SEARCH · PubMed Health

Results for “Graph”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources

PubMed2025

Pairwise graph edit distance characterizes the impact of the construction method on pangenome graphs.

MOTIVATION: Pangenome variation graphs are an increasingly used tool to perform genome analysis, aiming to replace a linear reference in a wide variety of genomic analyses. The construction of a variation graph from a collection of chromosome-size genome sequences is a difficult task that is generally addressed using a number of heuristics. The question that arises is to what extent the construction method influences the resulting graph, and the characterization of variability. RESULTS: We aim to characterize the differences between variation graphs derived from the same set of genomes with a metric which expresses and pinpoint differences. We designed a pairwise variation graph comparison algorithm, which establishes an edit distance between variation graphs, threading the genomes through both graphs. We applied our method to pangenome graphs built from yeast and human chromosome collections, and demonstrate that our method effectively characterizes discordances between pangenome graph construction methods and scales to real datasets. AVAILABILITY AND IMPLEMENTATION: pancat compare is published as free Rust software under the AGPL3.0 open source license. Source code and documentation are available at https://github.com/dubssieg/rs-pancat-compare. Snapshot available on Software Heritage at swh:1:dir:61acda8ba3dac1709ed60530147d3871831be629.

Algorithms↗

PubMed2026

Graph-KIR: graph-based KIR copy number estimation and allele calling using short-read sequencing data.

MOTIVATION: The Killer-cell Immunoglobulin-like Receptor (KIR) is a highly polymorphic region in the human genome, associated with autoimmune diseases and organ transplantation. The sequences of KIR genes are highly similar among star alleles as well as in between individual genes, with the copy number of each KIR gene typically ranging from 0 to 4. In this study, we introduce Graph-KIR, a tool designed to estimate gene copy numbers and predict full-resolution (7-digit, encompassing both coding and non-coding sequence variations) from a whole genome sequencing (WGS) sample. RESULTS: Graph-KIR is capable of independently typing KIR alleles per sample with no reliance on the distribution of any framework gene in a cohort. In a set of 100 simulated samples, Graph-KIR demonstrated 99.2% accuracy in copy number estimation and high F1-score of allele typing: 91.79% at 7-digit resolution, 97.37% at 5-digit resolution, and 97.11% at 3-digit resolution. Graph-KIR outperforms existing tools such as Geny (96.39% F1-score), PING's WGS version (92.77% F1-score), and T1K (90.44% F1-score) at 5-digit resolution. By analyzing the results on 44 HPRC samples, Graph-KIR achieves better F1-score than Geny and PING at 7-digit resolution. The release of Graph-KIR adds another valuable tool to assist users in accurately estimating copy numbers and calling alleles of KIR genes from WGS samples. AVAILABILITY AND IMPLEMENTATION: The Graph-KIR and paper-related pipeline codes are available at https://github.com/linnil1/KIR_graph.

Receptors, KIR↗

PubMed2026

Scalable computation of ultrabubbles in pangenomes by orienting bidirected graphs.

MOTIVATION: Pangenome graphs are increasingly used in bioinformatics, ranging from environmental surveillance and crop improvement to the construction of population-scale human pangenomes. As these graphs grow in size, methods that scale efficiently become essential. A central task in pangenome analysis is the discovery of variation structures. In directed graphs, the most widely studied such structures, superbubbles, can be identified in linear time. Their canonical generalization to bidirected graphs, ultrabubbles, more accurately models DNA reverse complementarity. However, existing ultrabubble algorithms are quadratic in the worst case. RESULTS: We show that all ultrabubbles in a bidirected graph containing at least one tip or one cutvertex-a common property of pangenome graphs-can be computed in linear time. Our key contribution is a new linear-time orientation algorithm that transforms such a bidirected graph into a directed graph of the same size, in practice. Orientation conflicts are resolved by introducing auxiliary source or sink vertices. We prove that ultrabubbles in the original bidirected graph correspond to weak superbubbles in the resulting directed graph, enabling the use of existing linear-time algorithms. Our approach achieves speedups of up to 25× over the ultrabubble implementation in vg, and of >200× over BubbleGun, enabling scalable pangenome analyses. For example, on the v2.0 pangenome graph constructed by the Human Pangenome Reference Consortium from 232 individuals, after reading the input, our method completes in under 3 min, while vg requires >1 hour, and four times more RAM. AVAILABILITY AND IMPLEMENTATION: Our method is implemented in the BubbleFinder tool github.com/algbio/BubbleFinder, via the new ultrabubbles subcommand.

Algorithms↗

PubMed2026

engGNN: a dual-graph neural network for omics-based disease classification and feature selection.

Omics data, such as transcriptomics, proteomics, and metabolomics, provide critical insights into disease mechanisms and clinical outcomes. However, their high dimensionality, small sample sizes, and intricate biological networks pose major challenges for reliable prediction and meaningful interpretation. Graph neural networks offer a promising way to integrate prior knowledge by encoding feature relationships as graphs. Yet, existing methods typically rely solely on either an externally curated feature graph or a data-driven generated graph, which limits their ability to capture complementary information. To address this, we propose the external and generated Graph Neural Network (engGNN), a dual-graph framework that jointly leverages both external biological networks and data-driven generated graphs. Specifically, engGNN constructs a biologically informed undirected feature graph from established network databases and complements it with a directed feature graph derived from tree-ensemble models. This dual-graph design produces more comprehensive representations, thereby improving predictive performance and interpretability. Through extensive simulation studies and real-world applications to three independent gene expression datasets, engGNN consistently demonstrates strong classification performance compared with competitive baselines. Beyond classification, engGNN provides feature- and source-level interpretability, enabling biologically meaningful analyses such as pathway enrichment analysis. Taken together, these results highlight engGNN as a robust, flexible, and interpretable framework for disease classification and biomarker discovery in high-dimensional omics contexts.

Graph Neural Networks↗

PubMed2026

Exploring differences across pangenome-graph representations using Escherichia coli O157:H7 as a model.

Pangenome graphs are increasingly used to represent population-scale bacterial diversity, yet construction methods span fundamentally different representation paradigms whose outputs and sensitivities to assembly quality remain poorly quantified. We systematically reviewed microbial pangenome graph tools and benchmarked seven representative methods spanning gene-cluster, compacted coloured de Bruijn graph, one hybrid approach and one multiple sequence alignment method. Using a repeat-rich Escherichia coli O157:H7 dataset with complete genomes and matched short-read data, we constructed graphs from identical inputs and observed orders-of-magnitude differences in graph size and fragmentation, indicating that global topology is driven by representation strategy. Varying completeness composition revealed that assembly fragmentation is a first-order determinant of graph structure: gene-cluster graphs contracted as draft assemblies replaced complete genomes, whereas compacted coloured de Bruijn graphs expanded, with distinct degree-prevalence fingerprints across tools. In contrast, the multiple sequence alignment method could not be evaluated across fragmented inputs because it did not run reliably on draft-assembly datasets. Computational cost mirrored these shifts and depended strongly on completeness composition, including a pronounced runtime penalty for one compacted coloured de Bruijn graph implementation on all-draft inputs. Finally, analysis of Shiga toxin loci showed that pangenome-level reconciliation by gene-cluster-based tools does not reliably correct assembly artefacts at challenging multi-copy genes and that performance varies by locus. Together, these findings show that pangenome graphs are representation-dependent models of bacterial diversity, and that, in this repeat-rich O157:H7 benchmark dataset, assembly completeness is a primary determinant of their topology, scalability, and locus-level accuracy.

Escherichia coli O157↗

PubMed2025

BioMedGraphica: An All-in-One Platform for Joint Textual Biomedical Prior Knowledge and Numeric Graph Generation.

Multi-omic data analysis is essential for scientific discovery in precision medicine. However, translating statistical results of omic data analysis into novel scientific hypothesis remains a significant challenge. Human experts must manually review analysis results and generate new hypothesis based on extensive and inter-connected biomedical prior knowledge, which is subjective and not scalable. While large language models (LLMs) can accelerate the discovery, their reasoning improves when grounded in structured, auditable and comprehensive biomedical prior knowledge. Biomedical knowledge, however, is scattered across heterogeneous databases that use diverse and inconsistent nomenclature systems, making it difficult to integrate resources into a unified format for scalable analysis. This fragmentation limits the ability of AI systems to fully leverage biomedical data for scientific discovery. To address these challenges, we developed BioMedGraphica , an all-in-one platform that harmonizes fragmented biomedical resources by integrating 11 entity types and 30 relation types from 43 databases into a unified knowledge graph containing 2,306,921 entities and 27,232,091 relations. In addition, to the best of our knowledge, this is the first work to propose a novel Textual-Numeric Graph (TNG) data-structure for multi-omics data analysis. In TNG, textual information captures prior biological knowledge (e.g., transcription start sites, functions, mechanisms), while numeric values represent quantitative biomedical features, and the integrated relations can help uncover mechanisms. By bridging prior knowledge with user-specific data, TNG is a novel and ideal data-structure for the development of graph foundation models, with the potential to improve prediction performance and interpretability, while also augmenting LLMs by supplying graph-structured mechanistic context to strengthen reasoning. The details for BioMedGraphica code can be accessed by github link: https://github.com/FuhaiLiAiLab/BioMedGraphica and BioMedGraphica knowledge graph data can be downloaded from huggingface dataset: https://huggingface.co/datasets/FuhaiLiAiLab/BioMedGraphica.

biomedical knowledge graph↗

PubMed2026

Theseus: fast and optimal affine-gap sequence-to-graph alignment.

MOTIVATION: Sequence-to-graph alignment is a central problem in bioinformatics, with applications in multiple sequence alignment (MSA) and pangenome analysis, among others. However, current algorithms for optimal affine-gap alignment impose high memory and computational requirements, limiting their scalability to aligning long sequences to complex graphs. Practical solutions partially address this problem using heuristic strategies that ultimately trade off optimality for speed. RESULTS: This work presents Theseus, a novel, fast, and optimal affine-gap sequence-to-graph alignment algorithm. Theseus leverages similarities between genomic sequences to accelerate the alignment computation and reduces the overall memory requirements without compromising optimality. To that end, Theseus processes only a subset of the dynamic programming cells, using a sparse-data strategy that enables efficient sequence-to-graph alignment. Moreover, our algorithm supports optimal affine-gap alignment on arbitrary directed graphs, including those with cycles. We evaluate Theseus on two key problems: MSA and pangenome read mapping. For MSA, we compare it against SPOA, abPOA, and POASTA. Theseus is 1.6× to 17.6× faster than POASTA, and 7.3× faster, on average, than SPOA, both optimal aligners. Compared with abPOA, Theseus ensures optimality and scales to the largest problems. For pangenome read mapping, we benchmark Theseus against the alignment stage of the mapping tool vg map, along with the alignment kernels of SPOA, abPOA, and POASTA. Theseus outperforms the other methods, showing a 1.9× to 16.9× speedup on short reads. Moreover, Theseus is 1.5× to 36.3× faster than vg when aligning against synthetic cyclic graphs. AVAILABILITY AND IMPLEMENTATION: Theseus code and documentation are publicly available at https://github.com/albertjimenezbl/theseus-lib.

Algorithms↗

PubMed2026

DPAS-Graph: adaptive spatial-feature relation learning for spatial RNA-to-protein prediction and virtual protein profiling.

Paired spatial multi-omics provides a supervised basis for learning RNA-protein correspondence in situ, but predicting protein abundance from spatial transcriptomic data alone remains challenging across tissue contexts and protein panels. Here, we present DPAS-Graph, an adaptive relation-learning framework for spatial RNA-to-protein prediction. Rather than directly merging spatial proximity and transcriptomic similarity as fixed graph priors, DPAS-Graph represents them as two relation channels on a shared edge support and updates their contributions during representation learning for protein prediction. Its Niche-Coupled Field Encoder combines layer-wise edge-relation modeling, intra-branch relation refinement, and cross-branch residual correction to learn spot representations for protein abundance prediction. In a leave-one-dataset-out benchmark across seven paired spatial multi-omics datasets, DPAS-Graph achieved lower aggregate prediction errors and improved spot-level agreement of protein expression profiles, with gains mainly reflected in error-based metrics and PCC-Spot. Spatial autocorrelation and protein-derived domain agreement analyses were further used to characterize the spatial behavior of the predicted protein maps. When applied to external RNA-only spatial sections, DPAS-Graph generated qualitatively interpretable marker-level virtual protein maps, illustrating its use as a complementary tool for protein-level interpretation of transcriptomics-only spatial data.

RNA↗

PubMedDate not supplied

Graphs and stochastic relaxation for hierarchical Bayes modelling.

This expository paper describes two useful tools for the statistical analysis of processes that generate repeated measures and longitudinal data. The first tool is a graph for a visual description of dependency structures. The second tool is a stochastic relaxation method ('Gibbs sampling') for fitting hierarchical Bayes models. Graphs are concise and accessible summaries of stochastic models. Graphs aid communications between statistical and subject-matter scientists, during which formulations of scientific questions are modified. An uncluttered picture of the dependency structure of a model augments effectively its corresponding formulaic description. Stochastic relaxation is a computationally intense method that allows experimentation with broader classes of models than were previously thought feasible because of analytic intractability. Stochastic relaxation is intuitive and easily described to non-statisticians. Several sample graphs show how hierarchical Bayes models can use stochastic relaxation to obtain their fits. An example based on estimating drug shelf-life demonstrates some uses of graphs and stochastic relaxation compared with several frequentist growth curve analyses that use restricted maximum likelihood and generalized estimating equations approaches.

Bayes Theorem↗

PubMed2025

MO-GCAN: multi-omics integration based on graph convolutional and attention networks.

MOTIVATION: Cancer subtypes play a critical role in disease progression, prognosis, and treatment, making their detection essential for tailoring precision medicine. Studies have shown that multi-omics integration outperforms single-omics approaches in cancer subtyping tasks. However, due to the high-dimensionality of multi-omics data, many existing studies either fail to capture the correlation between true labels and learned features, or lack sufficient capacity to model complex biological representations. These limitations hinder the full potential of leveraging the rich and complementary information embedded in multi-omics datasets. RESULT: We propose a framework that leverages supervised feature learning and classification based on a graph-based learning approach with attention mechanism for cancer subtyping. More specifically, we train graph convolutional network models on each omics dataset to extract latent representations, which are then concatenated to form a comprehensive multi-omics feature embedding. We further develop sample fusion network based on the omics-specific graphs, incorporating the derived features and feeding them into a graph attention model for subtype classification. This two-stage multi-omics framework is applied to eight cancer types, with performance evaluated in terms of test accuracy, training time, macro-averaged precision, recall, and F-score. Experimental results show that the proposed method outperforms state-of-the-art approaches across various cancer types. Additionally, we provide empirical evidence supporting the hypothesis that retaining a limited number of high-confidence edges and utilizing enriched embeddings from intermediate graph neural network layers can improve predictive performance. AVAILABILITY AND IMPLEMENTATION: Data and the code are available at https://github.com/YD-00/MO-GCAN-Updated.git.

Neoplasms↗

PubMed2025

Large Language Model and Knowledge Graph-Driven AJCC Staging of Prostate Cancer Using Pathology Reports.

Background/Objectives: To develop an automated American Joint Committee on Cancer (AJCC) staging system for radical prostatectomy pathology reports using large language model-based information extraction and knowledge graph validation. Methods: Pathology reports from 152 radical prostatectomy patients were used. Five additional parameters (Prostate-specific antigen (PSA) level, metastasis stage (M-stage), extraprostatic extension, seminal vesicle invasion, and perineural invasion) were extracted using GPT-4.1 with zero-shot prompting. A knowledge graph was constructed to model pathological relationships and implement rule-based AJCC staging with consistency validation. Information extraction performance was evaluated using a local open-source large language model (LLM) (Mistral-Small-3.2-24B-Instruct) across 16 parameters. The LLM-extracted information was integrated into the knowledge graph for automated AJCC staging classification and data consistency validation. The developed system was further validated using pathology reports from 88 radical prostatectomy patients in The Cancer Genome Atlas (TCGA) dataset. Results: Information extraction achieved an accuracy of 0.973 and an F1-score of 0.986 on the internal dataset, and 0.938 and 0.968, respectively, on external validation. AJCC staging classification showed macro-averaged F1-scores of 0.930 and 0.833 for the internal and external datasets, respectively. Knowledge graph-based validation detected data inconsistencies in 5 of 150 cases (3.3%). Conclusions: This study demonstrates the feasibility of automated AJCC staging through the integration of large language model information extraction and knowledge graph-based validation. The resulting system enables privacy-protected clinical decision support for cancer staging applications with extensibility to broader oncologic domains.

artificial intelligence↗

PubMed1992

Structure and strategy in encoding simplified graphs.

Tversky and Schiano (1989) found a systematic bias toward the 45 degrees line in memory for the slopes of identical lines when embedded in graphs, but not in maps, suggesting the use of a cognitive reference frame specifically for encoding meaningful graphs. The present experiments explore this issue further using the linear configurations alone as stimuli. Experiments 1 and 2 demonstrate that perception and immediate memory for the slope of a test line within orthogonal "axes" are predictable from purely structural considerations. In Experiments 3 and 4, subjects were instructed to use a diagonal-reference strategy in viewing the stimuli, which were described as "graphs" only in Experiment 3. Results for both studies showed the diagonal bias previously found only for graphs. This pattern provides converging evidence for the diagonal as a cognitive reference frame in encoding linear graphs, and demonstrates that even in highly simplified displays, strategic factors can produce encoding biases not predictable solely from stimulus structure alone.

Bias↗

PubMed1992

Graph-grammar productions for the modeling of medical dilemmas.

We introduce graph-grammar production rules, which can guide physicians to construct models for normative decision making. A physician describes a medical decision problem using standard terminology, and the graph-grammar system matches a graph-manipulation rule to each of the standard terms. With minimal help from the physician, these graph-manipulation rules can construct an appropriate Bayesian probabilistic network. The physician can then assess the necessary probabilities and utilities to arrive at a rational decision. The grammar relies on prototypical forms that we have observed in models of medical dilemmas. We have found graph grammars to be a concise and expressive formalism for describing prototypical forms, and we believe such grammars can greatly facilitate the modeling of medical dilemmas and medical plans.

Bayes Theorem↗

PubMed2026

CAGNet: a structure-aware clustering-alternated graph network for cell-cell interaction inference in spatial transcriptomics.

MOTIVATION: Understanding cell-cell interactions (CCIs) in spatial transcriptomics is crucial for uncovering the spatial organization and functional heterogeneity of tissues. However, existing graph-based models typically rely on static clustering or fixed adjacency structures, which limits their ability to capture dynamic cellular relationships. RESULTS: We propose CAGNet, a two-stage framework for CCI inference from spatial transcriptomics data. In Stage 1, a Graph Attention Network encoder with joint feature and graph reconstruction learns structure-aware node embeddings from spatial gene expression profiles. In Stage 2, an alternating optimization mechanism iteratively updates cluster centers via KL-guided soft assignment and refines node embeddings through spatial graph reconstruction, establishing a closed-loop between representation learning and clustering. Experiments on three 10x Genomics Visium datasets demonstrate that CAGNet consistently outperforms six CCI inference baselines across ACC, AUC, AP, Precision, Recall, and F1. CAGNet also achieves the highest Adjusted Rand Index on all three datasets against six spatial domain identification methods, confirming that the learned embeddings capture biologically relevant spatial organization. Information-theoretic analysis further shows that CAGNet retains the highest mutual information between input features and learned embeddings among all compared methods. Ablation studies and 5-fold cross-validation confirm the contribution of each component and the reproducibility of the results. AVAILABILITY: The proposed method is implemented in the CAGNet package available at http://github.com/mahan1233333-maker/CAGNet .

Spatial Transcriptomics↗

PubMed1976

Growth graphs for the clinical assessment of infants of varying gestational age.

Two graphs are presented showing means and 1 and 2 SD for growth in weight, length, and head circumference: (1) a fetal-infant graph with lines of growth from 26 weeks of gestational age until one year of age after ""term'' has been reached: and (2) a similarly constructed graph for children ages one through ten years. The standards of growth were obtained from published data in which the subjects received optimal health care. The graphs allow comparisons of infants of varying gestational age with standards for that age. Normal and abnormal deviations in growth are easily identified. Some examples of common variations in physical growth are described.

Body Height↗

PubMed2025

Exploiting uniqueness: seed-chain-extend alignment on elastic founder graphs.

SUMMARY: Sequence-to-graph alignment is a central challenge of computational pangenomics. To overcome the theoretical hardness of the problem, state-of-the-art tools use seed-and-extend or seed-chain-extend heuristics to alignment. We implement a complete seed-chain-extend alignment workflow based on indexable elastic founder graphs (iEFGs) that support linear-time exact searches unlike general graphs. We show how to construct iEFGs, find high-quality seeds, chain, and extend them at the scale of a telomere-to-telomere assembled human chromosome. AVAILABILITY AND IMPLEMENTATION: Our sequence-to-graph alignment tool and the scripts to replicate our experiments are available in https://github.com/algbio/SRFAligner.

Software↗

PubMed2025

CSGL: chemical synthesis graph learning for molecule representation.

MOTIVATION: Molecule representation learning (MRL) translates molecules into a real vector space, serving as input to downstream tasks in biology, chemistry, and computer science. This article introduces a chemical synthesis graph learning (CSGL) framework, which enhances MRL by considering both the atomic structures of molecules and their roles in chemical reactions through a hierarchical graph representation. Specifically, molecules are first modeled based on their molecular graphs, which capture atomic-level structural information. They are then further refined using a chemical synthesis graph, where nodes represent reactant and product molecule sets, and edges encode chemical transformations between reactants and products (e.g. changes in molecular structures). CSGL optimizes molecular embeddings of reactant and product nodes in a fashion that ensures the embeddings conform to a chemical balance constraint. RESULTS: Experimental results show that our method CSGL achieves strong performance on a variety of tasks, including product prediction, reaction classification, and molecular property prediction. AVAILABILITY AND IMPLEMENTATION: https://github.com/li-2023/CSGL.

Machine Learning↗

PubMed2026

SpatialRNA: a Python package for easy application of Graph Neural Network models on single-molecule spatial transcriptomics dataset.

SUMMARY: Image-based spatial transcriptomics (iST) deliver gene expression measurements of RNA transcripts in tissue slices with single-molecule resolution and spatial context preserved. Modern Graph Neural Network (GNN) models are promising methods for capturing the complex molecular and cellular phenotypes in tissues at single-transcript and single-cell levels. A key application of GNNs is the detection of spatial domains or niches, that is, groups of molecules and/or cells that collaboratively work together to produce complex phenotypes. Due to the vast number of detected transcripts in (iST) dataset, applying GNNs on RNA molecule graphs is not trivial. We present a Python package, SpatialRNA, for easy (sub)graph generation from tissue samples and provide comprehensive tutorials for convenient and efficient application of Graph Neural Network models under the PyG framework. This highly scalable tool comprehensively segments tissue into spatial domains, aiding in biological interpretation of iST data and its underlying molecular microenvironments. AVAILABILITY AND IMPLEMENTATION: The SpatialRNA package is freely accessible from online repository https://github.com/ruqianl/spatialrna and can be installed via pip. Comprehensive tutorials, guidance on parameter selection, and complete workflows of case studies are available from the documentation website https://ruqianl.github.io/spatialrna_docs/, and uploaded on Zenodo with a DOI 10.5281/zenodo.17339575.

Neural Networks, Computer↗