Protein contacts often serve as prerequisites for characterizing molecular interactions and bonds. Traditional implementations remain computationally expensive, posing significant scalability and usability challenges. We present COCaDA-web, an interactive and user-friendly Web Server that allows users to dynamically explore and visualize protein contact data, building upon the COCaDA (COntact search pruning by C α Distance Analysis) command-line tool, which is aimed for large-scale protein interatomic contact detection. Users can submit their own queries, or explore precomputed data for over 240,000 proteins in the Protein Data Bank. COCaDA-web includes novel features like pH value customization for protonation-aware analysis and biological assembly support, and takes less than a second to process proteins up to 1000 residues. Detailed results are provided for each entry in a dynamic table, alongside an interactive 3D visualization, annotated PyMOL sessions, and step-by-step usage guides. We demonstrate our tool by performing two comparative analyses of the interatomic contacts of Transthyretin and 5-Hydroxyisourate Hydrolase, two evolutionarily and structurally related proteins yet known to perform distinct biological functions associated with amyloidogenesis and gout. COCaDA-web reveals important differences, especially in their central cavities, that help explain the functional divergence of these proteins. At the moment, the COCaDA-web database contains approximately 746 million contacts, divided into 690 million intra-chain and 55 million inter-chain. COCaDA-web provides a fast, interactive, and scalable platform for protein interatomic contact analysis, combining efficient large-scale contact detection with intuitive visualization and exploration tools. COCaDA-web is freely accessible at https://bioinfo.dcc.ufmg.br/cocada-web, and there are no login requirements.
Machine learning models for toxicity prediction are routinely evaluated using random train/test splits, allowing structurally similar compounds to appear in both sets and inflating reported performance metrics. A rigorous benchmark quantifying this overestimation alongside calibration, uncertainty, and applicability domain analyses is needed to guide practitioners in selecting and trusting toxicity prediction models. We present ToxBench, a leakage-audited benchmark comprising three toxicology datasets (Tox21, 7,538 compounds, 12 tasks; ClinTox, 1,379 compounds, 2 tasks; SIDER, 1,350 compounds, 27 tasks) processed through a transparent standardization pipeline with explicit reporting of conflicting-label removals. Four model classes were evaluated: Random Forest, XGBoost, MLP, and Graph Neural Network (GNN), each trained under random and Bemis-Murcko scaffold-based splits across five independent seeds (120 experimental conditions). Analyses included post-hoc probability calibration, ensemble-based uncertainty quantification, nearest-neighbor applicability domain analysis, and scaffold-level error analysis. Scaffold splitting consistently reduced AUROC by 0.057–0.079 points across all model classes on Tox21 (mean drop: 0.070) and by 0.031–0.035 points on SIDER for three of four models, demonstrating systematic performance overestimation under random splitting. ClinTox showed reversed performance ordering due to small dataset size and extreme class imbalance, with high seed-to-seed variance (± 0.085–0.160) confirming results are dominated by sampling noise. Post-hoc calibration reduced ECE by 67–68
Channelrhodopsin variants with desired photocurrent properties are commonly developed through iterative experimental screening. Computational models are increasingly being used to prioritize candidate variants, but many existing approaches rely primarily on sequence-derived features. Because protein properties arise from physicochemical interactions in three-dimensional space, structure-derived representations may offer a useful perspective for modeling and interpreting variant–property relationships. We therefore developed Foldinsight, a structure-derived framework for modeling quantitative properties of channelrhodopsin variants and visualizing property-associated spatial regions. Foldinsight converts amino acid sequences into AlphaFold2-predicted structures, aligns the structures in a common coordinate system, and calculates van der Waals and electrostatic molecular fields on a shared three-dimensional grid. These fields provide fixed-length descriptors suitable for regression modeling. When applied to a published channelrhodopsin variant dataset, the molecular-field descriptors captured predictive signals across the measured photocurrent properties. Mapping the fitted regression coefficients back onto the molecular-field grid highlighted candidate spatial regions associated with the modeled properties and enabled their relationship to established functional and structural features to be examined. Foldinsight provides a workflow for connecting predicted protein structures with quantitative property modeling and spatial interpretation. AlphaFold-derived molecular fields offer an alternative spatial representation for channelrhodopsin variant analysis and may help generate hypotheses for future mutational experiments.
Accurate classification of enzymes and non-enzymes from protein sequences is fundamental to understanding plant metabolism, with applications in crop improvement and biotechnology. While deep learning has shown promise for protein function prediction, most approaches train from raw sequences requiring extensive computational resources. Transfer learning using pre-trained protein embeddings offers an efficient alternative, yet its application to plant enzyme classification across multiple species remains unexplored. We present a transfer learning framework combining UniProt-derived protein embeddings with attention-enhanced and baseline deep neural networks for enzyme classification in four major plant species: Arabidopsis thaliana, Brassica species, Oryza sativa, and Triticum aestivum. Our curated dataset comprises 22,267 unique protein sequences with 1024-dimensional embeddings. To prevent data leakage, we implemented homology-aware splitting using CD-HIT clustering at 60
Accurate classification of protein–protein interaction (PPI) categories is critical for elucidating intracellular signaling pathways and disease mechanisms. Reliable computational prediction methods can substantially reduce the cost of high-throughput wet-lab screening. However, existing multimodal PPI predictors generalize poorly, primarily for two reasons. First, most multi-category PPI predictors integrate only one or two of the three key feature modalities: evolutionary sequence signatures, three-dimensional (3D) structural profiles, and Gene Ontology (GO) functional annotations. This incomplete modal coverage prevents them from building comprehensive protein representations. Second, even models that cover all three modalities typically rely on shallow fusion strategies, which fail to capture the deep complementary relationships among orthogonal biological signals. This limitation leads to performance degradation on low-homology proteins and rare PPI categories. To address these limitations, we propose Tri-modal Chained Cross-Attention Protein–Protein Interaction (TriCCA-PPI), a framework with two key contributions. First, a fully decoupled feature extraction pipeline independently generates ESM-2 sequence, ESM-IF1 structural, and GO-anc2vec functional embeddings. This modular architecture supports independent replacement and upgrading of each modality’s feature extractor, and compensates for the incomplete biological characterization inherent in single- or dual-modal inputs. Second, a chained pairwise cross-attention module performs three rounds of progressive modal alignment to capture layered cross-modal complementary relationships. We further employ a global–local dual-channel Graph Isomorphism Network (GIN) with Jumping Knowledge aggregation to enhance graph topological representation. Asymmetric loss (ASL) is applied to mitigate class imbalance. Evaluations on the SHS27K and SHS148K datasets across Random, BFS, and DFS splits show that TriCCA-PPI outperforms state-of-the-art methods, with substantial gains observed on low-homology proteins and rare PPI categories. Ablation experiments validate the contribution of each modality and the advantage of chained cross-attention over shallow fusion. TriCCA-PPI addresses two key limitations of existing multimodal PPI predictors. Its decoupled, replaceable feature extraction pipeline integrates multi-dimensional biological cues into comprehensive protein representations, while chained cross-attention enables deep progressive fusion that leverages cross-modal complementary relationships. The method improves generalization for low-homology proteins and rare PPI categories, and its modular design offers a practical, interpretable, and extensible multimodal fusion framework for large-scale multi-category PPI prediction.
Accurate phasing of genomic sequences is necessary for knowing genetic variation and its role in human genomics. Formal phasing methods, such as Mendel Impute, Eagle, and Beagle, require large reference panels, which curtail scalability and limit applicability to undersampled populations. To this, we propose RefFree-Phaser, a reference-free deep learning model for genotype phasing assembled on a BigBird transformer architecture. The BigBird model architecture, founded on sparse attention, is suitable for genomic sequencing as it is computationally less expensive than full-attention-based transformers while modeling long-range dependencies. The RefFree-Phaser’s framework operates with positional embeddings and tokenizes input sequences, processes them through a 12-layer BigBird transformer with sparse attention, and derives contextualized hidden states that are mapped into final hidden state, logits, confidence scores, and binary haplotype predictions aligned with unphased genotypes and true labels. We adopted a lexicographical haplotype-pairing strategy, in which all possible haplotypes were sorted and systematically tagged according to their input genotypes. We evaluated RefFree-Phaser across two cohorts, one from the 1000 Genomes Project subset and the other from Omni2.5 M common-variants dataset. Experiments across diverse populations showed strong performance for European (EUR) and other superpopulations, while accuracy was slightly lower for African (AFR) individuals, indicating higher phase-switch, genetic diversity, and limited representation in training data. RefFree-Phaser attains average accuracies of 92.60
Lysine acetylation is a pervasive post-translational modification with critical regulatory roles, yet computational prediction of acetylation sites remains hampered by unreliable benchmarking practices including dataset redundancy and non-independent test set evaluation. We report a systematic investigation demonstrating that three independent sources of metric inflation, including near-ubiquitous sequence redundancy, non-independent test sets, and distribution-locked dimensionality reduction collectively reduced an apparent accuracy of 99.38
Transcriptomics arrived with the prospect of mechanistic deduction and quantification of active molecular pathways, providing insights into both state and function of cells. However, it remains a challenging task to interpret functional analysis of single samples of RNA-sequencing data, because of inconsistencies between methods, and inherent reliance on a priori gene signatures encoding known biological knowledge. Initially, methods were designed for experimental setups with known conditions and biological replicates, but for many use-cases, particularly in clinical diagnostics, the problem is N-of-1, where each single sample presents a unique and independent case, without replicates or baseline for comparison. Here, we are comparing the performance of 17 single-sample GSEA methods on a diverse set of datasets, with known biology, and test them on a matched collection of gene signatures, with relevance to both experimental research and clinical diagnostics. We find that truly single-sample methods perform well and that the methods that we adapted to work on individual samples, by introducing a large data collection as a universal reference, are generally able to correctly classify different samples of known phenotypes. Single-sample GSEA remains a challenging task where the tool, query data, gene signature, and potential baseline influence the results. Here, we have systematically assessed a range of tools using a designed truth set of data and gene sets. Z-score-based and truly single-sample rank-based methods were consistently competitive, but method choice must be validated for each dataset–gene set context. The benchmark is implemented in the OmniBenchmark framework, inviting continuous additions of relevant tools and datasets.
Abstract Background Protein complexes constitute fundamental functional modules within cells and play a crucial role in regulating many biological processes. Detecting protein complexes from protein-protein interaction (PPI) networks has therefore become a central problem in computational systems biology. However, many existing computational approaches struggle to accurately identify overlapping complexes where proteins participate in multiple functional modules simultaneously. In addition, large-scale PPI networks are inherently noisy and incomplete due to experimental limitations, which significantly affects the reliability of complex detection methods. Results In this work, we propose TOMOC, a topology-driven multi-objective evolutionary framework for robust detection of overlapping protein complexes in noisy PPI networks. The novelty of TOMOC lies in the integration of a topology-driven bi-objective formulation, an edge-based evolutionary representation that naturally supports overlapping memberships, and a topology-aware structural refinement mechanism within a unified framework for protein complex detection in noisy PPI networks. The proposed framework introduces an edge-based evolutionary representation that models candidate solutions at the interaction level, allowing overlapping memberships to emerge naturally during decoding. It further optimizes two complementary structural objectives by minimizing average conductance and triangle-density loss, enabling the algorithm to balance boundary quality and internal structural density. In addition, a topology-aware structural overlap refinement (SOR) operator is designed to improve structural coherence and robustness against noisy interactions through boundary-aware repair, triangle-closure expansion, and triangle-support pruning. Extensive experiments conducted on three benchmark PPI networks (Yeast-D1, Yeast-D2, and Collins) demonstrate that TOMOC achieves competitive performance compared with several state-of-the-art methods in terms of precision, recall, and F1-score. Conclusions The proposed TOMOC framework provides an effective and scalable topology-driven approach for detecting overlapping protein complexes directly from PPI network topology. By integrating multi-objective evolutionary optimization with topology-aware refinement mechanisms, TOMOC effectively captures the structural characteristics of protein complexes and demonstrates strong robustness when applied to large and noisy biological interaction networks.
MicroRNAs (miRNAs) are a class of small noncoding RNAs that inhibit the translation of target messenger RNAs (mRNAs). Given that a single miRNA can regulate the translation of many mRNAs, miRNAs have emerged as critical regulators of physiological processes. MiRNAs have been linked to the development and progression of cancers, neurodegenerative and other diseases, most recently using high-throughput miRNA “miRNome” sequencing. As miRNome sequencing represents a newer ‘omics application, limited guidance is available for how to analyze this data. Existing interfaces that enable non-computational users to interpret and perform comprehensive secondary analysis on their own miRNome data are limited in functionality and/or interactivity. Therefore, we developed MiRQuery to address this need. MiRQuery is an RShiny application which features common visualization methods for high-throughput sequencing data, such as multidimensional scaling, stacked column charts, heatmaps, and boxplots to compare expression across groups for a user-specified miRNA of interest. MiRQuery further provides support for differential miRNA and gene expression analysis. Unique to miRNome sequencing data analysis, users may retrieve predicted gene targets of differentially expressed miRNA and follow up with pathway overrepresentation analysis of the gene targets. Finally, if users upload paired bulk mRNA sequencing data, they may identify differentially expressed genes and negatively correlated miRNA-gene pairs. By providing access to sophisticated bioinformatics tools through a user-friendly interface, MiRQuery empowers both scientists new to bioinformatics and bioinformaticians new to the field to extract insights rapidly and reproducibly from their sequencing data. MiRQuery can be accessed through PositConnect at https://julianneyang-mirquery.share.connect.posit.cloud/ , and alternatively is available by user local installation via instructions on the Github project homepage.
Codon optimization is a routine yet high-impact step in de novo gene design for heterologous expression and serves as an important tool in synthetic biology. Protein expression output depends on multiple sequence-level determinants, such as global codon-usage, codon-pair context, initial mRNA folding, and motif/repeat content. However, many existing tools still provide limited transparency or restricted design flexibility. We developed Codon Design Online (CoDOn), a publicly accessible web application that formulates codon optimization as an explicit multi-objective design task and uses the non-dominated sorting genetic algorithm II (NSGA-II) to generate diverse Pareto-optimal coding sequences. CoDOn supports various design criteria that capture both host-level codon usage and local translation context, including individual codon usage (ICU), codon context (CC), codon adaptation index (CAI) and hidden stop codons. Users can also impose sequence-level constraints, e.g., GC/GC3 composition targets, 5′-proximal mRNA folding energy, and motif/repeat exclusion. Importantly, the platform features a modular interface that enables intuitive, interactive parameter configuration and result exploration through Pareto plots, codon-usage radar charts and tables, codon-pair heatmaps, and exportable reports. We showcase the utility of the platform using representative design cases in E. coli and S. cerevisiae under realistic practical constraints. CoDOn turns codon optimization from a black-box, single-output procedure into a transparent, user-configurable decision process based on Pareto trade-offs, supporting customizable gene design across hosts and applications. The CoDOn web service is available at https://codondesign.com/.
Predicting a protein’s binding sites helps to understand the functional mechanisms of protein interactions, which provides insights into drug discovery. Although experimentally determining the protein complex’s structure can accurately identify the binding residues, the process is labor-intensive and expensive. With the recent advances in the protein language model (PLM) and geometric deep learning, we introduce S2Site (Sequence and Structure based Binding Site Prediction), an end-to-end framework that incorporates the geometric deep learning model with the PLM to identify the protein binding sites. S2Site consistently outperforms various state-of-the-art methods in the protein binding site prediction of three different interactions, including protein-protein, antigen-antibody, and protein-peptide binding sites. Compared to methods based on multiple sequence alignments, PLM allows S2Site to predict protein binding sites on a large scale efficiently. Our experiments also show that both sequence and structural features contribute to the performance of binding site prediction. Overall, S2Site is a robust and practical model for efficiently identifying binding residues of various protein-ligand interactions. The source code and model can be accessed at https://github.com/LW-21/S2Site.
Enhancers are distal cis-regulatory elements that play essential roles in gene regulation, development, and disease. Although numerous computational methods have been developed for enhancer identification, commonly used DNA encoding strategies, such as one-hot and k-mer representations, typically treat DNA as a linear symbolic sequence. This simplification ignores the intrinsic geometry of the DNA double helix, where nucleotides are organized along a periodic three-dimensional structure with a helical repeat of approximately 10–11 base pairs. To address this limitation, we propose HelixPR (Helix-aware Periodic Representation), a biologically motivated DNA sequence representation for enhancer identification. HelixPR augments per-nucleotide one-hot encoding with a sinusoidal periodic encoding using a period of T=10 base pairs. It further incorporates a global nucleotide-composition token to capture sequence-level compositional information complementary to local nucleotide patterns. Together, these components form a compact, interpretable, and information-preserving representation of DNA sequences. Combined with a lightweight one-dimensional convolutional neural network, HelixPR achieved competitive performance across benchmark datasets. On Liu’s benchmark, HelixPR achieved an accuracy of 0.8434 and a Matthews correlation coefficient of 0.6874 for enhancer identification. For enhancer strength classification, HelixPR achieved an accuracy of 0.8400 and an AUC of 0.9346, outperforming baseline methods. On Basith’s benchmark, HelixPR obtained a mean balanced accuracy of 0.9778, substantially outperforming existing methods. Further analysis showed that HelixPR supports closed-form decoding and that HelixPR-highlighted regions are enriched for known transcription-factor binding motifs, supporting both the interpretability and biological relevance of the proposed representation. These results suggest that incorporating the periodic structure of the DNA double helix can improve enhancer modeling. By combining nucleotide identity, helical periodicity, and global compositional information, HelixPR offers a biologically grounded framework for enhancer identification and related regulatory sequence prediction tasks.
The Gene Ontology (GO) is a public resource that describes gene functions and characteristics through a structured vocabulary of standardised terms. It currently contains annotations for over 1.5 million gene products, each linked to one or more GO terms. In this study, we propose integrating this GO-based semantic structure into machine learning systems for medical diagnostics. This approach serves a dual purpose: first, to prioritise genes that are semantically relevant to a given clinical task, thereby refining model input; and second, to enable the analysis of biologically predefined gene sets, which may reveal novel mechanisms underlying disease. Evaluated across 16 benchmark data sets spanning diverse medical domains, our GO term-informed gene selection method generally outperformed models trained on full gene sets. Further analysis of individual GO terms not only enhanced classification performance but also identified high-performing, task-specific gene subsets that were overlooked during initial gene selection. Our findings demonstrate that Gene Ontology can be effectively leveraged for semantics-aware gene selection in clinical machine learning. Moreover, systematically evaluating individual GO terms offers a scalable strategy to uncover new, testable biological hypotheses–revealing gene functions that might otherwise remain hidden when examining only broadly selected gene combinations.
Abstract Background Standardisation, accessibility, and reproducibility remain persistent challenges in data‑intensive scientific research. The Galaxy platform addresses these issues by providing a web-based environment for executing, sharing, and publishing computational workflows, yet programmatic access has been largely centred on the Python ecosystem through BioBlend. Methods Here, we introduce GalaxyR, a native R package that provides a comprehensive and structured interface to the Galaxy application programming interface. GalaxyR enables users to manage histories, upload and retrieve data, execute tools and workflows, monitor jobs, and inspect results directly from within the R environment. By integrating Galaxy’s scalable computational infrastructure with R’s widely adopted data analysis ecosystem, GalaxyR facilitates automated, reproducible, and resource‑efficient workflows without requiring local high‑performance computing resources. The package supports both HTTPS‑ and FTP‑based data transfer, robust history and dataset management, and programmatic workflow orchestration across Galaxy instances. Results An application example demonstrates the use of GalaxyR for large-scale processing of drone-based laser scanning data, where computationally intensive tree‑level segmentation was delegated to the Galaxy infrastructure, while workflow control and preprocessing were handled in R within a few lines of code. Conclusions GalaxyR thus bridges a critical gap for R users, significantly expanding access to Galaxy‑based analyses and enabling scalable, reproducible research across bioinformatics, ecology, remote sensing, and related data-driven disciplines.
Hybridization is a pivotal evolutionary process that shapes speciation and genetic diversity across the tree of life. Traditional methods for hybridization inference rely on site-pattern summary statistics and lack the ability to capture higher-order sequence dependencies, limiting their performance in complex scenarios. Additionally, existing tools often fail to explicitly classify non-hybrid evolutionary scenarios or assign parental–hybrid lineage identities, creating challenges for interpreting results in genomic studies. There is a critical need for interpretable, efficient methods that leverage full genomic sequence information to address these limitations. DeepHyb is a convolutional neural network (CNN)-based deep learning framework designed to infer historical hybridization events directly from multiple sequence alignment-derived site-pattern and k-mer count features. It integrates four complementary feature representations—15 summary site patterns, 256 one-base site patterns, 75 summary k-mer patterns, and 256 sequence-level k-mer patterns—to capture both short-range and higher-order sequence dependencies. In the canonical four-taxon scenario, which serves as the standard framework for evaluating phylogenetic discordance under the multispecies coalescent (one outgroup + three ingroups), DeepHyb jointly predicts hybridization status and parental–hybrid lineage combinations. On simulated data under the setting of sequence length = 100,000 and mutation rate = 0.01, our method performs with high accuracy, achieving an accuracy of 0.8773, precision of 0.5000, and F1 score of 0.6667 (vs. HyDe's 0.8501, 0.4501, and 0.6202), while maintaining a recall of 1.0. On the empirical Heliconius dataset, DeepHyb reproduces the HyDe-derived hybrid/non-hybrid labels with over 93
The emergence and re-emergence of viral pathogens with pandemic potential necessitate robust computational frameworks capable of interpreting sequence variation in evolutionary and functional contexts. Lassa virus (LASV) and Ebola virus (EBOV), two members of the Arenaviridae and Filoviridae families, respectively, represent contrasting evolutionary paradigms: LASV exhibits substantial genetic diversity across West Africa, while EBOV outbreaks have historically been characterised by more constrained genetic variation. Understanding the differential mutational constraints governing these viruses provides critical insights for surveillance, vaccine design, and therapeutic development. This study presents a comprehensive, end-to-end computational framework bridging comparative virology and practical deployment. Analysis encompassed 2,502 glycoprotein (GP) sequences (780 LASV GP, 1722 EBOV GP) sourced from NCBI GenBank across all documented EBOV outbreaks (1976–2024) and curated LASV repositories. EBOV GP was extracted from full-genome assemblies via reference-guided alignment (MAFFT), enabling a direct, protein-scope-matched comparison. The framework integrates MAFFT-aligned site-level constraint categorisation through conservation and entropy analysis with substitution burden quantification to characterise the mutational landscape. Protein language model embedding-space characterisation using ESM-2 provides complementary descriptive insight through centroid geometry, outlier detection, and PCA visualisation. For supervised classification and deployment, the framework employs lightweight, interpretable composition features (sequence length and amino-acid frequencies) rather than ESM-2 embeddings, an intentional design choice that prioritises deployment efficiency and interpretability. The classifier is coupled with a computational atypicality scoring layer that quantifies sequence deviation from training-population centroids. The comparative analysis revealed profound asymmetries in mutational architecture. EBOV GP exhibited near-complete positional constraint with 94.7
Accurately predicting disease–protein relations in biomedical knowledge graphs helps link disease phenotypes to molecular mechanisms and supports disease-related knowledge discovery and candidate target identification. Biomedical knowledge graphs organize multisource biomedical knowledge, including diseases, proteins, drugs, and pathways, as entity nodes and relational edges, providing a structured foundation for modeling complex biomedical associations. Existing methods are often constrained by single-modality modeling, shallow graph–text fusion, and insufficient traceable evidence, which limits their ability to exploit graph–text complementarity and weakens downstream validation and structural evidence interpretation. To address these limitations, we propose NEOGRAN, a graph–text collaborative framework comprising three core modules for relation prediction in biomedical knowledge graphs. The dual-encoder architecture captures graph structural patterns and biomedical entity representations to mitigate single-modality modeling. The bidirectional cross-attention module enables deep graph–text interaction to overcome shallow fusion. The interpretable path module generates traceable evidence paths to support prediction verification, structural evidence interpretation, and hypothesis generation. On PrimeKG, NEOGRAN achieved an AUPR of 0.9860 and an AUROC of 0.9875 under the 1:1 sampled classification setting, and further obtained an MRR of 0.0735 in the all-candidate ranking evaluation. External validation on BioKG further shows that NEOGRAN remains effective under differences in entity coverage, relation composition, and local topology, supporting its method-level generalizability across knowledge graph sources. NEOGRAN provides an effective solution for relation prediction in biomedical knowledge graphs while offering traceable structural evidence for hypothesis generation and further biological validation.
In computational pathology, accurate multi-class tissue classification facilitates the timely detection of early stages of cancer, propitious to meticulous diagnostic chains. However, the majority of the histopathological deep learning (DL) frameworks are confined by global convolutional capabilities, inadequate sensitivity to texture patterns, and generalizability constrained from a non-binary space. To address this limitation, we propose MGH-DBNet, a multi-granular hybrid dual branch convolution neural network designed specifically for eight-class gastric histopathology classification using the GCHTID dataset, which consists of 31,096 H E-stained non-overlapping images. Texture cues are essential, as micro-structural patterns often drive accurate tissue differentiation. This multi-granular hybrid convolutional architecture includes a global feature-extraction branch built on a convolutional backbone and a lightweight local-texture encoder of Local Binary Patterns-Gray Level Co-occurrence Matrix branch designed to capture fine-grained texture patterns. Unlike simply deepening the CNN, which increases parameters without guaranteeing sensitivity to micro-textures, LBP-GLCM explicitly encodes boundary irregularities and spatial intensity dependencies, enabling MGH-DBNet to capture discriminative micro-structural patterns that deep CNNs typically miss. These two streams are integrated using an attention mechanism that adaptively emphasizes the most informative complementary cues. A comparative evaluation of contemporary Convolution Neural Networks, like DenseNet121 of similar configurations, revealed that the proposed network outperformed all other models, attaining an AUC score of 0.954. Furthermore, Grad-CAM, a heat-map-based visualization method, renders the model engaged in clinically pertinent tissue regions for improved explainability. In addition, these results maintain stability across different preprocessing settings, backbone selection, and fusion strategies during ablation studies, indicating high robustness and generalizability of the proposed MGH-DBNet framework. Pursuant to an exhaustive survey, the authors opine that the proffered solution intended for multi-class histopathology entails a distinct computationally efficient architecture that endorses quality assessment and decision support for real-world applications.
