendly Pfeature is available as a web server python library and stand-alone package.

Prediction of celiac disease associated epitopes and motifs in a protein

Introduction

Celiac disease (CD) is an autoimmune gastrointestinal disorder causes immune-mediated enteropathy against gluten. Gluten immunogenic peptides have the potential to trigger immune responses which leads to damage the small intestine. HLA-DQ2/DQ8 are major alleles that bind to epitope/antigenic region of gluten and induce celiac disease. There is a need to identify CD associated epitopes in protein-based foods and therapeutics.

Methods

In this study, computational tools have been developed to predict CD associated epitopes and motifs. Dataset used for training, testing and evaluation contain experimentally validated CD associated and non-CD associate peptides. We perform positional analysis to identify the most significant position of an amino acid residue in the peptide and checked the frequency of HLA alleles. We also compute amino acid composition to develop machine learning based models. We also developed ensemble method that combines motif-based approach and machine learning based models.

Results and Discussion

Our analysis support existing hypothesis that proline (P) and glutamine (Q) are highly abundant in CD associated peptides. A model based on density of P&Q in peptides has been developed for predicting CD associated peptides which achieve maximum AUROC 0.98 on independent data. We discovered motifs (e.g., QPF, QPQ, PYP) which occurs specifically in CD associated peptides. We also developed machine learning based models using peptide composition and achieved maximum AUROC 0.99. Finally, we developed ensemble method that combines motif-based approach and machine learning based models. The ensemble model-predict CD associated motifs with 100% accuracy on an independent dataset, not used for training. Finally, the best models and motifs has been integrated in a web server and standalone software package "CDpred". We hope this server anticipate the scientific community for the prediction, designing and scanning of CD associated peptides as well as CD associated motifs in a protein/peptide sequence (https://webs.iiitd.edu.in/raghava/cdpred/).

Sigma70Pred: A highly accurate method for predicting sigma70 promoter in Escherichia coli K-12 strains

Sigma70 factor plays a crucial role in prokaryotes and regulates the transcription of most of the housekeeping genes. One of the major challenges is to predict the sigma70 promoter or sigma70 factor binding site with high precision. In this study, we trained and evaluate our models on a dataset consists of 741 sigma70 promoters and 1,400 non-promoters. We have generated a wide range of features around 8,000, which includes Dinucleotide Auto-Correlation, Dinucleotide Cross-Correlation, Dinucleotide Auto Cross-Correlation, Moran Auto-Correlation, Normalized Moreau-Broto Auto-Correlation, Parallel Correlation Pseudo Tri-Nucleotide Composition, etc. Our SVM based model achieved maximum accuracy 97.38% with AUROC 0.99 on training dataset, using 200 most relevant features. In order to check the robustness of the model, we have tested our model on the independent dataset made by using RegulonDB10.8, which included 1,134 sigma70 and 638 non-promoters, and able to achieve accuracy of 90.41% with AUROC of 0.95. Our model successfully predicted constitutive promoters with accuracy of 81.46% on an independent dataset. We have developed a method, Sigma70Pred, which is available as webserver and standalone packages at https://webs.iiitd.edu.in/raghava/sigma70pred/. The services are freely accessible.

In silico method for predicting infectious strains of influenza A virus from its genome and protein sequences

Influenza A is a contagious viral disease responsible for four pandemics in the past and a major public health concern. Being zoonotic in nature, the virus can cross the species barrier and transmit from wild aquatic bird reservoirs to humans via intermediate hosts. In this study, we have developed a computational method for the prediction of human-associated and non-human-associated influenza A virus sequences. The models were trained and validated on proteins and genome sequences of influenza A virus. Firstly, we have developed prediction models for 15 types of influenza A proteins using composition-based and one-hot-encoding features. We have achieved a highest AUC of 0.98 for HA protein on a validation dataset using dipeptide composition-based features. Of note, we obtained a maximum AUC of 0.99 using one-hot-encoding features for protein-based models on a validation dataset. Secondly, we built models using whole genome sequences which achieved an AUC of 0.98 on a validation dataset. In addition, we showed that our method outperforms a similarity-based approach (i.e., blast) on the same validation dataset. Finally, we integrated our best models into a user-friendly web server 'FluSPred' (https://webs.iiitd.edu.in/raghava/fluspred/index.html) and a standalone version (https://github.com/raghavagps/FluSPred) for the prediction of human-associated/non-human-associated influenza A virus strains.

A deep learning-based method for the prediction of DNA interacting residues in a protein

DNA-protein interaction is one of the most crucial interactions in the biological system, which decides the fate of many processes such as transcription, regulation and splicing of genes. In this study, we trained our models on a training dataset of 646 DNA-binding proteins having 15 636 DNA interacting and 298 503 non-interacting residues. Our trained models were evaluated on an independent dataset of 46 DNA-binding proteins having 965 DNA interacting and 9911 non-interacting residues. All proteins in the independent dataset have less than 30% of sequence similarity with proteins in the training dataset. A wide range of traditional machine learning and deep learning (1D-CNN) techniques-based models have been developed using binary, physicochemical properties and Position-Specific Scoring Matrix (PSSM)/evolutionary profiles. In the case of machine learning technique, eXtreme Gradient Boosting-based model achieved a maximum area under the receiver operating characteristics (AUROC) curve of 0.77 on the independent dataset using PSSM profile. Deep learning-based model achieved the highest AUROC of 0.79 on the independent dataset using a combination of all three profiles. We evaluated the performance of existing methods on the independent dataset and observed that our proposed method outperformed all the existing methods. In order to facilitate scientific community, we developed standalone software and web server, which are accessible from https://webs.iiitd.edu.in/raghava/dbpred.

Prediction of risk-associated genes and high-risk liver cancer patients from their mutation profile: Benchmarking of mutation calling techniques

Identification of somatic mutations with high precision is one of the major challenges in the prediction of high-risk liver-cancer patients. In the past, number of mutations calling techniques have been developed that include MuTect2, MuSE, Varscan2, and SomaticSniper. In this study, an attempt has been made to benchmark the potential of these techniques in predicting the prognostic biomarkers for liver cancer. Initially, we extracted somatic mutations in liver cancer patients using Variant Call Format (VCF) and Mutation Annotation Format (MAF) files from the cancer genome atlas. In terms of size, the MAF files are 42 times smaller than VCF files and containing only high-quality somatic mutations. Further, machine learning based models have been developed for predicting high-risk cancer patients using mutations obtained from different techniques. The performance of different techniques and data files have been compared based on their potential to discriminate high and low-risk liver-cancer patients. Based on correlation analysis, we selected 80 genes having significant negative-correlation with the overall survival of liver cancer patients. The univariate survival analysis revealed the prognostic role of highly mutated genes. Single-gene based analysis showed that MuTect2 technique based MAF file has achieved maximum hazard ratio (HRLAMC3) of 9.25 with p-value 1.78E-06. Further, we developed various prediction models using risk-associated top-10 genes for each technique. Our results indicate that MuTect2 technique based VCF files outperform all other methods with maximum Area Under the Receiver-Operating Characteristic (AUROC) curve of 0.765 and HR 4.50 (p-value 3.83E-15). Eventually, VCF file generated using MuTect2 technique performs better among other mutation calling techniques for the prediction of high-risk liver cancer patients. We hope that our findings will provide a useful and comprehensive comparison of various mutation calling techniques for the prognostic analysis of cancer patients. In order to serve the scientific community, we have provided a Python-based pipeline to develop the prediction models using mutation profiles (VCF/MAF) of cancer patients. It is available on GitHub at https://github.com/raghavagps/mutation_bench.

IL13Pred: A method for predicting immunoregulatory cytokine IL-13 inducing peptides

BACKGROUND

Interleukin 13 (IL-13) is an immunoregulatory cytokine, primarily released by activated T-helper 2 cells. IL-13 induces the pathogenesis of many allergic diseases, such as airway hyperresponsiveness, glycoprotein hypersecretion, and goblet cell hyperplasia. In addition, IL-13 inhibits tumor immunosurveillance, leading to carcinogenesis. Since elevated IL-13 serum levels are severe in COVID-19 patients, predicting IL-13 inducing peptides or regions in a protein is vital to designing safe protein therapeutics particularly immunotherapeutic.

OBJECTIVE

The present study describes a method to develop, predict, design, and scan IL-13 inducing peptides.

METHODS

The dataset experimentally validated 313 IL-13 inducing peptides, and 2908 non-inducing homo-sapiens peptides extracted from the immune epitope database (IEDB). A total of 95 key features using the linear support vector classifier with the L1 penalty (SVC-L1) technique was extracted from the originally generated 9165 features using Pfeature. These key features were ranked based on their prediction ability, and the top 10 features were used to build machine learning prediction models. Various machine learning techniques were deployed to develop models for predicting IL-13 inducing peptides. These models were trained, tested, and evaluated using five-fold cross-validation techniques; the best model was evaluated on an independent dataset.

RESULTS

Our best model based on XGBoost achieves a maximum AUC of 0.83 and 0.80 on the training and independent dataset, respectively. Our analysis indicates that certain SARS-COV2 variants are more prone to induce IL-13 in COVID-19 patients.

CONCLUSION

The best performing model was incorporated in web-server and standalone package named 'IL-13Pred' for precise prediction of IL-13 inducing peptides. For large dataset analysis standalone package of IL-13Pred is available at (https://webs.iiitd.edu.in/raghava/il13pred/) webserver and over GitHub link: https://github.com/raghavagps/il13pred.

Computer-aided prediction of inhibitors against STAT3 for managing COVID-19 associated cytokine storm

Background

Proinflammatory cytokines are correlated with the severity of disease in patients with COVID-19. IL6-mediated activation of STAT3 proliferates proinflammatory responses that lead to cytokine storm promotion. Thus, STAT3 inhibitors may play a crucial role in managing the COVID-19 pathogenesis. The present study discusses a method for predicting inhibitors against the STAT3 signaling pathway.

Method

The main dataset comprises 1565 STAT3 inhibitors and 1671 non-inhibitors used for training, testing, and evaluation of models. A number of machine learning classifiers have been implemented to develop the models.

Results

The outcomes of the data analysis show that rings and aromatic groups are significantly abundant in STAT3 inhibitors compared to non-inhibitors. First, we developed models using 2-D and 3-D chemical descriptors and achieved a maximum AUC of 0.84 and 0.73, respectively. Second, fingerprints are used to build predictive models and achieved 0.86 AUC with an accuracy of 78.70% on the validation dataset. Finally, models were developed using hybrid descriptors, which achieved a maximum of 0.87 AUC with 78.55% accuracy on the validation dataset.

Conclusion

We used the best model to identify STAT3 inhibitors in FDA-approved drugs and found few drugs (e.g., Tamoxifen and Perindopril) to manage the cytokine storm in COVID-19 patients. A webserver “STAT3In” (https://webs.iiitd.edu.in/raghava/stat3in/) has been developed to predict and design STAT3 inhibitors.

ChAlPred: A web server for prediction of allergenicity of chemical compounds

BACKGROUND

Allergy is the abrupt reaction of the immune system that may occur after the exposure to allergens such as proteins, peptides, or chemicals. In the past, various methods have been generated for predicting allergenicity of proteins and peptides. In contrast, there is no method that can predict allergenic potential of chemicals. In this paper, we described a method ChAlPred developed for predicting chemical allergens as well as for designing chemical analogs with desired allergenicity.

METHOD

In this study, we have used 403 allergenic and 1074 non-allergenic chemical compounds obtained from IEDB database. The PaDEL software was used to compute the molecular descriptors of the chemical compounds to develop different prediction models. All the models were trained and tested on the 80% training data and evaluated on the 20% validation data using the 2D, 3D and FP descriptors.

RESULTS

In this study, we have developed different prediction models using several machine learning approaches. It was observed that the Random Forest based model developed using hybrid descriptors performed the best, and achieved the maximum accuracy of 83.39% and AUC of 0.93 on validation dataset. The fingerprint analysis of the dataset indicates that certain chemical fingerprints are more abundant in allergens that include PubChemFP129 and GraphFP1014. We have also predicted allergenicity potential of FDA-approved drugs using our best model and identified the drugs causing allergic symptoms (e.g., Cefuroxime, Spironolactone, Tioconazole). Our results agreed with allergenicity of these drugs reported in literature.

CONCLUSIONS

To aid the research community, we developed a smart-device compatible web server ChAlPred (https://webs.iiitd.edu.in/raghava/chalpred/) that allows to predict and design the chemicals with allergenic properties.

Computer-aided prediction and design of IL-6 inducing peptides: IL-6 plays a crucial role in COVID-19

Interleukin 6 (IL-6) is a pro-inflammatory cytokine that stimulates acute phase responses, hematopoiesis and specific immune reactions. Recently, it was found that the IL-6 plays a vital role in the progression of COVID-19, which is responsible for the high mortality rate. In order to facilitate the scientific community to fight against COVID-19, we have developed a method for predicting IL-6 inducing peptides/epitopes. The models were trained and tested on experimentally validated 365 IL-6 inducing and 2991 non-inducing peptides extracted from the immune epitope database. Initially, 9149 features of each peptide were computed using Pfeature, which were reduced to 186 features using the SVC-L1 technique. These features were ranked based on their classification ability, and the top 10 features were used for developing prediction models. A wide range of machine learning techniques has been deployed to develop models. Random Forest-based model achieves a maximum AUROC of 0.84 and 0.83 on training and independent validation dataset, respectively. We have also identified IL-6 inducing peptides in different proteins of SARS-CoV-2, using our best models to design vaccine against COVID-19. A web server named as IL-6Pred and a standalone package has been developed for predicting, designing and screening of IL-6 inducing peptides (https://webs.iiitd.edu.in/raghava/il6pred/).

AlgPred 2.0: an improved method for predicting allergenic proteins and mapping of IgE epitopes

AlgPred 2.0 is a web server developed for predicting allergenic proteins and allergenic regions in a protein. It is an updated version of AlgPred developed in 2006. The dataset used for training, testing and validation consists of 10 075 allergens and 10 075 non-allergens. In addition, 10 451 experimentally validated immunoglobulin E (IgE) epitopes were used to identify antigenic regions in a protein. All models were trained on 80% of data called training dataset, and the performance of models was evaluated using 5-fold cross-validation technique. The performance of the final model trained on the training dataset was evaluated on 20% of data called validation dataset; no two proteins in any two sets have more than 40% similarity. First, a Basic Local Alignment Search Tool (BLAST) search has been performed against the dataset, and allergens were predicted based on the level of similarity with known allergens. Second, IgE epitopes obtained from the IEDB database were searched in the dataset to predict allergens based on their presence in a protein. Third, motif-based approaches like multiple EM for motif elicitation/motif alignment and search tool have been used to predict allergens. Fourth, allergen prediction models have been developed using a wide range of machine learning techniques. Finally, the ensemble approach has been used for predicting allergenic protein by combining prediction scores of different approaches. Our best model achieved maximum performance in terms of area under receiver operating characteristic curve 0.98 with Matthew's correlation coefficient 0.85 on the validation dataset. A web server AlgPred 2.0 has been developed that allows the prediction of allergens, mapping of IgE epitope, motif search and BLAST search (https://webs.iiitd.edu.in/raghava/algpred2/).

Computing Skin Cutaneous Melanoma Outcome From the HLA-Alleles and Clinical Characteristics

Human leukocyte antigen (HLA) are essential components of the immune system that stimulate immune cells to provide protection and defense against cancer. Thousands of HLA alleles have been reported in the literature, but only a specific set of HLA alleles are present in an individual. The capability of the immune system to recognize cancer-associated mutations depends on the presence of a particular set of alleles, which elicit an immune response to fight against cancer. Therefore, the occurrence of specific HLA alleles affects the survival outcome of cancer patients. In the current study, prediction models were developed, using 401 cutaneous melanoma patients, to predict the overall survival (OS) of patients using their clinical data and HLA alleles. We observed that the presence of certain favorable superalleles like HLA-B∗55 (HR = 0.15, 95% CI 0.034-0.67), HLA-A∗01 (HR = 0.5, 95% CI 0.3-0.8), is responsible for the improved OS. In contrast, the presence of certain unfavorable superalleles such as HLA-B∗50 (HR = 2.76, 95% CI 1.284-5.941), HLA-DRB1∗12 (HR = 3.44, 95% CI 1.64-7.2) is responsible for the poor survival. We developed prediction models using key 14 HLA superalleles, demographic, and clinical characteristics for predicting high-risk cutaneous melanoma patients and achieved HR = 4.52 (95% CI 3.088-6.609, p-value = 8.01E-15). Eventually, we also provide a web-based service to the community for predicting the risk status in cutaneous melanoma patients (https://webs.iiitd.edu.in/raghava/skcmhrp/).

SAMbinder: A Web Server for Predicting S-Adenosyl-L-Methionine Binding Residues of a Protein From Its Amino Acid Sequence

MOTIVATION

S-adenosyl-L-methionine (SAM) is an essential cofactor present in the biological system and plays a key role in many diseases. There is a need to develop a method for predicting SAM binding sites in a protein for designing drugs against SAM associated disease. To the best of our knowledge, there is no method that can predict the binding site of SAM in a given protein sequence.

RESULT

This manuscript describes a method SAMbinder, developed for predicting SAM interacting residue in a protein from its primary sequence. All models were trained, tested, and evaluated on 145 SAM binding protein chains where no two chains have more than 40% sequence similarity. Firstly, models were developed using different machine learning techniques on a balanced data set containing 2,188 SAM interacting and an equal number of non-interacting residues. Our random forest based model developed using binary profile feature got maximum Matthews Correlation Coefficient (MCC) 0.42 with area under receiver operating characteristics (AUROC) 0.79 on the validation data set. The performance of our models improved significantly from MCC 0.42 to 0.61, when evolutionary information in the form of the position-specific scoring matrix (PSSM) profile is used as a feature. We also developed models on a realistic data set containing 2,188 SAM interacting and 40,029 non-interacting residues and got maximum MCC 0.61 with AUROC of 0.89. In order to evaluate the performance of our models, we used internal as well as external cross-validation technique.

AVAILABILITY AND IMPLEMENTATION

https://webs.iiitd.edu.in/raghava/sambinder/.

NAGbinder: An approach for identifying N-acetylglucosamine interacting residues of a protein from its primary sequence

N-acetylglucosamine (NAG) belongs to the eight essential saccharides that are required to maintain the optimal health and precise functioning of systems ranging from bacteria to human. In the present study, we have developed a method, NAGbinder, which predicts the NAG-interacting residues in a protein from its primary sequence information. We extracted 231 NAG-interacting nonredundant protein chains from Protein Data Bank, where no two sequences share more than 40% sequence identity. All prediction models were trained, validated, and evaluated on these 231 protein chains. At first, prediction models were developed on balanced data consisting of 1,335 NAG-interacting and noninteracting residues, using various window size. The model developed by implementing Random Forest using binary profiles as the main principle for identifying NAG-interacting residue with window size 9, performed best among other models. It achieved highest Matthews Correlation Coefficient (MCC) of 0.31 and 0.25, and Area Under Receiver Operating Curve (AUROC) of 0.73 and 0.70 on training and validation data set, respectively. We also developed prediction models on realistic data set (1,335 NAG-interacting and 47,198 noninteracting residues) using the same principle, where the model achieved MCC of 0.26 and 0.27, and AUROC of 0.70 and 0.71, on training and validation data set, respectively. The success of our method can be appraised by the fact that, if a sequence of 1,000 amino acids is analyzed with our approach, 10 residues will be predicted as NAG-interacting, out of which five are correct. Best models were incorporated in the standalone version and in the webserver available at https://webs.iiitd.edu.in/raghava/nagbinder/.