Search bioRxiv⌕ Search

Biology subjects

Dhall, A.

Publications and source records attributed to Dhall, A..

At least 37 records · Page 2Linked to original sources
bioRxiv2022

Identification of Antigenic Regions Responsible for inducing Type 1 diabetes mellitus

There are a number of antigens that induce autoimmune response against {beta}-cells, leading to Type 1 diabetes mellitus (T1DM). Recently several antigen-specific immunotherapies have been developed to treat T1DM. Thus identification of T1DM associated peptides with antigenic regions or epitopes is important for peptide based-therapeutics (e.g., immunotherapeutic). In this study, for the first time an attempt has been made to develop a method for predicting, designing and scanning of T1DM associated peptides with high precision. We analyzed 815 T1DM associated peptides and observed that these peptides are not associated with a specific class of HLA alleles. Thus, HLA binder prediction methods are not suitable for predicting T1DM associated peptides. Firstly, we developed a similarity/alignment based method using BLAST and achieved a high probability of correct hits with poor coverage. Secondly, we developed an alignment free method using machine learning techniques and got maximum AUROC 0.89 using dipeptide composition. Finally, we developed a hybrid method that combines the strength of both alignment free and alignment based methods and achieve maximum AUROC 0.95 with MCC 0.81 on independent dataset. We developed a webserver "DMPPred" and standalone server, for predicting, designing and scanning of T1DM associated peptides (https://webs.iiitd.edu.in/raghava/dmppred/). Key PointsO_LIPrediction of peptides responsible for inducing immune system against {beta}-cells C_LIO_LICompilation and analysis of Type 1 diabetes associated HLA binders C_LIO_LIBLAST based similarity search against Type 1diabetes associated peptides C_LIO_LIAlignment free method using machine learning techniques and composition C_LIO_LIA hybrid method using alignment free and alignment based approach C_LI Authors BiographyO_LINishant Kumar is currently working as Ph.D. in Computational biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LIO_LISumeet Patiyal is currently working as Ph.D. in Computational biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LIO_LIShubham Choudhury is currently working as Ph.D. in Computational biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LIO_LIRitu Tomer is currently working as Ph.D. in Computational biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LIO_LIAnjali Dhall is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as Professor and Head of Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI

bioinformatics↗
bioRxiv2022

A hybrid approach for predicting transcription factors

Transcription factors (TFs) are essential DNA-binding proteins that regulate the rate of transcription of several genes and controls the expression of genes inside a cell. The prediction of TFs with high precision is important for understanding number of biological processes such as cell-differentiation, intracellular signaling, cell-cycle control. In this study, we developed a hybrid method that combine 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 contain 19406 TFs and 523560 non-TFs protein sequences. In order to avoid biasness in evaluation, dataset is divided in training and validation/independent dataset, where 80% data was used for training and remaining 20% for external validation. In case of alignment-free methods, models are developed based on machine learning techniques using compositional features of a protein. Our best alignment-free model obtained AUC 0.97 on independent dataset. In case of alignment-based method, we used BLAST at different cut-off to predict transcription factors. Though alignment-based method shows excellent performance but unable to cover all transcription factor due to no-hits. In order to combine power of both, we developed a hybrid method that combine alignment-free and alignment-based method; achieved maximum AUC of 0.99 on independent dataset. The method proposed in this study perform better than existing methods. We incorporated the best models in the webserver/standalone package "TransFacPred" (https://webs.iiitd.edu.in/raghava/transfacpred). Key PointsO_LITranscription factors (TFs) are vital DNA-binding proteins. C_LIO_LIA hybrid method for the prediction of TFs using sequence information. C_LIO_LIComputer-aided model were developed using machine-learning algorithm to predict TFs. C_LIO_LIAlignment-based and alignment-free approaches were used for the prediction. C_LIO_LIA user-friendly webserver, python- and Perl-based standalone package available. C_LI

bioinformatics↗
bioRxiv2022

Prediction of RNA-interacting residues in a protein using CNN and evolutionary profile

This paper describes a method Pprint2, which is an improved version of Pprint developed for predicting RNA-interacting residues in a protein. Training and validation datasets used in this study comprises of 545 and 161 non-redundant RNA-binding proteins, respectively. All models were trained on training dataset and evaluated on the validation dataset. The preliminary analysis reveals that positively charged amino acids such as H, R, and K, are more prominent in the RNA-interacting residues. Initially, machine learning based models have been developed using binary profile and obtain maximum area under curve (AUC) 0.68 on validation dataset. The performance of this model improved significantly from AUC 0.68 to 0.76 when evolutionary profile is used instead of binary profile. The performance of our evolutionary profile based model improved further from AUC 0.76 to 0.82, when convolutional neural network has been used for developing model. Our final model based on convolutional neural network using evolutionary information achieved AUC 0.82 with MCC of 0.49 on the validation dataset. Our best model outperform existing methods when evaluated on the validation dataset. A user-friendly standalone software and web based server named "Pprint2" has been developed for predicting RNA-interacting residues (https://webs.iiitd.edu.in/raghava/pprint2 and https://github.com/raghavagps/pprint2) Key PointsO_LIMachine learning based models were developed using different profiles C_LIO_LIPSSM profile of a protein was created to extract evolutionary information C_LIO_LIPSSM profiles of proteins were generated using PSI-BLAST C_LIO_LIConvolutional neural network based model was developed using PSSM profile C_LIO_LIWebserver, Python- and Perl-based standalone package, and GitHub is available C_LI Authors BiographyO_LISumeet Patiyal is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAnjali Dhall is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIKhushboo Bajaj is currently working as MTech in Computer Science and Engineering from Department of Computer Science and Engineering, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIHarshita Sahu is currently working as MTech in Computer Science and Engineering from Department of Computer Science and Engineering, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as Professor and Head of Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI

bioinformatics↗
bioRxiv2022

An ensemble method for designing phage-based therapy against bacterial infections

Phage therapy is a viable alternative to antibiotics for treating microbial infections, particularly managing drug-resistant strains of bacteria. One of the major challenges in designing phage based therapy is to identify the most appropriate phage to treat a bacterial infection. In this study, an attempt has been made to predict phage-host interaction with high accuracy to identify the best virus for treating a bacterial infection. All models have been developed on a training dataset containing 826 phage host-interactions, whereas models have been evaluated on a validation dataset comprising 1201 phage-host interactions. Firstly, alignment based models have been developed using similarity between phage-phage (BLASTPhage), host-host (BLASTHost) and phage-CRISPR (CRISPRPred) where we achieved accuracy between 42.4%-66.2% for BLASTPhage, 55%-78.4% for BLASTHost, and 43.7%-80.2% for CRISPRPred at five taxonomic levels. Secondly, alignment free models have been developed using machine learning techniques. Thirdly, hybrid models have been developed by integrating alignment-free models and similarity-score where we achieved maximum performance of (60.6%-93.5%). Finally, an ensemble model has been developed that combines hybrid and alignment based model. Our ensemble model achieved highest accuracy of 67.9%, 80.6%, 85.5%, 90%, 93.5% at Genus, Family, Order, Class and Phylum levels, which is better than existing methods. In order to serve the scientific community we have developed a webserver named PhageTB and standalone software package (https://webs.iiitd.edu.in/raghava/phagetb/). Key PointsO_LIPhage therapy provides an alternative to mange drug resistant strains of bacteria C_LIO_LIPrediction bacterial strains that can be treated by a given phage C_LIO_LIAlignment-based, alignment-free and ensemble models have been developed. C_LIO_LIPrediction of appropriate phage/virus that can lyse a given strain of bacteria. C_LIO_LIWebserver and standalone package provided to predict phage-host interactions. C_LI

bioinformatics↗
bioRxiv2022

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. Virus gradually undergoes host adaptive mutations in their genome and proteins, resulting in different strain s/vari ants which might spread virus from avians/mammals to humans. In this study, we have developed an in-silico models to identify infectious strains of Influenza A virus, which has the potential of getting transmitted to humans, from its whole genome/proteins. Firstly, machine learning based models were developed for predicting infectious strains using composition of 15 proteins of virus. Random Forest based model of protein Hemagglutinin, achieved maximum AUC 0.98 on validation data using dipeptide composition. Secondly, we obtained maximum AUC of 0.99 on validation dataset using one-hot-encoding features of each protein of virus. Thirdly, models build on DNA composition of whole genome of Influenza A, achieved maximum AUC 0.98 on validation dataset. Finally, a web-based service, named "FluSPred"(https://webs.iiitd.edu.in/raghava/fluspred/) has been developed which incorporate best 16 models (15 proteins and one based on genome) for prediction of infectious strains of virus. In addition, we provided standalone software for the prediction and scanning of infectious strains at large-scale (e.g., metagenomics) from genomic/proteomic data. We anticipate this tool will help researchers in prioritize high-risk viral strains of novel influenza virus possesses the capability to spread human to human, thereby being useful for pandemic preparedness and disease surveillance. Key PointsO_LIInfluenza A is a contagious viral disease responsible for four pandemics. C_LIO_LIVirus can cross species barrier and infect human beings. C_LIO_LIIn silico models developed for predicting human infectious strains of virus. C_LIO_LIModels developed were build using 15 proteins and whole genome datasets. C_LIO_LIWebserver and standalone package for predicting and scanning of high-risk viral strains. C_LI

bioinformatics↗
bioRxiv2021

Prediction of 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 prediction of high-risk liver-cancer patients. In the past, number of mutation calling techniques have been developed that include MuTect2, MuSE, Varscan2, and SomaticSniper. In this study, an attempt has been made to benchmark potential of these techniques in predicting prognostic biomarkers for liver cancer. Initially, we extracted somatic mutations in liver-cancer patients using VCF and 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 obtain 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. Finally, univariate survival analysis revealed the prognostic role of highly mutated genes. Based on correlation analysis, we selected 80 genes negatively associated with the overall survival of the liver cancer patients. Single-gene based analysis showed that MuTect2 technique based MAF file has achieved maximum HRLAMC3 9.25 with p-value 1.78E-06. Further, we developed various prediction models using selected genes for each technique, and the results indicate that MuTect2 technique based VCF files outperform all other methods with maximum AUROC of 0.72 and HR 4.50 (p-value 3.83E-15). Eventually, VCF file generated using MuTect2 technique performs better among other mutation calling techniques to explore the prognostic potential of mutations in liver cancer. We hope that our findings will provide a useful and comprehensive comparison of various mutation calling techniques for the prognostic analysis of cancer patients.

bioinformatics↗
bioRxiv2021

Nfeature: A platform for computing features of nucleotide sequences

In the past few decades, public repositories on nucleotides have increased with exponential rates. This pose a major challenge to researchers to predict the structure and function of nucleotide sequences. In order to annotate function of nucleotide sequences it is important to compute features/attributes for predicting function of these sequences using machine learning techniques. In last two decades, several software/platforms have been developed to elicit a wide range of features for nucleotide sequences. In order to complement the existing methods, here we present a platform named Nfeature developed for computing wide range of features of DNA and RNA sequences. It comprises of three major modules namely Composition, Correlation, and Binary profiles. Composition module allow to compute different type of compositions that includes mono-/di-tri-nucleotide composition, reverse complement composition, pseudo composition. Correlation module allow to compute various type of correlations that includes auto-correlation, cross-correlation, pseudo-correlation. Similarly, binary profile is developed for computing binary profile based on nucleotides, mono-nucleotides, di-/tri-nucleotide properties. Nfeature also allow to compute entropy of sequences, repeats in sequences and distribution of nucleotides in sequences. In addition to compute feature in whole sequence, it also allows to compute features from part of sequence like split, start, end, and rest. In a nutshell, Nfeature amalgamates existing features as well as number of novel features like nucleotide repeat index, distance distribution, entropy, binary profile, and properties. This tool computes a total of 29217 and 14385 features for DNA and RNA sequence, respectively. In order to provide, a highly efficient and userfriendly tool, we have developed a standalone package and web-based platform (https://webs.iiitd.edu.in/raghava/nfeature).

bioinformatics↗
bioRxiv2021

HLAncPred: A method for predicting promiscuous non-classical HLA binding sites

In the last two decades, ample of methods have been developed to predict the classical HLA binders in an antigen. In contrast, limited attempts have been made to develop methods for predicting binders for non-classical HLA; due to the scarcity of sufficient experimental data and lack of community interest. Of Note, non-classical HLA plays a crucial immunomodulatory role and regulates various immune responses. Recent studies revealed that non-classical HLA (HLA-E & HLA-G) based immunotherapies have many advantages over classical HLA based-immunotherapy, particularly against COVID-19. In order to facilitate the scientific community, we have developed an artificial intelligence-based method for predicting binders of non-classical HLA alleles (HLA-G and HLA-E). All the models were trained and tested on experimentally validated data obtained from the recent release of IEDB. The machine learning based-models achieved more than 0.98 AUC for HLA-G alleles on validation or independent dataset. Similarly, our models achieved the highest AUC of 0.96 and 0.88 on the validation dataset for HLA-E*01:01, HLA-E*01:03, respectively. We have summarized the models developed in the past for non-classical HLA binders and compared with the models developed in this study. Moreover, we have also predicted the non-classical HLA binders in the spike protein of different variants of virus causing COVID-19 including omicron (B.1.1.529) to facilitate the community. One of the major challenges in the field of immunotherapy is to identify the promiscuous binders or antigenic regions that can bind to a large number of HLA alleles. In order to predict the promiscuous binders for the non-classical HLA alleles, we developed a web server HLAncPred (https://webs.iiitd.edu.in/raghava/hlancpred), and a standalone package. Key PointsO_LINon-classical HLAs play immunomodulatory roles in the immune system. C_LIO_LIHLA-E restricted T-cell therapy may reduce COVID-19 associated cytokine storm. C_LIO_LIIn silico models developed for predicting binders for HLA-G and HLA-E. C_LIO_LIIdentification of non-classical HLA binders in strains of coronavirus C_LIO_LIA webserver for predicting promiscuous binders for non-classical HLA alleles C_LI Authors BiographyO_LIAnjali Dhall is currently working as Ph.D. in Bioinformatics from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LISumeet Patiyal is currently working as Ph.D. in Bioinformatics from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as Professor and Head of Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI

bioinformatics↗
bioRxiv2021

IL13Pred: A method for predicting immunoregulatory cytokine IL-13 inducing peptides for managing COVID-19 severity.

Interleukin 13 (IL-13) is an immunoregulatory cytokine that is primarily released by activated T-helper 2 cells. It induces the pathogenesis of many allergic diseases, such as airway hyperresponsiveness, glycoprotein hypersecretion and goblet cell hyperplasia. IL-13 also inhibits tumor immunosurveillance, which leads to carcinogenesis. In recent studies, elevated IL-13 serum levels have been shown in severe COVID-19 patients. Thus it is important to predict IL-13 inducing peptides or regions in a protein for designing safe protein therapeutics particularly immunotherapeutic. This paper describes a method developed for predicting, designing and scanning IL-13 inducing peptides. The dataset used in this study contain experimentally validated 313 IL-13 inducing peptides and 2908 non-inducing homo-sapiens peptides extracted from the immune epitope database (IEDB). We have extracted 95 key features using SVC-L1 technique from the originally generated 9165 features using Pfeature. Further, these key features were ranked based on their prediction ability, and top 10 features were used for building machine learning prediction models. In this study, we have deployed various machine learning techniques to develop models for predicting IL-13 inducing peptides. These models were trained, test and evaluated using five-fold cross-validation techniques; best model were evaluated on independent dataset. 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 indicate that certain SARS-COV2 variants are more prone to induce IL-13 in COVID-19 patients. A standalone package as well as a web server named IL-13Pred has been developed for predicting IL-13 inducing peptides (https://webs.iiitd.edu.in/raghava/il13pred/). Key PointsO_LIInterleukin-13, an immunoregulatory cytokine plays an important role in increasing severity of COVID-19 and other diseases. C_LIO_LIIL-13Pred is a highly accurate in-silico method developed for predicting the IL-13 inducing peptides/ epitopes. C_LIO_LIIL-13 inducing peptides are reported in various SARS-CoV2 strains/variants proteins. C_LIO_LIThis method can be used to detect IL-13 inducing peptides in vaccine candidates. C_LIO_LIUser friendly web server and standalone software is freely available for IL-13Pred C_LI Authors BiographyO_LIShipra Jain is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAnjali Dhall is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LISumeet Patiyal is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as Professor and Head of Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI

bioinformatics↗
bioRxiv2021

Transcriptomics based prediction of metastasis in TNBC patients: Challenges in cross-platforms validation

Triple-negative breast cancer (TNBC) is more prone to metastasis and recurrence than other breast cancer subtypes. This study aimed to identify genes that can act as diagnostic biomarkers for predicting lymph node metastasis in TNBC patients. The transcriptomic data of TNBC with or without lymph node metastasis was acquired from TCGA, and the differentially expressed genes were identified. Further, logistic-regression method has been used to identify the top 15 genes (or 15 gene signatures) based on their ability to predict metastasis (AUC>0.65). These 15 gene signatures were used to develop machine learning techniques based prediction models; Gaussian Naive Bayes classifier outperformed other with AUC>0.80 on both training and validation datasets. The best model failed drastically on nine independent microarray datasets obtained from GEO. We investigated the reason for the failure of our best model, and it was observed that the certain genes in 15 gene signatures were showing opposite regulating trends, i.e., genes are upregulated in TCGA-TNBC patients while it is downregulated on other microarray datasets or vice-versa. In conclusion, the 15 gene signatures may act as diagnostic markers for the detection of lymph node metastatic status in TCGA dataset, but quite challenging across multiple platforms. We also identified the prognostic potential of the 15 selected genes and found that overexpression of ZNRF2, FRZB, and TCEAL4 was associated with poor survival with HR>2.3 and p-value[≤]0.05. In order to provide services to the scientific community, we developed a webserver named "MTNBCPred" for the prediction of metastatic and non-metastatic lymph node status of TNBC patients (http://webs.iiitd.edu.in/raghava/mtnbcpred/).

bioinformatics↗
bioRxiv2021

DBpred: A deep learning method for the prediction of DNA interacting residues in protein sequences

DNA-protein interaction is one of the most crucial interactions in the biological system, which decide the fate of many processes such as transcription, regulation of gene expression, splicing, and many more. Though many computational approaches exist that can predict the DNA interacting residues from the protein sequences, there is still a significant opportunity for improvement in terms of performance and accessibility. In this study, we have downloaded the benchmark dataset from method hybridNAP and recently published method ProNA2020, for training and validation purposes, that comprise 864 and 308 proteins, respectively. We have implemented CD-HIT software to handle the redundancy with 30% identity, and left with 646 proteins for training and 46 proteins for validation purposes, in which the validation dataset do not share more than 30% of sequence identity with the training dataset. We have generated amino acid binary profiles, physicochemical-properties based binary profiles, PSSM profiles, and a combination of all profiles described as hybrid feature. 1D-CNN based model performed best as compared to other models for each set of features. The model developed using amino acid binary profile achieved AUROC of 0.83 and 0.74 for training and validation dataset. Using physicochemical properties based binary profile, model attained AUROC of 0.86 and 0.73 for training and validation dataset. Model generated using PSSM profile resulted in the better performance with AUROC 0.91 and 0.74 for training and validation dataset. And, model developed using hybrid of all features performed best with AUROC of 0.91, and 0.79 for training and validation dataset, respectively. We have compared our methods performance with the current approach and shown improvements. We have included the best-performing models in the standalone and web server accessible at https://webs.iiitd.edu.in/raghava/dbpred. DBPred is an effective approach to predict the DNA interacting residues in the protein using its primary structure.

bioinformatics↗
bioRxiv2021

Prediction of antibiotic resistant strains of bacteria from their beta-lactamases protein

Number of beta-lactamase variants have ability to deactivate ceftazidime antibiotic, which is the most commonly used antibiotic for treating infection by Gram-negative bacteria. In this study an attempt has been made to develop a method that can predict ceftazidime resistant strains of bacteria from amino acid sequence of beta-lactamases. We obtained beta-lactamases proteins from the {beta}-lactamase database, corresponding to 87 ceftazidime-sensitive and 112 ceftazidime-resistant bacterial strains. All models developed in this study were trained, tested, and evaluated on a dataset of 199 beta-lactamases proteins. We generate 9149 features for beta-lactamases using Pfeature and select relevant features using different algorithms in scikit-learn package. A wide range of machine learning techniques (like KNN, DT, RF, GNB, LR, SVC, XGB) has been used to develop prediction models. Our random forest-based model achieved maximum performance with AUROC of 0.80 on training dataset and 0.79 on the validation dataset. The study also revealed that ceftazidime-resistant beta-lactamases have amino acids with non-polar side chains in abundance. In contrast, ceftazidime-sensitive beta-lactamases have amino acids with polar side chains and charged entities in abundance. Finally, we developed a webserver "ABCRpred", for the scientific community working in the era of antibiotic resistance to predict the antibiotic resistance/susceptibility of beta-lactamase protein sequences. The server is freely available at (http://webs.iiitd.edu.in/raghava/abcrpred/). Key PointsO_LICeftazidime is commonly used to treat infection caused by Gram-negative bacteria. C_LIO_LIBeta-lactamase is responsible for lysing ceftazidime, make it resistant to bacteria. C_LIO_LIComparison of resistant and sensitive variants of beta-lactamase. C_LIO_LIClassification of sensitive and resistant strain of bacteria based on beta-lactamase. C_LIO_LIPrediction models have been developed using different machine learning techniques. C_LI

bioinformatics↗
bioRxiv2021

ProCanBio: a database of manually curated biomarkers for Prostate Cancer

BackgroundProstate Cancer is the second lethal malignancy in men worldwide. In the past, numerous research groups investigated the omics profiles of patients and scrutinized biomarkers for the diagnosis and prognosis of prostate cancer. However, information related to the biomarkers is widely scattered across numerous resources in complex textual format, which poses hindrance to understand the tumorigenesis of this malignancy and scrutinization of robust signature. To the best of authors knowledge, there is no resource that can consolidate the information contained in all the published literature. ResultsHere, we present ProCanBio, a manually curated database that maintains detailed data on 2053 entries of potential prostate cancer biomarkers obtained from 412 publications in user friendly tabular format. Among them, 766 protein-based, 488 RNA-based, 157 genomic mutations, 261 miRNA-based, and 122 are metabolites-based biomarkers. To explore the information in the resource, a web-based interactive platform was developed with searching, and browsing facilities. ProCanBio is freely available and is compatible with most web browsers and devices. Eventually, we anticipated this resource will be highly useful for the research community involved in the area of prostate malignancy. AvailabilityProCanBio is available at: https://webs.iiitd.edu.in/raghava/procanbio/

cancer biology↗
bioRxiv2021

ChAlPred: A Web Server for Prediction of Allergenicity of Chemical Compounds

Allergy is the abrupt reaction of the immune system that may occur after the exposure with allergens like protein/peptide or chemical allergens. In past number of methods of have been developed for classifying the protein/peptide based allergen. To the best of our knowledge, there is no method to classify the allergenicity of chemical compound. Here, we have proposed a method named "ChAlPred", which can be used to fill the gap for predicting the chemical compound that might cause allergy. In this study, we have obtained the dataset of 403 allergen and 1074 non-allergen chemical compounds and used 2D, 3D and FP descriptors to train, test and validate our prediction models. The fingerprint analysis of the dataset indicates that PubChemFP129 and GraphFP1014 are more frequent in the allergenic chemical compounds, whereas KRFP890 is highly present in non-allergenic chemical compounds. Our XGB based model achieved the AUC of 0.89 on validation dataset using 2D descriptors. RF based model has outperformed other classifiers using 3D descriptors (AUC = 0.85), FP descriptors (AUC = 0.92), combined descriptors (AUC = 0.93), and hybrid model (AUC = 0.92) on validation dataset. In addition, we have also reported some FDA-approved drugs like Cefuroxime, Spironolactone, and Tioconazole which can cause the allergic symptoms. A user user-friendly web server named "ChAlPred" has been developed to predict the chemical allergens. It can be easily accessed at https://webs.iiitd.edu.in/raghava/chalpred/.

immunology↗
bioRxiv2019

Computing Skin Cutaneous Melanoma Outcome from the HLA-alleles and Clinical Characteristics

Human Leukocyte Antigen (HLA) is an essential component of the immune system which stimulates immune cells to provide protection and defense against cancer. More than thousands of HLA alleles have been reported in the literature; but, only a specific set of HLA alleles expressed in an individual. Recognition of cancer-associated mutations by the immune system depends on the presence of a particular set of alleles, that elicit an immune response to fight against cancer. It indicates that the occurrence of specific HLA alleles also affects the outcome of the cancer patients. In the current study, prediction models have been developed using 415 skin cutaneous melanoma (SKCM) patients for predicting the overall survival of patients from their HLA-alleles. It has been observed that, the presence of certain superalleles in the patients, is responsible for improved overall survival which were referred as favourable superalleles like HLA-B*55 (HR=0.15, 95% CI 0.034 to 0.67), HLA-A*01 (HR=0.5, 95% CI 0.3 to 0.8). In contrast, presence of certain superalleles in the patients is responsible for their poor survival, those superalleles were referred as unfavourable superalleles such as HLA-B*50 (HR=2.76, 95% CI 1.284 to 5.941), HLA-DRB1*12 (HR=3.44, 95% CI 1.64 to 7.2). We developed prediction models using 14 HLA-superalleles and five clinical characteristics for predicting high-risk SKCM patients and achieve HR=4.52 (95% CI 3.088-6.609) with p-value = 8.01E-15. Lastly, we provide a web-based service to community for predicting the risk in SKCM patients (https://webs.iiitd.edu.in/raghava/skcmhrp/)

bioinformatics↗
bioRxiv2019

GPSRdocker: A Docker-based Resource for Genomics, Proteomics and Systems biology

BackgroundIn past number of web-based resources has been developed in the field of Bioinformatics. These resources are heavily used by scientific community to provide solution for challenges faced by experimental researchers particularly in the field of biomedical sciences. There are number of challenges in utilizing full potential of these services that includes internet speed, limits on computing power, and security of data. In order to enhance utilities of these web-based assets, we developed a docker-based container that integrates large number resources available in literature.\n\nResultsThis paper describes GPSRdocker a docker-based container developed for providing wide-range of computational tools in the field of bioinformatics particularly in genomics, proteomics and system biology. Majority of tools integrated in GPSRdocker are based on web services developed at Raghavas group in last two decades. Broadly, these tools can be categorized in three categories; i) general scripts, ii) supporting software and iii) major standalone software. In order to facilitate students or developers working in the field of bioinformatics, we developed general scripts in Perl and Python. These general-purpose scripts serve as building block for any bioinformatics tools like computing features/descriptors of a protein. Supporting software packages includes SCIKIT, WEKA, SVMlight, and PSI-BLAST; these software packages allow one to develop/implement bioinformatics software. Major Standalone software is core of this container which allows predicting function/class of biomolecules. These tools can be classified broadly in following categories; protein annotation, epitope-based vaccines, prediction of interaction and drug discovery.\n\nConclusionA docker-based container has been developed which can be easily run on any operating system as well as it can be directly ported on cloud. Scripts can be run to build pipelines for addressing problems at system level like prediction of vaccine candidate for a pathogen. GPSRdocker including manual is available free for academic use from https://webs.iiitd.edu.in/gpsrdocker.

bioinformatics↗
bioRxiv2019

Identification of Platform-Independent Diagnostic Biomarker Panel for Hepatocellular Carcinoma using Large-scale Transcriptomics Data

The high mortality rate of hepatocellular carcinoma (HCC) is primarily due to its late diagnosis. In the past numerous attempts have been made to design genetic biomarkers for the identification of HCC; unfortunately, most of the studies are based on a small dataset obtained from a specific platform or lack of their reasonable validation performance on the external datasets. In order to identify a universal expression-based diagnostic biomarker panel for HCC that can be applicable across multiple platforms; we have employed large scale transcriptomic profiling datasets containing a total of 2,306 HCC and 1,655 non-tumorous tissue samples. These samples were obtained from 29 studies generated by mainly four types of profiling techniques include Affymetrix, Illumina, Agilent and High-throughput-seq, which implemented a wide range of platforms. Firstly, we scrutinized 26 genes that are differentially expressed or regulated in uniform pattern among numerous datasets. Subsequently, we identified three genes (FCN3, CLEC1B, & PRC1) panel-based HCC biomarker using different machine learning techniques include Simple-threshold based approach, Extra Trees, Support Vector Machine, Random Forest, K Neighbors Classifier, Logistic Regression etc. Three-genes panel-based HCC biomarker classified HCC samples and non-tumorous samples of training and three external validation datasets with an accuracy between 93 to 98% and AUROC (Area Under Receiver Operating Characteristic curve) in a range of 0.97 to 1.0. Furthermore, the prognostic potential of these genes was evaluated on TCGA cohort and GSE14520 cohort using univariate survival analysis revealed that these genes are independent prognostic indicators for various types of the survivals, i.e. OS (Overall Survival), PFS (Progression-Free Survival), DFS/RFS (Disease-Free Survival/Recurrence-Free Survival) and DSS (Disease-Specific Survival) of HCC patients and significantly stratify high-risk and low-risk HCC patients (p-value <0.05). In conclusion, we identified a universal platform-independent three genes-based biomarker that can predict HCC patients with high precision; also possess significant prognostic potential. Eventually, to provide service to the scientific community, we developed a webserver HCCPred based on the above study (http://webs.iiitd.edu.in/raghava/hccpred/).

bioinformatics↗
bioRxiv2019

Computing wide range of protein/peptide features from their sequence and structure

MotivationIn last three decades, a wide range of protein descriptors/features have been discovered to annotate a protein with high precision. A wide range of features have been integrated in numerous software packages (e.g., PROFEAT, PyBioMed, iFeature, protr, Rcpi, propy) to predict function of a protein. These features are not suitable to predict function of a protein at residue level such as prediction of ligand binding residues, DNA interacting residues, post translational modification etc.\n\nResultsIn order to facilitate scientific community, we have developed a software package that computes more than 50,000 features, important for predicting function of a protein and its residues. It has five major modules for computing; composition-based features, binary profiles, evolutionary information, structure-based features and patterns. The composition-based module allows user to compute; i) simple compositions like amino acid, dipeptide, tripeptide; ii) Properties based compositions; iii) Repeats and distribution of amino acids; iv) Shannon entropy to measure the low complexity regions; iv) Miscellaneous compositions like pseudo amino acid, autocorrelation, conjoint triad, quasi-sequence order. Binary profile of amino acid sequences provides complete information including order of residues or type of residues; specifically, suitable to predict function of a protein at residue level. Pfeature allows one to compute evolutionary information-based features in form of PSSM profile generated using PSIBLAST. Structure based module allows computing structure-based features, specifically suitable to annotate chemically modified peptides/proteins. Pfeature also allows generating overlapping patterns and feature from whole protein or its parts (e.g., N-terminal, C-terminal). In summary, Pfeature comprises of almost all features used till now, for predicting function of a protein/peptide including its residues.\n\nAvailabilityIt is available in form of a web server, named as Pfeature (https://webs.iiitd.edu.in/raghava/pfeature/), as well as python library and standalone package (https://github.com/raghavagps/Pfeature) suitable for Windows, Ubuntu, Fedora, MacOS and Centos based operating system.

bioinformatics↗