Latest bioRxiv papers

Category: bioinformatics — Showing 50 items

• Systematic cross-study assessment of RNA-Seq experimental workflows for plasma cell-free transcriptome profiling

  Tuni-Dominguez, C.; Asole, G.; Monteagudo-Mesas, P.; Rusu, E. C.; Cabus, L.; Gonzalez, L.; Sanchez, L.; Neto, B.; Sanders, P.; Weber, M.; Lagarde, J.

  Abstract

  Plasma cell-free RNA (cfRNA) is a promising source of non-invasive biomarkers, but its clinical translation is hindered by technical challenges and a lack of protocol standardization, which compromises reproducibility and comparability across studies. There is a need for a systematic evaluation of existing cfRNA-Seq workflows to understand the drivers of technical variability. Here, we address this gap by performing a comprehensive cross-study analysis of 2,166 cfRNA-Seq samples from 15 published studies and an in-house generated dataset, applying a uniform bioinformatics pipeline to enable a controlled comparison of experimental workflows. Our analysis reveals that the donor phenotype typically explains a negligible fraction of the transcriptomic variation, whose main determinants are technical -- principally protocol choice, genomic DNA contamination levels and library diversity. Remarkably, this technical noise is so profound that variation within plasma cfRNA samples exceeds that found across a wide range of human tissues. Finally, we demonstrate that critical pre-analytical factors are often confounded with patient phenotypes, jeopardizing the validity of biomarker discovery efforts. Our work serves as a comprehensive benchmark of current cfRNA-Seq methodologies and provides evidence-based guidelines to improve experimental design. By highlighting the dominance of controllable technical factors, we offer a path towards more robust and reproducible cfRNA research.

  bioinformatics2026-07-28v5

• Identifying spatially variable genes by projecting to morphologically relevant curves

  Nicol, P. B.; Ma, R.; Xu, R. J.; Moffitt, J. R.; Irizarry, R. A.

  Abstract

  Spatial transcriptomics enables high-resolution gene expression measurements while preserving the two-dimensional spatial organization of the biological sample. A common objective in spatial transcriptomics data analysis is to identify spatially variable genes within predefined cell types or regions within the tissue. However, these regions are often implicitly one-dimensional, making standard two-dimensional coordinate-based methods less effective as they overlook the underlying tissue organization. Here we introduce a methodology grounded in spectral graph theory to elucidate a one-dimensional curve that effectively approximates the spatial coordinates of the examined sample. This curve is then used to establish a new coordinate system that reflects tissue morphology. We then develop a generalized additive model (GAM) to estimate spatial patterns which permits the detection of genes with variable expression in the new morphologically relevant coordinate system. Our approach directly models gene counts, thereby eliminating the need for normalization or transformations to satisfy normality assumptions. A second important advantage over existing hypothesis-testing approaches is that our method not only improves performance but also accurately estimates gene expression patterns and precisely pinpoints spatial loci where deviations from constant expression occur. We validate our approach through extensive simulation and by analyzing experimental data from multiple platforms such as Slide-seq and MERFISH. As an example of its ability to enable biological discovery, we demonstrate how our methodology enables the identification of novel interferon-related subpopulations in the mouse mucosa, as well as markers of inflammation-associated fibroblasts in a multi-sample spatial transcriptomic dataset.

  bioinformatics2026-07-28v3

• Melody: Decoding the Sequence Determinants of Locus Specific DNA Methylation Across Human Tissues

  Jin, J.; Wang, D.; Qiao, J.; Gao, W.; Liu, Y.; Chen, S.; Zou, Q.; Wu, S.; Su, R.; Wei, L.

  Abstract

  DNA methylation is a fundamental epigenetic modification that plays crucial roles in transcriptional regulation, cellular differentiation, and genome stability. However, how locus-specific DNA methylation is determined by intrinsic DNA sequence remains poorly understood. Here, we introduce Melody, a deep learning framework that predicts DNA methylation from 10-kb genomic sequences, enabling the integration of both local and long-range sequence signals. Across 39 human tissues, Melody accurately predicts methylation profiles and consistently outperforms existing state-of-the-art methods in whole-chromosome, hypomethylated-region, and cell-type-specific benchmarks. Melody also generalizes to methylation quantitative trait locus (meQTL) effect prediction and identifies regulatory sequence motifs associated with methylation variability. To extend prediction beyond profiled tissues, we further develop Melody-G, which incorporates single-cell RNA-seq foundation model embeddings to infer methylation states in previously unseen cell types directly from transcriptomic data. Together, Melody provides a unified framework for linking genomic sequence and cellular state to DNA methylation and offers new insights into the regulatory logic governing the human methylome.

  bioinformatics2026-07-28v3

• SQUARNA: stem maximization for accurate de novo RNA secondary structure prediction

  Serdakov, M. D.; Bohdan, D. R.; Nikolaev, G. I.; Bujnicki, J. M.; Baulin, E. F.

  Abstract

  Non-coding RNAs play diverse roles in a wide range of cellular processes, with their spatial structure being pivotal to their function. RNA secondary structure is a key determinant of its overall fold. Given the scarcity of experimentally determined RNA 3D structures, understanding secondary structure is vital for discerning RNA function. Currently, there is no universally effective solution for de novo RNA secondary structure prediction. Existing methods are becoming increasingly complex without marked improvements in accuracy and often overlook critical features such as pseudoknots and alternative folds. Here, we introduce SQUARNA, a new approach to de novo RNA secondary structure prediction that is suitable for both individual RNA analysis and large-scale structural searches. SQUARNA revisits the concept of base pair maximization and develops it into a stem maximization idea coupled with the widely used free energy minimization (MFE) framework. SQUARNA can predict alternative structures and handle pseudoknots of arbitrary complexity. Benchmarking shows that SQUARNA outperforms existing methods, including deep learning models, in both single-sequence and alignment-based RNA secondary structure prediction. SQUARNA seamlessly integrates sequence and alignment information with experimental data, such as residue reactivities obtained by chemical probing, as well as other structural restraints, including automated searches for Rfam database templates, G-quadruplex patterns, and protein-binding motifs. SQUARNA is available as a standalone tool at https://github.com/febos/SQUARNA and as a web server at https://larnal.imol.institute.

  bioinformatics2026-07-28v2

• Pinc: a simple probabilistic AlphaFold interaction score

  Badonyi, M.; Toth-Petroczy, A.

  Abstract

  AlphaFold has enabled large-scale prediction of protein-protein and protein-nucleic acid complexes, but ranking and assessing the quality of predicted models remain challenging. Existing confidence scores are often highly parametrised and provide limited interpretability. We introduce a simple geometric framework that converts AlphaFold predicted aligned error (PAE) into conditional contact probability. We show that these probabilities are well calibrated to the fraction of native contacts observed across experimentally determined structures. Motivated by this, we define the Pinc score (Probability of interface native contacts) as the mean contact probability between interacting chains. Because the probabilistic interpretation extends to individual residues, Pinc captures local structural constraint beyond interfacial burial, enabling residue-level prioritisation of hotspot positions for mutational studies. Depending solely on a single empirically fixed contact radius, Pinc offers an interpretable path from PAE to interface confidence, matching or exceeding the classification performance of more complex methods across five independent benchmark sets. We provide a portable, dependency-free C program and a Google Colab notebook for calculating Pinc scores for AlphaFold models at https://git.mpi-cbg.de/tothpetroczylab/Pinc.

  bioinformatics2026-07-28v2

• ProtSyntax: a protein large language model for decoding post-translational modification syntax and function

  Lin, Y.; Wu, J.; You, Z.; Ni, X.; Chang, S.; Ding, J.; Wang, Y.; Gao, X.; Yang, S.

  Abstract

  Post-translational modifications (PTMs) expand protein function by encoding context-dependent regulatory states, and their dysregulation contributes to cancer, neurodegeneration and metabolic disease. However, existing methods treat PTMs as independent residue labels, limiting their ability to distinguish contextually permissible sites, model crosstalk and infer functional consequences. Here we introduce ProtSyntax, a PTM-aware foundation protein language model combining protein-aware positional encoding, bidirectional state-space propagation, geometry-constrained attention and adaptive multi-objective learning. This design integrates residue chemistry, motif order, long-range context and three-dimensional microenvironments while coupling PTM recognition to enzyme function. Across 40 PTM-site benchmarks, ProtSyntax exceeded the strongest baselines in mean MCC and AP by 12.66% and 10.67%. ProtSyntax also recovered masked PTM types and sites, rejected structural decoys, generalized to data-scarce modifications, reconstructed crosstalk and linked PTM perturbations to enzyme kinetics. Applications to pathogenic variants, biomolecular condensates and disease-associated PTM landscapes demonstrate its potential to decode the regulatory language of the modified proteome.

  bioinformatics2026-07-28v2

• TAMIPAMI: Software and methods for PAM/TAM identification in CRISPR and OMEGA gene editing systems

  Orosco, C.; Jain, P. K.; Rivers, A. R.

  Abstract

  Protospacer adjacent motifs (PAMs) and target-adjacent motifs (TAMs) are essential for target recognition by CRISPR-Cas and TnpB nucleases. Here we present TAMIPAMI, an efficient experimental and computational framework for rapid PAM/TAM identification. TAMIPAMI requires only a single control library and Cas or TnpB-treated library, simplifying experimental design, reducing cost, and providing greater accessibility for users. The platform interprets sequencing data with interactive visualizations and introduces a novel algorithm that determines the minimal exact set of degenerate IUPAC sequences describing the observed PAM/TAM patterns. Using this approach, we accurately recovered canonical motifs for several nucleases, including SpCas9, LbCas12a, AsCas12a, BrCas12b, Cas12i1, and AmaTnpB. TAMIPAMI is available as both a web application and command-line tool, ultimately providing an accessible and efficient platform for PAM/TAM discovery and characterization across CRISPR and OMEGA systems.

  bioinformatics2026-07-28v2

• ProNA3D: Distance-Based Analysis of Nucleic Acid-Containing Interfaces

  Genz, L. R.; Topf, M.

  Abstract

  Biomolecular interactions are central to many essential cellular processes, but RNA-containing complexes remain challenging to resolve structurally, even as experimental methods and AI-based prediction have expanded structural coverage. Tools for the integrated analysis of complex interfaces remain limited. We present ProNA3D, a tool that provides a unified platform for analyzing protein-nucleic acid and nucleic acid-only complexes, bridging the gap between structure prediction and functional interpretation. ProNA3D supports both experimental and computationally predicted structures, incorporating scoring metrics for AlphaFold3 predictions. It also offers interactive two-dimensional interface visualization and secondary-structure topology plots for RNA and DNA. An interface-based density zoning feature facilitates structure analysis in cryo-EM maps, allowing evaluation of dynamic complexes in the context of heterogeneous density. We demonstrate ProNA3D on diverse complexes solved by X-ray crystallography or cryo-EM, as well as on computational models. For example, in a trimeric complex of HIV-1 RNA and a human antibody, ProNA3D identified a high-connectivity nucleotide with potential functional relevance. Applying ProNA3D to the entire Protein Data Bank revealed distinct interface connectivity trends and interaction modes characteristic of specific complexes (e.g., in methyltransferase-DNA and CRISPR-associated) in nucleic acid-containing interfaces. The method is available as both a UCSF ChimeraX plug-in for visualization and a command-line tool at https://gitlab.com/topf-lab/ProNA3D. In addition, the repository contains the results of the large-scale analyses.

  bioinformatics2026-07-28v2

• Ordered Gromov-Hausdorff Metric: A New Tool for Comparative Analysis of Protein Structures

  Timofeev, A.; Anufriev, A.

  Abstract

  Motivation: Classical protein structure comparison metrics such as RMSD and TM-score assess geometric similarity via rigid-body superposition and sequence-dependent alignment, but they do not explicitly incorporate the linear order of amino-acid residues into the metric itself. The Gromov-Hausdorff (GH) metric compares metric spaces by their intrinsic shape, yet it also ignores order. Consequently, proteins with rearranged domains can appear geometrically similar under GH even when their evolutionary relationship is ambiguous. We introduce the Ordered Gromov-Hausdorff (OGH) metric, defined on linearly ordered metric spaces via optimal order-preserving isometric embeddings into a common host space, to rigorously incorporate residue order into structural comparison. Results: The theoretical OGH distance satisfies all metric axioms for finite ordered spaces (non-negativity, symmetry, identity of indiscernibles, and the triangle inequality), proved by standard metric-gluing arguments. For computation, we introduce an efficient surrogate based on a greedy monotonic alignment with an exponential order-penalty; we prove that any monotone alignment produced by the surrogate induces a monotone correspondence whose distortion rigorously bounds the theoretical distance from above (Lemma 2.2.5). The algorithm runs in O(n*w), where w is the search window width. Analytical properties include invariance under rigid-body motions, upper boundedness, Lipschitz continuity under small coordinate perturbations, and concavity in the weight parameter . On the Viral Affinity Dataset (28 viral proteins from HIV-1, SARS-CoV-2 and MERS-CoV), the practical OGH score increases monotonically with residue shuffling (up to 0.363 at 100% shuffling) and correlates strongly with TM-score (r=0.706). In the task of separating homologs at fixed global structural similarity (TM-score {approx}0.5), OGH achieves "AUC"=0.800, whereas TM-score gives "AUC"=0.467, demonstrating that order conservation is a more reliable signal of evolutionary relatedness than global geometry alone in the twilight zone of homology. Availability: The Python source code for OGH is freely available at https://github.com/andytimoffilim/OGH. The VAD dataset (PDB IDs listed in the paper) is publicly accessible from the RCSB Protein Data Bank [1,2].

  bioinformatics2026-07-28v2

• PanTEon: a cross-kingdom framework to guide the design of transposable element classifiers

  Orozco-Arias, S.; Ferrer-Pomer, I.; Rodrigues de Goes, F.; Gaviria-Orrego, S.; Gomiz-Fernandez, J.; Llatser-Torres, J.; Paschoal, A. R.; Guyot, r.; Gabaldon, T.

  Abstract

  Transposable elements (TEs) are major drivers of genome evolution, yet their annotation and classification remain inconsistent and hard to reproduce across species. Fragmented repeats, lineage-specific innovations, and heterogeneous taxonomies across databases and tools complicate comparisons and slow progress in TE biology. To address this, we developed PanTEon, a cross-kingdom deep learning framework for reproducible TE classification that combines a harmonized database with an open, modular benchmarking platform. The PanTEon Database is an automatically curated, taxonomically broad TE repository spanning animals, plants, and fungi. The PanTEon platform standardizes training, evaluation, and inference across nine Machine Learning methods, while remaining extensible to user-defined architectures. Using this framework, we benchmark state-of-the-art Machine Learning-based TE classifiers across TE superfamilies and major eukaryotic lineages and find that performance varies markedly by kingdom and superfamily. Ensemble approaches and phylum-specific models improve predictive F1 scores, but cross-species generalization remains a major challenge. Together, PanTEon Database and PanTEon platform provide a reproducible, scalable, and extensible foundation for TE classification, enabling standardized evaluation of future AI methods and supporting community-driven annotation efforts.

  bioinformatics2026-07-28v2

• Bayesian Network Analysis Identifies PREX1 as a Master Regulator of Cytoskeletal Disruption in Inflammatory Bowel Disease

  Medvedeva, S.; Kulygina, J.; Morozova, K.; Popova, J.; Struchalin, M.; Osipenko, M.; Kozhevnikova, E.

  Abstract

  Background: Inflammatory bowel diseases are complex multifactorial and polygenic conditions with incompletely understood etiology. Transcriptomic and metabolomic studies reveal hundreds of genes and metabolites associated with the inflammatory dowel diseases (IBD), while about 240 genetic loci are associated with these diseases. IBD are accompanied by numerous epithelial lesions including epithelial cells damage and barrier dysfunction. Recent studies suggest that cytoskeleton dysregulation underlies these aspects of IBD. We have previously shown that the disruption of cortical actin filaments and microvilli degeneration are characteristic of Muc2 mouse IBD model. Methods: We used transmission electron microscopy to evaluate ultrastructural defects in the intestinal epithelium of IBD patients. A probabilistic graphical model (Bayesian network) was employed in order to identify the key gene network hierarchy that might define cytoskeletal architecture among other regulatory events in IBD. The Bayesian network was based on preselected key node genes from open access transcriptomic data obtained in patients with Crohn's disease. Results: Electron microscopy of IBD patients demonstrated disruption of the brush border ultrastructure, similar to the microvillar defects previously described in Muc2 colitis model mice. We highlighted a list of genes contributing to actin polymerization and bundling, of which PREX1 were further confirmed using the transcriptome data obtained from Muc2 mice. Conclusion: Our study underscores the utility of Bayesian network analysis in complex cellular phenotypes that helped to identify potential target genes responsible for cortical cytoskeleton and microvilli disruption upon chronic intestinal inflammation.

  bioinformatics2026-07-28v1

• Sensitive Chromosomal Translocation Quantitation from Amplicon Sequencing Using Primer-Anchored Statistical Translocation Analysis (PASTA)

  Schmaljohn, E.; Usman, O.; Brommel, C.; Kinney, K. J.; White, N.; Turchiano, G.; Osborne, T.; Sanchez-Pena, A.; Sterrett, J.; Turk, R.; Rettig, G.; Jacobi, A. M.; Sturgeon, M.; Kurgan, G.

  Abstract

  Chromosomal translocations are rare structural rearrangement outcomes of genome editing, requiring analytical frameworks that combine high quantitative accuracy with performant sensitivity and specificity. Amplicon sequencing offers a scalable means to detect rare rearrangements with ultra-deep targeted sequencing, but existing methods often rely on heuristic thresholds or ad hoc normalization steps that limit reproducibility and have unknown analytical performance. Here, we present a computational tool we call PASTA (Primer-Anchored Statistical Translocation Analysis), using a count-based differential-event statistical framework to quantify and statistically confirm translocation junctions from targeted amplicon sequencing data. Comparison of this method to ddPCR demonstrates that quantitation is highly accurate, and outperforms other NGS-based methods even when randomized adapter chemistry is not present in amplicon sequencing structures. To measure analytical performance, we create a benchmarking dataset for measuring chromosomal translocation analysis performance with frequencies ranging from 1% to sub-0.01%, and demonstrate that the method can detect frequencies down to 0.01% with >75% sensitivity when sufficient read depth is present. Taken together, this work demonstrates using amplicon sequencing with PASTA as a bioinformatics analysis tool is a solution for translocation detection in amplicon sequencing genotoxicity assessments, enabling identification of rare genome rearrangements in both research and preclinical applications

  bioinformatics2026-07-28v1

• scINTILLA: Single-Cell Integrated Inference, Labelling, and Landscape Analysis for Cell-Type Annotation Quality Assessment

  Kanannejad, S.; Bongiorni, N.; Nordera, E.; Redaelli, S.; Rusconi, I.; Zanin, R.; Giustacchini, A.; Chatterjee, S.

  Abstract

  Single-cell RNA sequencing has enabled the construction of comprehensive cell atlases, yet the quality and coherence of the cell-type annotations within these atlases remain largely unexamined. When a label is applied to a transcriptionally heterogeneous population, the downstream analyses that depend on it, and automated label transfer in particular, become unreliable. We present scINTILLA (Single-Cell Integrated Inference, Labelling, and Landscape Analysis), a computational framework that combines supervised and unsupervised machine learning to score the learnability and internal consistency of cell-type labels in single-cell datasets. The unsupervised arm benchmarks a broad panel of clustering algorithms and derives a neighbourhood confusion score for every cell, whilst the supervised arm trains up to twelve classifiers and extracts prediction agreement, entropy, and confidence. These signals are normalised and aggregated into a single composite score per cell type, where a low score flags label ambiguity or concealed heterogeneity. As a by-product, scINTILLA also reports which clustering and classification algorithms perform best on a given dataset, offering practical guidance for downstream label transfer. We applied it to five Human Cell Atlas datasets spanning the adult brain, lung, eye, and two organoid atlases, and recovered clear differences in the learnability and internal consistency of annotations across atlases that were not driven by the number of annotated cell types. Focused re-analysis of low-scoring populations in the lung and endoderm-organoid atlases resolved biologically coherent sub-populations, in some cases with context-specific enrichment, much of it recovered from cells that had been assigned broad or catch-all labels. scINTILLA is advisory rather than prescriptive, guiding principled, data-driven re-annotation at atlas scale.

  bioinformatics2026-07-28v1

• HPAI H5N1 risk in Australia: a model for the prediction of poultry outbreaks

  Zhang, P.; Lim, S.; Quigley, A.; MacIntyre, C. R.

  Abstract

  The panzootic highly pathogenic avian influenza (HPAI) H5N1 virus has now been detected on the Australian mainland, with incursions from the sub-Antarctic region posing an increasing threat to domestic wildlife and poultry populations. Our study aimed to predict the risk of HPAI H5N1 poultry outbreaks across Australia at the local government area (LGA) level using a range of influential risk factors. We first used a Maximum Entropy (MaxEnt) model to estimate the environmental suitability for HPAI H5N1 occurrence across Australia. The resulting suitability layer was then integrated with five additional predictor layers, including abundance data for two Southern Ocean wild birds, one of which has introduced HPAI H5N1 into Australia; abundance data for 28 native Australian wild birds; native bird flyways across Australia; Australian chicken density; and poultry farm density. The six layers were aggregated and averaged to generate an HPAI H5N1 risk map for poultry outbreaks across Australian LGAs. Although most incursions have occurred in Western Australia (WA) and South Australia (SA), we identified New South Wales (NSW) and Victoria (VIC) as having the highest predicted risk of HPAI H5N1 poultry outbreaks. Additional high-risk areas were identified in WA, SA, and Tasmania (TAS). In contrast, the Northern Territory (NT) and large parts of Queensland (QLD), WA, and SA were predicted to be at low risk. These findings provide a spatially explicit framework to support targeted surveillance, preparedness, and biosecurity measures aimed at mitigating the impact of future HPAI H5N1 outbreaks in Australian poultry.

  bioinformatics2026-07-28v1

• Prioritizing Non-coding Variants in Rice GWAS Loci with a Chromatin-Informed DNA Language Model

  Shrestha, A. M. S.; Manlapaz, J. P.

  Abstract

  Numerous genome-wide association studies in rice have identified loci associated with diverse agronomic traits. However, interpreting the regulatory and functional significance of these loci remains challenging because each locus often contains multiple variants in linkage disequilibrium, many of which lie in non-coding regions. Here, we present a method for prioritizing non-coding variants within an associated locus by integrating chromatin feature information predicted by a pretrained DNA language model fine-tuned on rice ChIP-seq and ATAC-seq datasets. We demonstrate the utility of our method through three case studies. In a post-GWAS analysis of heat tolerance, prioritized variants overlapped promoters of candidate genes previously identified through integrated GWAS and transcriptomic analyses, providing independent support for their potential regulatory roles. For the high-yield gene DEP1, promoter variant prioritization combined with in silico saturation mutagenesis identified a localized regulatory region enriched for high-impact mutations overlapping predicted transcription factor binding sites. For the drought-associated gene OsHAK1, the highest-ranked variant was predicted to be associated with chromatin features in a manner consistent with the reported co-occurrence of H2Bub with H3K4 methylation marks in plants. Overall, these results demonstrate the utility of our method for functionally informative prioritization of non-coding variants, facilitating the interpretation of GWAS loci and the identification of candidate regulatory variants in rice.

  bioinformatics2026-07-28v1

• A geometric-to-neural cascade for cerebral microbleed detection in susceptibility-weighted MRI

  Bogdanov, S.; Rudravaram, G.; Saunders, A. M.; Kim, M. E.; LeFevre, J.; Charles, J.; Jain, S.; Schrag, M. S.; Landman, B. A.

  Abstract

  Cerebral microbleeds (CMBs) are established imaging biomarkers of cerebral small vessel disease and are a defining feature of cerebral amyloid angiopathy (CAA), yet their automated detection in susceptibility-weighted imaging (SWI) remains challenging due to high false-positive rates from vessel cross-sections, iron and calcium deposits, and other hypointense mimics. We present a fully automated, three-stage cascade pipeline that combines subject-adaptive unsupervised candidate generation with two successive lightweight 3D ResNet classifiers, trained with only human-in-the-loop quality-assurance (QA) labels (yes/no per candidate) rather than dense voxel-wise segmentation masks. The candidate generation stage is performed by fitting a Gaussian Mixture Model (GMM) to each subject's SWI intensity histogram to define an adaptive low-intensity threshold, followed by anatomical masking to exclude physiologically irrelevant regions (image edges, ventricles/CSF/choroid plexus, and cerebellum), and filters candidates by size and sphericity. The model was trained and evaluated across a nested 3x5-fold cross-validation on N = 30 subjects from a publicly available labeled microbleed dataset and a CAA cohort (11,424 CMB candidate lesions) with data augmentation during training. Stage A classifies all geometric candidates as CMB or non-CMB and Stage B refines the predicted positives to suppress false positives (cascade AUC = 0.9587, sensitivity = 0.712, specificity = 0.975, PPV = 0.676, F1 = 0.693). The cascade reduces Stage A false positives by 76.8% (888/1,157 false positives eliminated) while retaining competitive sensitivity. Inference was performed on 141 SWI scans, detecting a mean 40.3 CMBs per scan and being preferred for use in 85% of high CMB cases, as evaluated by a blinded neurologist. The inference pipeline outputs binary CMB segmentation NIfTI images and radiologist-ready QA visualizations.

  bioinformatics2026-07-28v1

• Sex-Specific Modulation of Gene Expression by 17beta-Estradiol in Human Meniscal Cells: Pathways to Targeted Osteoarthritis Therapies

  Yu, Y.; Vergis, J.; Eby, H.; Markho, M.; Kopacz, J.; Cartwright, K.; Hershey, M.; Liu, J.; McCullumsmith, R.

  Abstract

  Osteoarthritis (OA) disproportionately affects women, and estrogen has been implicated in cartilage and joint homeostasis, yet its effects on meniscal fibrochondrocytes (MFCs), and whether those effects differ by sex, remain poorly defined. We reanalyzed a publicly available RNA-sequencing dataset (Gene Expression Omnibus, GSE199087) comprising human MFCs from a male and a female donor treated with 17{beta}-estradiol (E2) or vehicle. Differential expression, Gene Set Enrichment Analysis, Enrichr, and iLINCS were integrated to identify the transcriptional programs modulated by E2 in each sex. In female MFCs, E2 upregulated pathways governing DNA replication, cell-cycle progression, and genomic maintenance (e.g., MCM8, BRCA1, RAD51), while downregulating inflammatory and extracellular matrix-degrading genes, including MMP1, IL12A, CXCL12, and MYD88. In male MFCs, E2 instead upregulated chromatin remodeling and developmental signaling programs, led by SRCAP, ERCC6, and NOTCH1, and downregulated antigen presentation and mitochondrial genes. These divergent responses indicate that E2 engages distinct, sex-specific transcriptional programs in MFCs, with the female profile favoring proliferation and matrix preservation. Although derived from a limited sample and therefore hypothesis-generating, these findings nominate candidate mechanisms underlying sex differences in meniscal biology and OA susceptibility, and warrant validation in larger, sex-balanced cohorts.

  bioinformatics2026-07-28v1

• STRIDE: Signal Transfer and Aligned Ion-Peak Discrimination for Peptidoform Evidence for Consistent Quantification of Site-Localized Post-Translational Modifications in Large-Scale DIA-MS

  Sing, J. C.; Gupta, S.; Rost, H. L.

  Abstract

  Data-independent acquisition (DIA) mass spectrometry has emerged as a powerful method for comprehensive post-translational modification profiling in proteomics, but faces challenges in consistently assigning peptidoforms to the same chromatographic peaks across multiple samples. This study introduces STRIDE to address this challenge by implementing dynamic programming alignment and propagating unique ion signature signals across runs. We benchmarked STRIDE using a synthetic phosphopeptide dilution series dataset, demonstrating an 11.3-fold reduction in false-negative rate compared to DIA-NN, from 68% with DIA-NN to 6% with STRIDE at 5% false-positive rate when requiring both correct site-localization and correct peak assignment. STRIDE also improved over the base OpenSWATH (IPF), reducing the false-negative rate from 14% to 6% for correct peak assignment. When applied to a phospho-enriched U2OS nocodazole dataset, our approach reduced missing values from 38.6% to 15.2% in a representative quantification matrix, increased highly reproducible phosphopeptide detections from 7,698 to 12,510 in nocodazole-treated samples, and identified 5,431 differentially abundant phosphopeptides compared to 2,588 with DIA-NN. This increased the number of enriched pathways recovered from differential phosphopeptide analysis, including pathways related to mitotic arrest, microtubule organization, chromatin regulation, RNA processing and kinase signalling. Lastly, we analyzed acetyllysine and glycopeptide-enriched DIA datasets, where STRIDE improved complete replicate detection, reduced missing quantification values, and increased site-specific glycan reproducibility. Together, these results demonstrate that STRIDE improves peptidoform proteomics through reduced false-negative rates, consistent peak assignment, and more complete quantification across runs.

  bioinformatics2026-07-28v1

• Baseline regulatory programs in larval and adult neural progenitors converge towards an injury-induced state after spinal cord injury

  Cosacak, M. I.; Severinov, D.; Westphal, M.; Heilemann, K.; Baerhold, D.; Bretschneider, A.; Reinhardt, S.; Roscito, J. G.; Becker, T.; Becker, C. G.; Poetsch, A. R.

  Abstract

  Regeneration after spinal cord injury requires progenitor cells to convert injury-associated signals into coordinated remodeling of gene regulatory programs. Mammalian spinal progenitors show limited neurogenic output after injury, whereas zebrafish regenerate spinal neurons and recover motor function. To investigate the regulatory changes that allow ependymo-radial glia (ERG) cells, the progenitor cells of the zebrafish spinal cord, to generate new neurons, we combined single-nucleus gene expression and chromatin accessibility profiling across embryonic, larval, and adult stages with topic-based gene regulatory network (GRN) inference. We found that larval and adult ERGs enter the injury response from distinct regulatory baselines: larval progenitors are characterized by a gliogenic program, whereas adult progenitors maintain a comparatively quiescent state. Following injury, both populations gradually change their baseline programs and shift towards a lesion-associated module marked by stress-responsive and chromatin-associated regulators, including jun, hmga1a, hmga2, ybx1, and foxj1a. The shift away from homeostatic states is supported by decreased expression of the Notch-associated regulators nuclear factor I A (nfia) and hey1 in larvae, while in adults, downregulation of the same nuclear factor and other TFs such as bhlhe41 is associated with quiescence exit. Pathway analysis showed stage-specific alterations after injury, characterized predominantly by extracellular signaling and cytoskeletal reorganization in larvae and by metabolic and translational remodeling in adults. Despite divergence from the homeostatic states, injury-induced larval and adult GRNs remain distinct from embryonic hERG regulatory programs. Thus, larval and adult progenitors follow different trajectories from their baselines towards a related lesion-reactive state, in which shared regeneration-associated features are acquired within respective contexts.

  bioinformatics2026-07-28v1

• PG-LLM: Benchmarking General-Purpose Language Models for Protein Variant Ranking

  Arora, R. K.; Chen, L. T.; Du, M.; Marks, D.; Church, G.

  Abstract

  General-purpose language models are being increasingly utilized in protein-design workflows, yet their ability to evaluate variant effects remains unclear. To answer this question, we introduce PG-LLM, a benchmark built on ProteinGym to evaluate general-purpose language models on 217 protein-variant prioritization tasks. Each task follows the same format: a language model receives a wild-type protein sequence, an assay description, and is tasked with ranking 50 mutant sequences by fitness without access to multiple-sequence alignments or protein structures. We evaluate thirteen language models and rescore 95 published protein predictors on the same candidate sets with the same evaluation metric. Claude Opus 5 leads the primary leaderboard with a Spearman correlation of {rho} = 0.406, narrowly ahead of GPT-5.6 Sol at 0.402. However, GPT-5.6 Sol scores higher than Opus 5 when the two models are compared only on assays scored by both. Opus 5 outperforms 49 of 95 published protein predictors, including 41 of 46 sequence-only methods, and approaches ESM2-650M at {rho} = 0.411, but remains below the leading predictor VenusREM at {rho} = 0.523. Variant-ranking performance improves with test-time compute across GPT, Claude, and Gemini models, but the gains taper before closing the gap to specialist protein predictors. Unlike sequence-only predictors, which perform better on proteins with deeper evolutionary alignments, LLM accuracy changes little across alignment-depth. PG-LLM shows that tool-free language models capture substantial protein-variant signal and already outperform many established sequence-based predictors. These results establish the emerging capability of language models as biomolecular reasoners while defining the remaining headroom for their reliable use in variant-prioritization workflows.

  bioinformatics2026-07-28v1

• A Preparation-Free Mixture-of-Experts Framework for Protein-Ligand Affinity Prediction

  Bao, H.; Dong, S.

  Abstract

  Protein-ligand affinity (PLA) prediction is central to AI-driven drug discovery, but precise interaction-based methods require costly conformation preparation and data encoding, limiting their throughput. To reconcile accuracy with efficiency, we first investigate whether pre-trained molecular representation models can replace complex encoders. A unified and diverse assessment of sequence-, graph-, and image-based representations reveals both strong overall performance and family-wise variability, delivering the first practical guidance for encoder selection in PLA tasks. Next, to achieve high computational efficiency without sacrificing expressiveness, we adopt the mixture-of-experts (MoE) strategy from large language models. Systematic ablation studies uncover key design principles for deploying MoE in molecular prediction. The resulting model, HydrAffinity, is an interaction-free, dynamic sparse model that uses pre-trained encoders and MoE for parameter-efficient learning. It outperforms all interaction-free methods and matches state-of-the-art interaction-based methods on CASF-2016. Routing analysis confirms that MoE develops distinct, family-specific activation patterns, providing interpretable evidence of dynamic parameterization across protein classes. Zero-shot tests on DUDE-Z and LIT-PCBA further show strong EF5% performance, making HydrAffinity a practical, scalable solution acting as an effective early-stage pre-filter.

  bioinformatics2026-07-28v1

• Image-based Disease-wide Association Study via Self-supervised Learning links Abdominal MRI Features to 158 Diseases

  Mousavi, S.; Arora, J.; Agarwal, R.; Fischer, A.; Mueller, S.; Ding, Z.; de Jong, J.; Yuan, K.

  Abstract

  Medical images contain rich phenotypic information that is often not fully captured by manual clinical assessment. Here, we present a systematic framework for extracting such information and conducting image-based disease-wide association studies (iDWAS) using self-supervised learning (SSL). We applied this framework to abdominal MRI data from the UK Biobank and evaluated associations between MRI-derived features and diseases. Features were learned using a VICReg-based SSL model and tested for disease associations using logistic regression models. We identified 158 diseases that were significantly associated with the MRI-derived features, including the ones which are not directly linked to abdominal anatomy. Focusing on metabolic dysfunction-associated steatohepatitis (MASH), we showed that the MRI-derived features captured disease-relevant information and separated MASH cases from controls better than established biomarkers such as PDFF and Iron-cT1. These findings highlight the ability of SSL to uncover clinically meaningful signals from routine imaging data. The proposed framework is broadly applicable to other imaging datasets and modalities, enabling more systematic approaches to incidental and early disease detection. The trained model and analysis pipeline are publicly available at https://github.com/srm2022/iDWAS.

  bioinformatics2026-07-28v1

• A Curvature Guided Composite Kernel Framework for Differential Gene Selection in Cancer Transcriptomics

  Gupta, M.; Sarkar, A. P.

  Abstract

  Identification of differentially expressed genes is a crucial step for downstream tasks on gene data such as biomarker discovery, drug target identification. Traditional Methods assume negative binomial distribution on RNA-sequence data and models the DEGs using either generalized linear models or by estimating dispersion and assumption of mean-variance rate. The proposed method uses axiomatic approach by using quantum mechanics principles to project transcript data onto a Hilbert space using a composite kernel. Using the curvature generated by the transcripts on the latent manifold within the Hilbert space, a gravitational search inspired mechanism is used to identify the optimal number of differentially expressed genes by minimizing a representational loss function, and a reduced gene feature space is constructed as the potential differentially expressed genes. The proposed method has been compared with existing empirical methods for validation using proper statistical and biological benchmark analysis.

  bioinformatics2026-07-28v1

• PrimeKG-Plus: a refreshed and rare-disease-enriched precision medicine knowledge graph

  Nguyen, T. T. D.; Nguyen-Phuong, T.; Nguyen, Q.-H.; Abbasi, A. M.; Le Phan, H.-D.; Nguyen, L. B.-A.; Phan, N.-T.; Curabaz, N. N.; Hauser, A. S.; Tanoli, Z.; Nguyen, D. T.; Kooistra, A. J.

  Abstract

  Biomedical knowledge evolves rapidly, yet most disease-centered knowledge graphs remain unchanged after publication. We present PrimeKG-Plus, an extension of PrimeKG that updates all 20 original data resources to releases available as of Dec 2025 and incorporates additional resources, including OpenTargets, RepurposeDrugs, and nSIDES. The graph is further expanded with relations extracted from 637 PubMed abstracts and PMC full-text articles using a large-language-model-assisted curation workflow. Extracted relations were refined through normalization, UMLS-based synonym mapping, SapBERT embedding based similarity ranking, and human expert review to ensure data quality. This literature-driven expansion focuses on rare neurological disorders, including Canavan disease, Niemann-Pick disease type C, Tay-Sachs disease and Batten disease. Network topology analyses indicate that the expanded graph improves indirect drug-disease connectivity of 3-6 hops through the graph while adding 447,288 Drug-Protein-Disease paths linking drug-disease pairs that were previously unreachable. Temporal FDA validation captured 55 new molecular entities after the June 2021 PrimeKG data cut-off as drug nodes, 46 absent from the original PrimeKG. By integrating newly incorporated and updated resources with systematically curated literature-derived associations, PrimeKG-Plus provides an up-to-date knowledge graph for network-based drug repurposing and precision medicine applications. Data and code are publicly available.

  bioinformatics2026-07-27v3

• WITHDRAWN: Deviation Error: assessing machine learning predictions for replicate measurements in genomics and beyond

  Abdulnabi, H.; Westwood, J. T.

  Abstract

  The authors have withdrawn this manuscript because the foundational metric used throughout the study, the Deviation Error, requires substantial mathematical formalization to be established as a proper scoring rule. Completing this rigorous theoretical validation and the necessary overhaul of the accompanying synthetic case studies requires significant additional research. We intend to revisit the Deviation Error methodology in future research. Therefore, the authors do not wish this work to be cited as reference for the project. If you have any questions, please contact the corresponding author.

  bioinformatics2026-07-27v3

• The practical impact of numerical variability on structural MRI measures of Parkinson's disease

  Chatelain, Y. M. B.; Sokołowski, A.; Sharp, M.; Poline, J.-B.; Glatard, T.

  Abstract

  Numerical variability is rarely quantified in neuroimaging despite many measures relying on subtle morphometric differences across individuals. We instrumented FreeSurfer 7.3.1, a widely used neuroimaging pipeline, to simulate numerical differences across computational environments, and used it to measure numerical variability in MRI analyses of Parkinson's disease patients and controls. In multiple cortical and subcortical regions, numerical variation reached nearly one-third of the population variability, altering statistical conclusions about group differences and clinical associations. To assess the impact of numerical noise in existing studies, we developed a practical tool that estimates the Numerical-Population Variability Ratio (NPVR) in a study, and propagates the resulting numerical variability to common statistics and associated p-values. By applying this framework to thirteen previously published studies reporting MRI measures in Parkinson's disease, we quantified the probability of numerically induced false positives and false negatives in the literature, highlighting a substantial impact of numerical variability on MRI measures of Parkinson's disease with an average significance-flip probability of 5% for cross-sectional studies and 10% for longitudinal studies. These results underscore the importance of systematically evaluating numerical stability in neuroimaging and provide a practical framework to do so.

  bioinformatics2026-07-27v3

• Explainable Artificial Intelligence for Cross-Dataset Generalizable Biomarker Discovery in Cardiovascular diseases (CVDs)

  Abbasi, A. F.; Sajjad, M.; Vollmer, S.; Dengel, A.; Asim, M. N.

  Abstract

  CVDs are heterogeneous, multifactorial disorders that remain the leading cause of global mor- tality from infancy to old age. It requires an early identification and treatment of risk factors to accelerate disease prevention and morbidity improvement. Advancements in transcriptomics tech- nologies gives large pool of heterogenous gene expression data. The technical heterogeneity of gene expression data reduces ability to compare multiple cross-platform datasets at once. To bridge gap, we systematically evaluate three data harmonization techniques: Shambhala-2, TDM, and UPC to align heterogeneous data into a shared expression space while preserving biological signals. Our pipeline integrates 25 independent datasets comprising 983 samples across 23 distinct CVDs phe- notypes from both RNA-seq and microarray platforms. The framework benchmarks 35 Machine learning (ML) and Deep learning (DL) classifiers, including Transformers and ResNets, across three data modalities such as RNA-seq, microarray hybridization and RNA-seq + microarray and multiple tissue types. To ensure clinical trustworthiness, we apply multiple Explainable artificial intelligence (XAI) methods, such as SHapley additive exPlanations (SHAP) and Integrated gradi- entss (IGs), and assess their reliability using quantitative metrics like Area over the perturbation curve (AOPC), Sensitivity, and Infidelity. Results indicate that Shambhala-2 provides superior harmonization by maximizing the biological signal-to-platform ratio. Evaluation of XAI methods reveals that Shapley-based approaches offer the highest stability for identifying influential genomic features in high-dimensional data. Functional enrichment and pathway analyses further confirmed the involvement of identified biomarkers in key cardiovascular processes, including inflammation, immune regulation, oxidative stress, and vascular remodeling. Collectively, this study provides a scalable and interpretable road-map that integrates XAI with cross-dataset biomarker discovery, supporting the transition toward precision cardiology.

  bioinformatics2026-07-27v1

• Estimation of biological age using HRV data: comparison of the Klemera-Dubal method with the multiple linear regression method

  Pysaruk, A.

  Abstract

  The aim of this study was to compare three methods for estimating biological age (BA) based on heart rate variability (HRV) indices recorded in the supine position: multiple linear regression (MLR), MLR corrected for regression-to-the-mean bias using the Dubina method (1984), and the Klemera-Doubal Method (KDM, 2006). A total of 343 subjects were examined (193 women and 150 men aged 20-90 years); nine time- and frequency-domain HRV indices were analyzed (NN, lnSDNN, lnRMSSD, lnVLF, lnLF, lnHF, VLF%, LF%, HF%). The association between HRV indices and chronological age was substantially in women and men (p<0.01). KDM produced the lowest estimation error (MAE=4.34 years in women, 3.67 years in men), whereas uncorrected MLR produced the largest error (MAE=6.57 and 7.47 years, respectively); the Dubina correction substantially improved MLR accuracy (MAE=4.22 and 4.82 years) but relied directly on actual chronological age, which limits its independent diagnostic value. The strengths and limitations of each method and recommendations for their application are discussed. Keywords: biological age, heart rate variability, Klemera-Doubal method, multiple linear regression.

  bioinformatics2026-07-27v1

• Discrete Inverse Rendering: Biological Data Analysis with Integer Programming

  Kirkegaard, J. B.; Zdyb, F. O.

  Abstract

  Biological image analysis is full of discrete decisions: whether an object is present, which of several overlapping detections is real, whether two detections match across time, and whether a cell divides. Standard pipelines resolve them locally with non-max suppression, thresholding, or greedy linking, committing before all image and temporal evidence is in. We recast such problems as discrete inverse rendering: candidate renderings are generated then jointly selected to reconstruct the movie subject to temporal and biological constraints, solved to certified optimality with a modern integer-programming solver. The same formulation covers suppression of overlapping detections, selection of a structure as a path, and event-structured tracking with birth, death, and division. Applied to C. elegans splines, sperm flagella, and dividing cells, the method matches specialised state-of-the-art pipelines across three imaging modalities on a single objective, with the largest gains where per-frame segmentation is unreliable (on a low-signal fluorescence movie of Huh7 hepatoma cells, detection F1 doubles from 0.31 to 0.58).

  bioinformatics2026-07-27v1

• An integrated single-cell atlas of human lung across the lifespan

  Huang, L.; Huang, Z.; Feng, S.; Fang, K.; Wu, J.; Ao, Y.; Huang, L.; Zhang, J.; Sun, H.; Miao, Z.

  Abstract

  The healthy adult lung is largely quiescent but can respond to injury and replace damaged or lost cells. However, the identities and origins of regenerative cell states remain poorly understood. Here we present the Human Developmental Lung Cell Atlas (HDLCA), a curated single-cell reference atlas of the respiratory system across the lifespan, integrating 253 datasets from 225 studies, and comprising over 18 million cells from 3,198 samples and 2,460 individuals across 34 anatomical locations in both health and disease. The HDLCA defines 142 consensus lung cell types, including 13 rare and 8 previously undescribed ones. Notably, we identify a rare intermediate alveolar epithelial progenitor (Int AP) population in normal lungs, with transcriptional signatures shared by alveolar type 2 (AT2) and alveolar type 1 (AT1) cells. Trajectory inference indicates that Int AP cells arise from both AT2 and SCGB1A1+ secretory cells and give rise to AT1 cells, with Hippo-YAP/TAZ signalling governing lineage specification. Int AP cells are associated with genetic susceptibility to idiopathic pulmonary fibrosis and chronic obstructive pulmonary disease, and their dysfunction may contribute to abnormal alveolar repair and regenerative failure in both diseases. The HDLCA provides a unified atlas-level reference for mapping respiratory cellular diversity, uncovering reparative cell dynamics and informing regenerative and cell-based therapeutic strategies.

  bioinformatics2026-07-27v1

• Spaceland: Histology-Guided Reconstruction of High-Resolution Whole-Organ 3D Molecular Atlases from Sparse Spatial Transcriptomics

  Xu, F.; Zhuang, Z.; Zhu, Y.; Ying, B.; Hou, N.; Lin, W.; Wang, L.; Yang, C.; song, j.

  Abstract

  Reconstructing whole organs in three-dimensional molecular detail is a key step toward building virtual organs for modeling tissue organization, disease progression and drug perturbation responses. However, high-resolution whole-organ spatial transcriptomic profiling remains impractical, forcing a trade-off between reconstruction fidelity and sampling density. Here, we introduce Spaceland, a morphology-guided framework that reconstructs continuous, high-resolution 3D molecular landscapes from sparsely sampled spatial transcriptomic sections and serial H&E histology. Spaceland formulates this task as learning continuous gene-expression fields within a morphology-informed histological space. It constructs a dense 3D morphological scaffold by optical-flow interpolation of foundation model-derived H&E representations and decodes sparse spot-level transcriptomic measurements onto an 8 m histology-aligned grid. Across mouse olfactory bulb, mouse hemibrain and spatiotemporal planarian regeneration, Spaceland generalized across platforms, tissue scales and biological contexts. In mouse benchmarks, Spaceland bridged 400 m molecular gaps, resolved sub-spot organization, outperformed ST-based interpolation and 2D H&E-based prediction methods, and remained robust with 160-320 m H&E intervals. In planarian regeneration, it enabled time-resolved whole-organism analysis from only four Visium sections per stage, revealing dynamic neoblast-neural spatial remodeling. Together, Spaceland shifts 3D molecular atlas construction from exhaustive experimental sampling toward data-driven virtual tissue and organ modeling, providing a scalable route to whole-organ molecular reconstruction.

  bioinformatics2026-07-27v1

• Decoding the Oral-Cardiac Axis: FCN1 and LYN as Key Players in the Molecular Dialogue between Acute Myocardial Infarction and Periodontitis

  Zhang, K.; Wang, Y.

  Abstract

  Background: Acute myocardial infarction (AMI) and periodontitis (PD) have been epidemiologically linked, but the molecular mechanisms underlying this association remain elusive. We aimed to elucidate shared pathogenic signatures between AMI and PD using a comprehensive bioinformatics approach. Methods: We integrated transcriptomic data from multiple Gene Expression Omnibus datasets, including an AMI cohort profiled from enriched circulating endothelial cells (GSE66360) with whole-blood validation (GSE48060), and PD gingival tissue cohorts (GSE16134 and GSE10334). Weighted gene co-expression network analysis, protein-protein interaction network analysis, and LASSO-based feature selection were applied. Functional enrichment, immune deconvolution, transcription factor-gene regulatory network analysis, and single-cell RNA sequencing analysis were performed to characterize shared molecular features. Results: We identified 95 shared differentially expressed genes (DEGs) between AMI and PD. By intersecting the shared upregulated DEGs with disease-associated WGCNA modules, we obtained 46 candidate shared genes. LASSO-based feature selection further highlighted FCN1 and LYN as overlapping candidates, which showed good discriminative performance in both training and external validation cohorts in ROC analyses. Enrichment analyses suggested that the shared signature was mainly related to myeloid cell migration, phagocytosis, and neutrophil-related inflammatory pathways (e.g., neutrophil extracellular trap formation). Immune deconvolution in PD gingival tissues suggested increased plasma cells and neutrophils and decreased resting memory CD4+ T cells; immune deconvolution results in the AMI cohort were interpreted cautiously due to the CEC-enriched sample source. Single-cell analysis revealed that FCN1 and LYN were predominantly expressed in macrophage/monocyte-derived populations. Conclusions: Our study suggests a shared inflammatory and immune-mediated transcriptomic program linking AMI and PD, and identifies FCN1 and LYN as candidate shared immune markers. These findings provide a molecular rationale for the oral-cardiovascular association and are hypothesis-generating, warranting future experimental and prospective validation.

  bioinformatics2026-07-27v1

• PUMA: A Phenotypic Unsupervised Model of Aging Reveals Distinct Aging Dimensions

  Ghorbani, F.; Nollen, E. A. A.; Guryev, V.

  Abstract

  Aging is a multidimensional process, yet most aging models reduce it to a single score to estimate biological aging and predict health outcomes, disease risk, or mortality. Here, we introduce PUMA (Phenotypic Unsupervised Model of Aging), a framework that characterizes aging through multiple phenotypic dimensions. Applying PUMA to more than 1,000 traits spanning behavioral, psychological, social, physical, environmental, and biomedical domains in over 150,000 individuals from the Lifelines cohort, we identified seven distinct phenotypic aging dimensions. These dimensions were significantly associated with the future incidence of major age-related diseases, including cancer, diabetes, COPD, heart failure, stroke, and Parkinson's disease, demonstrating the potential of PUMA to stratify individuals by disease risk and identify phenotypic domains for targeted intervention. Notably, dimensions reflecting psychosocial factors, particularly cumulative life stress, predicted disease risk as strongly as, or more strongly than, traditional biomedical risk factors, highlighting the importance of psychological and social influences in aging and disease risk. The observation that phenotypic aging dimensions are differentially associated with the future risk of age-related diseases supports a multidimensional model of aging, indicating that aging is not a single uniform process. Because PUMA relies on accessible phenotypic data, it provides an interpretable framework for disease risk stratification and targeted preventive strategies.

  bioinformatics2026-07-27v1

• Perturbation response decomposition enables biologically aligned generalization to unseen perturbations and cellular contexts

  Molina, A.; Zhang, X.

  Abstract

  Predicting single-cell responses to genetic perturbations could reveal the vast combinatorial space of perturbations and cellular contexts that is infeasible to measure experimentally, yet current deep learning models generalize poorly and often fail to outperform simple baselines. Here we demonstrate that generalizability in perturbation prediction requires identifying and representing distinct components of cellular response rather than on increasing model complexity alone. We introduce a decomposition framework that explicitly separates transcriptional responses into global, perturbation-specific, cell-line-specific, and perturbation-by-cell-line interaction components. Applied to four CRISPR-interference Perturb-seq screens on multiple cell lines, our framework reveals that these components have distinct structures and information requirements. The global response component is low-dimensional, reflects recurrent proliferation and stress response programs, and can be inferred from control gene expression. In contrast, the perturbation and cell-line specific components are high-dimensional and cannot be recovered from control expression. We therefore develop response-component-aligned models that map biological priors, such as gene coessentiality, onto the geometry of observed transcriptional responses. Critically, this alignment enables simple linear or multilayer perceptron (MLP) based models to outperform state-of-the-art architectures across multiple generalization settings, including unseen cell lines and combinations of unseen perturbations. Together, our framework for response decomposition and alignment provides a principled basis for evaluating and designing perturbation-prediction models, showing that generalization depends primarily on matching biological information to the response components rather than on model complexity alone.

  bioinformatics2026-07-27v1

• Towards Principled Evaluation of Single-Cell Perturbation Prediction Models

  Schäfer, P. S. L.; Reid, K.; Boldyga, Z.; Aksu, E. D.; Hakem, H.; Saez-Rodriguez, J.

  Abstract

  Single-cell perturbation experiments measure how interventions alter cellular phenotypes. However, the number of possible perturbations and biological contexts far exceeds what can be tested experimentally. Motivated by this constraint, predictive models aim to extrapolate cellular responses to unseen conditions. Despite substantial efforts in model development, benchmark studies have reached inconsistent conclusions about the capabilities of current perturbation-response models. A major challenge is that evaluation protocols vary widely across studies, making results difficult to compare. Furthermore, the lack of consensus on evaluation hampers progress because it is unclear which predictive capabilities new models should prioritize. To help build consensus on evaluation principles, we develop a taxonomy that decomposes evaluation protocols into their representation, metric, score transformation, and reporting strategies. We characterize how these choices determine which aspects of prediction quality a benchmark measures and discuss criteria for selecting and assessing protocols in relation to specific benchmarking goals. We additionally provide scPertEval, a Python package with reference implementations of selected evaluation protocols, and use it to assess protocol behavior across seven publicly available single-cell perturbation datasets. By making evaluation choices and their underlying trade-offs explicit, we aim to stimulate a community discussion about developing more comparable and task-aligned evaluation protocols.

  bioinformatics2026-07-27v1

• Utanos: A general-purpose shallow whole-genome sequencing analysis workflow identifies interpretable copy number signatures

  Douglas, J. M.; Lynch, B. J.; Yiu, J. C. H.; Nicholson, S.; Vasquez-Rios, C.; Ma, D.; Huntsman, D. G.; Park, Y.

  Abstract

  Summary: A modular FASTQ-to-figures solution for analyzing low-depth or shallow whole-genome sequencing (sWGS) data. Shallow WGS can be used to detect copy number (CN) aberrations, Homologous Recombination Deficiency (HRD), and to detect and create CN signatures. Growing in popularity, this sequencing type is used for neonatal diagnostics and studying cancer. One of the major benefits is the reduced cost compared with deeper sequencing modalities such as Whole Genome Sequencing (WGS). With just 15 million reads often targeted, and sample substrate options like Formalin-Fixed, Paraffin-Embedded (FFPE) blocks widely available, this approach enables an affordable study to be performed at scale. Our pipeline and R package are an end-to-end solution implemented with reusability and modularity in mind. It makes entry and exit from the ecosystem easy, providing regular standardized output formats throughout execution. The pipeline is written in the well-supported and cross-platform Nextflow framework and has been submitted for inclusion in nf-core. Additionally, a Docker image for the utanos R package has been created to improve modularity. Availability and Implementation: The latest version of all software is freely available on GitHub. For the full processing pipeline, visit: https://github.com/Huntsmanlab/swgs-processing-pipeline. For just the utanos R package, visit: https://github.com/Huntsmanlab/utanos.

  bioinformatics2026-07-27v1

• Functional Characterization of Transcriptome-Wide Isoform Switching in Hürthle Cell Carcinoma (HCC)

  Butt, R. S.; Amir, A.; Paracha, R. Z.

  Abstract

  Hurthle cell carcinoma (HCC) is an aggressive form of thyroid cancer. While mitochondrial DNA mutations and chromosomal losses have been identified in HCC, isoform switching, and its functional consequences remain uncharacterized. This study reanalyzed NCBI GEO dataset GSE228870 (n = 32), using Salmon and IsoformSwitchAnalyzeR() to identify isoform switching. The analysis resulted in 371 switches across 335 genes showing functional consequences including loss of protein domains, shorter open reading frames (ORFs), loss of signal peptides and novel sub-cellular localizations. Most significant isoform switches (q-value < 0.05, |dIF| > 0.1) were observed in LAMA2, LSP1, MAD2L2, FBLN2 and CXCL12, implicating extracellular matrix dysregulation, DNA damage response, immune signaling and cytoskeleton regulation. These genes are expressed in normal thyroid (median TPM 20.69, 11.66, 14.79, 134.1 & 80.76). However, specific isoforms of LAMA2 and MAD2L2 are not expressed in normal thyroid, explaining tumor-specific expression in HCC. Alternative transcription termination site (ATTS) gain was significant, suggesting altered 3' end in HCC transcripts. TCGA SpliceSeq showed LSP1, FBLN2 and CXCL12 undergo alternative promoter (LSP1 exon1 PSI=94.5%, FBLN2 exon2 PSI=99.0%) and alternative termination (CXCL12 exon3.3 PSI=53.9%) in thyroid cancer, suggesting ATTS and alternative transcription start site (ATSS) as shared splicing dysregulation mechanisms. This is the first systematic characterization of isoform-level dysregulation in HCC.

  bioinformatics2026-07-27v1

• SyntenyPair Explorer: an installation-free, browser-based tool for interactive pairwise genome synteny visualization

  Gibbons, J. G.

  Abstract

  Comparisons of genome structure between related organisms are central to understanding genome evolution, gene family dynamics, and the genomic basis of phenotypic variation. Synteny, the conserved co-localization of genes along chromosomes, is most readily interpreted visually, yet many existing synteny visualization tools require local software installation, command-line proficiency, and/or dedicated server infrastructure, and produce static images that cannot be explored interactively. Here, I present SyntenyPair Explorer, a lightweight, installation-free tool for interactive visualization of synteny between two genomes. The application runs entirely within a standard web browser as a single, self-contained HTML file with no external dependencies and no server-side component. SyntenyPair Explorer accepts standard file formats already produced by common comparative genomics workflows, including FASTA genome assemblies (used to compute optional assembly summary statistics), GFF3/GTF gene annotations, and either BLAST tabular output (outfmt 6) or MCScanX collinearity files. Syntenic relationships are resolved by gene-identifier matching between the relationship file and the gene annotations, so that each relationship corresponds to a discrete gene-to-gene link. Interactive features include continuous zoom and pan, gene search with automatic centering of the partner genome on the syntenic counterpart, synteny block coloring, extensively customizable gene highlights and annotation callouts, session saving and restoration, and publication-quality image export. I demonstrate the tool by visualizing structural differences at the alpha-amylase loci between two strains of the industrially important fungus Aspergillus oryzae. SyntenyPair Explorer lowers the technical barrier to interactive synteny visualization and is freely available under the MIT license at https://github.com/GibbonsLabGenomics/SyntenyPair-Explorer, with a live browser-based version at https://gibbonslabgenomics.github.io/SyntenyPair-Explorer/.

  bioinformatics2026-07-27v1

• B-SMART-Former: An Explainable Transformer-Based Deep Learning Model for Predicting Drug-Drug Interactions Between Biotech and Small-Molecule Drugs

  Nasiri, F.; Hooshmand, M.; Nouroozi, M.

  Abstract

  Drug-drug interactions between biotech and small-molecule drugs play a critical role in medication safety and therapeutic efficacy. However, most existing computational DDI prediction methods focus primarily on interactions between small-molecule drugs, leaving biotech-small-molecule interactions comparatively underexplored. In this study, we propose B-SMART-Former, an explainable deep learning framework for predicting interaction types between biotech and small-molecule drugs. The proposed framework integrates ChemBERTa embeddings and Morgan molecular fingerprints for small molecules with ProtBERT embeddings for biotech drugs, eliminating the need for similarity-based features while leveraging complementary molecular representations. These multimodal features are processed by a hybrid architecture that combines Transformer-based self-attention, residual convolutional learning, and a multi-layer perceptron classifier to capture both global contextual dependencies and local discriminative patterns. The model is formulated as a multi-class classification task and evaluated using stratified 10-fold cross-validation. To improve model transparency, Integrated Gradients is employed as a post-hoc explainability method to identify the molecular features that contribute most strongly to each prediction. Experimental results demonstrate that B-SMART-Former achieves a micro-averaged AUROC of 0.9978 and an AUPR of 0.9682 while relying solely on intrinsic molecular representations, remaining competitive with similarity-based approaches. The proposed framework offers an effective and explainable solution for biotech-small-molecule DDI prediction and provides a practical foundation for future computational drug interaction studies.

  bioinformatics2026-07-27v1

• Detecting the Information Flow in Proteins by Hodge Decomposition

  Hacisuleyman, A.

  Abstract

  Allosteric communication in proteins is commonly quantified as a directed or undirected coupling between residues, but such descriptors mix distinct modes of signalling into a single pattern. Here we treat the net transfer entropy flux from a dynamic Gaussian network(dGNM) model as an edge flow on the residue contact graph and apply the combinatorial Hodge decomposition, which dissects the flow orthogonally into a gradient (global source--to--sink hierarchy), a curl (local three--clique circulation) and a harmonic (cavity--scale circulation) component. Applied to the wild--type KRAS and ten oncogenic KRAS variants spanning the principal GTPase--cycle mechanism classes, partial--hydrolysis position--12 (G12D, G12C, G12S), GAP--occluding position--12 (G12V, G12R), catalytic switch II (Q61R, Q61H), fast--cycling (G13D, A146T) and a combined steric and catalytic double mutant (G12D/Q61H), on a side--chain--centroid contact network, the decomposition shows that the transfer entropy flux is overwhelmingly hierarchical: the gradient term carries 97.5--98.4% of the flux in every variant (permutation p = 0.002), and the recovered scalar potential is strongly anti--correlated with each residue's net outgoing transfer entropy (Spearman {rho} {approx} -0.92 to -0.95). The hierarchy is conserved in magnitude but relocated by mutations: the dominant information sources move from the C terminal 5/hypervariable region in wild type into the nucleotide--processing core, the switch I/II machinery and the 4/distal lobe in a way that tracks the GTPase--cycle mechanism of the substitution, while the sinks remain fixed. The method provides a parameter--free, residue--level readout of how mutations of different mechanism reposition the source of allosteric signalling in KRAS.

  bioinformatics2026-07-27v1

• deepthought: the microscopy acquisition stack as an object of study

  Kesavan, P. S.; Devadasan, S.; Bohra, D.

  Abstract

  Analysis-in-the-loop microscopy has been demonstrated many times, but it is rarely used outside the laboratories that build it. Each demonstration constructs its own acquisition infrastructure, so little transfers between them, and it has remained unclear which parts of the problem are already solved. In this work, the microscopy acquisition stack was itself treated as the object of study, and was investigated by construction. A minimal stack was built end to end, and four applications were then driven through it as test conditions. These were fixed-cell high-throughput immunofluorescence, live time-lapse imaging of an unsynchronized population, fluorescence anisotropy imaging, and autonomous focus and exposure. Each element of the stack was then classified by how it varied across these applications. Device access, sequencing, data storage and viewing held constant, and mature implementations of each were adopted unchanged. Interpretation, or how an image becomes a set of entities, differed with the application and belongs behind an interface. Two elements had nothing available to adopt and were therefore built. These are a geometric representation of the sample that a plan can traverse, and a representation of a run that yields detected objects rather than images. With those two in place, feedback from analysis into acquisition was ordinary control flow. The system was applied to the DNA damage response, where 22,000 cells were acquired and analyzed without operator intervention, and cells were followed through mitosis over 24 hours in an unsynchronized population without chemical synchronization. One element, targeting, or the choice of where to observe next, varies between applications and remains unabstracted in this implementation. It is identified here as the next requirement.

  bioinformatics2026-07-26v3

• An integrated resource for systems-level analysis of aging hallmarks and associated genes

  Tiwari, R.; Balaji, M.; Chivukula, N.; Sil, P.; Samal, A.

  Abstract

  Aging is a complex biological process involving progressive cellular dysfunction, tissue decline, and increased susceptibility to multiple chronic diseases. A systemic view of aging through its established hallmarks provides a structured framework to understand this complexity and drive therapeutic discovery. To this end, we present AgingHallmarksDB, an interactive web platform that enables systems-level analysis of hallmark-associated gene sets. Aging-related genes were first curated from seven established resources, and those present in at least two of these resources were considered as consensus aging-related genes. Using functional annotations derived from GO, KEGG, and Reactome, a total of 3111 genes were mapped to the 11 aging hallmarks, of which 2593 were supported by additional experimental or manually curated evidence, with 1089 of these forming the consensus set. Further, AgingHallmarksDB supplements hallmarks and gene annotations with tissue or cell-type class specificity, exosomal profiles, and regulatory interactions, enabling users to perform hallmark enrichment, protein-protein and regulatory interaction-based analysis. To elucidate the interconnectedness of hallmarks, network separation and proximity analyses of hallmark-associated modules were performed, revealing functional overlap between hallmarks on the human interactome. Furthermore, the utility of AgingHallmarksDB was demonstrated through network topological and regulatory interaction analyses of common hallmark genes, hallmark enrichment and network proximity analyses of eight chronic age-related diseases and seven developmental and congenital diseases, and gene set enrichment analysis of a PM2.5-associated skin transcriptome. Together, these analyses highlight the utility of AgingHallmarksDB for aging hallmark-centred systems biology research. The resource is accessible at https://cb.imsc.res.in/aginghallmarksdb/.

  bioinformatics2026-07-26v2

• Glycine molecule radical: Predicted properties and dipeptide formation

  Synak, J.; Blazewicz, J.

  Abstract

  The formation of the first peptide bonds under prebiotic conditions remains an open question. We used density functional theory calculations with the B3LYP functional to predict a novel pathway of peptide bond formation, which could have taken place without the sophisticated catalysts used by modern biological systems, utilising only radical chemistry. To make our investigation more extensive, the properties of intermediates (glycine-derived radicals) were thoroughly analysed, using the DFT, resonance hybrid model and orbital hybridisation. These methods shed more light on the exact nature of processes which should take place, explaining why this pathway could be favoured by the system. The result is a series of reactions, which without any sophisticated catalysts and with relatively low electronic energy barrier (<20 kcal/mol) can lead to formation of dipeptides, suggesting also a possible starting point for further peptide chain extension.

  bioinformatics2026-07-25v2

• Phenotype-driven de novo molecular design from gene expression signatures

  Xu, Y.; Kuang, T.; Ge, S.; Wu, H.; Wang, M.; Xu, H.; An, F.; Ma, Z.; Cheng, Q.; Ren, Z.

  Abstract

  Target-based and structure-guided drug design remain central to modern drug discovery, but complementary strategies are needed when predefined targets or binding pockets do not fully capture disease biology. Gene-expression signatures provide scalable system-level readouts of disease and perturbation states, making them attractive inputs for phenotype-guided molecular design. However, preserving phenotypic information during molecular generation remains challenging, and chemically plausible molecules may lose connection to the intended biological response. Here, we present Tx2Mol, a transcriptome-guided framework that translates gene-expression signatures into candidate molecules while maintaining biological guidance throughout generation. We evaluated Tx2Mol across three biological settings: bulk gene perturbation, single-cell perturbation, and patient-derived disease signatures; and three validation dimensions: chemical plausibility, structural compatibility, and phenotypic preservation. Across 10 cancer-relevant bulk gene-perturbation benchmarks, Tx2Mol outperformed 9 transcriptome-guided baselines, improving maximum Tanimoto similarity to known ligands by 24.10% on average and by 50.67% on HDAC1. Structure-based analyses further supported structurally novel candidates with favorable predicted target binding. Tx2Mol also generalized to noisy single-cell perturbation profiles and preserved drug-induced transcriptional responses through in silico drug-perturbation validation. Patient-derived disease signatures further guided molecular generation toward approved-drug chemical space. Together, these results support gene-expression phenotypes as actionable guidance signals for phenotype-directed molecular design and candidate prioritization.

  bioinformatics2026-07-25v2

• STAR Suite: an open-source single-executable transcriptomics engine for reproducible, AI agent-assisted processing

  Hung, L.-H.; Baker, D.; Flynn, B.; Huangfu, D.; Luo, R.; Robson, P.; Zhou, T.; Yeung, K. Y.

  Abstract

  Processing sequencing data means chaining many specialized tools, a barrier for bench biologists and for the AI agents increasingly used to run analyses. Open, integrated pipelines remain incomplete: the de facto single-cell standard, Cell Ranger, is proprietary - its license bars redistribution, modification, and non-10x use - so it cannot serve as a shareable, AI-discoverable layer, and no production-ready open-source pipeline exists for 10x Flex. Here, we present STAR Suite, which extends the STAR aligner into a single executable for transcriptomics processing.Adapter handling, feature-barcode assignment, Flex probe processing, SLAM-seq analysis, sorting, and quality control are integrated directly into the 28,228-line STAR codebase with no additional external dependencies, adding 132,226 lines of C/C++ made tractable through human-directed AI software engineering. Novel methodologies include dynamic thread interleaving, fast-Hamming feature matching, alignment-validated probe hashing, and variance-based auto-trimming (SLAM-seq); in-process integrations include Y-chromosome removal, per-sample variant masking, and Variational Bayes transcript quantification (bulk RNA-seq). STAR Suite reproduces Cell Ranger 9.0.1 to gene-level Pearson 0.99-1.0 while running 3.6- to 5.7-fold faster, and 3.9-fold faster than stepwise bulk pipelines. Used across the NIH MorPhiC consortium, its source code, workflow recipes (morphic-recipes), and immutable per-run provenance records (morphic-provenance) are released under the permissive open-source MIT license.

  bioinformatics2026-07-24v5

• Phylogenetic detection of protein sites associated with continuous traits

  Duchemin, L.; Muntane, G.; Boussau, B.; Veber, P.

  Abstract

  Comparative genomic data can be used to look for substitutions in coding sequences that are associated with the variation of a particular phenotypic trait. A few statistical methods have been proposed to do so for phenotypes represented by discrete values. For continuous traits, no such statistical approach has been proposed, and researchers have resorted to sensible but uncharacterized criteria. Here, we investigate a phylogenetic model for coding sequences where amino acid preferences at a site are given by a continuous function of a quantitative trait. This function is inferred from the amino acids and the trait values in extant species and requires inferred point estimates of ancestral values of the trait at internal nodes. For detecting sites whose evolution is associated with this trait, we use a significance test against the hypothesis that amino acid preference does not depend on the trait. This procedure is compared to simpler strategies on simulated alignments. It displays an increased recall for low false positive rates, which is of special importance for performing whole-genome scans. This comes however at a much higher computational cost, and we suggest using a simple test to filter promising candidate sites. We then revisit a dataset of alignments for 62 species of mammals, using longevity as a phenotypic trait. We apply our method to three protein families that have previously been proposed to display sites associated with variation in lifespan in mammals. Using a graphical representation extracted from the detailed phylogenetic analysis of candidate sites, we suggest that the evidence for this in the sequence data alone is weak. The proposed method has been added to our Pelican software. It is available at https://gitlab.in2p3.fr/phoogle/pelican and can now be used with both discrete and continuous phenotypes to search for sites associated with phenotypic variation, on data sets with thousands of alignments.

  bioinformatics2026-07-24v5

• Leveraging Uncertainty Estimates for Drug Response Prediction in Cancer Cell Lines

  Iversen, P.; Renard, B. Y.; Baum, K.

  Abstract

  Machine learning models for drug response prediction in cancer cell lines carry the potential to advance precision oncology by tailoring treatments to the molecular tumor profile. Their application is challenged by variability in prediction quality and distribution shifts between training and application. Uncertainty estimation provides more information on the predictive distribution than point estimates, enabling comprehensive decision support and downstream analysis of predictions. Yet, the most effective uncertainty estimator is domain-specific. In this work, we benchmark uncertainty-aware models for drug response prediction. We focus on epistemic uncertainty via ensemble agreement, and aleatoric uncertainty via distributional modeling, or both. We find that ensemble-based estimates are more sensitive to distribution shift and can flag out-of-distribution examples. In contrast, distributional models yield stronger prediction error reductions among high-confidence subsets. Despite higher computational cost, the combination can provide both advantages: an ensemble of neural networks that estimate a Gaussian predictive distribution can reduce the mean squared error by 64 percent when restricting predictions to the 10 percent most confident drug-cell line pairs, and reliably indicates distribution shifts and platform differences. Beyond benchmarking, probabilistic predictions can identify drugs whose uncertainty bounds overlap with therapeutically relevant ranges. We also show that uncertainty estimates enable a new dimension of model interpretability: by attributing predicted uncertainty to input features, we identify genes that signal unpredictability of drug response rather than sensitivity or resistance. We further demonstrate uncertainty-guided selection of measurements for active learning. In summary, including uncertainty in drug response prediction supports better-informed model application. The code is available at https://github.com/PascalIversen/LUDRP.

  bioinformatics2026-07-24v2

• ViroSeek: a viral detection pipeline for second-generation sequencing

  Berger, A.; Lefebvre, M. J. M.; Dainat, J.; Jiolle, D.; Conclois, I.; Talignani, L.; Mastriani, E.; Cornelie, S.; Berthet, N.; Paupy, C.

  Abstract

  Arbovirus emergences represent a rising public health issue and are exacerbated by climate change and globalization. Virome analysis has become a key approach for monitoring and managing infectious diseases, yet existing tools often remain technically complex and inaccessible to non-specialists. In this context, we present ViroSeek, a reproducible and accessible bioinformatics pipeline specifically designed for the taxonomic analysis of second-generation sequencing data from target-enriched libraries. ViroSeek performs a series of automated steps: quality control, trimming, host and bacterial sequence removal, assembly, taxonomic assignment, read remapping for quantification, and PCR duplicate removal. The whole process is designed to produce a clear, usable viral taxonomy table that is suitable for diversity studies. ViroSeek was empirically validated on enriched control samples containing a known panel of viruses. All the expected viruses were correctly detected. Bacterial and host contaminant sequences were effectively removed. The pipeline is freely available and fully documented, supporting its adoption and adaptation by the research community.

  bioinformatics2026-07-24v2

• DOME Copilot: A resource to automate transparent reporting of artificial intelligence methods

  Farrell, G.; Attafi, O. A.; Fragkouli, S.-C.; Heredia, I.; Fernandez Tobias, S.; Harrison, M.; Hermjakob, H.; Jeffryes, M.; Mehdiabadi, M.; Obregon Ruiz, M.; Pearce, M.; Pechlivanis, N.; Quaglia, F.; Lopez Garcia, A.; Psomopoulos, F.; Tosatto, S. C. E.

  Abstract

  Artificial intelligence (AI) methods are transforming life science research and witnessing unprecedented adoption across literature. While AI is driving impactful discoveries, this rapid growth in application has inundated researchers with poorly described models and datasets which lack transparency, impeding reusability and eroding trust. The DOME Recommendations aimed to address this issue and established structured reporting guidelines to standardize AI methodology descriptions. However, the need to manually create these comprehensive disclosures imposed a major bottleneck, requiring substantial effort from authors to comply. To bridge this gap, we present DOME Copilot, an open-source, easily deployable system that automates the generation of transparent AI methodology reports supplementing publications. Evaluated against a benchmark of human-created annotations, DOME Copilot was determined to match or exceed manual annotation quality across the majority of reporting fields while reducing the creation time from hours to minutes. Ultimately, the system provides a novel and scalable solution to restore confidence in complex life science AI method publications.

  bioinformatics2026-07-24v2

• Graph in Graph (GiG): A novel graph AI framework for integrating and interpreting whole-person healthmedical and omics data

  Zhang, H.; Lu, Y.; Fang, K.; XU, Z.; Akbary Moghaddam, V.; An, P.; Jin, S.; Wojczynski, M.; Province, M.; Li, F.

  Abstract

  Medical records and omics data are rapidly becoming standard in healthcare settings, which characterize the whole-person from dysfunctional molecules to phenotypes, and thus offer potential for precise disease diagnosis and target discovery. Whereas, it remains an open problem to systematically integrate and interprete medical record and omics data of individual patients. In this study, for the first time, we propose a novel graph AI model framework, Graph in Graph (GiG), to integrate and interpret the whole-person medical and omic datasets. Specifically, the medical record data is modeled using a person-phenotype graph, followed by omics signaling graphs of invidival patients, which enables the integration of information learned from omic-signaling graph and medical phenotype features to characterize individual patients and to prioritize important omic biomarkers and phenotypes. As an exploratory study, we applied and evaluated the GiG model to study the type 2 diabetes (T2D) and pre-T2D vs healthy using the Long Life Family Study (LLFS) cohort, which enrolls families with exceptional longevity to uncover biological mechanisms of healthy aging with medical and omics data. The evaluation results showed that GiG not only achieve a high prediction but also can interpret the prediction by ranking the essential clinical and omic biomarkers. The GiG framework can be applied to other studies by effectively integrating and interpreting medical and omic datasets for disease diagnosis and pathogenesis discovery.

  bioinformatics2026-07-24v1