Biology subjects

Raghava, G. P. S.

Publications and source records attributed to Raghava, G. P. S..

At least 55 records · Page 3Linked to original sources

bioRxiv2023

A Deep Learning method for classification of HNSCC and HPV patients using single-cell transcriptomics

Head and Neck Squamous Cell Carcinoma (HNSCC) is the seventh most highly prevalent cancer type worldwide. Early detection of HNSCC is one of the important challenges in managing the treatment of the cancer patients. Existing techniques for detecting HNSCC are costly, expensive, and invasive in nature. In this study, we aimed to address this issue by developing classification models using machine learning and deep learning techniques, focusing on single-cell transcriptomics to distinguish between HNSCC and normal samples. Additionally, we built models to classify HNSCC samples into HPV-positive (HPV+) and HPV-negative (HPV-) categories. The models developed in this study have been trained on 80% of the GSE181919 dataset and validated on the remaining 20%. To develop an efficient model, we performed feature selection using mRMR method to shortlist a small number of genes from a plethora of genes. Artificial Neural Network based model trained on 100 genes outperformed the other classifiers with an AUROC of 0.91 for HNSCC classification for the validation set. The same algorithm achieved an AUROC of 0.83 for the classification of HPV+ and HPV-patients on the validation set. We also performed Gene Ontology (GO) enrichment analysis on the 100 shortlisted genes and found that most genes were involved in binding and catalytic activities. To facilitate the scientific community, a software package has been developed in Python which allows users to identify HNSCC in patients along with their HPV status. It is available at https://webs.iiitd.edu.in/raghava/hnscpred/. Key PointsO_LIApplication of single cell transcriptomics in cancer diagnosis C_LIO_LIDevelopment of models for predicting HNSCC patients C_LIO_LIClassification of HPV+ and HPV-HNSCC patients C_LIO_LIIdentification of gene biomarkers from single cell sequencing C_LIO_LIA standalone software package HNSCpred for predicting HNSCC patients C_LI Authors BiographyO_LIAkanksha Jarwal is currently pursuing an M. Tech. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAnjali Dhall is currently pursuing a Ph.D. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAkanksha Arora is currently pursuing a Ph.D. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LISumeet Patiyal is currently pursuing a Ph.D. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAman Srivastava is currently pursuing an M. Tech. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as a Professor and Head of the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI

bioinformatics↗

bioRxiv2023

ToxinPred 3.0: An improved method for predicting the toxicity of peptides

Toxicity emerges as a prominent challenge in the design of therapeutic peptides, causing the failure of numerous peptides during clinical trials. In 2013, our group developed ToxinPred, a computational method that has been extensively adopted by the scientific community for predicting peptide toxicity. In this paper, we propose a refined variant of ToxinPred that showcases improved reliability and accuracy in predicting peptide toxicity. Initially, we used BLAST for alignment-based toxicity prediction, yet coverage was limited. We adopted a motif-based approach with MERCI software to identify unique toxic patterns. Despite specificity gains, sensitivity was compromised. We developed alignment-free methods using machine/deep learning, achieving a balance sensitivity and specificity of prediction. A deep learning model (ANN - LSTM with fixed sequence length) developed using one-hot encoding attained a 0.93 AUROC and 0.71 MCC on independent data. The machine learning model (extra tree) developed using compositional features of peptides achieved 0.95 AUROC and 0.78 MCC. Lastly, we developed hybrid or ensemble methods combining two or more models to enhance performance. Hybrid approaches, including motif-based and machine learning, achieved a 0.98 AUROC and 0.81 MCC. Evaluation on independent data demonstrated our methods superiority. To cater to the needs of the scientific community, we have developed a standalone software, pip package and web-based server ToxinPred3 (https://github.com/raghavagps/toxinpred3 and https://webs.iiitd.edu.in/raghava/toxinpred3/). Authors BiographyO_LIAnand Singh Rathore is currently pursuing a Ph.D. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAkanksha Arora is currently pursuing a Ph.D. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIShubham Choudhury is currently pursuing a Ph.D. in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIPurava Tijare is a Project Fellow in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as a Professor and Head of the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI HighlightsO_LIImplementation of alignment or similarly based techniques for predicting toxic peptides. C_LIO_LIDiscovery of toxicity-associated patterns and identification of toxic regions in peptides. C_LIO_LIDevelopment of machine and deep learning-based models for toxicity prediction. C_LIO_LIEnsemble methods that combine alignment-based and alignment-free methods. C_LIO_LIWeb server and standalone software package for screening toxicity in peptides/proteins. C_LI

bioinformatics↗

bioRxiv2023

HLA-DR4Pred2: an improved method for predicting HLA-DRB1*04:01 binders

HLA-DRB1*04:01 is associated with many disease that include sclerosis, arthritis, diabetes and Covid19. Thus, it is important to scan binders of HLA-DRB1*04:01 in an antigen to develop immunotherapy, vaccine and protection against these diseases. One of the major limitations of existing methods for predicting with HLA-DRB1*04:01 binders is that these methods trained on small datasets. This study present a method HLA-DR4Pred2 developed on a large dataset contain 12676 binders and equal number of non-binders. It is an improved version of HLA-DR4Pred, which was trained on a small dataset contain only 576 binders and equal number of binders. All models in this study were trained, optimized and tested on 80% of data called training datasets using five-fold cross-validation; final models were evaluated on 20% of data called validation/independent dataset. A wide range of machine learning techniques have been employed to develop prediction models and achieved maximum AUC of 0.90 and 0.87 on validation dataset using composition and binary profile features respectively. The performance of our composition based model increased from 0.90 to 0.93 when combined with BLAST search. In addition, we also developed our models on alternate or realistic dataset that contain 12676 binders and 86300 non-binders and achieved maximum AUC 0.99. Our method perform better than existing methods when we compare the performance of our best model with performance of existing methods on validation dataset. Finally, we developed standalone and online version of HLA-DR4Pred2 for predicting, designing and virtual scanning of HLA- DRB1*04:01(https://webs.iiitd.edu.in/raghava/hladr4pred2/; https://github.com/raghavagps/hladr4pred2). Key PointsO_LIHLADR4Pred2.0 is an update of HLADR4Pred C_LIO_LIPredict the binding or non-binding peptides for MHC-Class II allele HLA- DRB1*04:01 C_LIO_LIUsed alignment free and alignment based hybrid approach C_LIO_LIMotifs which are highly specific to HLA-DRB1*04:01 binders C_LIO_LIBenchmark the performance of the other existing methods with HLADR4Pred2.0 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_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_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↗

bioRxiv2023

AntiBP3: A hybrid method for predicting antibacterial peptides against gram-positive/negative/variable bacteria

This study focuses on the development of in silico models for predicting antibacterial peptides as a potential solution for combating antibiotic-resistant strains of bacteria. Existing methods for predicting antibacterial peptides are mostly designed to target either gram-positive or gram-negative bacteria. In this study, we introduce a novel approach that enables the prediction of antibacterial peptides against several bacterial groups, including gram-positive, gram-negative, and gram-variable bacteria. Firstly, we developed an alignment-based approach using BLAST to identify antibacterial peptides and achieved poor sensitivity. Secondly, we employed a motif-based approach to predict antibacterial peptides and obtained high precision with low sensitivity. To address the similarity issue, we developed machine learning-based models using a variety of compositional and binary features. Our machine learning-based model developed using the amino acid binary profile of terminal residues achieved maximum AUC 0.93, 0.98 and 0.94 for gram-positive, gram-negative, and gram-variable bacteria, respectively, when evaluated on a validation/independent dataset. Our attempts to develop hybrid or ensemble methods by merging machine learning models with similarity and motif-based techniques did not yield any improvements. To ensure robust evaluation, we employed standard techniques such as five-fold cross-validation, internal validation, and external validation. Our method performs better than existing methods when we compare our method with existing approaches on an independent dataset. In summary, this study makes significant contributions to the field of antibacterial peptide prediction by providing a comprehensive set of methods tailored to different bacterial groups. As part of our contribution, we have developed the AntiBP3 web server and standalone package, which will assist researchers in the discovery of novel antibacterial peptides for combating bacterial infections (https://webs.iiitd.edu.in/raghava/antibp3/). Key Points BLAST-based similarity for annotating antibacterial peptides. Machine learning-based models developed using composition and binary profiles. Identification and mapping of motifs exclusively found in antibacterial peptides Improved version of AntiBP and AntiBP2 for predicting antibacterial peptides. Web server for predicting/designing/scanning antibacterial peptides for all groups of bacteria Authors BiographyO_LINisha Bajiya 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_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↗

bioRxiv2023

Prediction of Alzheimer's Disease from Single Cell Transcriptomics Using Deep Learning

Alzheimers disease (AD) is a progressive neurological disorder characterized by brain cell death, brain atrophy, and cognitive decline. Early diagnosis of AD remains a significant challenge in effectively managing this debilitating disease. In this study, we aimed to harness the potential of single-cell transcriptomics data from 12 Alzheimers patients and 9 normal controls (NC) to develop a predictive model for identifying AD patients. The dataset comprised gene expression profiles of 33,538 genes across 169,469 cells, with 90,713 cells belonging to AD patients and 78,783 cells belonging to NC individuals. Employing machine learning and deep learning techniques, we developed prediction models. Initially, we performed data processing to identify genes expressed in most cells. These genes were then ranked based on their ability to classify AD and NC groups. Subsequently, two sets of genes, consisting of 35 and 100 genes, respectively, were used to develop machine learning-based models. Although these models demonstrated high performance on the training dataset, their performance on the validation/independent dataset was notably poor, indicating potential overoptimization. To address this challenge, we developed a deep learning method utilizing dropout regularization technique. Our deep learning approach achieved an AUC of 0.75 and 0.84 on the validation dataset using the sets of 35 and 100 genes, respectively. Furthermore, we conducted gene ontology enrichment analysis on the selected genes to elucidate their biological roles and gain insights into the underlying mechanisms of Alzheimers disease. While this study presents a prototype method for predicting AD using single-cell genomics data, it is important to note that the limited size of the dataset represents a major limitation. To facilitate the scientific community, we have created a website to provide with code and service. It is freely available at https://webs.iiitd.edu.in/raghava/alzscpred. Key PointsO_LIPredictive Model for Alzheimers Disease Using Single Cell Transcriptomics Data C_LIO_LIOveroptimization of models trained on single-cell genomics data. C_LIO_LIApplication of dropout regularization technique of ANN for reducing overoptimization C_LIO_LIRanking of genes based on their ability to predict patients Alzheimers Disease C_LIO_LIStandalone software package for predicting Alzheimers Disease C_LI Authors BiographyO_LIAman Srivastava is pursuing M. Tech. 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_LIAkanksha Arora is currently working as Ph.D. in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIAkanksha Jarwal is pursuing M. Tech. 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↗

bioRxiv2023

Prediction of peptide hormones using an ensemble of machine learning and similarity-based methods

Peptide hormones are genome-encoded signal transduction molecules released in multicellular organisms. The dysregulation of hormone release can cause multiple health problems and it is crucial to study these hormones for therapeutic purposes. To help the research community working in this field, we developed a prediction server that classifies hormonal peptides and non-hormonal peptides. The dataset used in this study was collected for both plants and animals from Hmrbase2 and PeptideAtlas databases. It comprises non-redundant 1174 hormonal and 1174 non-hormonal peptide sequences which were combined and divided into 80% training and 20% validation sets. We extracted a wide variety of compositional features from these sequences to develop various Machine Learning (ML) and Deep Learning (DL) models. The best performing model was logistic regression model trained on top 50 features which achieved an AUROC of 0.93. To enhance the performance of ML model, we applied Basic Local Alignment Search Tool (BLAST) to identify hormonal sequences using similarity among them, and motif search using Motif-Emerging and Classes-Identification (MERCI) to detect motifs present in hormonal and non-hormonal sequences. We combined our best performing classification model, i.e., logistic regression model with BLAST and MERCI to form a hybrid model that can predict hormonal peptide sequences accurately. The hybrid model is able to achieve an AUROC of 0.96, an accuracy of 89.79%, and an MCC of 0.8 on the validation set. This hybrid model has been incorporated on the publicly available website of HOPPred at https://webs.iiitd.edu.in/raghava/hoppred/.

bioinformatics↗

bioRxiv2023

Hmrbase2: A comprehensive database of hormones and their receptors

Background and objectiveHormones are essential for cell communication and hence regulate various physiological processes. The discrepancies in the hormones or their receptors can break this communication and cause major endocrinological disorders. It is, therefore, indispensable for the therapeutics and diagnostics of hormonal diseases. MethodsWe collected widespread information on peptide and non-peptide hormones and hormone receptors. The information was collected from HMDB, UniProt, HORDB, ENDONET, PubChem and literature. ResultsHmrbase2 is an updated version of Hmrbase. The current version contains a total of 12056 entries which is more than twice the entries in the previous version. These include 7406, 753, and 3897 entries for peptide hormones, non-peptide hormones and hormone receptors, respectively, from 803 organisms compared to the 562 organisms in the previous version. The database also hosts 5662 hormone receptor pairs. The source organism, function, and subcellular location are provided for peptide hormones and receptors and properties like melting point; water solubility is provided for non-peptide hormones. Besides browsing and keyword search, an advanced search option has also been provided. Additionally, a similarity search module has been incorporated, enabling users to run similarity searches against peptide hormone sequences using BLAST and Smith-Waterman. ConclusionsTo make the database accessible to various users, we designed a user-friendly, responsive website that can be easily used on smartphones, tablets, and desktop computers. The updated database version, Hmrbase2, offers improved data content compared to the previous version. Homebase 2.0 is freely available at https://webs.iiitd.edu.in/raghava/hmrbase2.

bioinformatics↗

bioRxiv2023

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

A host-specific technique has been developed for annotating interferon-gamma (IFN-{gamma}) inducing peptides, it is an updated version of IFNepitope. In this study, dataset used for developing prediction method contain experimentally validated 25492 and 7983 IFN-{gamma} 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. 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. In order 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 and achieved 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-{gamma} inducing peptides, thus server/software have been developed (https://webs.iiitd.edu.in/raghava/ifnepitope2/). HighlightsO_LIAn updated method for predicting interferon-gamma (IFN-{gamma}) inducing peptides. C_LIO_LIA wide range of features have been generated using Pfeature tool. C_LIO_LIModels were trained and tested on experimentally validated datasets. C_LIO_LIHybrid models developed by combining machine-learning and BLAST. C_LIO_LIIFNepitope2 server is available to design subunit or peptide-based vaccines. C_LI

bioinformatics↗

bioRxiv2023

A random forest model for predicting exosomal proteins using evolutionary information and motifs

Identification of secretory proteins in body fluids is one of the key challenges in the development of non-invasive diagnostics. It has been shown in the part that a significant number of proteins are secreted by cells via exosomes called exosomal proteins. In this study, an attempt has been made to build a model that can predict exosomal proteins with high precision. All models are trained, tested, and evaluated on a non-redundant dataset comprising 2831 exosomal and 2831 non-exosomal proteins, where no two proteins have more than 40% similarity. Initially, the standard similarity-based method BLAST was used to predict exosomal proteins, which failed due to low-level similarity in the dataset. To overcome this challenge, machine learning based models have been developed using compositional features of proteins and achieved highest AUROC of 0.70. The performance of the ML-based models improved significantly to AUROC of 0.73 when evolutionary information in the form of PSSM profiles was used for building models. Our analysis indicates that exosomal proteins have wide range of motifs. In addition, it was observed that exosomal proteins contain different types of sequence-based motifs, which can be used for predicting exosomal proteins. Finally, a hybrid method has been developed that combines a motif-based approach and an ML-based model for predicting exosomal proteins, achieving a maximum AUROC 0.85 and MCC of 0.56 on an independent dataset. The hybrid model in this study performs better than the presently available methods when assessed on an independent dataset. A web server and a standalone software ExoProPred has been created for the scientific community to provide service, code, and data. (https://webs.iiitd.edu.in/raghava/exopropred/). KeypointsO_LIExosomal proteins or non-classical secretory proteins are secreted by via exosomes C_LIO_LIA method has been developed for predicting exosomal proteins C_LIO_LIModels have been trained, tested, and evaluated on non-redundant dataset C_LIO_LIWide range of sequence motifs have been discovered in exosomal proteins C_LIO_LIA web server and standalone software have been developed C_LI

bioinformatics↗

bioRxiv2023

A method for predicting linear and conformational B-cell epitopes in an antigen from its primary sequence

B-cell is an essential component of the immune system that plays a vital role in providing the immune response against any pathogenic infection by producing antibodies. Existing methods either predict linear or conformational B-cell epitopes in an antigen. In this study, a single method was developed for predicting both types (linear/conformational) of B-cell epitopes. The dataset used in this study contains 3875 B-cell epitopes and 3996 non-B-cell epitopes, where B-cell epitopes consist of both linear and conformational B-cell epitopes. Our primary analysis indicates that certain residues (like Asp, Glu, Lys, Asn) are more prominent in B-cell epitopes. We developed machine-learning based methods using different types of sequence composition and achieved the highest AUC of 0.80 using dipeptide composition. In addition, models were developed on selected features, but no further improvement was observed. Our similarity-based method implemented using BLAST shows a high probability of correct prediction with poor sensitivity. Finally, we came up with a hybrid model that combine alignment free (dipeptide based random forest model) and alignment-based (BLAST based similarity) model. Our hybrid model attained maximum AUC 0.83 with MCC 0.49 on the independent dataset. Our hybrid model performs better than existing methods on an independent dataset used in this study. All models trained and tested on 80% data using cross-validation technique and final model was evaluated on 20% data called independent or validation dataset. A webserver and standalone package named "CLBTope" has been developed for predicting, designing, and scanning B-cell epitopes in an antigen sequence (https://webs.iiitd.edu.in/raghava/clbtope/).

bioinformatics↗

bioRxiv2023

A hybrid approach for predicting multi-label subcellular localization of mRNA at genome scale

In the past, number of methods have been developed for predicting single label subcellular localization of mRNA in a cell. Only limited methods had been built to predict multi-label subcellular localization of mRNA. Most of the existing methods are slow and cannot be implemented at transcriptome scale. In this study, a fast and reliable method had been developed for predicting multi-label subcellular localization of mRNA that can be implemented at genome scale. Firstly, deep learning method based on convolutional neural network method have been developed using one-hot encoding and attained an average AUROC - 0.584 (0.543 - 0.605). Secondly, machine learning based methods have been developed using mRNA sequence composition, our XGBoost classifier achieved an average AUROC - 0.709 (0.668 - 0.732). In addition to alignment free methods, we also developed alignment-based methods using similarity and motif search techniques. Finally, a hybrid technique has been developed that combine XGBoost models and motif-based searching and achieved an average AUROC 0.742 (0.708 - 0.816). Our method - MRSLpred, developed in this study is complementary to the existing method. One of the major advantages of our method over existing methods is its speed, it can scan all mRNA of a transcriptome in few hours. A publicly accessible webserver and a standalone tool has been developed to facilitate researchers (Webserver: https://webs.iiitd.edu.in/raghava/mrslpred/). Key PointsO_LIPrediction of Subcellular localization of mRNA C_LIO_LIClassification of mRNA based on Motif and BLAST search C_LIO_LICombination of alignment based and alignment free techniques C_LIO_LIA fast method for subcellular localization of mRNA C_LIO_LIA web server and standalone software C_LI

bioinformatics↗

bioRxiv2022

Prediction and scanning of IL-5 inducing peptides using alignment-free and alignment-based method

Interleukin-5 (IL-5) is the key cytokine produced by T-helper, eosinophils, mast and basophils cells. It can act as an enticing therapeutic target due to its pivotal role in several eosinophil-mediated diseases. Though numerous methods have been developed to predict HLA binders and cytokines-inducing peptides, no method was developed for predicting IL-5 inducing peptides. All models in this study have been trained, tested and validated on experimentally validated 1907 IL-5 inducing and 7759 non-IL-5 inducing peptides obtained from IEDB. First, alignment-based methods have been developed using similarity and motif search. These alignment-based methods provide high precision but poor coverage. In order to overcome this limitation, we developed machine learning-based models for predicting IL-5 inducing peptides using a wide range of peptide features. Our random-forest model developed using selected 250 dipeptides achieved the highest performance among alignment-free methods with AUC 0.75 and MCC 0.29 on validation dataset. In order to improve the performance, we developed an ensemble or hybrid method that combined alignment-based and alignment-free methods. Our hybrid method achieved AUC 0.94 with MCC 0.60 on validation/ independent dataset. The best model developed in this study has been incorporated in the web server IL5pred (https://webs.iiitd.edu.in/raghava/il5pred/). Key PointsO_LIIL-5 is a regulatory cytokine that plays a vital role in eosinophil-mediated diseases C_LIO_LIBLAST-based similarity search against IL-5 inducing peptides was employed C_LIO_LIA hybrid approach combines alignment-based and alignment-free methods C_LIO_LIAlignment-free models are based on machine learning techniques C_LIO_LIA web server IL5pred and its standalone software have been developed C_LI Authors BiographyO_LIDr. Naorem Leimarembi Devi is currently working as a DBT-Research Associate in Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LINeelam Sharma is pursuing her Ph.D. in Computational Biology from the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIProf. G.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

Risk assessment of cancer patients based on HLA-I alleles, neobinders and expression of cytokines

Advancements in cancer immunotherapy have shown significant outcomes in treating various types of cancers. In order to design effective immunotherapy, it is important to understand immune response of a patient based on its genomic profile. We compute prognostic biomarkers from 8346 cancer patients for twenty types of cancer. These prognostic biomarkers has been computed based on i) presence of 352 human leucocyte antigen class-I (HLA-I), ii) 660959 tumor-specific HLA1 neobinders and iii) expression profile of 153 cytokines. It was observed that survival risk of cancer patients depends on presence of certain type of HLA-I alleles; for example LIHC cancer patients with HLA-A*03:01 are on lower risk. Our analysis indicate that neobinders of HLA-I alleles have high correlation with overall survival of certain type of cancer patients. For example HLA-B*07:02 binders have 0.49 correlation with survival of LUSC and -0.77 with KICH cancer patients. It is clear from above analysis that HLA and their binders have major role in survival of cancer patients suffering from different types of cancer. In addition, we compute prognostic biomarkers for 20 types of cancer based on each type of cytokine expression. Higher expression of few cytokines is survival favourable like IL-2 for BLCA cancer patients whereas IL-5R survival unfavourable for KICH cancer patients. In order to facilitate scientific community we developed a web-based platform CancerHLA1 that maintain raw and analyzed data (https://webs.iiitd.edu.in/raghava/cancerhla1/).

cancer biology↗

bioRxiv2022

Prediction, scanning and designing of TNF-α inducing epitopes for human and mouse

Tumor Necrosis Factor alpha (TNF-) is a pleiotropic pro-inflammatory cytokine that plays a crucial role in controlling signaling pathways within the immune cells. Recent studies reported that the higher expression levels of TNF- is 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- progression in various disease conditions. In the pilot study, we have proposed a host-specific in-silico tool for the prediction, designing and scanning of TNF- inducing epitopes. The prediction models were trained and validated on the experimentally validated TNF- inducing/non-inducing for human and mouse hosts. Firstly, we developed alignment free (machine learning based models using composition of peptides) methods for predicting TNF- inducing peptides and achieved maximum AUROC of 0.79 and 0.74 for human and mouse hosts, respectively. Secondly, alignment based (using BLAST) method has been used for predicting TNF- inducing epitopes. Finally, a hybrid method (combination of alignment free and alignment-based method) has been developed for predicting epitopes. Our hybrid method achieved maximum AUROC of 0.83 and 0.77 on an independent dataset for human and mouse hosts, respectively. We have also identified the potential TNF- inducing peptides in different proteins of HIV-1, HIV-2, SARS-CoV-2 and human insulin. Best models developed in this study has been incorporated in a webserver TNFepitope (https://webs.iiitd.edu.in/raghava/tnfepitope/), standalone package and GitLab (https://gitlab.com/raghavalab/tnfepitope). Key PointsO_LITNF- is a multifunctional pleiotropic pro-inflammatory cytokine. C_LIO_LIAnti-TNF- therapy used as an effective treatment in several autoimmune disorders. C_LIO_LIComposition-based features generated using Pfeature for each peptide sequence. C_LIO_LIAlignment-based and alignment-free models developed. C_LIO_LIPrediction and scanning of TNF- inducing regions in antigens. C_LIO_LITNFepitope is available as a web-server, standalone package and GitLab. C_LI

bioinformatics↗

bioRxiv2022

Prediction of celiac disease associated epitopes and motifs in a protein

Celiac disease (CD) is an autoimmune gastrointestinal disorder which causes immune-mediated enteropathy against gluten. The gluten immunogenic peptides have the potential to trigger immune responses which leads to damage the small intestine. HLA-DQ2 and HLA-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. In addition, prediction of CD associated epitope/peptide is also required for developing antigen-based immunotherapy against celiac disease. In this study, computational tools have been developed to predict CD associated epitopes and motifs. Dataset used in this study for training, testing and evaluation contain experimentally validated CD associated and non-CD associate peptides. 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 which achieve maximum AUROC 0.98. We discovered CD associated 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/). Key PointsO_LICeliac disease is one of the prominent autoimmune diseases C_LIO_LIGluten immunogenic peptides are responsible for celiac disease C_LIO_LIMapping of celiac disease associated epitopes and motifs on a proteins C_LIO_LIIdentification of proline and glutamine rich regions C_LIO_LIA web server and software package for predicting CD associate peptides C_LI Authors BiographyO_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_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_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

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

Penetratin inhibits α-synuclein fibrillation and improves locomotor functions in mice model of Parkinsons disease

Parkinsons disease (PD) is the second most common neurodegenerative disease. The presence of lewy bodies, primarily consisting of -synuclein (-syn) aggregates is one of the common features seen in the substantia nigra region of the brain in PD patients. The disease remains incurable and only symptomatic relief is available. We screened various cell-penetrating peptides and reveal that penetratin is a potent inhibitor of -syn aggregation in-vitro, and significantly improved locomotor coordination in mice models of PD in-vivo. The peptide inhibits -syn aggregation in vitro as well as in yeast, and C.elegans models. We further made a cyclic derivative of penetratin by disulfide coupling of N- and C-terminal cysteine residues. Both penetratin and its cyclized derivative interact with -syn. NMR studies show that both linear as well as cyclic derivative interact at the acidic C-terminal tail of the protein. Similar to penetratin, its cyclic derivative inhibited -syn aggregation in the C.elegans model of Parkinsons disease, and also improved worm motility. Molecular Dynamics studies show that penetratin interacts with -synuclein and prevents its conformational transition from disordered into {beta}-sheet rich structure. The therapeutic efficacy of penetratin was further confirmed in a transgenic mice model of the disease, wherein penetratin treatment over a period of 90 days improved locomotor coordination, and halted disease progression. Overall, the present work provides a potent therapeutic agent that could be further explored in the management of PD.

neuroscience↗