Biology subjects

Raghava, G. P. S.

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

At least 73 records · Page 4Linked to original sources

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

Sigma70Pred: A highly accurate method for predicting sigma70 promoter in prokaryotic genome

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 1400 non-promoters. We have generated a wide range of features around 8000 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 selected features. In order to check the robustness of our model we have tested our model on the independent dataset made by using latest version of RegulonDB10.8, which included 1134 sigma70 and 638 non-sigma70 promoters, and able to achieve accuracy of 90.41% with AUROC of 0.95. 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.

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

In silico model for predicting IL-2 inducing peptides in human

Interleukin-2 (IL-2) based immunotherapy has been approved for treating certain types of cancer, as IL-2 plays a crucial role in regulating the immune system. In this study, we developed a method for predicting IL-2-inducing peptides. Our method was trained, tested, and validated on a main dataset containing 6,574 experimentally validated Major histocompatibility complex (MHC) binders, including 3,429 IL-2-inducing and 3,145 non-inducing peptides. A primary analysis of IL-2 inducing and non-inducing peptides revealed that certain residues, such as alanine and leucine, are more abundant in IL-2-inducing peptides. Initially, we developed alignment-based methods, which demonstrated high precision but limited coverage. Subsequently, we developed artificial intelligence-based models, including machine learning (ML), deep learning (DL), and large language models (LLM), to predict IL-2-inducing peptides. Our Extra Tree-based model, developed using dipeptide composition and peptide length, achieved a maximum AUC of 0.82. Finally, we constructed ensemble models that combined artificial intelligence and alignment-based methods. Our best ensemble model, which integrates the Extra Tree-based model with MERCI, achieved the highest AUC of 0.84 and an MCC of 0.51 on the main dataset. One limitation of the main dataset is that both IL-2-inducing and non-inducing peptides are MHC binders. To address this limitation, we created two additional datasets: Alternate Dataset 1, consisting of 3,429 IL-2-inducing peptides and 3,429 non-inducing peptides (MHC non-binders), and Alternate Dataset 2, consisting of 3,429 IL-2-inducing peptides and 3,439 non-inducing peptides (MHC binders + MHC non-binders). Our best ensemble model achieved AUCs of 0.9 and 0.8 with MCCs of 0.61 and 0.44 on Alternate Datasets 1 and 2, respectively. To assist the scientific community, we have integrated the best models from this study into a standalone software and web server, IL2pred, which enables users to predict, scan, and design IL-2-inducing peptides (https://webs.iiitd.edu.in/raghava/il2pred/). HighlightsO_LIDevelopment of alignment-based techniques for predicting IL-2-inducing peptides. C_LIO_LIIdentification of amino acid patterns associated with IL-2 induction. C_LIO_LIImplementation of machine learning, deep learning, and LLM-based models for peptide prediction. C_LIO_LIEnsemble approaches combining alignment-based and AI-driven methods and integration into the webserver. 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

Prediction of pancreatic adenocarcinoma patient risk status using alternative splicing events

In literature, several mRNA, miRNA, lncRNA based biomarkers are identified by genomic analysis to stratify the patients into high and low risk groups of pancreatic adenocarcinoma (PAAD). The identified biomarkers are of limited use in terms of sensitivity and prediction ability. Thus, we aimed to identify the prognostic alternative splicing events and their related mutations in the PAAD. PAAD splicing data of 174 samples (17874 AS events in 6209 genes) and corresponding clinical information was obtained from the SpliceSeq and The Cancer Genome Atlas (TCGA), respectively. Prognostic-index based modeling was used to obtain the best predictive models for the seven AS types. However, model based on multiple spliced events genes (APP; LATS1; MRPL4; LAS1L; STARD10; PHF21A; NMRAL1) outperformed the single event models with a remarkable HR of 9.13 (p-value = 6.42e-10) as well as other existing models. Results from g:Profiler suggest that transcription factors ZF5, ER81, E2F-1/2/3, ER81, Erg, and PEA3 are most related to the prognostic spliced genes. We also identified 565 mutations across 160 spliced genes that have a strong association with the prognostic AS events. The analysis revealed that around 560 of these mutations were not reported before in context to splice event/region. Overall, we conclude that altered AS events may serve as strong indicators for overall survival in pancreatic cancer patients, and novel linkage of the known mutations to the survival-related AS events may provide a new dimension to the advancement of diagnostic and therapeutic interventions in these patients.

bioinformatics↗

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↗

bioRxiv2021

A highly accurate model for screening prostate cancer using propensity index panel of ten genes

Prostate-specific antigen (PSA) is a key biomarker, which is commonly used to screen patients of prostate cancer. There is a significant number of unnecessary biopsies that are performed every year, due to poor accuracy of PSA based biomarker. In this study, we identified alternate biomarkers based on gene expression that can be used to screen prostate cancer with high accuracy. All models were trained and test on gene expression profile of 500 prostate cancer and 51 normal samples. Numerous feature selection techniques have been used to identify potential biomarkers. These biomarkers have been used to develop various models using different machine learning techniques for predicting samples of prostate cancer. Our logistic regression-based model achieved highest AUROC 0.91 with accuracy 82.42% on validation dataset. We introduced a new approach called propensity index, where expression of gene is converted into propensity. Our propensitybased approach improved the performance of classification models significantly and achieved AUROC 0.99 with accuracy 96.36% on validation dataset. We also identified and ranked selected genes which can be used to discriminate prostate cancer patients from health individuals with high accuracy. It was observed that single gene-based biomarkers can only achieve accuracy around 90%. In this study, we got best performance using a panel of 10 genes; random forest model using propensity index. HighlightsO_LIApplication of Machine learning techniques to identify Biomarkers for PRAD cancer. C_LIO_LIHighly accurate models developed for classifying prostate cancer vs. normal sample. C_LIO_LIIntroducing Propensity index concept for enhancing model performance. C_LIO_LITop 10 genes identified using feature selection techniques. C_LI

bioinformatics↗

bioRxiv2021

Integrative multi-omics approach for stratification of tumor recurrence risk groups of Hepatocellular Carcinoma patients

Postoperative tumor recurrence is one of the major concerns associated with the poor prognosis of HCC patients. There is yet to elucidate a standard surveillance system for HCC recurrence risk owing to complexity of this malignancy. Generation of multi-omics data from patients facilitate the identification of robust signatures for various diseases. Thus, the current study is an attempt to develop the prognostic models employing multi-omics data to significantly (p-value <0.05) stratify the recurrence high-risk (median Recurrence Free Survival time (RFS) =<12 months) and low-risk groups (median RFS >12 months). First, we identified key 90RNA, 50miRNA and 50 methylation features and developed prognostic models; attained reasonable performance (C-Index >0.70, HR >2.5), on training and validation datasets. Subsequently, we developed a prognostic (PI) model by integrating the four multi-omics features (SUZ12, hsa-mir-3936, cg18465072, and cg22852503), that are biologically inter-linked with each other. This model achieved reasonable performance on training and validation dataset, i.e. C-Index 0.72, HR of 2.37 (1.61 - 3.50), p-value of 6.72E-06, Brier score 0.19 on training dataset, and C-Index 0.72 (95% CI: 0.63 - 0.80), HR of 2.37 (95% CI: 1.61 - 3.50), p-value of 0.015, Brier score 0.19 on validation dataset. Eventually, Drugbank data was investigated to elucidate therapeutic potential of these signatures. We have identified nine potential drugs against three genes (CA9, IL1A, KCNJ15) that are positively correlated with the tumor recurrence. We anticipate these results from our study will help researchers and clinicians to improve the HCC recurrence surveillance, eventually outcome of patients.

bioinformatics↗

bioRxiv2020

Prognostic Biomarkers for Predicting Papillary Thyroid Carcinoma Patients at High Risk Using Nine Genes of Apoptotic Pathway

ObjectivesAberrant expression of apoptotic genes has been associated with papillary thyroid carcinoma (PTC) in the past, however, their prognostic role and utility as biomarkers remains poorly understood. Materials and methodsIn this study, we analysed 505 PTC patients by employing Cox-PH regression techniques, prognostic index models and machine learning methods to elucidate the relationship between overall survival (OS) of PTC patients and 165 apoptosis related genes. ResultsIt was observed that nine genes (ANXA1, TGFBR3, CLU, PSEN1, TNFRSF12A, GPX4, TIMP3, LEF1, BNIP3L) showed significant association with OS of PTC patients. Five out of nine genes were found to be positively correlated with OS of the patients, while the remaining four genes were negatively correlated. These genes were used for developing risk prediction models. Our voting-based model achieved highest performance (HR=41.59, p=3.36x10-4, C=0.84, logrank-p=3.8x10-8). The performance of voting-based model improved significantly when we used the age of patients with prognostic biomarker genes and achieved HR=57.04 with p=10-4 (C=0.88, logrank-p=1.44x10-9). We also developed classification models that can classify high risk patients (survival [≤] 6 years) and low risk patients (survival > 6 years). Our best model achieved AUROC of 0.92. Since these genes can also be used as potential therapeutic targets in PTC, we identified potential drug molecules which could modulate their expression profile. ConclusionThis study briefly revealed the key prognostic biomarker genes in the apoptotic pathway whose altered expression is associated with PTC progression and aggressiveness. In addition to this, risk assessment models proposed here can help in efficient management of PTC patients.

bioinformatics↗