Latest bioRxiv papers

Category: bioinformatics — Showing 50 items

• Trends in Machine Learning and Feature Selection Stability for Human Gut Microbiome (Shotgun Metagenomics) and Metabolomics Matched Datasets

  Palmer, S. N.; Mishra, A. A.; Zarek, C. M.; Gan, S.; Wang, R.; Kim, J.; Liu, D.; Koh, A.; Zhan, X.

  Abstract

  Microbiome research is often limited by methodological inconsistencies that reduce reproducibility and functional insight. Traditional taxonomy-based profiling is limited by sparse data, variable resolution, and reliance on gDNA sequencing which provides only indirect links to microbial function. Multi-omics integration offers a framework for linking community composition to functional outputs, but progress has been hindered by the lack of standardized frameworks and inconsistent use of machine learning. In particular, feature selection stability, which is central to biomarker discovery and experimental validation, remains underexplored. Here, we systematically benchmarked three widely used algorithms (Elastic Net, Random Forest, XGBoost) across seven multi-omics integration strategies and single-omics models. Additionally, we evaluated the impact of transforming metabolomics and taxonomic abundance data. Using human gut microbiome datasets that integrate metagenomic taxonomic profiles with metabolomics, we evaluated models for 9 binary and 8 continuous outcomes across 20 train/test splits per dataset. We further assessed the effect of feature reduction on both predictive accuracy and feature selection stability. Nonlinear learners were most consistently competitive: continuous outcomes favored metabolomics-dominant models, whereas binary outcomes favored stacked multi-omics models. Random Forest and XGBoost also yielded greater feature selection stability, particularly for full dimensional metabolomics data. Together, these findings demonstrate how integration strategy, algorithm choice, and data preprocessing jointly shape predictive performance and feature selection reproducibility in multi-omics microbiome modeling.

  bioinformatics2026-08-29v4

• CIViC-Fact: a proof-of-concept framework for AI-assisted verification of cancer variant interpretations

  Reisle, C.; Grisdale, C. J.; Krysiak, K.; Danos, A. M.; Khanfar, M.; Pleasance, E.; Saliba, J.; Hanos, M.; Patel, N. V.; Jain, A.; Seifi, M.; McMichael, J. F.; Venigalla, A. C.; Griffith, M.; Griffith, O. L.; Jones, S. J. M.

  Abstract

  Accurate interpretation of genomic variants is critical for precision oncology but remains slow and dependent on specialized expertise. Public knowledgebases such as the Clinical Interpretation of Variants in Cancer (CIViC) help by curating literature-backed variant interpretations in a structured form, yet verification and review have become major bottlenecks. Large language models (LLMs) offer a potential mechanism for accelerating biomedical claim verification, but their rapid turnover, variable availability, and known risks of unsupported reasoning require standardized and reproducible evaluation before integration into curation workflows. To address this, we developed CIViC-Fact, an expert-curated, full-text benchmark and evaluation framework. Domain experts linked structured cancer-variant claims to sentence-level evidence from source publications, including evidence from full-text articles, tables, and non-abstract sections that are commonly omitted from existing biomedical question-answering and scientific fact-checking datasets. Claim-verification reference labels were derived from CIViC records, revision histories and controlled data augmentation. A major finding of CIViC-Fact is that abstracts are insufficient for realistic biomedical claim verification. In the evaluated development subset of text-verifiable entries with full-text access, fewer than 30% could be fully validated from the abstract alone, highlighting the importance of full-text evaluation for biomedical curation. Upon the application of our fact-checking pipeline to newly submitted CIViC entries, after excluding entries requiring supplementary material or images for validation, automated retrieval successfully identified appropriate evidence for most cases (93%), supporting low-incremental-effort evaluation of future systems. Fine-tuning improved agreement with CIViC-Fact reference labels on the static benchmark, but larger general-purpose models performed better on a heterogeneous post-cutoff cohort. These findings support CIViC-Fact primarily as a reproducible framework for comparing evolving retrieval and verification systems rather than as validation of a single deployment-ready model. These findings suggest that, in a rapidly changing model landscape, the durable contribution is not a single optimized model but a reproducible benchmark framework that enables continual testing, model substitution, and lightweight updating through small high-quality few-shot exemplar sets.

  bioinformatics2026-08-29v3

• HANSEN: An Integrated Structural and Functional Proteome Resource for Structure-Guided Drug Discovery in Mycobacterium leprae

  Vedithi, S. C.; Rees, R.; Malhotra, S.; Munir, A.; Matusevicius, M.; Alsulami, A. F.; Beaudoin, C. A.; Sunkara, K. S.; Das, M.; Blundell, T. L.; Floto, R. A.

  Abstract

  Leprosy remains a leading infectious cause of preventable disability, yet its causative agent, Mycobacterium leprae (M. leprae), is structurally under-characterised. Only ten Protein Data Bank (PDB) entries represent seven of its 1,603 protein-coding genes. We present HANSEN, a proteome-wide structural and functional resource for M. leprae. Monomeric and oligomeric models were generated with AlphaFold 3, Boltz-1, Boltz-2 and Chai-1, and annotated with per-residue confidence, predicted aligned error and, for assemblies, interface confidence. Ligand-binding pockets were predicted with AF2BIND, P2Rank and fpocket, template-derived ligands were modelled within oligomeric complexes, residue-level B-cell epitope propensity was estimated with DiscoTope-3.0, and gene essentiality was transferred from Mycobacterium tuberculosis transposon-sequencing labels. These features are integrated in a relational database with interactive visualisation and combined into a calibrated Target Priority Score that ranks all 1,603 proteins into four tiers and recovers established antimycobacterial targets. HANSEN (https://hansen-leprosy.medschl.cam.ac.uk/home) provides a practical basis for target prioritisation and structure-guided drug discovery in leprosy.

  bioinformatics2026-08-29v2

• FuncSeek: Multi-PLM contrastive learning for protein functional similarity search

  Cloete, L. J.; Patterton, H. G.

  Abstract

  Below 30% pairwise sequence identity, alignment-based methods struggle to reliably distinguish true homologs from chance, and enzyme function prediction degrades accordingly: on proteins in this regime, even advanced methods (CLEAN) achieves only 55.1% accuracy at full EC specificity on the CARE benchmark. To this end Protein Language Models (PLMs) have gained favor as alternatives. However, PLMs often encode only a subset of the biology, whereas the understanding of enzyme function requires among other things a combination of sequence, structure and functional-context simultaneously. In this work, we describe FuncSeek, a contrastive learning model which utilizes three diverse, complementary PLMs: ESM2 (to model evolutionary co-variation), ProstT5 (for bilingual sequence and structure embeddings), and ProteinBERT (for functional semantic similarities). Using SwissProt data, these 2816-D embeddings are labelled with Enzyme Commission numbers (EC) and are trained through a supervised contrastive head into a 256-D space. FuncSeek attains 64.6% nearest-neighbour EC4 accuracy on the CARE out-of-distribution benchmark set (ood30; proteins below 30% identity to training set), outperforming CLEAN (55.1%) and Diamond BLASTp (51.4%), and obtains 93.7% nearest-neighbour EC4 accuracy on the promiscuous, multi-functional enzymes benchmark (CLEAN, 69.4%). We also show that the learned representations transfer without retraining to the TrEMBL database, achieving 97.3% nearest-neighbour EC4 accuracy on an 8,031 BRENDA-validated enzyme set, never seen during training. Because only projected embeddings are stored in the target index, and function is inferred from an annotated reference set, we propose this paradigm for rapidly searching extremely large metagenomic databases, bypassing costly sequence alignment and annotation pipelines.

  bioinformatics2026-08-29v2

• Genome-Wide in silico analysis reveals activation of a silent resistome driving imipenem resistance in Pseudomonas aeruginosa

  Anwar, S.; Aromal, A. R.; Anurag Anand, A.; Samanta, S. K.

  Abstract

  Resistance to imipenem in Pseudomonas aeruginosa relies on multiple factors that remain poorly understood. In our work, we performed a systemic analysis of genome-wide changes involved in resistance in a set of 95 clinically unrelated strains, including 41 resistant (MIC [≥] 64 mg/L) and 54 susceptible (MIC [≤] 2 mg/L) isolates. Our approach is based on the pan-genomics analysis, combining the use of core-genome phylogenetic analysis, MLST (Multilocus Sequence Typing), GWAS (Genome-Wide Association Studies) and variant level profiling of the blaOXA genes. Higher-order structure within the set was studied using methods of the co-occurrence networks and WGCNA (weighted gene co-expression network analysis) specifically adjusted to handle presence/absence data. Despite having a broader and more diverse resistome, no clonal grouping of the resistant isolates was observed indicating independent evolutionary origins. The LASSO model using a lineage-aware approach showed robust predictive capability (AUC = 0.836) that validates the polygenic characteristic of resistance. Twelve accessory genes were found to be significant determinants of resistance; however, only four genes (group_10880, group_10887, group_4947, and phzB) were identified using both GWAS and gene network analysis, showing involvement in protein folding, metal stress response, genome plasticity, and metabolic adaptation. Interestingly, some carbapenemase-active variants of blaOXA were also found in imipenem-susceptible strains, showing that gene presence alone does not ensure resistance. We therefore propose the Silent Resistome Activation Model, where resistance genes become functional only with support from identified accessory genes and coordinated interactions at both the genomic and network levels.

  bioinformatics2026-08-29v2

• Bacterial metagenome in plaque, saliva, and tumor samples from individuals with and without OSCC by next-generation sequencing

  ERIRA, A.; ROBAYO, D. A. G.; GAMBOA, F.; CHALA, A.; MORENO, A.; ARREGUI, A. C.; MUNOZ, E.; NOGUERA, J.; TOBAR-TOSSE, F.

  Abstract

  Background: Oral dysbiosis has been associated with oral squamous cell carcinoma (OSCC); however, most microbiome studies rely on 16S ribosomal RNA (rRNA) gene sequencing, limiting species-level taxonomic resolution. Methods: Dental plaque, saliva, and tumor tissue samples from 10 patients with OSCC and dental plaque and saliva samples from 10 healthy controls were analyzed in this exploratory cross-sectional study. DNA was extracted and subjected to shotgun metagenomic sequencing using the Illumina MiSeq platform. Sequence reads were quality filtered with fastp, taxonomically classified using Kraken2 v2.1.3, and species-level abundances were re-estimated with Bracken v2.9 following the removal of human reads and low abundance taxa. Relative abundances were compared using the Mann Whitney U test with the Benjamini Hochberg false discovery rate correction, while the Bray Curtis principal coordinate analysis was used as an exploratory approach to visualize microbial community patterns. Results: Shotgun metagenomic sequencing revealed distinct bacterial community profiles across the oral microenvironment. Dental plaque exhibited the highest taxonomic diversity and relative abundance. The control plaque was enriched in Streptococcus koreensis, Capnocytophaga sp. oral taxon 878, Treponema sp. Marseille Q4132, and Leptotrichia sp. oral taxon 498, whereas the plaque from patients with OSCC showed a higher relative abundance of Pyramidobacter piscolens, Parvimonas parva, and Gemella sanguinis. Salivary samples displayed lower diversity and a more homogeneous composition, predominantly comprising Capnocytophaga endodontalis, Prevotella jejuni, Aggregatibacter aphrophilus, and Gemella sanguinis. The tumor tissue showed relatively higher abundance of Sellimonas catena, Escherichia coli, Solobacterium moorei, and Lacrimispora sp. HJ 01. Conclusions: This exploratory study provides species-level characterization of the oral microbiome across multiple oral microenvironments in OSCC and generates hypotheses for future integrative metagenomic and functional studies investigating the potential contribution of oral bacterial communities to OSCC pathogenesis.

  bioinformatics2026-08-29v1

• Quantifying the Rearrangement Complexity of Pangenomes

  Bohnenkaemper, L.; Stoye, J.

  Abstract

  The study of evolution between species (phylogenetics) and the study of evolution within a species (population genetics) are highly related, as the same biological mechanisms are fundamental to both fields. Although both have been studied for a long time, their joint study in a unified setting has been prevented by the different time scales they consider and the different data types they employ. A similar discrepancy holds for their whole-genome specializations, comparative genomics and pangenomics. Two active areas in these fields are genome rearrangement studies and graphical pangenomics, respectively. Since the emergence of graphical pangenomics, these have existed as separate fields, despite observations that central data structures representing genomic variants in both fields are highly similar. While there exists a wealth of theoretical results for various rearrangement models in comparative genomics, the application to pangenomic data is hampered by the limitations of rearrangement problem formulations. On the practical side, pangenomes typically contain too many individual genomes for classical problems, such as the often NP-hard parsimony problems, to be solved, or for all-vs-all comparisons using rearrangement distances to be performed. On the theoretical side, some assumptions in the formulation of rearrangement problems, such as the assumption of an underlying tree, are inadequate for many pangenomes. In this work, we propose the Complete Ancestral Reconstruction for Pangenomes (CARP) problem, which overcomes these limitations while retaining intuitive relationships to both classical rearrangement problems and pangenome graphs.

  bioinformatics2026-08-29v1

• When AI encounters natural history: Morphological OTUs reshape our understanding of Earth's life

  Zhan, Z.; Ye, M.; Orr, M. C.; Chen, W.; Liu, X.; Yue, L.; Sun, X.; Zhang, F.

  Abstract

  Biodiversity can be quantified only after organisms are assigned to reproducible units, yet most individuals encountered in nature lack reliable species-level identifications. Molecular operational taxonomic units can organize unnamed diversity, whereas image-based approaches generally depend on predefined species levels. Here, we show that operational biodiversity units can be derived directly from phenotypes. We developed morphOTU, a framework combining self-supervised representation learning, operational metric supervision, and adaptive hierarchical clustering to organize specimen images in continuous phenotypic space. Across five benchmark datasets comprising flowers, wood anatomy, and beetle habitus, morphOTUs recovered coherent species-level structure and produced -diversity estimates close to those obtained from expert identifications. This structure remained informative when species were excluded from representation learning, when labeled data were sparse, and per-species sampling was limited. In a heterogeneous field-survey dataset of 4,717 insects representing 269 species across 12 orders, fine-tuning on only 28 common species produced diversity estimates close to expert labels (Shannon index, 3.75 versus 3.53). Visual explanations localized variation to biologically meaningful structures, including body outliers, surface sculpture, floral symmetry, and wood vessels. Morphological units therefore provide an operational layer for organizing and quantifying biodiversity before, alongside, or in the absence of formal species names.

  bioinformatics2026-08-28v3

• Can SMILES be fragmented into a concatenable ordered sequence of retrosynthetically interesting string block ?

  Reboul, E.; Prabakaran, H.; Waldispuhl, J.; Taly, A.

  Abstract

  Molecules generated by deep learning models are often difficult to synthesize. Their synthetic accessibility can be improved with automated retrosynthetic analysis, which allows for identifying synthons. However, synthons in a SMILES can be scattered throughout the string depending on the path taken through the molecular graph used to generate the SMILES. We tested whether the ensemble of possible SMILES for a molecule can be used to generate a concatenable ordered sequence of string fragments (blocks) from SMILES that match potential synthons obtained through automated retrosynthetic analysis. We found that exhaustively sampling the SMILES space of a molecule improves the coverage of retrosynthetic breaks. We achieved full coverage of retrosynthetic bonds in string form for 85\% of the 1.9 million molecules in the MOSES dataset. Doing so allowed us to test our block SMILES in an unconditional de novo drug design test case with MolGPT and Monte Carlo Tree Search (MCTS). We found that using blocks as an LLM's token did degrade MolGPT performance due to the curse of dimensionality. However, using the SMILES selected by our blocking algorithm with the default SMILES tokenizer improved the reproduction of physico-chemical properties of samples and also improved uniqueness, novelty, and validity. The MCTS outperforms our MolGPT models in terms of validity and novelty. However, samples generated by the MCTS had physico-chemical properties that were further away from the MOSES baseline than the samples produced by molGPT, with an improved distribution of quantitative estimation of drug-likeness (QED).

  bioinformatics2026-08-28v2

• Evaluating Aggregated Gene Level eQTL Scores

  Meyer, D.; Popko, N.; Laub, D.; Schofield, P.; Amariuta, T.; Alexandrov, L. B.; Carter, H.

  Abstract

  Genetic feature engineering, used in methods such as transcriptome-wide association study, supports gene-trait association testing by aggregating single variants into gene-level features predictive of expression. To evaluate how different model architectures, LD filtering thresholds, and variant prioritization methods affect expression prediction quality, we trained over 3 million models and evaluated their performance in independent cohorts. Using the best performing models to impute expression and immunotherapy response as an example trait, we found a significant association with the reactive oxygen species pathway (p=0.032). Our model training workflow will support genetic feature engineering towards improved complex trait modeling.

  bioinformatics2026-08-28v2

• Gene expression inference from cell-free DNA using uncertainty-aware deep learning

  Patton, R. D.; McDeed, A. P.; Netzley, A.; Pawar, A.; Persse, T. W.; Nair, A.; Galipeau, P. C.; Coleman, I. M.; Itagi, P.; Chandra, P.; Sayar, E.; Adil, M.; Vashisth, M.; Hiatt, J. B.; Dumpit, R.; Kollath, L.; Demirci, R. A.; Ghodsi, A.; Lam, H.-M.; Morrissey, C.; Chen, D. L.; Schweizer, M. T.; Iravani, A.; Hsieh, A. C.; MacPherson, D.; Haffner, M. C.; Nelson, P. S.; Ha, G.

  Abstract

  Tumor gene expression profiling provides crucial diagnostic information for guiding therapy, but standard tissue biopsies are invasive, spatially biased, and may inadequately sample metastatic disease. Cell-free DNA (cfDNA) provides a minimally invasive alternative for tumor genotyping, yet reconstructing robust, transcriptome-wide expression from standard-depth cfDNA whole-genome sequencing (WGS) remains a major challenge. We developed a deep learning framework comprising Triton, for comprehensive cfDNA feature extraction, and Proteus, a probabilistic model that infers single-gene expression from standard-depth cfDNA WGS. Proteus outperformed prior cfDNA approaches in reconstructing molecular phenotypes from matched tumor transcriptomes across multiple cancer types, including prostate, lung, and bladder cancer cohorts, with uncertainty-guided withholding improving model reliability. Proteus further enabled assessment of therapeutic target activity, prognostic transcriptional programs, and candidate treatment-emergent resistance states, establishing a generalizable framework for minimally invasive functional genomics in precision oncology.

  bioinformatics2026-08-28v2

• CoTRA: an integrated R/Shiny framework for transparent bulk and single-cell RNA-seq analysis

  Seemab, U.; Vainionpaa, K.; Tanoli, Z.; Leinonen, H. O.

  Abstract

  Bulk and single-cell RNA sequencing (scRNA-seq) have become essential for investigating disease mechanisms and identifying diagnostic biomarkers. However, the growing volume of transcriptomic data remains difficult to reuse efficiently for many researchers. Downstream analysis often requires multiple statistical, visualization, and reporting tools, creating fragmented workflows that reduce transparency and reproducibility, particularly when analyzing scRNA-seq data. To address this gap, we developed CoTRA (Comprehensive Toolbox for RNA-seq Analysis), an open-source R/Shiny package for bulk and scRNA analysis. CoTRA integrates established methods into modular workflows, exposes parameters, and offers alternatives at selected stages. It supports bulk RNA-seq quality assessment, differential expression, annotation, enrichment, and reporting, as well as scRNA quality control, dimensionality reduction, clustering, marker identification, cell-type annotation, differential abundance, trajectory inference, pathway activity, and cell-cell communication. CoTRA runs on workstations or HPC environments without mandatory external data submission and was tested on Linux, Windows, and macOS. Compared with 14 other platforms for bulk RNA-seq/scRNA-seq, CoTRA supported 46 of 49 predefined functionality criteria. Tool validation using published rd10 retinal bulk RNA-seq identified 1,947 shared differentially expressed genes with concordant direction and strong log2 fold-change agreement. A retinal scRNA-seq case study demonstrated appropriate clustering, cell-type resolved analysis, and pathway activity scoring. CoTRA provides a graphical environment for bulk and single-cell RNA-seq analysis while retaining parameter transparency, methodological flexibility, and reproducible outputs. Strong concordance with the published bulk RNA-seq analysis supports the workflow consistency, while the single-cell case study demonstrates its applicability to advanced scRNA-seq analysis. The source code is freely available at https://github.com/UmairSeemab/CoTRA.

  bioinformatics2026-08-28v1

• OmicsFM brings proteomics into the foundation model era

  Heyndrickx, S.; Gabriels, R.; Ramadasan, H.; Martens, L.; Claeys, T.

  Abstract

  While foundation models have been shown to learn biological representations from large transcriptomic atlases, it remained unknown whether proteomics data allow the same. We here therefore introduce OmicsFM, a modality-agnostic transformer pretrained through masked abundance reconstruction on an unprecedented proteomics data corpus of 48,837 quality-filtered proteomics profiles from 1,397 reprocessed PRIDE projects. Interestingly, despite training on 14- to 93-fold fewer profiles than matched bulk- and single-cell transcriptomic models, respectively, our proteomics model rivals both. On held-out projects, OmicsFM attention networks recovered more molecular relationships than co-expression methods and existing single-cell foundation models across nine reference databases that reveal pathway-level organization. Sample-level embeddings preserved biological structure across independent studies, and its representations transferred successfully to cell-type classification, gene-essentiality prediction, and perturbation-response prediction, while consistently outperforming task-specific models. Moreover, our results show that proteomics and transcriptomics representations capture complementary biology. OmicsFM thus firmly establishes the possibility of training highly performant proteomics-based foundation models, and their importance in modelling and uncovering fundamental biology.

  bioinformatics2026-08-28v1

• A pretrained unified model enables cellular functional profile prediction and multi-objective virtual drug screening

  Chen, R.; Huang, L.; Qiao, Y.; Mandal, S.; Mo, L.; Li, L.; Leshchiner, D.; Zhang, X.; Pu, J.; Xie, Y.; Girgis, R.; Ellsworth, E.; Huang, L.; Chen, X.; Li, X.; Zhou, J.; Chen, B.

  Abstract

  Cells are characterized by molecular states, coordinated molecular interactions, regulatory programs, and responses to perturbations. Systematic mapping of these cellular functional profiles across biological contexts remains experimentally costly and fragmented. Here we present InsilicoCell, a pretrained multi-modal, multi-task model that unifies prediction of cellular functional profiles spanning molecular states, molecular interactions, and perturbation-induced responses. Built on a supervised transformer architecture and pretrained on more than 88 million measurements across seven tasks, including drug sensitivity, drug-induced gene expression, and drug-protein binding, InsilicoCell learns a shared representation that links molecular profiles to cellular phenotypes, improves performance over task-specific models, and generalizes to unseen entities, contexts, and conditions. InsilicoCell extends beyond cell line systems to patient, spatial and single-cell settings, and enables multi-objective virtual drug screening. It identifies novel candidate compounds with experimental validation, including c-Myc activity inhibitors, antifibrotic agents and stemness-inducing compounds. Together, InsilicoCell provides a scalable framework for predictive cellular biology and therapeutic discovery.

  bioinformatics2026-08-28v1

• Label Noise Limits TCR-pMHC Specificity Prediction: Improved Performance Through AlphaFold3-Based Structural Modeling and Data Denoising

  Ballesteros-Cuartero, P.; Lund, J.; Nielsen, M.

  Abstract

  T cell receptor (TCR) binding to peptides presented by major histocompatibility complex (MHC) molecules is a key step in T cell activation, and forms the basis of adaptive immunity. Predicting this specificity is therefore essential to developing effective TCR-based immunotherapies and vaccines. Despite its clinical relevance, predicting TCR-pMHC specificity for previously unseen peptides remains an open problem, with structural modeling so far the only strategy showing any predictive power in this setting. In this study, we find that this limited performance is substantially driven by label noise in the data used to train and evaluate these methods, an effect that has so far been largely underexplored. Using an AlphaFold3-based pipeline adapted for TCR-pMHC structural modeling, we achieve state-of-the-art specificity prediction, outperforming AlphaFold2.3-based and sequence based methods, and performing at par with the leading Immrep2025 competition submission. Combining this pipeline with a cluster-based denoising algorithm, we show that removing mislabeled points from a large specificity dataset increased binder ranking accuracy by more than 70% relative to the full dataset. Together, these results highlight label noise as a major factor limiting the performance that any method in this field can achieve, and show that combining structural modeling with label denoising substantially improves TCR-pMHC specificity prediction, making such approaches an attractive complement to current sequence-based approaches for refining TCR target selection.

  bioinformatics2026-08-28v1

• FOCUS-3D: Robust, generalizable volumetric cell segmentation for three-dimensional fluorescence microscopy

  Zhang, Q.; Mu, Z.; Liu, B.; Chi, Y.; Li, D.; Wang, W.; Ni, J.-Q.; Wan, Y.; Yu, L.; Navajas Acedo, J.; Yu, G.

  Abstract

  Understanding how cells establish spatial organization within tissues is a fundamental question in life sciences. While modern three-dimensional fluorescence microscopy captures large-volume tissue architecture, extracting quantitative cellular insights from complex volumetric datasets remains a major barrier. Here, we introduce FOCUS-3D, a robust, broadly generalizable volumetric cell segmentation framework built on a large, diverse manually annotated cell resource and advanced AI designs. Integrating volumetric representation learning, multi-scale feature extraction, and query-based mask prediction, FOCUS-3D achieves state-of-the-art performance across diverse species, tissues, fluorescent reporters and imaging modalities. During zebrafish (Danio rerio) development, FOCUS-3D uncovers three successive phases of notochord morphogenesis. We disentangle early motility-driven rearrangements from later cell shape remodeling and tissue repacking, and further link these morphological states to spatial and developmental transcriptional programs across independent datasets.

  bioinformatics2026-08-28v1

• Deciphering the Gut-Brain Dialogue: A Survey-Based and In-Silico Comparative Analysis of Gut Microbial Dysbiosis in Common Neurological Disorders

  Goyal, S.; Kalra, A.

  Abstract

  The gut microbiome maintains a complex, bidirectional communication network with the central nervous system, commonly referred to as the gut-brain axis and its disruption has been implicated in several neurological disorders. This study combines a survey-based assessment of public awareness with an in-silico comparative analysis of gut microbial dysbiosis across four prevalent neurological disorders as observed in the current study: depression, anxiety, schizophrenia and autism spectrum disorder (ASD). A structured, anonymous online survey (n = 230) captured perceptions of the gut-brain connection along with dietary, lifestyle and gastrointestinal correlates of stress in a predominantly young, health-sciences-affiliated Indian cohort. In parallel, disorder-specific lists of elevated and reduced faecal microbial taxa were retrieved from the Disbiome database, compared using a multiple list comparator and taxonomically classified using the NCBI Taxonomy tool to construct phylogenetic trees in iTOL. Approximately three-quarters of respondents were aware of a potential gut-mental health link, yet about half reported no specific dietary practice and roughly 60% experienced stress-related digestive symptoms while rarely seeking medical consultation for them. Comparative analysis showed that depression, anxiety and schizophrenia shared a substantially overlapping dysbiosis signature, with common elevation of Actinomyces, Bacteroidaceae, Blautia, Eggerthella, Oscillibacter, Parasutterella and Veillonella and common reduction of Coprococcus, Lachnospiraceae, Ruminococcaceae, Clostridium, Faecalibacterium and Sutterella. In contrast, ASD displayed a distinct microbial signature with limited overlap with the other three disorders. Phylogenetic clustering confirmed that the shared taxa belonged predominantly to the phyla Bacillota (formerly Firmicutes), Bacteroidota (formerly Bacteroidetes), Actinomycetota (formerly Actinobacteria) and Pseudomonadota (formerly Proteobacteria). Notably, this phylum-level pattern parallels recent comparative analyses of microbial dysbiosis in neurodegenerative diseases, suggesting that broad phylogenetic shifts may be a relatively general correlate of chronic neurological disease, while disorder specificity emerges at the level of individual taxa. These findings support a shared microbial pathway linking depression, anxiety and schizophrenia that is distinct from the dysbiosis pattern observed in ASD and they underscore the value of microbiome-informed, disorder-specific therapeutic strategies.

  bioinformatics2026-08-28v1

• Erosion of regenerative regulation: age-associated shifts in the skeletal muscle fiber epigenome and transcriptome

  Moo, K. G.; Orchard, P.; Varshney, A.; D'Oliveira Albanus, R.; Manickam, N.; Kinnunen, L.; Lakka, T. A.; Saramies, J.; Laakso, M.; Tuomilehto, J.; Mohlke, K. L.; Boehnke, M.; Scott, L. J.; Koistinen, H. A.; Collins, F. S.; Parker, S. C.

  Abstract

  Skeletal muscle aging is characterized by the deterioration of muscle function, which can lead to negative quality-of-life outcomes including frailty and sarcopenia. While understanding the mechanisms of this process is increasingly important as the global population ages, previous molecular studies of skeletal muscle aging have been limited by statistical power and cell type resolution. In this study, we analyzed single-nucleus gene expression and chromatin accessibility data from 287 human skeletal muscle samples from individuals aged 20-79 years to explore sex- and cell type- specific aging effects. Across 467,126 nuclei from 13 cell types, we identify 384 age-associated genes and 4,061 age-associated chromatin regions. These age-associated molecular features are enriched for functional pathways, including metabolic processes, cell-to-cell communication, and senescence Kyoto Encyclopedia of Genes and Genomes KEGG terms. Age-associated closing chromatin was more common across fiber types and sexes than opening chromatin, and was enriched in active enhancer regions while depleted for active transcription start sites. We observe enrichment for specific transcription factor motifs in closing chromatin, including those of glucocorticoid and androgen receptors, both of which play a key role in the maintenance of healthy skeletal muscle. Together, these findings identify an age-associated regulatory shift, largely invisible in matched transcriptomic data, characterized by closing chromatin which reduces accessibility to hormone receptor binding sites and enhancer regions in the muscle fiber epigenome.

  bioinformatics2026-08-27v2

• ASAREE: An Analytical Sandbox for Agentic AI Research, Engineering, and Experimentation

  Moran, J.; Freda, P. J.; Ghosh, A.; Walker, C. T.; Hernandez, M. E.; Moore, J. H.

  Abstract

  Summary: Agentic AI platforms enable the engineering of autonomous workflows but are not designed for experimentation and hypothesis testing. ASAREE (Analytical Sandbox for Agentic AI Research, Engineering, and Experimentation), is an open-source platform to address this gap. ASAREE creates agents, connects to MCP servers and tools, and designs factorial experiments through a visual interface or Python SDK. It records a full provenance trace for every run and routes all model calls through a provider-agnostic bridge that supports local deployments, ensuring data privacy. As a use-case, we use ASAREE to evaluate key design choices in a mutli-agent machine learning pipeline. Across a 2 x 2 x 2 factorial design, more advanced models, greater reasoning effort, and critic agent use significantly increased compute time, token use, cost, and feature count without improving predictive performance. The lowest-cost baseline, Claude Sonnet 5 with medium effort and no critic, achieved the highest mean PR AUC while Claude Opus 5 with extra high effort and a critic agent cost 15.5x more (USD) and ran 13.1x longer while performing worse on average. These findings highlight ASAREE as a robust framework for evaluating agentic system performance and resource efficiency.

  bioinformatics2026-08-27v2

• HIDE-Deconv: A hierarchical deconvolution framework for multiscale characterization of cellular remodeling

  Voelkl, D.; Bolz, S.; Rayford, A.; Sterr, T.; Mensching-Buhr, M.; Seifert, N.; Arp, J.; Tausche, J.; Engel, L.; Schuster, C.; Stevenson, T.; Zacharias, H. U.; Altenbuchinger, M.; Goertler, F.

  Abstract

  Most deconvolution methods estimate cellular composition at a single level of cellular resolution despite biological processes often manifesting within fine-grained cellular subpopulations. We present HIDE-Deconv, a hierarchical deconvolution framework that jointly optimizes cellular compositions across multiple levels of a cell-type hierarchy while maintaining consistency between resolutions. In benchmark experiments, HIDE-Deconv achieved the highest overall predictive performance among evaluated methods. Analyses of lung adenocarcinoma, sepsis, COVID-19 and systemic lupus erythematosus revealed biologically relevant cellular remodeling that remained concealed at broader levels of cellular resolution. HIDE-Deconv is available as an open-source framework at https://github.com/dvoelkl/HIDE-deconv.

  bioinformatics2026-08-27v2

• Benchmarking Imputation Methods for Single-Cell RNA Sequencing Data Using Peripheral Blood Mononuclear Cells from Acute Myocardial Infarction Patients

  Ramesh, P.; Fyta, M.

  Abstract

  Acute myocardial infarction (AMI) remains one of the leading causes of mortality worldwide, and the following post-effects, such as post-AMI inflammation and tissue repair, involve peripheral blood mononuclear cells playing a critical role. The influence of imputation methods in biological data is assessed with respect to high-resolution single-cell RNA sequencing (scRNAseq) data relevant to these cells. Still scRNAseq data often encounter a lot of dropout events, leading to sparse and noisy datasets, hampering downstream results. To assess the influence of the missingness in the data, we artificially impose different levels of dropout in available scRNAseq data by leveraging various imputation techniques. Specifically, we introduce artificial missingness at 10%, 20%, and 30% levels under a missing completely at random (MCAR) framework, repeated across 10 independent runs. We benchmarked six imputation strategies - MAGIC, IterativeImputer, KNNImputer, Mean Imputation, SoftImpute, and a Generative adversarial network (GAN) - based approaches using multiple evaluation metrics: marker gene preservation, clustering consistency (Adjusted Rand Index - ARI), gene-wise correlation with ground truth, and structural separation (silhouette scores). The results clearly underline that no single imputation method dominated across all metrics. Overall, Mean and KNN imputers showed limited recovery across all benchmarks. GAN excelled in global transcriptional recovery and SoftImpute in preserving biologically meaningful cell-type signals. Our results highlight the importance of selecting the imputation methods as part of the pre-processing step towards the downstream biological questions related to transcriptome recovery, detection of marker genes, or maintaining cell-type-specific resolution.

  bioinformatics2026-08-27v1

• DeMoP: A Language-Model-Guided Mixture-of-Experts Framework for Cancer Prognosis

  Tang, C.; Yu, L.; Li, Q.; Xu, L.

  Abstract

  Integrating heterogeneous clinical and molecular data for cancer prognosis remains challenging because their dimensionality, semantics and distributions differ across patients and cohorts. Here we present DeMoP, a language-model-guided mixture-of-experts framework that serializes structured patient profiles as natural-language sequences and learns adaptive prognostic representations from clinical variables, copy-number alterations, and gene descriptions. DeMoP combines a fine-tuned DeBERTa-v3-large encoder, attention-based token pooling, and a residual mixture-of-experts prediction head. In held-out tests from two independent pan-cancer cohorts, GENIE (63,090 patients) and TCGA (4,123 patients), DeMoP outperformed the conventional machine-learning and deep-learning baselines evaluated, achieving AUROCs of 0.939 and 0.805 and class-1 F1 scores of 0.72 in both cohorts. A GENIE-trained model transferred directly to TCGA with an overall class-1 F1 score of 0.62. Gene-level ablations recovered established cancer-associated genes and highlighted less-studied candidates. DeMoP provides a unified approach to heterogeneous biomedical data integration, cross-cohort outcome prediction, and model interpretation.

  bioinformatics2026-08-27v1

• Proteome modulation by opposite inotropic drugs in human engineered cardiac tissue revealed by topology-driven cross-modal integration

  Staykova, D. K.; Snippert, D.; Wessels, H. J. C. T.; Passier, R.; Conte, F.

  Abstract

  Engineered heart tissues (EHTs) represent an innovative platform enabling physiologically relevant in vitro evaluation of drug-induced cardiac responses. While functional characterization remains central to EHTs, molecular profiling is increasingly used to elucidate mechanisms underlying drug-induced phenotypes. Proteomics provides broad molecular characterization of drug responses at the protein level, yet the complexity, heterogeneity, and high dimensionality of proteomics datasets challenge conventional statistical approaches, which are not designed for cross-modal integration and streamlined multi-omics analysis. In this study, we developed an innovative framework based on topological data analysis (TDA) for the integration of large proteomics profiles and functional readouts to investigate system-level responses to drugs with opposing inotropic effects, epinephrine and doxorubicin. Samples were organized into a topological connectivity network according to multimodal similarity enabling simultaneous exploration of treatments, cardiac function and proteome alterations. Highly correlated features were then used for pathway enrichment analysis, which revealed strong similarities between the enrichment profiles associated with contractile force and epinephrine. These findings are consistent with the positive inotropic effect of epinephrine, whereas doxorubicin exhibited an opposing enrichment profile. Energy homeostasis, mitochondrial translation and proteostasis emerged as the major cellular processes displaying opposite associations with the two inotropic drugs, highlighting a link between cardiac contractility and perturbations in these processes. In conclusion, our TDA-based framework successfully integrated functional and proteomic data to uncover treatment-specific remodeling in EHTs, offering a modular and scalable approach that could be adapted to other in vitro organ models for systems-level mechanistic studies and next-generation drug development.

  bioinformatics2026-08-27v1

• DeepTMHMM2 enables accurate prediction of transmembrane protein topology and subcellular location

  Teufel, F.; Hallgren, J.; Nielsen, H.; Krogh, A.; Tsirigos, K. D.; Winther, O.

  Abstract

  Transmembrane -helical and {beta}-barrel proteins are a ubiquitous component of proteomes. Topology prediction infers how proteins are embedded in lipid bilayers, identifying membrane-spanning segments and their orientation. While recent methods achieve high performance for membrane-spanning segments, they cannot predict re-entrant regions and interfacial helices - membrane-associated segments that partially insert but do not cross the bilayer - nor identify which biological membrane a protein resides in. Here, we present DeepTMHMM2, the first predictor to include re-entrant regions and interfacial helices in its topologies and jointly predict localization across 17 biological membranes. Benchmark results show that DeepTMHMM2 successfully learns to predict the additional elements, while achieving strong performance on canonical -helical and {beta}-barrel topology prediction. Applying DeepTMHMM2 to Swiss-Prot reveals that non-crossing segments are a ubiquitous feature of the transmembrane proteome, with interfacial helices present in nearly a quarter of all -helical transmembrane proteins.

  bioinformatics2026-08-27v1

• reactifpTM: an accessible reimplementation of actifpTM

  Simpkin, A. J.; Johnson, E.; Rigden, D.

  Abstract

  Motivation: The actual interface pTM score (actifpTM) is a modified version of the ipTM score that limits the calculation to only those residues at the interface. Whilst actifpTM provides an effective interface quality score, a limiting factor is that it makes use of the predicted aligned error (PAE) with probabilities, information that is generated during a ColabFold run, but not output by the package or other model prediction software. The consequent inability to generate actifpTM scores for the results of software such as AlphaFold 2 or AlphaFold 3 has limited its adoption. With reactifpTM we address this problem by providing a standalone tool that can be run on the standard outputs of most model prediction packages. Results: Using the same underlying principles as actifpTM, reactifpTM has been developed to use standard output files from model prediction software (a model and corresponding PAE) to perform an actifpTM-like calculation. ColabFold models were generated for a dataset of 1079 known interfaces in the PDB. A strong correlation was shown between actifpTM and reactifpTM for this dataset. Availability and implementation: reactifpTM is coded in Python. All scripts and associated documentation are available from https://github.com/hlasimpk/reactifptm or https://pypi.org/project/reactifptm.

  bioinformatics2026-08-27v1

• SPC-Clean: A napari Plugin for Reducing Speckle and Isolated Pixel Noise in Fluorescence Microscopy Images

  Alirezazadeh, P.; Kirsch, E. M.; Tian, Y.; Bewersdorf, J.; Rittscher, J.; Mergenthaler, P.

  Abstract

  Speckle artifacts and isolated foreground pixels are common in fluorescence microscopy and can interfere with segmentation and subsequent quantitative image analysis. Conventional denoising methods often modify image intensities through filtering or smoothing, potentially altering biologically relevant fluorescence signals. We introduce Sparse Pixel Cluster Cleaning (SPC-Clean), a topology-aware method that removes poorly supported foreground pixels through iterative neighborhood analysis of a thresholded mask. SPC-Clean is deterministic, training-free, preserves original fluorescence intensities for practical microscopy workflows.

  bioinformatics2026-08-27v1

• NeuroMesh: A Bottleneck Topology Controller for Missing-Modality Brain Tumor Segmentation - A Mechanistic Pilot Study on BraTS

  Kamalakannan, N. K.; Kamalakannan, J.

  Abstract

  Deep segmentation networks can degrade sharply when an expected MRI sequence is unavailable at inference. We present NeuroMesh, a bottleneck controller that combines a gated recurrent unit (GRU) with a graphconvolutional edge-activation mask, designed to adapt a U-Net-style segmentation backbone to missing input. We evaluate NeuroMesh in a pilot study using a 30-patient subset of the BraTS 2020 benchmark (22 training, 4 validation, and 4 held-out test patients) under a prespecified frozentest protocol. On the frozen test set, NeuroMesh has higher tumor-core and enhancing-tumor Dice than a plain U-Net in most evaluated missing-modality conditions, but wholetumor Dice falls from 0.596 to 0.108 when FLAIR is missing, compared with 0.604 to 0.545 for the plain U-Net. Direct analysis of the predicted edge-activation mask shows negligible change across modality-availability conditions. A parameter-light static-gating control reproduces the FLAIR failure mode without recurrence, a failure-signal input, or graph-structured machinery. These results do not support the intended interpretation that the trained controller performs input-conditional topology rewiring at the scale of this pilot. Instead, they expose a discrepancy between architectural intent and realized behavior and identify a specific missing-modality failure mode that warrants further investigation. Given the small validation and test sets, the findings are descriptive and do not establish clinical or population-level generalization.

  bioinformatics2026-08-27v1

• PMPNN-DDG: an accurate machine learning-based {triangleup}{triangleup}G prediction pipeline trained on a novel interpretable feature set extracted from ProteinMPNN

  Jani, R.; Ahmed, S.

  Abstract

  An accurate and tractable approximation of the single-point mutation-induced change in protein thermodynamic stability, denoted by DDG, is critical for understanding the genotype-phenotype relationship. Several computational methods have been proposed for this problem; however, limited and error-prone training data and the difficult-to-predict magnitude of structural perturbations make this a challenging task. Consequently, the computational predictors proposed throughout the past decade incrementally improved prediction performance by proposing novel features, combining existing features, task-adapted neural network architectures, loss functions, data augmentation techniques, and pre-training procedures. In this work, we propose PMPNN-DDG, a Random Forest-based DDG prediction model, trained on a novel set of interpretable features extracted from the recently proposed message-passing neural network-based fixed backbone protein design model, ProteinMPNN. On the S669 independent test set, PMPNN-DDG achieves rF +R = 0.64 and RMSE = 1.45, outperforming all compared baseline methods across the reported evaluation measures. On the Ssym independent test set, it achieves rF +R = 0.81, rF -R = -0.99, and RMSE = 1.10, showing competitive performance relative to the compared baselines. PMPNN-DDG is publicly available at https://github.com/dRanger666/PMPNN-DDG.

  bioinformatics2026-08-27v1

• Identification of novel HDAC11 inhibitors: In silico & in vitro studies

  Paul, M.; Kumar, D. S.; Mishra, S.; Kalle, A. M.

  Abstract

  Histone deacetylases (HDACs) are pivotal epigenetic regulators that modulate diverse cellular pathways by removing acetyl groups from lysine residues on both histone and non-histone proteins. Histone deacetylase 11 (HDAC11), the sole member of class IV HDACs, exhibits both deacetylation and fatty acid deacylation activities. Accumulating evidence implicates HDAC11 as a key epigenetic regulator of fundamental cellular processes, including metabolism, immune responses, and tissue development. Dysregulation of HDAC11 activity has been associated with inflammatory diseases, metabolic disorders, neurodegenerative conditions, and cancer, highlighting its potential as a therapeutic target. Although several HDAC11-specific inhibitors have been identified, none have progressed to clinical development. In this study, we aimed to discover HDAC11-selective inhibitors by integrating in silico and in vitro validation approaches. Homology modelling of the HDAC11 structure was conducted, followed by model validation, structure-based virtual screening, molecular dynamics (MD) simulations, and binding free energy calculations. We identified and validated three lead compounds and their intermediates using biochemical and cell-based assays. Fluorescence-based and HPLC-based enzymatic assays demonstrated potent inhibition of both the deacetylase and deacylase activities of HDAC11, with Inhibitor 6 and Inhibitor 3 exhibiting the strongest effects among the six compounds tested. Further, a decrease in lipid accumulation, reduced stability of the HDAC11 substrate SHMT2, as determined by immunoblot analysis and decreased cell viability, as assessed by MTT assay, confirmed HDAC11 inhibition in cellular models. The study shows that new HDAC11 inhibitors significantly reduce the viability of breast cancer cells and induce apoptosis; inhibitor 6, in particular, showed high potency, similar to the reference compound SIS-17. Flow cytometry showed that treated MDA-MB-231 cells exhibited cell-cycle arrest and increased apoptosis, a finding further confirmed by Annexin V/PI staining. Molecular analysis showed that BAX increased while BCL2 decreased, indicating that apoptotic pathways were activated in novel compound-treated MDA-MB-231 cells. The results suggest that inhibiting HDAC11 is an effective way to induce cancer cell death and provide a basis for further assessment of these compounds as potential treatments for breast cancer. Collectively, this study identifies novel zinc-chelating HDAC11 inhibitors containing a nitro-sp2 group, providing promising candidates for further therapeutic development.

  bioinformatics2026-08-27v1

• AntiSite: Modality Dropout Enables Antibody Paratope Prediction With or Without Structure From a Single Model

  Papadopoulos, A. M.; Alvarez, F.; Daras, P.

  Abstract

  Summary: Reliable paratope identification is central to understanding antibody antigen recognition and advancing therapeutic antibody discovery. AntiSite is a unified antibody paratope prediction framework that combines protein language-model sequence embeddings with structure-derived molecular-surface features and, through modality dropout, trains a single checkpoint to predict both with and without a structure. This lets one model support sequence-only inference when no structure is available and structure-aware inference when an antibody structure is provided. Availability and implementation: Source code, trained models and evaluation scripts are freely available at https://github.com/aggelos-michael-papadopoulos/AntiSite. Processed benchmark structures and corrected split metadata are archived on Zenodo at https://doi.org/10.5281/zenodo.21705412.

  bioinformatics2026-08-27v1

• EcoXAI: Autonomous Agentic Ecosystem for Explainable Artificial Intelligence and Biomedical Discovery

  Matsumoto, N.; Choi, H.; Freda, P. J.; Hernandez, M. E.; Wang, Z. P.; Moore, J. H.

  Abstract

  Motivation: As biomedical datasets and knowledge graphs continue to grow in size, complexity, and heterogeneity, navigating and extracting actionable insights from them presents a major bottleneck for researchers. There is a clear need for autonomous analytical solutions that can utilize recent advancements in agentic AI such as agent harnessing and loop engineering without introducing hallucination or workflow fragmentation. Researchers, regardless of technical expertise, need tools that streamline complex data analysis and deliver meaningful, actionable insights grounded in both data and established biomedical knowledge. EcoXAI addresses this by introducing a modular, customizable, containerized multi-agent system that structures analysis into explicit pipeline execution stages, lowering the computational barrier for clinical and translational researchers. Result: EcoXAI replaces monolithic AI text interfaces with an autonomous execution-driven framework with specialized bioinformatics agents for delivering proactive, data-driven insights grounded in established biological knowledge. Unlike purely LLM-driven or less integrated AI solutions prone to hallucinations or biologically implausible outcomes, EcoXAI's multi-agent framework, which leverages modern agentic management and explicit knowledge graph integration, provides greater transparency and verifiability in its reasoning. In our use case in drug repurposing for Alzheimer's Disease, EcoXAI evaluated 103 drug candidates and identified 79 novel candidates whose predictive models exceeded a randomized baseline, including the CCR5 antagonist Maraviroc, whose generated hypothesis was subsequently supported by the literature. These results demonstrate the potential of knowledge graph-grounded AI agents to accelerate hypothesis-driven biomedical research.

  bioinformatics2026-08-26v4

• UMITIC: An unsupervised framework for the joint characterization of cellular phenotypes and spatial neighborhoods in multiplex and hyperplex immunofluorescence imaging data

  Sangüesa Recalde, M.; De Andrea, C. E.; Ariz, M.

  Abstract

  Multiplexed imaging technologies enable the simultaneous measurement of dozens of protein markers while preserving context, providing a high-resolution view of tissue organization schemes. However, extracting meaningful insights from these high-dimensional datasets--particularly in hyperplex settings (>20 markers)--remains a major computational challenge, especially in the absence of annotated data. Here, we present UMITIC (Unsupervised Analysis of Multiplex Images via TIssue Characterization), a modular and unsupervised computational framework for the joint characterization of cell phenotypes and tissue neighborhoods from multiplex imaging data. UMITIC integrates three components: (i) CellCut, a strategy that combines nuclear and cytoplasmic predictions to improve the delineation capabilities of the framework; (ii) CellMap, a contrastive learning approach that generates low-dimensional representations of single-cell image crops that are enriched with morphological features; and (iii) TissueNet, a graph neural network that models spatial cell-cell interactions to identify tissue neighborhoods. We evaluated UMITIC across four datasets of increasing complexity to assess its robustness, scalability and biological relevance. With respect to a 7-plex human tonsil dataset, the framework identified canonical immune cell populations and reconstructed well-established anatomical regions. When applied to a 43-plex tonsil image, UMITIC preserved these tissue-level structures while enabling a finer cell subtype stratification process driven by increased marker dimensionality. We further validated our method on a 58-plex colorectal cancer cohort, where UMITIC was able to recover previously reported immune composition differences and spatial organization variations between patient groups with different prognoses. Finally, when an expert-annotated mass cytometry imaging dataset concerning human lung tissue was used, UMITIC achieved higher agreement with the reference tissue annotations than the existing approaches did, demonstrating improved lung microanatomy reconstruction accuracy. Together, these results show that UMITIC enables consistent and interpretable analyses of both cellular phenotypes and tissue architectures across diverse multiplex and hyperplex imaging datasets without the need for manual annotations.

  bioinformatics2026-08-26v3

• Enrichment-free glycoproteomics harnessing real-time mass defect-driven glycopeptide classification reveals sex differences in murine fucosylation

  Zhang, B.; Chau, T. H.; Bienes, K. M.; Arakawa, H.; Hane, M.; Sato, C.; Yokoi, A.; Kaji, H.; Ashwood, C.; Matsui, Y.; Kawahara, R.; Thaysen-Andersen, M.

  Abstract

  Glycopeptide enrichment remains a cornerstone in glycoproteomics, but bias and reproducibility issues continue to hinder biological insight and clinical translation. Employing curated glycoproteomics datasets and machine learning, we trained a glycopeptide classifier to recognize N-glycopeptide precursors through mass defect signatures. Integration of the classifier into a data-dependent acquisition framework facilitated real-time prediction of N-glycopeptides from human serum and revealed sex differences in murine plasma fucosylation opening avenues for enrichment-free glycoproteomics.

  bioinformatics2026-08-26v3

• CRISPR-HAWK: Haplotype- and Variant-aware Guide Design Toolkit for CRISPR-Cas

  Kumbara, A.; Tognon, M.; Carone, G.; Fontanesi, A.; Bombieri, N.; Giugno, R.; Pinello, L.

  Abstract

  Current CRISPR guide RNA design tools rely on reference genomes, overlooking how genetic variation impacts editing outcomes. As genome editing advances toward clinical applications, incorporating population diversity becomes essential for ensuring therapeutic efficacy across diverse populations. We present CRISPR-HAWK, a framework integrating individual- and population-scale variants and haplotypes into gRNA design. Analyzing therapeutic targets across 79,648 genomes reveals that genetic variants substantially alter guide performance. For the clinically approved sickle cell disease therapeutic guide targeting BCL11A, we identify haplotypes that completely abolish predicted cutting activity. Across seven therapeutic loci, 82.5% of guides contain variants modifying on-target activity. Variants also create novel protospacer adjacent motif sites generating individual-specific guides invisible to reference-based design. These findings demonstrate that variant-aware selection is critical for equitable genome editing. CRISPR-HAWK is available at https://github.com/pinellolab/CRISPR-HAWK and https://github.com/InfOmics/CRISPR-HAWK

  bioinformatics2026-08-26v3

• scDisent: regulatory-aware disentangled representation learning for multi-omic single-cell analysis

  Xi, G.

  Abstract

  Single-cell multi-omic technologies measure complementary aspects of cellular identity and regulatory state, yet most integration models compress these signals into one entangled latent space. Such representations are useful for clustering but poorly suited to regulator-centered interpretation or perturbation-oriented analysis. We present scDisent (https://github.com/xiguoren/scDisent), a generative framework that separates expression-associated variables (zexpr) from regulation-associated variables (zreg) and links them through a sparse directed mapping. scDisent combines modality-specific encoding, variational disentanglement, total-correlation and orthogonality regularization, and a Gumbel-gated causal module protected by detach-based gradient isolation. Across benchmark datasets with matched modalities, scDisent achieved the strongest clustering performance among the tested methods while exposing regulatory structure that competing integration models do not represent explicitly. The learned causal atlas remained sparse, perturbation analyses recovered biologically coherent lineage-associated programs, and branch-separation analyses showed that benchmark-label information concentrated in zexpr rather than zreg. These results position scDisent as a multi-omic representation model that improves both integration quality and biological interpretability

  bioinformatics2026-08-26v2

• A mechanism-annotated benchmark reveals limited fidelity to drug-response signatures in single-cell perturbation models

  Li, L.; Duan, S.; Zha, X.; Ye, F.; Zhang, Y.; Zhang, X.; Cao, Y.; Liu, C.; Fang, B.

  Abstract

  Single-cell drug perturbation models are increasingly used to predict how compounds remodel cellular states, but they are still largely assessed by expression reconstruction. Whether high expression similarity reflects preservation of drug-response signatures remains unclear. Here we present scDrugPerturb-Bench, a mechanism-annotated benchmark that links matched control and drug-treated single-cell RNA-sequencing profiles to literature-curated directional key-gene evidence. The resource covers 181 datasets, 423 annotated response cases, 717 unique key genes and 2.5 million cells. We introduce the Mechanism Fidelity Score (MFS) to evaluate key-gene direction, effect-size recovery, gene-set coherence, mechanism specificity and pathway-level response polarity. Across 12 perturbation-prediction models, 3 baselines and 10 data splits, expression-similarity metrics were weakly aligned with MFS and selected different model configurations. Mechanism-aware selection improved early drug retrieval in a transcriptome-based drug design evaluation, indicating that MFS provides practical information beyond benchmark reporting. Systematic benchmarking revealed limited fidelity to drug-response signatures across cell-line and source-integrated settings. Frozen single-cell foundation model embeddings produced local, metric-dependent gains rather than universal improvements, and source context substantially reshaped model assessment. Hard-negative tests further showed that plausible perturbation responses can arise from non-specific transcriptional shortcuts. These results show that expression reconstruction is an insufficient proxy for preserving drug-response signatures and establish scDrugPerturb-Bench as a benchmark for mechanism-aware evaluation of single-cell drug perturbation models.

  bioinformatics2026-08-26v2

• Identification of Altered Potassium Channels for Drug Repurposing in Long COVID Patients

  George, J. P.; Gaikwad, K. B.; Sharma, J.

  Abstract

  Long COVID (LC) is a complex condition characterized by persistent, chronic multisystem manifestations, with a significant proportion of patients exhibiting neurological symptoms. Human ion channels (HICs), particularly potassium channels, are abundantly expressed in the nervous system and linked to key metabolic processes, making them potential candidates for understanding LC pathophysiology and drug repurposing. Meta-analysis of RNA-Seq datasets from COVID-19-recovered and LC patients was performed to identify altered HICs in LC. Differential gene expression analysis, functional enrichment analysis, and weighted gene co-expression network analysis were performed to uncover key genes, pathways, and co-expression modules consisting of HICs, lipid metabolism-, and immune signaling-related genes. A total of 715 dysregulated genes, including eighteen HICs were identified, among which seven were potassium channels. Three significant modules containing HICs, lipid metabolism-, and immune signaling-related genes were identified and found to be associated with antigen processing and presentation, complement and coagulation cascades, and cytokine-related pathways. Additionally, drug-gene interaction analysis led to identification of approved drugs targeting KCNA6, KCNJ10, KCNN3, and KCNH4 that might provide opportunities for drug repurposing in neurological manifestations in LC. Further experimental validation is required to establish their efficacy and assess their potential for translation into clinical applications for patients with LC.

  bioinformatics2026-08-26v2

• On the illusion of scRNA-seq batch effect correction

  Codice', F.; Fariselli, P.; Raimondi, D.

  Abstract

  Batch correction methods in single-cell RNA sequencing are essential for removing technical variation that can otherwise lead to misleading downstream analyses. The reliability of these methods is typically evaluated using unsupervised metrics. Here, we apply a Machine Learning (ML) technique called probing, formalized as the Batch Probing Score (BPS), to empirically demonstrate across six datasets that the most popular batch correctors fail to fully remove batch signal. In most cases, the batch of origin remains clearly identifiable after correction, even though standard evaluation metrics cannot detect it. We show that existing unsupervised metrics lack the sensitivity and specificity required to capture residual batch signal, whereas ML-based approaches can still detect it. This residual signal can similarly be picked up by downstream analysis tools, potentially leading to biased results. Because BPS is supervised, it directly quantifies batch signal strength by measuring how accurately the batch of origin can be predicted for each sample. It therefore provides an upper bound on the residual ML-actionable batch signal that could otherwise remain unnoticed. Our findings suggest that probing-based metrics should become a standard for assessing batch correction methods in single-cell RNA-seq and other areas of genomics.

  bioinformatics2026-08-26v2

• MONTE enables unified pan-cancer tumor purity estimation andmethylation correction from bulk DNA methylation arrays

  Kim, M.; Lee, W.-H.; Yao, V.

  Abstract

  Bulk DNA methylation profiling is widely used to study cancer epigenomics in clinical settings, but these measurements aggregate signals from malignant and non-malignant cells, introducing composition-dependent confounding that complicates tumor-intrinsic interpretation and cross-cohort analyses. While existing methods can estimate tumor purity and, in some cases, correct methylation measurements, they typically require cancer-specific reference models, matched normal samples, or predefined probe sets, limiting their applicability to rare cancers, different clinical cohorts, and cross-dataset comparisons. We present MONTE (Methylation-based Observation Normalization and Tumor purity Estimation), a unified, cancer label-free framework for tumor purity inference and CpG-resolved methylation correction from bulk DNA methylation data. MONTE learns probe-wise relationships between methylation and tumor purity using an empirical Bayes-moderated linear model and infers purity in new samples via signal-to-noise weighted aggregation, without requiring matched normals, cancer labels, or predefined probe sets. A single pan-cancer MONTE model outperforms existing cancer-specific methods for purity estimation across 21 cancer types, generalizes across purity references, and runs orders of magnitude faster on full-dataset analyses. MONTE also introduces Bayesian transfer learning, which enables efficient recalibration to alternative purity definitions, validated on three independent external cohorts. Methylation correction with MONTE further amplifies tumor-relevant regulatory signal and improves the reproducibility of differential methylation analyses. By unifying purity estimation and correction in a single flexible, scalable, and interpretable framework, MONTE broadens the accessibility of tumor-intrinsic methylation analysis across cancer types and datasets.

  bioinformatics2026-08-26v2

• KSTITCH links cellular morphology and gene expression in spatial transcriptomics

  Kumar, S.; Shi, Y.; Vallius, T.; Day, C.-P.; Absil, P.- A.; Srivastava, A.; Hannenhalli, S.; Gopalan, V.

  Abstract

  In situ spatial (ISS) sequencing can uncover co-variation between cellular morphology and gene expression in vivo. However, a principled and interpretable mathematical representation of morphology has not yet been applied in this context. In particular, current deep learning-based representations of cell images confound a cell's shape with its size. We present an interpretable representation of cellular boundary contours, based on tangent principal component analysis (TPCA) in a Kendall shape manifold, that captures size-independent contour shape features. This approach successfully recovers shape-perturbing genes in an RNAi screen than a previous metric geometry-based approach. We build on TPCA to develop KSTITCH (Kendall Shape-TranscriptomIc Correlation and Harmonization), an approach to reveal covariation between cell morphology with gene expression in ISS datasets. In a Xenium dataset, KSTITCH recovers known morphology-transcriptomic relationships in keratinocytes, macrophages and endothelial cells. Across samples in a melanoma CosMx dataset, KSTITCH reproducibly associates elongated and triangular fibroblasts with proximity to malignant cells and myofibroblast-like transcriptional program. Finally, KSTITCH independently recovers a known link between mesenchymal-like malignant cell states and increased cell area in two melanoma cohorts. KSTITCH can thus yield interpretable morphology-transcriptome relationships across cell types, patients, and spatial transcriptomics platforms. KSTITCH is available at https://github.com/vishakagopalan/kstitch .

  bioinformatics2026-08-26v2

• BatchRefiner: fast, significant improvement in batch integration of single-cell embeddings with ensemble refinement

  Schäffer, D. E.; Kang, H.; Aksu, E. D.; Edelman, D.; Berger, B.

  Abstract

  Data from single-cell RNA sequencing (scRNA-seq) and the Assay for Transposase-Accessible Chromatin (scATAC-seq) are high-dimensional, sparse, and undesirably capture technical variability between experiments or batches. Many analysis methods thus seek to produce a low-dimensional cell-by-feature embedding space that groups together biologically similar cells across batches while distancing dissimilar cells. Here, we introduce ensemble refinement for scRNA-seq and scATAC-seq embeddings, inspired by ensemble methods from statistical machine learning, and implement BatchRefiner, a fast post-processing tool to enhance batch integration. We extensively benchmark widely-used scRNA-seq embedding methods on both batch integration and biological conservation over a wide range of datasets, before and after the addition of BatchRefiner. We extend these benchmarking approaches to provide the first comprehensive benchmark of batch integration for scATAC-seq embedding methods, including BatchRefiner. Importantly, we formalize a significance statistic, which we use to demonstrate BatchRefiner's significant improvement in batch integration across a wide range of embedding methods, atlas-scale datasets, and established metrics.

  bioinformatics2026-08-26v1

• Interpretable Forecasting of Kidney Cancer Progression via Generative AI and Symbolic Reasoning

  Prol-Castelo, G.; Syrri, E.; Manginas, N.; Manginas, V.; Sanchez-Valle, J.; Katzouris, N.; Paliouras, G.; Valencia, A.; Cirillo, D.

  Abstract

  Predicting cancer stage progression from omics data, and deriving molecular insight into the mechanisms driving it, remains a major challenge, owing in part to the lack of adequate longitudinal data and the interpretability limitations of current forecasting models. Large cancer datasets such as TCGA capture patient profiles cross-sectionally rather than longitudinally, complicating timely treatment decisions as tumors become more invasive. Deep neural networks typically used for forecasting, such as LSTMs, compound this problem by remaining largely opaque and offering clinicians no straightforward way to audit their predictions. Clear cell renal cell carcinoma (ccRCC) illustrates the clinical stakes of both challenges. Five-year survival falls from over 94% at stage I to 28% at stage IV, yet early-stage tumors are often managed under active surveillance, a strategy constrained by sparse molecular evidence of progression risk. Detecting progression in time, meanwhile, demands forecasts clinicians can interpret and trust, not black-box predictions. We address both challenges by combining generative and symbolic AI: a Variational Autoencoder trained on bulk RNA-Seq profiles of 530 TCGA ccRCC patients generates synthetic pseudo-time trajectories that overcome the absence of longitudinal data, while a symbolic rule-induction framework (ASAL) learns finite-state automata from these trajectories, encoding stage transition as human-readable Boolean conditions over gene expression, which a complex event forecasting system (Wayeb) converts into probabilistic forecasts of stage advancement. An independent XGBoost classifier trained on real patients (F1 score = 0.71-0.81) shows a gradual early-to-late probability shift along the synthetic trajectories, absent in non-progressing control trajectories. Pathway enrichment of those trajectories reveals stage-dependent changes in established kidney cancer-related processes, including the TCA cycle and DNA repair. Finally, our symbolic forecaster nearly matches an LSTM baseline (macro F1 = 0.928 vs. 0.964), while additionally offering an inspectable rule set and a probability distribution over transition timing rather than a single opaque score. This work shows that generative and symbolic AI, paired together, can turn cross-sectional cohorts into a transparent, forecast-oriented framework for modeling disease progression, demonstrated here in ccRCC.

  bioinformatics2026-08-26v1

• Automated Detection of Livestock Gastrointestinal Parasite Eggs and Cysts Using YOLOv8-Based Deep Learning

  Sarwer, A.

  Abstract

  Parasitic infection is one of the common health problems of livestock in Bangladesh. Due to the country's climate, heavy monsoon rainfall, low biosecurity in farms, and high humidity, along with presence of suitable vector organisms, gastrointestinal parasitism remains widespread in cattle and other livestock. The standard method of diagnosis is microscopic examination of fecal samples, but this depends on manual observation, which is time-consuming and can lead to human error, mainly because many parasite eggs look similar to each other and samples often contain contaminants that can be mistaken for eggs or cysts. In this study, we tried to apply the YOLOv8 deep learning model for automated detection of parasitic eggs and cysts from microscopic images of livestock fecal samples. Images of clinical cases were collected, annotated, and used to train the model in Python, with batch size 16, auto optimizer, learning rate 0.01, momentum 0.937 and weight decay 0.0005. Training was done using Google Colab, and the model was evaluated using precision, recall, F1-score, mAP50, and mAP50-95. The model achieved a precision of 56%, recall of 24%, F1-score of 33.6%, mAP50 of 33%, and mAP50-95 of 22%. The relatively low recall and F1-score indicate that the model still has considerable limitations, largely due to insufficient species-specific training data and presence of image artifacts. Underrepresentation of some parasite species, such as Trichuris spp., in the dataset also caused class imbalance, which affected the model's ability to detect these species reliably. Despite these limitations, the study indicates that YOLOv8 architecture has some potential to be used for detection of parasitic eggs and cysts from microscopic images, and that further work with larger and more balanced datasets may improve performance and applicability in veterinary diagnostics. Keywords: YOLOv8, livestock parasites, deep learning, microscopic image analysis, veterinary diagnostics, Bangladesh

  bioinformatics2026-08-26v1

• Robustness to nuisance perturbations enables unsupervised evaluation of single-cell foundation models

  Sallam, A.; Gillis, J.

  Abstract

  Single-cell foundation model evaluations have relied almost exclusively on downstream tasks. While these tasks measure whether an embedding recovers annotated cell types, batches, or trajectories, they cannot determine if that structure is reproducible or merely an artifact of a single noisy draw, a key limitation since incomplete sampling is intrinsic to single-cell measurement. Here, we introduce a fully unsupervised evaluation framework grounded in a fundamental principle: a faithful representation must preserve its neighbourhood structure under nuisance perturbations that mimic technical and sampling variation. Across five scFMs, a PCA baseline, and 39 datasets, we show that models ranked as near-equivalent by standard benchmarks differ nearly twofold in local neighbourhood preservation under a perturbation discarding just 5% of counts. This structural instability is scale-dependent and often masked by visually coherent embeddings. Cluster-level stability under resampling tracks established bio-conservation metrics (Spearman {rho}=0.78), showing that invariance to nuisance perturbations captures representation quality no benchmark measures directly.

  bioinformatics2026-08-26v1

• Orthology transfer maps only the conserved core of the Varroa destructor proteome and over-calls host absence two times in three

  Ryba, S.

  Abstract

  The ectoparasitic mite Varroa destructor is the principal threat to managed honey bees, and a test case for the genome-scale methods applied to non-model organisms, nearly all of which infer from orthology. We reconstructed the first genome-wide protein-interaction network for V. destructor (7,080 proteins, 335,914 interactions), whose modular structure exceeds a degree-preserving null by 368 standard deviations, but whose every edge is interolog-transferred and every node conserved at least to Eukaryota. None of the 791 genes lacking an orthologous group enters it - arithmetic rather than discovery - yet the excluded compartment is large and coherent. It comprises 3,161 genes (30.9% of the proteome), shorter and less annotated than the rest; an annotation-free genome search detects orphans in a tick genome at 4.0% against 70.4% for networked genes. Within the orthology-bearing compartment visibility is non monotonic: the Acari-level bin (74.1%) falls below the Arthropoda-level bin (89.9%). The same logic applied to host comparison yields a benchmarked error: of genes called absent from Apis on group identity alone, 67.4% recover a sequence homologue - against zero for a shuffled null and 1.3% in the presence direction - rising to 78.3% in the least panel-biased stratum. Both figures are properties of the calling rule: under an identity floor the error directions cross near 34% identity; orthology cannot be said to err in either direction without fixing the criterion first. Host divergence resolves into gene absence and residue level substitution, falling in those two compartments respectively. A bee-sparing target map follows as broader impact.

  bioinformatics2026-08-26v1

• Assay concordance sets exact ceilings on what one biological score can predict

  Liu, Z.

  Abstract

  Computational models of biology are ranked by averaging one prediction against many experimental realizations of a phenotype that are treated as interchangeable. We show this imposes an exact, model-free ceiling fixed by how much those realizations agree with each other, and that the ceiling depends on the evaluation metric through a single support-function identity. Measuring assay concordance across four public registries, 2,822 MaveDB score sets, 217 ProteinGym assays, two drug screens and 1,150 CRISPR cell lines, we find that two assays of one target agree at 0.56-0.68, and that 541 domains measured twice with different proteases fix assay reliability at 0.897, so 70-90% of every ceiling is irreducible biology rather than noise. Published predictors realize 63% of the achievable on the correlation benchmarks report and 18% on the top-1% selection their users perform. We provide the estimator, the ceilings, and the measurements the field has not made.

  bioinformatics2026-08-26v1

• HIDE-Deconv: A hierarchical deconvolution framework for multiscale characterization of cellular remodeling

  Goertler, F.; Voelkl, D.; Bolz, S.; Rayford, A.; Stevenson, T.; Sterr, T.; Mensching-Buhr, M.; Seifert, N.; Altenbuchinger, M.; Arp, J.; Schuster, C.; Tausche, J.; Engel, L.; Zacharias, H. U.

  Abstract

  Most deconvolution methods estimate cellular composition at a single level of cellular resolution despite biological processes often manifesting within fine-grained cellular subpopulations. We present HIDE-Deconv, a hierarchical deconvolution framework that jointly optimizes cellular compositions across multiple levels of a cell-type hierarchy while maintaining consistency between resolutions. In benchmark experiments, HIDE-Deconv achieved the highest overall predictive performance among evaluated methods. Analyses of lung adenocarcinoma, sepsis, COVID-19 and systemic lupus erythematosus revealed biologically relevant cellular remodeling that remained concealed at broader levels of cellular resolution. HIDE-Deconv is available as an open-source framework at https://github.com/dvoelkl/HIDE-deconv.

  bioinformatics2026-08-26v1

• Tree-aware conditional language modeling recovers mutational patterns of viral evolution

  Polunina, P. V.; Maier, W.; Rubin, A. F.

  Abstract

  The evolutionary accessibility of a protein mutation depends on the sequence background in which it arises and its lineage history, yet most protein language models estimate sequence plausibility without explicitly considering the ordered sequence changes through which descendants arise. We developed evoPLM-Tree, a tree-aware conditional autoregressive language model that predicts descendant protein sequences from ancestral sequences together with phylogenetically derived evolutionary features. We demonstrated our approach using SARS-CoV-2 spike protein, pairing sequences from early Omicron lineages according to their positions on a mutation-annotated phylogeny, and evaluating model performance on sequence pairs from later lineages. Prompt-masking experiments showed that incorporating phylogenetic context substantially increased reliance on the supplied input information compared with a sequence-only model. Generated descendant sequences accurately reproduced the positional distribution of mutations observed during viral evolution, with strong correlations between predicted and observed mutation-frequency profiles for both the receptor-binding domain (Spearman's {rho} = 0.823) and the full spike protein ({rho} = 0.736). Although prediction accuracy for individual substitutions decreased with increasing evolutionary distance, the model consistently captured aggregate mutational patterns across the spike protein. Model-assigned mutation probabilities were also enriched among substitutions experimentally tolerated in deep mutational scanning assays of Omicron BA.2 receptor-binding domain expression (1.19-fold enrichment) and ACE2 binding (1.04-fold enrichment), despite the model being trained solely on observed ancestor-descendant sequence pairs and associated phylogenetic context features. These results demonstrate that explicitly providing protein language models with phylogenetic context during sequence generation can recover lineage-specific mutational patterns and yields probabilistic predictions consistent with experimentally measured functional constraints. evoPLM-Tree provides a framework for modeling protein evolution along phylogenetic lineages and prioritizing plausible future mutations from genomic surveillance data.

  bioinformatics2026-08-26v1

• Context-dependent regulatory networks connect Alzheimer's disease genetics to microglial inflammatory responses

  Fu, T.-T.; Kurkela, M.; Tu, J.; Zhang, J.; Sun, N.; Farrer, L. A.; TCW, J.; Hou, L.

  Abstract

  Inflammation is central to Alzheimer's disease (AD) pathogenesis. Microglia, the resident innate immune cells of the brain, exhibit diverse inflammatory states and are enriched for AD-associated genetic variants within active cis-regulatory elements (CREs). However, the interplay among genetic variants, transcription factor (TF)-CRE-gene programs, and microglial responses across inflammatory and disease contexts remain poorly understood. Here, we develop context-dependent epigenomic networks (cEpiNets), integrating bulk and single-nucleus assay for transposase-accessible chromatin using sequencing (ATAC-seq) to reconstruct regulatory programs across inflammatory, genetic perturbation, and disease contexts. Leveraging TF footprinting and graph embedding, cEpiNets identifies shared and context-specific programs and predicts regulatory circuits in unseen biological contexts. In a SORL1-marked inflammatory microglial state that expands during AD progression, cEpiNets annotates AD risk variants at the SORL1 locus and identifies variants associated with cellular state abundance across donors. Cross-context analysis further identifies ZBTB14, whose inflammation-associated program connects AD risk variant-harboring CREs to target genes and widespread TF remodeling in AD. Donor-level ZBTB14 footprint activity is negatively associated with AD pathology, while combined IFN{gamma}/TNF stimulation represses ZBTB14 and activates a subset of inferred targets. Collectively, cEpiNets bridges genetic variation, regulatory programs, and disease-associated cellular phenotypes to facilitate mechanistic interpretation of complex disease genetics.

  bioinformatics2026-08-26v1

• CytoGate-Bench: an LLM benchmark for cross-panel cell gating in cytometry

  Kim, J.; Lee, B.; Ahn, N.; Ionita, M.; McKeague, M. L.; Lee, M. E.; Jeong, C.-U.; Apostolidis, S. A.; Baxter, A. E.; Shwetank, ; Greenplate, A. R.; Wherry, E. J.; Sohn, K.-A.; Kim, D.

  Abstract

  In cytometry, the workhorse single-cell technology of clinical immunology, every study defines its own antibody panel and cell-type vocabulary, so a classifier trained on one cannot annotate the next. Immunologists instead annotate by manual gating, splitting one parent population at a time on a two-marker plot, down an expert-defined hierarchy. We introduce CytoGate-Bench, a benchmark that reformulates this per-step procedure as a zero-shot, panel-agnostic task for large language models. It comprises 23,646 expert-annotated instances re-curated from 11 public flow- and mass-cytometry cohorts spanning eight marker panels. Across six open- and closed-weight backbones, the strongest formulation draws one rectangular gate per candidate and falls within the range of trained, panel-specialized baselines. It degrades less under distribution shift. Walking the hierarchy stepwise outperforms predicting every cell type at once. Ablations trace the signal to the data distribution shape and curated marker priors. However, adding vision or a self-verification loop systematically tightens gates.

  bioinformatics2026-08-26v1