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

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

Universal and cross-cancer prognostic biomarkers for predicting survival risk of cancer patients from expression profile of apoptotic pathway genes.

Numerous cancer-specific prognostic models have been developed in the past, wherein one model is applicable for only one type of cancer. In this study, an attempt has been made to identify universal or multi-cancer prognostic biomarkers and develop models for predicting survival risk across different types of cancer patients. In order to accomplish this, we gauged the prognostic role of mRNA expression of 165 apoptosis-related genes across 33 cancers in the context of patient survival. Firstly, we identified specific prognostic biomarker genes for 30 cancers. The cancer-specific prognostic models achieved a minimum Hazard Ratio, HRSKCM = 1.99 and maximum HRTHCA = 41.59. Secondly, a comprehensive analysis was performed to identify universal biomarkers across many cancers. Our best prognostic model consisted of 11 genes (TOP2A, ISG20, CD44, LEF1, CASP2, PSEN1, PTK2, SATB1, SLC20A1, EREG, and CD2) and stratified risk groups across 27 cancers (HROV = 1.53-HRUVM = 11.74). The model was validated on eight independent cancer cohorts and exhibited a comparable performance. Further, we clustered cancer-types on the basis of shared survival related apoptosis genes. This approach proved helpful in development of cross-cancer prognostic models. To show its efficacy, a prognostic model consisting of 15 genes was thereby developed for LGG-KIRC pair (HRKIRC = 3.27, HRLGG = 4.23). Additionally, we predicted potential therapeutic candidates for LGG-KIRC high risk patients.

The landscape of cancer-rewired GPCR signaling axes.

We explored the dysregulation of G-protein-coupled receptor (GPCR) ligand systems in cancer transcriptomics datasets to uncover new therapeutics opportunities in oncology. We derived an interaction network of receptors with ligands and their biosynthetic enzymes. Multiple GPCRs are differentially regulated together with their upstream partners across cancer subtypes and are associated to specific transcriptional programs and to patient survival patterns. The expression of both receptor-ligand (or enzymes) partners improved patient stratification, suggesting a synergistic role for the activation of GPCR networks in modulating cancer phenotypes. Remarkably, we identified many such axes across several cancer molecular subtypes, including many involving receptor-biosynthetic enzymes for neurotransmitters. We found that GPCRs from these actionable axes, including, e.g., muscarinic, adenosine, 5-hydroxytryptamine, and chemokine receptors, are the targets of multiple drugs displaying anti-growth effects in large-scale, cancer cell drug screens, which we further validated. We have made the results generated in this study freely available through a webapp (gpcrcanceraxes.bioinfolab.sns.it).

EXPANSION: a webserver to explore the functional consequences of protein-coding alternative splice variants in cancer genomics.

Summary: EXPANSION (https://expansion.bioinfolab.sns.it/) is an integrated web-server to explore the functional consequences of protein-coding alternative splice variants. We combined information from Differentially Expressed (DE) protein-coding transcripts from cancer genomics, together with domain architecture, protein interaction network, and gene enrichment analysis to provide an easy-to-interpret view of the effects of protein-coding splice variants. We retrieved all the protein-coding Ensembl transcripts and mapped Interpro domains and post-translational modifications on canonical sequences to identify functionally relevant splicing events. We also retrieved isoform-specific protein-protein interactions and binding regions from IntAct to uncover isoform-specific functions via gene-set over-representation analysis. Through EXPANSION, users can analyze precalculated or user-inputted DE transcript datasets, to easily gain functional insights on any protein spliceform of interest. Availability and Implementation: EXPANSION is freely available at http://expansion.bioinfolab.sns.it/. The code of the scripts used for EXPASION is available at: https://github.com/raimondilab/expansion. Datasets associated to this resource are available at the following URL: https://doi.org/10.5281/zenodo.8229120. The web-server was developed using Apache2 (https://https.apache.org/) and Flask (v2.0.2) (http://flask.pocoo.org/) for the web frontend and for the internal pipeline to handle back-end processes. We additionally used the following Python and JavaScript libraries at both back- and front-ends: D3 (v4), jQuery (v3.2.1), DataTables (v2.3.2), biopython (v1.79), gprofiler-officia l(v1.0.0), Mysql-connector-python (v8.0.31). To construct the API, Fast API library (v0.95.1) was used.

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

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

The landscape of cancer rewired GPCR signaling axes.

We explored the dysregulation of GPCR ligand signaling systems in cancer transcriptomics datasets to uncover new therapeutics opportunities in oncology. We derived an interaction network of receptors with ligands and their biosynthetic enzymes, which revealed that multiple GPCRs are differentially regulated together with their upstream partners across cancer subtypes. We showed that biosynthetic pathway enrichment from enzyme expression recapitulated pathway activity signatures from metabolomics datasets, providing valuable surrogate information for GPCRs responding to organic ligands. We found that several GPCRs signaling components were significantly associated with patient survival in a cancer type-specific fashion. The expression of both receptor-ligand (or enzymes) partners improved patient stratification, suggesting a synergistic role for the activation of GPCR networks in modulating cancer phenotypes. Remarkably, we identified many such axes across several cancer molecular subtypes, including many pairs involving receptor-biosynthetic enzymes for neurotransmitters. We found that GPCRs from these actionable axes, including e.g., muscarinic, adenosine, 5-hydroxytryptamine and chemokine receptors, are the targets of multiple drugs displaying anti-growth effects in large-scale, cancer cell drug screens. We have made the results generated in this study freely available through a webapp (gpcrcanceraxes.bioinfolab.sns.it).

Prognostic Biomarker-Based Identification of Drugs for Managing the Treatment of Endometrial Cancer.

INTRODUCTION: Uterine corpus endometrial carcinoma (UCEC) causes thousands of deaths per year. To improve the overall survival of patients with UCEC, there is a need to identify prognostic biomarkers and potential drugs. OBJECTIVES: The aim of this study was twofold: the identification of prognostic gene signatures from expression profiles of pattern recognition receptor (PRR) genes and identification of the most effective existing drugs using the prognostic gene signature. METHODS: This study was based on the expression profile of PRR genes of 541 patients with UCEC obtained from The Cancer Genome Atlas. Key prognostic signatures were identified using various approaches, including survival analysis, network, and clustering. Hub genes were identified by constructing a co-expression network. Representative genes were identified using k-means and k-medoids-based clustering. Univariate Cox proportional hazard (PH) analysis was used to identify survival-associated genes. 'cmap2' was used to identify potential drugs that can suppress/enhance the expression of prognostic genes. RESULTS: Models were developed using hub genes and achieved a maximum hazard ratio (HR) of 1.37 (p = 0.294). Then, a clustering-based model was developed using seven genes (HR 9.14; p = 1.49 × 10-12). Finally, a nine gene-based risk stratification model was developed (CLEC1B, CLEC3A, IRF7, CTSB, FCN1, RIPK2, NLRP10, NLRP9, and SARM1) and achieved HR 10.70; p = 1.1 × 10-12. The performance of this model improved significantly in combination with the clinical stage and achieved HR 15.23; p = 2.21 × 10-7. We also developed a model for predicting high-risk patients (survival ≤ 4.3 years) and achieved an area under the receiver operating characteristic curve (AUROC) of 0.86. CONCLUSION: We identified potential immunotherapeutic agents based on prognostic gene signature: hexamethonium bromide and isoflupredone. Several novel candidate drugs were suggested, including human interferon-α-2b, paclitaxel, imiquimod, MESO-DAP1, and mifamurtide. These biomolecules and repurposed drugs may be utilised for prognosis and treatment for better survival.

Prognostic biomarkers for predicting papillary thyroid carcinoma patients at high risk using nine genes of apoptotic pathway.

Aberrant expressions of apoptotic genes have been associated with papillary thyroid carcinoma (PTC) in the past, however, their prognostic role and utility as biomarkers remains poorly understood. In 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. It 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, which can be utilized to classify patients with a higher risk of death from the patients which have a good prognosis. 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. Further, the expression pattern of the prognostic genes was verified at mRNA level, which showed their differential expression between normal and PTC samples. Also, the immunostaining results from HPA validated these findings. Since these genes can also be used as potential therapeutic targets in PTC, we also identified potential drug molecules which could modulate their expression profile. The 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.

In-Silico Tool for Predicting, Scanning, and Designing Defensins.

Defensins are host defense peptides present in nearly all living species, which play a crucial role in innate immunity. These peptides provide protection to the host, either by killing microbes directly or indirectly by activating the immune system. In the era of antibiotic resistance, there is a need to develop a fast and accurate method for predicting defensins. In this study, a systematic attempt has been made to develop models for predicting defensins from available information on defensins. We created a dataset of defensins and non-defensins called the main dataset that contains 1,036 defensins and 1,035 AMPs (antimicrobial peptides, or non-defensins) to understand the difference between defensins and AMPs. Our analysis indicates that certain residues like Cys, Arg, and Tyr are more abundant in defensins in comparison to AMPs. We developed machine learning technique-based models on the main dataset using a wide range of peptide features. Our SVM (support vector machine)-based model discriminates defensins and AMPs with MCC of 0.88 and AUC of 0.98 on the validation set of the main dataset. In addition, we created an alternate dataset that consists of 1,036 defensins and 1,054 non-defensins obtained from Swiss-Prot. Models were also developed on the alternate dataset to predict defensins. Our SVM-based model achieved maximum MCC of 0.96 with AUC of 0.99 on the validation set of the alternate dataset. All models were trained, tested, and validated using standard protocols. Finally, we developed a web-based service "DefPred" to predict defensins, scan defensins in proteins, and design the best defensins from their analogs. The stand-alone software and web server of DefPred are available at https://webs.iiitd.edu.in/raghava/defpred.

A Hybrid Model for Predicting Pattern Recognition Receptors Using Evolutionary Information.

This study describes a method developed for predicting pattern recognition receptors (PRRs), which are an integral part of the immune system. The models developed here were trained and evaluated on the largest possible non-redundant PRRs, obtained from PRRDB 2.0, and non-pattern recognition receptors (Non-PRRs), obtained from Swiss-Prot. Firstly, a similarity-based approach using BLAST was used to predict PRRs and got limited success due to a large number of no-hits. Secondly, machine learning-based models were developed using sequence composition and achieved a maximum MCC of 0.63. In addition to this, models were developed using evolutionary information in the form of PSSM composition and achieved maximum MCC value of 0.66. Finally, we developed hybrid models that combined a similarity-based approach using BLAST and machine learning-based models. Our best model, which combined BLAST and PSSM based model, achieved a maximum MCC value of 0.82 with an AUROC value of 0.95, utilizing the potential of both similarity-based search and machine learning techniques. In order to facilitate the scientific community, we also developed a web server "PRRpred" based on the best model developed in this study (http://webs.iiitd.edu.in/raghava/prrpred/).

Risk prediction in cutaneous melanoma patients from their clinico-pathological features: superiority of clinical data over gene expression data.

Risk assessment in cutaneous melanoma (CM) patients is one of the major challenges in the effective treatment of CM patients. Traditionally, clinico-pathological features such as Breslow thickness, American Joint Committee on Cancer (AJCC) tumor staging, etc. are utilized for this purpose. However, due to advancements in technology, most of the upcoming risk prediction methods are gene-expression profile (GEP) based. In this study, we have tried to develop new GEP and clinico-pathological features-based biomarkers and assessed their prognostic strength in contrast to existing prognostic methods. We developed risk prediction models using the expression of the genes associated with different cancer-related pathways and got a maximum hazard ratio (HR) of 2.52 with p-value ~10-8 for the apoptotic pathway. Another model, based on combination of apoptotic and notch pathway genes boosted the HR to 2.57. Next, we developed models based on individual clinical features and got a maximum HR of 2.45 with p-value ~10-6 for Breslow thickness. We also developed models using the best features of clinical as well as gene-expression data and obtained a maximum HR of 3.19 with p-value ~10-9. Finally, we developed a new ensemble method using clinical variables only and got a maximum HR of 6.40 with p-value ~10-15. Based on this method, a web-based service and an android application named 'CMcrpred' is available at (https://webs.iiitd.edu.in/raghava/cmcrpred/) and Google Play Store respectively to facilitate scientific community. This study reveals that our new ensemble method based on only clinico-pathological features overperforms methods based on GEP based profiles as well as currently used AJCC staging. It also highlights the need to explore the full potential of clinical variables for prognostication of cancer patients.

Identification of prognostic biomarkers for major subtypes of non-small-cell lung cancer using genomic and clinical data.

PURPOSE: Intra-tumor heterogeneity and high mortality among patients with non-small-cell lung carcinoma (NSCLC) emphasize the need to identify reliable prognostic markers unique to each subtype. METHODS: In this study, univariate cox regression and prognostic index (PI)-based approaches were used to develop models for predicting NSCLC patients' subtype-specific survival. RESULTS: Prognostic analysis of TCGA dataset identified 1334 and 2129 survival-specific genes for LUSC (488 samples) and LUAD (497 samples), respectively. Individually, 32 and 271 prognostic genes were found and validated in GSE study exclusively for LUSC and LUAD. Nearly, 9-10% of the validated genes in each subtype were already reported in multiple studies thus highlighting their importance as prognostic biomarkers. Strong literature evidence against these prognostic genes like "ELANE" (LUSC) and "AHSG" (LUAD) instigates further investigation for their therapeutic and diagnostic roles in the corresponding cohorts. Prognostic models built on five and four genes were validated for LUSC [HR = 2.10, p value = 1.86 × 10-5] and LUAD [HR = 2.70, p value = 3.31 × 10-7], respectively. The model based on the combination of age and tumor stage performed well in both NSCLC subtypes, suggesting that despite having distinctive histological features and treatment paradigms, some clinical features can be good prognostic predictors in both. CONCLUSION: This study advocates that investigating the survival-specific biomarkers restricted to respective cohorts can advance subtype-specific prognosis, diagnosis, and treatment for NSCLC patients. Prognostic models and markers described for each subtype may provide insight into the heterogeneity of disease etiology and help in the development of new therapeutic approaches for the treatment of NSCLC patients.

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

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

A Web-Based Platform on Coronavirus Disease-19 to Maintain Predicted Diagnostic, Drug, and Vaccine Candidates.

A web-based resource CoronaVIR (https://webs.iiitd.edu.in/raghava/coronavir/) has been developed to maintain the predicted and existing information on coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). We have integrated multiple modules, including "Genomics," "Diagnosis," "Immunotherapy," and "Drug Designing" to understand the holistic view of this pandemic medical disaster. The genomics module provides genomic information of different strains of this virus to understand genomic level alterations. The diagnosis module includes detailed information on currently-in-use diagnostics tests as well as five novel universal primer sets predicted using in silico tools. The Immunotherapy module provides information on epitope-based potential vaccine candidates (e.g., LQLPQGTTLPKGFYA, VILLNKHIDAYKTFPPTEPKKDKKKK, EITVATSRTLS, GKGQQQQGQTV, SELVIGAVILR) predicted using state-of-the-art software and resources in the field of immune informatics. These epitopes have the potential to activate both adaptive (e.g., B cell and T cell) and innate (e.g., vaccine adjuvants) immune systems as well as suitable for all strains of SARS-CoV-2. Besides, we have also predicted potential candidates for siRNA-based therapy and RNA-based vaccine adjuvants. The drug designing module maintains information about potential drug targets, tertiary structures, and potential drug molecules. These potential drug molecules were identified from FDA-approved drugs using the docking-based approach. We also compiled information from the literature and Internet on potential drugs, repurposing drugs, and monoclonal antibodies. To understand host-virus interaction, we identified cell-penetrating peptides in the virus. In this study, state-of-the-art techniques have been used for predicting the potential candidates for diagnostics and therapeutics.

Prediction of risk scores for colorectal cancer patients from the concentration of proteins involved in mitochondrial apoptotic pathway.

One of the major challenges in managing the treatment of colorectal cancer (CRC) patients is to predict risk scores or level of risk for CRC patients. In past, several biomarkers, based on concentration of proteins involved in type-2/intrinsic/mitochondrial apoptotic pathway, have been identified for prognosis of colorectal cancer patients. Recently, a prognostic tool DR_MOMP has been developed that can discriminate high and low risk CRC patients with reasonably high accuracy (Hazard Ratio, HR = 5.24 and p-value = 0.0031). This prognostic tool showed an accuracy of 59.7% when used to predict favorable/unfavorable survival outcomes. In this study, we developed knowledge based models for predicting risk scores of CRC patients. Models were trained and evaluated on 134 stage III CRC patients. Firstly, we developed multiple linear regression based models using different techniques and achieved a maximum HR value of 6.34 with p-value = 0.0032 for a model developed using LassoLars technique. Secondly, models were developed using a parameter optimization technique and achieved a maximum HR value of 38.13 with p-value 0.0006. We also predicted favorable/unfavorable survival outcomes and achieved maximum prediction accuracy value of 71.64%. A further enhancement in the performance was observed if clinical factors are added to this model. Addition of age as a variable to the model improved the HR to 40.11 with p-value as 0.0003 and also boosted the accuracy to 73.13%. The performance of our models were evaluated using five-fold cross-validation technique. For providing service to the community we also developed a web server 'CRCRpred', to predict risk scores of CRC patients, which is freely available at https://webs.iiitd.edu.in/raghava/crcrpred.