Gajendra P. S. Raghava

The paper develops HLAncPred, an AI-based method to predict non-classical HLA (HLA-G and HLA-E) binders, achieving high AUC scores and providing a web server for this purpose.

This paper introduces IL-13Pred, a method to predict IL-13 inducing peptides in proteins, with high accuracy for managing COVID-19 severity.

The paper benchmarks mutation calling techniques for liver cancer prognosis using VCF and MAF files, finding MuTect2's VCF files best predict high-risk patients with high AUROC and HR.

Nfeature computes a large number of features for DNA and RNA sequences, providing a standalone package and web platform for researchers.

The paper identifies nine apoptotic pathway genes associated with prognosis in papillary thyroid carcinoma and develops risk prediction models with high accuracy.

The paper organizes a DREAM challenge to benchmark predictive models of single-cell signaling using mass cytometry data from breast cancer cell lines.

This paper identifies 15 gene signatures for predicting lymph node metastasis in TNBC using TCGA data, but finds poor cross-platform validation and develops a webserver for prediction.

The paper introduces Sigma70Pred, a method for predicting sigma70 promoters in prokaryotic genomes, achieving high accuracy on training and independent datasets.

This paper develops a machine learning model to predict ceftazidime-resistant bacterial strains from beta-lactamase amino acid sequences, achieving AUROC of 0.80 on training data.

The paper identifies prognostic alternative splicing events and mutations in pancreatic adenocarcinoma, showing improved risk prediction compared to existing models.

SAPdb is a database of experimentally validated peptide nanostructures formed by self-assembly, providing information on chemical modifications, nanostructure types, and experimental conditions.

The paper develops a prognostic model using multi-omics data to stratify HCC patients into recurrence risk groups, identifying key RNA, miRNA, and methylation features with significant predictive performance.

The paper identifies prognostic biomarkers for UCEC survival using gene expression profiles of PRRs and develops risk stratification models with improved performance when combined with clinical data.

AntiCP 2.0 predicts anticancer peptides using machine learning models trained on two datasets, achieving high MCC and AUROC scores on training data.

OvirusTdb is a manually curated repository of oncolytic viruses used in cancer treatment, providing comprehensive information on 5927 virus records and their therapeutic applications.

This study identifies key transcripts and machine learning models to classify early and late stage Papillary Thyroid Carcinoma samples using TCGA data, achieving up to 75.43% accuracy.

The paper develops prediction models using HLA-alleles and clinical characteristics to predict overall survival in skin cutaneous melanoma patients and identifies favorable and unfavorable superalleles.

SAMbinder predicts SAM binding residues in proteins from amino acid sequences using machine learning, achieving MCC 0.61 and AUROC 0.89 on a realistic dataset.

This study develops a hybrid model combining BLAST and machine learning to predict pattern recognition receptors, achieving high accuracy with an MCC of 0.82 and AUROC of 0.95.

IndiaBioDb is a curated repository of bioinformatics resources developed in India, providing access to 258 databases and 543 resources with search and browsing tools.

This study identifies a three-gene biomarker panel for hepatocellular carcinoma using large-scale transcriptomics data, showing high accuracy and prognostic potential across multiple platforms.

GPSRdocker provides a docker-based container integrating bioinformatics tools for genomics, proteomics, and systems biology, enabling local or cloud use of computational resources.

This study predicts melanoma progression using genomic features from TCGA SKCM data, identifying key genes and miRNAs that distinguish primary from metastatic tumors.

This paper develops models to predict risk scores for colorectal cancer patients using protein concentrations in the mitochondrial apoptotic pathway, achieving higher accuracy than existing tools.

The paper develops models to classify early and late stage Liver Hepatocellular Carcinoma using genomic and epigenomic data, achieving high accuracy and AUROC scores.

HumCFS is a manually curated database of human chromosomal fragile sites with annotated genes, miRNAs, and disease associations.

PEP2D predicts peptide secondary structure from PSSM evolutionary profiles, reaching Q3 83.5% on 3107 peptides against 76.9% for the protein-trained PSIPRED; a webserver is provided.

The paper evaluates seven docking methods on peptide-ligand complexes and finds AutoDock performs best with TOP poses, while performance differences are smaller with BEST poses.

The paper develops machine learning models to predict antigen presenting cell modulators (A-cell epitopes) and implements them in a web server for vaccine adjuvant design.

The paper develops proteomics-based prediction models to distinguish urinary tract oncological samples from healthy controls using urine data and creates a web tool for data mining.