Biology subjects

Raghava, G. P. S.

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

At least 19 recordsLinked to original sources

bioRxiv2026

AntiOxiPred: Predicting Antioxidant Peptides using Machine Learning Techniques and BLAST

Antioxidant peptides (AOPs) offer significant therapeutic potential in counteracting oxidative damage associated with chronic diseases. As AOPs gain market traction in cosmeceuticals, functional foods, and clinical trials for disease intervention, efficient computational methods are essential to accelerate their discovery. In this study, a systematic attempt has been made to develop a highly accurate and reliable method for predicting AOPs from their primary sequences. The dataset comprises 1,511 experimentally validated AOPs and 1,511 randomly generated non-AOPs, partitioned into 2,417 sequences for training and 606 for testing. First, we developed machine learning-based models using one-hot encoded (OHE) representations, sequence-derived compositional features, protein language model (PLM) embeddings, and feature fusion. Our CatBoost model, developed using selected fused features, achieved the best performance, with an AUC of 0.945 and an MCC of 0.788 on the independent testing dataset. An ensemble model combining CatBoost with BLAST achieved a peak AUC of 0.956 on the same testing dataset. Furthermore, our method outperformed existing state-of-the-art predictors when benchmarked on two external validation datasets comprising 150 peptides (75 AOPs and 75 non-AOPs) and 248 peptides (124 AOPs and 124 non-AOPs). AntiOxiPred (https://webs.iiitd.edu.in/raghava/antioxipred/) is freely available as an interactive web server, a standalone package, and a pip-installable tool to support the scientific community.

bioinformatics↗

bioRxiv2026

AntiCapt: Fine-Tuned Nucleotide Language Models for Predicting and Designing Anticancer Aptamers

Over the past decade, aptamers have emerged as promising therapeutics, with cancer therapeutics as a major research area. Existing computational methods, however, either predict aptamer-target pairs or design aptamers against a specific target. In this study, we present AntiCapt, a computational method for identifying single-stranded DNA (ssDNA) anticancer aptamers (ACAs) using sequence descriptors and fine-tuned nucleotide language models. The main dataset comprises 1,021 experimentally validated ACAs and an equal number of non-aptamer sequences. Comparative analysis revealed distinct patterns in the nucleotide, dinucleotide, and trinucleotide compositions associated with ACAs. We developed machine learning (ML) models using composition, autocorrelation, binary profiles and structural features. Among these, the best-performing composition-based model achieved an AUC of 0.93 on an independent dataset, while chemical descriptor-and structural feature-based models achieved a maximum AUC of 0.89. ML models using pretrained and fine-tuned NLM embeddings were also developed, with fine-tuned HyenaDNA embeddings achieving the highest performance, with an independent AUC of 0.94. Furthermore, we developed a model for discriminating anticancer aptamers from general aptamers. The best-performing models were integrated into AntiCapt, a web server and a standalone tool for predicting, designing, and genome-scale scanning anticancer aptamers (https://webs.iiitd.edu.in/raghava/anticapt/).

bioinformatics↗

bioRxiv2026

EdiProPred: Prediction of Edible Plant Tissue-Associated Proteins Using Large Language Models

Ensuring the safety and suitability of proteins considered for food and biotechnology applications is an important challenge. Computational approaches can facilitate the prioritisation of candidate proteins for further investigation, particularly given the rapid growth of genomic and metagenomic sequence datasets. In this study, we developed computational models to distinguish edible plant tissue-associated (EPTA) proteins from non-EPTA proteins. The positive class comprised 939 proteins with experimentally validated evidence of expression in plant tissues commonly consumed by humans, hereafter referred to as EPTA proteins. The negative class comprised 939 proteins annotated in UniProt as toxic, allergenic, or antinutritional, hereafter referred to as non-EPTA proteins. Models were evaluated using five-fold cross-validation with a cluster-based partitioning strategy, ensuring that no protein in the validation set shared more than 40% sequence identity with proteins in the corresponding training set. First, composition-based sequence features were evaluated to establish a baseline for EPTA or non-EPTA classification, with the Extra Trees (ET) classifier achieving a validation AUROC of 0.848. To incorporate evolutionary information beyond amino acid composition, PSSM profiles were subsequently evaluated, yielding an AUROC of 0.842 with an SVM classifier. Finally, to capture richer sequence patterns and contextual information using protein language modelling, we evaluated ESM2-based models. The fine-tuned ESM2-T33 model achieved the highest validation AUROC of 0.925 and was selected as the final predictive model. The resulting approach was implemented as the EdiProPred web server (https://webs.iiitd.edu.in/raghava/edipropred/) and standalone software for computational classification of plant proteins. The EdiProPred framework provides a useful computational tool for prioritising candidate plant proteins and facilitating the exploration of novel protein resources for food and biotechnology applications.

plant biology↗

bioRxiv2026

CPPLocPred: Subcellular Localization of Cell-Penetrating Peptides

Cell-penetrating peptides (CPPs) are widely used to deliver therapeutic cargoes into cells. Although numerous computational methods have been developed for identifying CPPs and several predictors are available for protein subcellular localization, no method has been developed to predict the subcellular localization of CPPs. Here, we present CPPLocPred, a hierarchical machine-learning (ML) framework that predicts CPPs and their subcellular localization. In the first stage, we developed ML models to identify CPPs, achieving an AUC of 0.953 with an MCC of 0.7842 on an independent set, exhibiting performance equivalent to or better than existing state-of-the-art methods. In the second stage, we developed a method for predicting the subcellular localization of CPPs. Subcellular localization methods were trained (80% data using five-fold cross-validation) and validated (20% data) on experimentally validated CPPs for 663 Cytoplasm, 287 Nucleus, 57 Mitochondria, 186 Endo_lysosome, and 328 Others. Our primary analysis revealed that Mitochondrial and Nuclear associated CPPs are abundant in positively charged arginine- and lysine-rich patterns, whereas Endo_lysosomal CPPs preferentially comprise glycine-, proline-, and cysteine-rich motifs. We used a wide range of traditional peptide features, along with the embedding of protein language models, to develop ML models. Among all evaluated models, the CatBoost-based subcellular localization models with Distance Distribution of Residues (DDR) achieved AUCs of 0.814, 0.775, 0.970, 0.782, and 0.798 for Cytoplasm, Nucleus, Mitochondria, Endo_lysosome, and Others, respectively, on validation dataset. We developed CPPLocPred, which offers a practical platform for functional annotation and rational design of localization-specific CPPs for therapeutic applications (https://webs.iiitd.edu.in/raghava/cpplocpred/). HighlightsO_LIPrediction and subcellular localization of cell-penetrating peptides. C_LIO_LILocalization of CPPs depends on their amino acid and dipeptide composition. C_LIO_LIBest feature for subcellular localization was Distance Distribution of Residues. C_LIO_LICatBoost model achieved the highest performance for subcellular localization. C_LIO_LIA web server and standalone software to facilitate its use by the scientific community. C_LI

bioinformatics↗

bioRxiv2026

AptViralDB: A Repository of Experimentally Validated Antiviral Aptamers

In an era of increasing drug resistance, exploring alternative molecules is crucial for the efficient management and treatment of viral diseases. Nucleic acid aptamers have emerged as highly promising candidates due to their exceptional target specificity, low immunogenicity, and versatile mechanisms for viral blocking. This manuscript describes AptViralDB, a manually curated database providing comprehensive information on experimentally validated antiviral aptamers. It contains 1,768 entries of antiviral aptamers against 40 viral species and 104 molecular targets, compiled from literature and existing databases. Each entry provides detailed annotations, including sequence, aptamer type, target, chemical modifications, binding affinity, antiviral activity, stability, and cytotoxicity. We also provide predicted secondary structures and their corresponding minimum free energy (MFE) values. Additionally, a knowledge graph created using ArcadeDB/openCypher enables users to seamlessly explore connections among aptamers, viruses, molecular targets, and biological activities. Finally, the platform offers advanced search and browsing tools, BLAST-based sequence similarity searches, GC-content analysis, downloadable datasets, and REST API access to support computational applications. (https://webs.iiitd.edu.in/raghava/aptviraldb/).

bioinformatics↗

bioRxiv2026

PEPstrMOD2: Next-generation tertiary structure prediction of chemically modified and non-natural peptides

While most existing methods are limited to predicting the tertiary structures of proteins containing only canonical residues, the PEPstrMOD server (developed in 2015) pioneered structure prediction for chemically modified and non-natural peptides. Despite its widespread use, the original framework was restricted to peptides of 7 to 25 residues and relied on older backbone-prediction algorithms. To address these limitations, we present PEPstrMOD2, which introduces three major advancements over its predecessor. First, it replaces the original in-house coordinate generation with state-of-the-art deep learning (DL) algorithms, leveraging AlphaFold2 and ESMFold for highly accurate initial structure prediction. Secondly, it greatly expands the accessible chemical space through incorporation of new, AMBER force-field compatible library of 257 post-translational modifications (PTMs), 428 non-canonical amino acids (NCAAs), and 243 terminal modifications. Lastly, through the application of native scalability of AlphaFold2 (AF2) and ESMFold (EF), PEPstrMOD2 eliminates the original restrictions of the length, enabling the structural modeling of longer, complex therapeutic peptides and small proteins. We evaluated the performance of PEPstrMOD2 against state-of-the-art methods across three distinct peptide datasets. For the AfCyc dataset consisting of 80 cyclic peptides, PEPstrMOD2 obtained a competitive average atom-level Root Mean Square Deviation (RMSD) of 2.05 [A], compared to 1.13 [A] by AlphaFold3 (AF3) and 1.82 [A] by AfCycDesign. Remarkably, for the modified peptide ModPep433 dataset, PEPstrMOD2 outperformed AF3, achieving the lower average RMSD score of 4.49 [A] against 4.67 [A] of AF3. Furthermore, in the case of the ModPep16 benchmark, PEPstrMOD2 achieved 2.50 [A] average RMSD value, which is two times more accurate than that of the original PEPstrMOD (5.84 [A]). In summary, PEPstrMOD2 provides a powerful, high-throughput, and highly accurate platform to facilitate peptide-based drug development and structural biology research. While the original PEPstrMOD was restricted to a web server interface, PEPstrMOD2 is available as both an intuitive webserver and a standalone command-line tool via GitHub, featuring Docker support for easy deployment and reproducible, large-scale modeling pipelines (https://webs.iiitd.edu.in/raghava/pepstrmod/). HighlightsO_LIPEPstrMOD2 predicts structures of chemically modified peptides using deep learning and molecular dynamics refinement. C_LIO_LISupports 928 chemical modifications through custom AMBER based force-field libraries including PTMs, NCAAs, terminal, D- as well as cyclic modifications. C_LIO_LIRemoves peptide length restrictions through AlphaFold2 and ESMFold integration. C_LIO_LIutperforms PEPstrMOD and is competitive with AF3 on different benchmark datasets. C_LIO_LIAvailable as both a web server and a standalone platform via GitHub and Docker. C_LI Authors BiographyO_LISaloni 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_LINaman Kumar Mehta is currently working as Ph.D. in Computational biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LIO_LISahil Raina is currently working as Ph.D. in Computational biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LIO_LIPankaj 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_LIVarun is currently an integrated BS-MS student at Indian Institute of Science Education and Research (IISER) Pune, India. He is currently working as an intern on a project position at Department of Computational Biology, Indraprastha Institute of Information Technology (IIIT), New Delhi, India. C_LIO_LIGajendra P. S. Raghava is currently working as a Professor in the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LI

bioinformatics↗

bioRxiv2026

AptBacterialDB: A Comprehensive, Manually Curated Database of Antibacterial Aptamers

In recent years, aptamers have transitioned from mere laboratory tools to highly potent molecular recognition agents capable of overcoming the strict limitations of conventional antibiotic therapies. We have developed AptBacterialDB, a manually curated, large, comprehensive database of experimentally validated antibacterial aptamers spanning 1996 to 2026. The database contains a total of 2131 aptamers targeting approx 75 different bacterial classes, and 124 aptamer targets with 95 entries found in UTexas databases, 97 in AptaDB, and 28 in Aptabase. It contains 1555 unique aptamer sequences, 189 unique modifications, 40 different selection approaches, and 44 different affinity methods. It integrates detailed annotations of about 20 fields, including sequence information, nucleic acid type, binding affinity, modifications, experimental and functional details. The secondary structure of the aptamers was predicted using ViennaRNA Package 2.0, demonstrating that they adopt mostly stable conformations, with a structured stem region. MySQL was implemented for database development, and a knowledge graph was integrated using ArcadeDB/openCypher for graphical visualization of aptamer-target-organisation relationships. Facilities such as different search modes, browsing, similarity search, REST API access, and entries linked to the existing database for a broader view of the aptamers have been provided. AptBacterialDB (https://webs.iiitd.edu.in/raghava/aptbacterialdb/) provides a user-friendly centralized platform to accelerate antibacterial aptamer research, therapeutic development, biosensor design, and computational modelling efforts. Authors BiographyO_LINisha Bajiya is currently working as Ph.D. Student in Computational Biology from Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIIshika Gupta is currently working as an M.Tech Student 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 a Professor in the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India C_LI

bioinformatics↗

bioRxiv2026

AptCancerDB: A Curated Knowledgebase and Translational Discovery Platform for Anticancer Aptamers

Aptamers are emerging as important molecular recognition ligands in oncology, playing significant roles in cancer diagnostics, targeted therapies, drug delivery systems, and molecular imaging. Numerous aptamers have advanced to clinical trials, indicating their potential for real-world applications; however, existing databases fail to capture that. To bridge this critical gap, we developed AptCancerDB (https://webs.iiitd.edu.in/raghava/aptcancerdb/), a comprehensive, manually curated database of experimentally verified anticancer aptamers. The current release contains 1,941 entries collected from studies published between 2000 and 2025, covering 29 cancer types, approximately 200 cancer cell lines, and direct links to 22 clinical trials. Each entry is annotated with sequence information, target details, cancer type, cell line, SELEX methodology, affinity determination data, chemical modifications, and biological activities. The dataset is dominated by 82.7% ssDNA, reflecting its superior stability and ease of synthesis, while only 16.6% is ssRNA and appears primarily in studies targeting complex intracellular or protein-protein interactions. To facilitate structural analysis, predicted secondary structures, dot-bracket notations, specific structural elements, and minimum free energy values were also included. AptCancerDB integrates a MySQL backend with an ArcadeDB/OpenCypher-based Knowledge Graph, enabling exploration of relationships among aptamers, targets, cancer types, cell lines, and functional applications. The platform provides advanced search and browsing facilities, BLASTn-based similarity searching, and GC Calculator. Built on a modern, responsive frontend (React/TypeScript/Tailwind CSS), the platform includes a REST API for data retrieval. By integrating fragmented experimental data into a unified cancer-focused resource, AptCancerDB serves as a valuable resource for comparative analysis, aptamer discovery, and the development of next-generation aptamer-based diagnostics and therapeutics. HighlightsO_LICurated knowledge base of experimentally validated anticancer aptamers. C_LIO_LIAptCancerDB contain therapeutic, tumor-homing and cell-penetrating aptamers. C_LIO_LISummarizes clinical progress and translational trends in anticancer aptamer research. C_LIO_LISupports rational aptamer design using molecular, functional, and clinical annotations C_LIO_LIDisease-focused resource for cancer diagnosis, therapy, and drug delivery C_LI TeaserAptCancerDB maintains experimentally validated anticancer aptamers relevant to diagnosis, drug delivery, and therapy.

cancer biology↗

bioRxiv2026

HAIRpred2: Human Host-Specific Prediction of Antibody-Interacting Residues Using Hybrid Physicochemical and Structural Features

1.Prediction of conformational B-cell epitopes is critical for vaccine design, immunotherapy, and antibody engineering. To date, several host-independent computational methods have been developed for predicting antibody-interacting residues in antigen structures. However, it is well established that antigen-antibody (Ag-Ab) interactions vary depending on the host immune system indicating the importance of developing host-specific prediction models. In this study, we present, for the first time, a human host-specific method, HAIRpred2, that predicts antibody-interacting residues in an antigen from its tertiary structure. The dataset was derived from HAIRpred and comprises 277 human Ag-Ab complexes, with 221 structures used for training and 56 for independent testing. Preliminary analysis revealed that residues with a relative surface accessibility (RSA) below 0.05, corresponding to buried regions, are highly likely to be non-interacting, underscoring the importance of structural accessibility in antibody recognition. To identify the most informative features, we evaluated multiple feature representations, including RSA, large language model (LLM)-based embeddings, distance-based features, and physicochemical properties. A model trained on single-residue RSA features achieved an AUC of 0.72. Incorporating a sliding window of 15 residues to capture local structural context improved performance to an AUC of 0.75. The best performance (AUC = 0.78 on the independent test set) was achieved by integrating RSA with physicochemical descriptors. Benchmarking against existing antibody-interaction prediction methods on the same independent dataset demonstrated that HAIRpred2 outperforms current tools, further highlighting the advantage of host-specific modeling. HAIRpred2 is freely available as a web server at https://webs.iiitd.edu.in/raghava/hairpred2/. HighlightsO_LIDevelopment of HAIRpred2, the first human host-specific method for predicting antibody-interacting residues. C_LIO_LIAnalysis of 277 human antigen-antibody complexes to capture host-dependent interaction patterns. C_LIO_LIRelative surface accessibility (RSA) identified as a key determinant, with buried residues rarely participating in interactions. C_LIO_LIIntegration of RSA with physicochemical features achieved the best performance (AUC = 0.78) on an independent dataset. C_LIO_LIHAIRpred2 outperforms existing methods and is available as a web server for epitope prediction. C_LI

bioinformatics↗

bioRxiv2026

Integrative Bioinformatics Approach to Identify Prognostic Gene Signatures for Risk Stratification in Thyroid Carcinoma

Thyroid cancer is a heterogeneous malignancy with variable outcomes, highlighting the need for reliable biomarkers and effective risk stratification. In this study, we implemented a multi-step integrative framework to identify distinct prognostic biomarker sets using transcriptomic data from 572 thyroid cancer patients. Correlation analysis followed by false discovery rate (FDR) correction revealed significant associations of genes. Notably, MAFF (r = 0.25, p = 1.34x10-, FDR = 2.46x10-), NR4A3 (r = 0.24, p = 1.26x10-, FDR = 9.25x10-), and SRF showed strong positive correlations, whereas LOC728264 (r = -0.21, p = 7.39x10-, FDR = 6.36x10-) and VAMP1 (r = -0.20, p = 1.20x10-, FDR = 1.3x10-) exhibited negative correlations with OS. Univariate Cox regression identified several survival-associated genes, including TMEM90B (HR = 10.66, p = 2.88x10-) and PTH1R (HR = 9.88, p = 5.55x10-). LASSO regression further identified 31 key prognostic genes, including 13 potential drug targets predominantly functioning as inhibitors. Machine learning models based on seven independent 20-gene biomarker sets effectively predicted Class 0 (0-1 years), Class 1 (1-3 years), Class 2 (3-5 years), and Class 3 (>5 years), achieving AUC values of 0.91-0.94 and Kappa up to 0.76. An ensemble model further improved prediction (AUC = 0.95, Kappa = 0.72). Incorporating clinical variables (age, gender, stage) enhanced model performance (AUC = 0.96, Kappa = 0.80). Reduced 10- and 5-gene subsets demonstrated consistent yet slightly lower performance (AUC = 0.90 and 0.86, respectively). Collectively, the 20-gene set exhibited the strongest predictive and prognostic potential, highlighting the importance of integrating molecular and clinical features for risk stratification in thyroid cancer.All data and code are openly available (https://github.com/raghavagps/THCA_prognostic_biomarkers), supporting future research in thyroid cancer prediction.

bioinformatics↗

bioRxiv2026

PCPpred: Prediction of Chemically Modified Peptide Permeability Across Multiple Assays for Oral Delivery

Chemically modified peptides, including cyclic peptides, have emerged as promising candidates for oral delivery yet they face the challenge of low membrane permeability. In this study, the datasets were sourced from CycPeptMPDB, a database for membrane permeability of peptides obtained from different assays. Our quantitative analysis showed a clear discordance between permeability measured using PAMPA and cell-based assays (Caco-2, MDCK, and, RRCK), thereby explaining its limits as surrogate for cell-based assays. Therefore, we developed assay-specific predictive models to more accurately capture permeability determinants in each system. We systematically compute diverse features of modified peptides using open-source software and used fine-tuned peptide embeddings generated using pretrained chemical language models. Baseline models were developed using the generated multi-hierarchical molecular features. We also developed a stacked ensemble architecture, which utilizes multi-hierarchical features in models as base learners. The ensemble model achieved the best PAMPA test set performance with an MSE of 0.200, R2 of 0.685, and PCC of 0.830; and a R2 of 0.783 on Caco-2 test set. Model trained on 2D Mordred descriptors attained the highest performance on the Caco-2 test-set with MSE of 0.129, R2 of 0.793, and PCC of 0.892, surpassing state-of-the-art approaches such as CPMP. To support widespread adoption, we developed an open-access web-server (https://webs.iiitd.edu.in/raghava/pcppred/) for users to design modified peptides using human comprehensible MAP (Modifications and Annotations of Proteins) format, converting MAP to SMILES format, and predict permeability across assays with result visualization. To ensure widespread adoption, and reproducibility, we also provided a standalone on GitHub (https://github.com/raghavagps/pcppred).

bioinformatics↗

bioRxiv2025

AntiFP2: Genome and Metagenome-Wide Prediction of Antifungal Proteins

The identification of antifungal proteins (AFPs) is crucial for understanding microbial interactions and facilitating the discovery of antifungals on a large scale from genomic and metagenomic data. Most existing computational tools are developed for predicting antifungal peptides rather than proteins. To address this limitation, we developed AntiFP2. A manually curated dataset of experimentally validated AFPs was used to train and develop prediction models using cross-validation techniques. The ensemble strategy, which combined ESM2, BLAST, and MERCI, achieved the best results across independent validation. Beyond prediction, we implemented a complete pipeline for genome- and metagenome-wide AFP screening. AntiFP2 is freely available as a web server, standalone package, and Docker container, enabling scalable and reproducible antifungal protein discovery.

bioinformatics↗

bioRxiv2025

A PLM-Based Method for Predicting Protein Ion Channel Modulators for Drug Discovery and Safety Evaluation

Ion channels are central to regulating neuronal communication, cardiac rhythm, and muscle contraction. Their modulation can induce therapeutic benefits but may also lead to adverse or toxic effects. This study presents IonNTXpred, a protein language model (PLM)-based method for predicting protein ion channel modulators, including channel-specific (Na{square}, K{square}, Ca{superscript 2}{square}, and others) and moonlighting proteins capable of modulating multiple ion channels. We train, test, and evaluate our models on the largest dataset of non-redundant ion channel-modulating proteins, where no two proteins have more than 40% sequence identity. Composition analysis revealed that residues Cys, Gly, and Trp are highly prevalent, whereas Ala, Glu, Leu, Gln, and Val are scarce in ion channel-modulating proteins, with Cys identified as a key discriminative residue. We explored both alignment-based (BLAST, MERCI) and alignment-free (machine learning, deep learning, and PLM-based) approaches. Among these, our evolutionary information-based PLM (ESM2-t33) achieved the best performance, with an AUROC of 0.97 across ion channels, which further improved to 0.98 when integrated with BLAST output. The proposed method outperformed existing approaches on independent datasets. We used IonNTXpred to screen FDA-approved and organismal proteins to identify candidates with ion channel-modulating potential, supporting drug repurposing, discovery of new therapeutic proteins, and safety assessment of existing biologics. We implemented these models in a user-friendly web server, IonNTXpred, which facilitates the design and discovery of ion channel-modulating protein-based drugs and supports the biosafety evaluation of therapeutic proteins through neurotoxin screening (https://webs.iiitd.edu.in/raghava/ionntxpred/). HighlightsO_LIPrediction, design, and large-scale screening of ion channel-modulating proteins. C_LIO_LIIdentifies neurotoxins to support safety evaluation of therapeutic proteins. C_LIO_LIEvolutionary information-based protein language model ESM2-t33 for prediction. C_LIO_LIPredicts moonlighting proteins capable of modulating multiple ion channels. C_LIO_LIProvides standalone software, a web server, and a PyPI package for user accessibility. C_LI

bioinformatics↗

bioRxiv2025

Prediction of lncRNA-protein interacting pairs using LLM embeddings based on evolutionary information

Interactions of long non-coding RNAs (lncRNAs) with proteins is responsible for numerous cellular processes, including transcriptional regulation, chromatin remodeling, cell differentiation, and intracellular signaling. In the past, numerous computational methods have been developed for predicting lncRNA-protein interacting (LPI) pairs. This study describes a highly accurate and reliable method for predicting LPI pairs built on largest possible non-redundant dataset having 262,244 interacting and equal number of non-interacting pairs. Initially, similarity-based approach BLAST has been tried which have poor discriminative power, due to low sequence similarity. Subsequently, we developed CNN based models and machine learning based models using traditional features and embedding. Our CatBoost model developed using embedding generated by DNABERT-2 and ESM-2-t30 achieved AUC of 0.989 with MCC 0.915 on an independent dataset. Our method performs better than existing methods on an independent dataset. We developed standalone software and web server lncrnaPI for predicting LPI pairs, scanning lncRNA interacting proteins in proteome and protein interacting lncRNA in genomes (https://webs.iiitd.edu.in/raghava/lncrnapi/). HIGHLIGHTSO_LIDiscrimination of LncRNA-protein interacting and non-interacting pairs. C_LIO_LINon-redundant dataset of 262,244 interacting and 262,244 non-interacting pairs. C_LIO_LIEmbedding of LncRNA using DNABERT-2 and protein using ESM-2-t30. C_LIO_LIRapid scanning of lncRNA interacting proteins at genome scale. C_LIO_LIA web server and software for predicting LncRNA-protein interacting pairs. C_LI

bioinformatics↗

bioRxiv2025

Saliva-based Biomarkers for Predicting Gastric Cancer

Saliva-based biomarkers offer a non-invasive, convenient, and patient-friendly approach for gastric cancer (GC) diagnosis, eliminating the need for uncomfortable procedures. This study aimed to identify salivary extracellular RNA (exRNA) biomarkers capable of distinguishing GC from normal samples. We used GEO dataset containing exRNA expression profiles of 98 GC and 100 normal samples. We filtered the data and applied the Mann-Whitney U test to identify statistically significant salivary exRNAs (p < 0.05). Initially, a single gene-based classification method identified potential biomarkers including GSDMA, SMR3B, NPTXR, TBCD, KCNC4, and KRT26, achieving accuracies ranging from 61.61% to 64.14%. Then, we applied AI-based methods to identify GC biomarkers. We developed machine learning models on different sets of biomarkers extracted from the original set of statistically significant exRNA using feature selection methods. An optimal primary biomarker set of eight mRNAs (GSDMA, CCDC141, TBCD, STARD13, WRB, ARHGAP23, CDHR3, BX842679.1) was identified, yielding an AUC of 0.905 and MCC of 0.770 with an ensemble stacking classifier. We performed comparative analysis with existing GC biomarker studies which demonstrated that our identified primary biomarker set outperformed previously reported biomarker panels. Out of the eight identified genes, seven have been reported in the literature to be associated with Gastric Cancer. Our results demonstrate the potential of salivary exRNA biomarkers as a non-invasive tool for GC diagnosis. Key pointsO_LIGC is often diagnosed at advanced stages using invasive procedures C_LIO_LISalivary exRNA has potential for non-invasive GC detection C_LIO_LIA machine learning model was developed to predict GC C_LIO_LIA panel of 8 salivary exRNA biomarkers for GC were identified C_LIO_LIThe biomarker panel outperformed existing salivary biomarkers for GC C_LI

bioinformatics↗

bioRxiv2025

PEPlife2: A Updated Repository of the Half-life of Peptides

This manuscript presents an updated version of PEPlife, a manually curated database that provides comprehensive information on peptide half-life. The updated version, PEPlife2, includes 4,412 entries, compared to 2,229 entries in the previous version. Each entry contains detailed information that include experimental methods used to determine half-life, chemical modifications, biological activity, routes of administration, and other relevant data. The database encompasses 402 proteins and 1,781 peptides, derived from 105 unique assays. In addition to natural peptide sequences, PEPlife2 includes cyclic peptides and chemically modified peptides, such as those with N- and C-terminal modifications. To provide structural insights, peptide and protein structures are sourced from the Protein Data Bank (PDB) or predicted using PEPstrMOD. To support the scientific community, we have developed a user-friendly interface and integrated advanced analytical tools, including BLAST, Smith-Waterman, GGSEARCH, CLUSTALW, and MUSTANG. The updated database is accessible at: https://webs.iiitd.edu.in/raghava/peplife2/. Authors BiographyO_LIUrooj Alam is currently pursuing a Masters degree in Computational Biology at the Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India. C_LIO_LIKunal Chaudhary is 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_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 a postdoctoral visiting fellow Cancer Data Science Laboratory, National Cancer Institute, National Institutes of Health, Bethesda, Maryland, USA. 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↗

bioRxiv2025

Hemolytik2: An Updated Database of Hemolytic Peptides and Proteins

Hemolytik 2.0 (http://webs.iiitd.edu.in/raghava/hemolytik2/) is a comprehensive, manually curated database that provides experimentally validated information on both hemolytic and non-hemolytic peptides. Data were meticulously extracted from peer-reviewed publications and established peptide repositories, including the Antimicrobial Peptide Database (APD), UniProt, the Collection of Anti-Microbial Peptides (CAMP-R4), and the Dragon Antimicrobial Peptide Database (DAMPD). This updated version of the original Hemolytik resource encompasses 13,215 entries, representing approximately 8,700 unique peptides. Each entry in Hemolytik 2.0 offers detailed annotations, including peptide name, amino acid sequence, biological source and origin, functional characterization, terminal modifications, stereochemistry, structural classification (linear or cyclic), and experimentally determined hemolytic activity. In addition, the database provides molecular representations of peptides in SMILES (Simplified Molecular Input Line Entry System) format, alongside predicted tertiary structures and annotated secondary structural states. Additionally, a RESTful API has been integrated into the Hemolytik 2.0 repository to enable programmatic access and automated retrieval of peptide data. Hemolytik 2.0 serves as a valuable resource for the scientific community, particularly for researchers involved in the design and development of therapeutic peptides, by facilitating the identification and optimization of peptide candidates with minimal hemolytic potential and enhanced safety profiles.

bioinformatics↗

bioRxiv2025

Benchmarking of Quantum SVM and Classical ML Algorithms for Prediction of Therapeutic Proteins

Over the past decade, quantum machine learning, particularly quantum support vector machines (QSVMs), has emerged as an optimistic alternative to classical machine learning (CML) techniques. This study rigorously benchmarks the performance of QSVM and CML-based models across four diverse datasets relevant to therapeutic proteins and peptides. Specifically, we evaluated these approaches for the prediction of B-cell epitopes (CLBtope), exosomal proteins (ExoPropred), hemolytic peptides (HemoPI), and toxic peptides (Toxinpred3). The maximum area under the receiver operating characteristic curve (AUC) for the CLBtope dataset achieved was 0.68 for QSVM and 0.82 for CML models. For the ExoPropred dataset, the maximum AUCs were 0.66 (QSVM) and 0.72 (CML). In contrast, both QSVM and CML models demonstrated high performance on the HemoPI dataset, yielding maximum AUCs of 0.95 and 0.98, respectively. Similarly, for the Toxinpred3 dataset, the maximum AUCs were 0.84 (QSVM) and 0.94 (CML). All models were evaluated using independent validation datasets not used during training. These results suggest that although CML currently demonstrates superior predictive capability for these tasks, the similar progression in performance indicates potential for future advancements in QSVM. HighlightsO_LIComparative study of QSVM and CML models on four bioinformatics datasets C_LIO_LIQSVM performance tries to approach CML in tasks involving hemolytic and toxic peptide prediction C_LIO_LIIndependent validation confirms robustness of performance metrics C_LIO_LIResults highlight the potential of QSVMs as real-world quantum hardware continues to matures C_LI

bioinformatics↗