MotivationDeveloping segmentation models that remain reliable across diverse medical imaging domains and accurately delineate complex anatomical boundaries remains a persistent challenge for clinical deployment. Variations in imaging modalities, scanners, and acquisition settings introduce significant domain shifts, while fuzzy or overlapping tissue boundaries further complicate precise segmentation. Despite extensive research, most approaches address these challenges separately, leading to limited generalization and reduced robustness in real-world clinical scenarios.ResultsTo overcome these limitations, we propose HyperSeg-DG, a novel medical image segmentation approach that integrates the WMamba backbone with the Multi-Scale Hyper Feature Context Block (HFCB). The HFCB addresses foreground–background uncertainty and boundary ambiguities by capturing multi-scale feature relations and long-range contextual dependencies. This enables the model to focus on relevant pathological features while helping reduce the influence of irrelevant co-occurring ones, such as similarly sized polyps, especially in low-contrast or poorly lit environments. WMamba further improves domain generalization by processing images in localized windows and using its selective 2D scanning mechanism to learn robust, transferable features that reduce feature misalignment under domain shift. Extensive experiments across multiple medical segmentation benchmarks demonstrate that HyperSeg-DG achieves consistent 2%–3% improvements over strong baselines, confirming its effectiveness in enhancing segmentation performance and generalization across diverse, unseen domains.Availability and implementationThe code and datasets of HyperSeg-DG are available at https://github.com/Pollob001/HyperSeg-DG.

MotivationRNA molecules adopt dynamic ensembles of secondary structures, where the local structural context of each nucleotide–such as whether it resides in a stem or a specific type of loop–strongly shapes molecular interactions and regulatory function. Structural-context probabilities therefore provide a more functionally informative view of RNA folding than the minimum free energy structures or base-pairing probabilities. However, existing tools either require time or employ span-restricted approximations that omit long-range base-pairs, limiting their applicability to large and biologically important RNAs.ResultsWe introduce LinearCapR, enabling linear-time, span-unrestricted computation of structural-context marginalized probabilities, using beam-pruned Stochastic Context Free Grammar-based computation. LinearCapR retains global ensemble features lost by span-limited methods and yields superior predictive power on bpRNA-1m(90) dataset, especially for multiloops and exterior regions, as well as long-distance stems. LinearCapR supports analysis of long RNAs, demonstrated on the full genome of SARS-CoV-2. LinearCapR provides the first base-pair-span-unrestricted, linear-time framework for RNA structural-context analysis, retaining key thermodynamic ensemble features essential for functional interpretation. It enables large-scale studies of viral genomes, long non-coding RNAs, and downstream analyses such as RNA-binding protein site prediction.Availability and ImplementationThe source code of LinearCapR is available at https://github.com/hoget157/LinearCapR. The archived software release used in this work is available at Zenodo: https://doi.org/10.5281/zenodo.19450645.

MotivationThe surge of genomic data from advanced sequencing technologies is outpacing current analytical pipelines. We introduce LCR-modules, an open-source suite of bioinformatics tools designed for flexible and automated cancer genome data analysis. LCR-modules enables reproducible analysis of diverse cancer genomics data at scale. The suite comprises 49 Snakemake-based workflows organized into three levels, facilitating tasks from low-level quality control to complex cohort-level analyses. LCR-modules supports various sequencing types and integrates pipelines such as mutation calling, expression quantification, and cohort-level aggregation, ensuring flexibility and reproducibility. LCR-modules represents a significant advancement in genomic data analysis, reducing barriers in reproducibility and scalability and has already been applied to a combination of exomes and genomes from over 10 800 samples.AvailabilityNo new data were generated in support of this research. The source code for the LCR-modules is openly available at https://github.com/LCR-BCCRC/lcr-modules.

MotivationMultiomics data analysis is essential for scientific discovery in precision medicine. However, translating analysis results of omics data analysis into novel scientific hypotheses remains a significant challenge. Human experts must manually review analysis results and generate new hypotheses based on extensive and interconnected biomedical prior knowledge, which is subjective and not scalable. While large language models can accelerate the discovery, their reasoning improves when grounded in structured, auditable, and comprehensive biomedical prior knowledge. However, biomedical knowledge is scattered across heterogeneous databases that use diverse and inconsistent nomenclature systems, making it difficult to integrate resources into a unified format for scalable analysis. This fragmentation limits the ability of artificial intelligence systems to fully leverage biomedical data for scientific discovery.ResultsWe developed BioMedGraphica, a novel all-in-one platform that harmonizes fragmented biomedical resources by integrating 11 entity types and 30 relation types from 43 databases into a unified textual prior knowledge graph containing 2 306 921 entities and 27 232 091 relations. In addition, we present a novel textual-numeric graph (TNG) data structure concept, where textual information captures prior biological knowledge (e.g. transcription start sites, functions, mechanisms), numeric values represent quantitative biomedical features, and the integrated relations can help uncover mechanisms. By bridging prior knowledge with user-specific data, TNG is a novel and ideal data structure for developing novel graph analysis models.Availability and implementationThe code is available at: https://github.com/FuhaiLiAiLab/BioMedGraphica and BioMedGraphica knowledge graph database can be downloaded from huggingface dataset: https://huggingface.co/datasets/FuhaiLiAiLab/BioMedGraphica

MotivationT cell receptor (TCR) recognition of peptide-major histocompatibility complex (pMHC) complexes is central to adaptive immunity, yet rational design of immunogenic epitopes remains elusive due to complex triplet binding constraints and data scarcity. No existing method can generate epitopes satisfying simultaneous requirements for antigenicity, MHC presentation, and TCR specificity.ResultsWe present EPIC, a multi-objective diffusion framework that decomposes TCR-pMHC binding into three biologically grounded sub-tasks, enabling training-free gradient guidance without end-to-end retraining. By integrating ESM-based classifiers with a peptide diffusion generator, EPIC leverages heterogeneous immunological interaction datasets to generate diverse, context-aware epitopes. EPIC-designed top-three epitopes achieve lower predicted interface energies compared to ground-truth epitopes in 78.31% of test cases, while maintaining 80.1% sequence novelty and comparable structural confidence. Generated epitopes exhibit 100% uniqueness, high diversity (64.05%), and high antigenicity scores (0.4723). To our knowledge, EPIC is the first computational framework capable of de novo epitope design while explicitly integrating the triplet constraints of TCR-pMHC binding. This paradigm shift from discovery to design unlocks new potential for personalized cancer vaccines, precision adoptive T cell therapy, and rapid response to emerging infectious diseases.Availability and implementationThe source code of EPIC is available at https://github.com/Octopus125/EPIC and archived on Zenodo (DOI: 10.5281/zenodo.18537646).

MotivationEnhancer–promoter interactions (EPIs) are essential for gene regulation and disease progression. Recent studies have shown that distal enhancers can regulate target genes through interactions with nearby promoters, providing important insights into transcriptional regulation mechanisms. Although high-throughput experimental techniques have enabled large-scale identification of EPIs, these methods are often costly and time-consuming. In addition, existing computational approaches still face challenges in effectively integrating heterogeneous feature representations from different cell lines.ResultsWe propose a stacked ensemble framework for EPI prediction that integrates feature representations from diverse cell line datasets using multiple machine learning algorithms. The extracted complementary patterns are further combined by an XGBoost classifier to improve robustness against overfitting. Experiments on six independent datasets show that the proposed method achieves superior accuracy and generalization compared with existing EPI prediction models, with an average AUROC of 0.909 while maintaining computational efficiency.AvailabilityThe source code and its archived release are available at GitHub and Zenodo. The Zenodo archive provides a versioned snapshot of the repository: https://zenodo.org/records/19952998

MotivationPredicting protein function is a fundamental and challenging task that requires integrating diverse biological data modalities to capture complex functional relationships. Traditional machine learning methods often rely on single modalities or combine only a limited number (typically two), without aligning them in a unified representation, thereby constraining predictive accuracy. Moreover, most existing machine learning approaches are limited to preselected subsets of Gene Ontology (GO) function terms with sufficient annotations, making the prediction of novel function terms a persistent challenge.ResultsHere, we present FunBind, a multimodal AI model that jointly learns from five modalities, i.e., protein sequences, textual descriptions, domain annotations, structures, and GO terms, to enhance prediction accuracy and infer previously unseen functions. FunBind operates in two modes: (1) self-supervised pretraining using contrastive learning to align the sequence modality with other heterogeneous modalities in a unified latent space, enabling unsupervised zero-shot function prediction, and (2) supervised fine-tuning of the pretrained model to leverage all non-function modalities for comprehensive and accurate function classification. Our results show that FunBind’s zero-shot capabilities allow it to generalize effectively to novel function terms never encountered before, while its joint multimodal fine-tuning strategy outperforms single-modality models and current state-of-the-art deep learning methods in typical function prediction settings.Availabilityhttps://github.com/jianlin-cheng/FunBind

SummaryWe assess batch correction methods for MALDI mass spectrometry imaging experiments. ComBAT reduced batch-related technical variance, maintained biological variation, and improved the overall score by 19.4%.Availability and implementationMethods are available in R. comBAT is used through the “sva” package while Harmony, CCA, FastMNN are available in the “Seurat” package https://github.com/satijalab/seurat. scVI, scANVI are Scanorama are available in the Python programming language and through their github https://github.com/scverse/scvi-tools. Associated R code is found at DOI: https://doi.org/10.5281/zenodo.19730022.

MotivationEpistasis, or genetic interaction, plays a crucial role in shaping complex traits and has been increasingly recognized for its widespread influence in genetic architectures. While epistasis detection has been extensively evaluated in case-control studies, its performance with quantitative phenotypes remains comparatively understudied.ResultsWe identified and evaluated six epistasis detection methods applicable to quantitative trait analysis: EpiSNP, Matrix Epistasis, MIDESP, PLINK Epistasis, QMDR, and REMMA. Using the EpiGEN simulator, we generated synthetic datasets modeling four classes of pairwise SNP interactions—dominant, multiplicative, recessive, and XOR. We also assessed BOOST and MDR algorithms using discretized (case-control) versions of the same datasets. Performance varied notably by interaction type: REMMA achieved the highest overall detection rate (55%), particularly excelling with dominant interactions (100%). MDR excelled with multiplicative (57%) and XOR (69%) interactions. Meanwhile, EpiSNP attained the best performance for recessive interactions (67%). All methods except BOOST produced F1 scores below 0.05 for most interaction types. We further evaluated the methods using a real-world dataset. When applied to the Adolescent Brain Cognitive Development dataset to analyse the externalizing behavior phenotype, both PLINK Epistasis and PLINK BOOST identified SNPs within the DRD2 and DRD4 genes, consistent with previously reported genetic associations. Given the variability in tool performance across interaction types, no single method provides optimal detection across all scenarios. Leveraging multiple detection algorithms may therefore yield more comprehensive insights into epistatic effects in quantitative trait analyses.Availability and implementationAll relevant code and simulated datasets can be found at github.com/staslist/Epistasis_Review repository.

MotivationMolecular maps are graphical representations of the molecular mechanisms underlying biological systems. They are a valuable tool for curating, exchanging, and understanding biological knowledge, and may serve as a backbone for data analysis and modelling. Molecular maps are supported by a rich software ecosystem. However, there are currently no tools that support advanced programmatic analysis and processing of maps, in particular the extraction of the biological concepts they represent or their comparison.ResultsWe introduce momapy, a generic Python library to work with molecular maps programmatically. At its core, momapy allows users to extract and separate the data model of a map from its graphical representation, and perform a variety of base operations on them, including their manipulation and comparison. momapy currently supports the SBGN and CellDesigner formats, two of the main standards to represent molecular maps graphically, and can be easily extended to support additional formats and functionalities.Availabilitymomapy is implemented in Python (RRID:SCR_008394) under a GPLv3 license. The code can be downloaded freely from https://github.com/adrienrougny/momapy and is archived on Zenodo (https://doi.org/10.5281/zenodo.19088611). Complete documentation and a user manual are available at https://adrienrougny.github.io/momapy.