SEARCH · PubMed Health

Results for “adaptive graph learning”

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.

18 recordsLinked to original sources

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↗

PubMed2025

ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction.

Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy.

Humans↗

PubMed2026

ORBIT: Oncogenic Representation Learning via Bi-Prototype Contrastive Learning in Hyperbolic Space for cancer driver gene identification.

Accurate identification of cancer driver genes is crucial for precision oncology but remains challenging due to the complexity of integrating heterogeneous data and modeling dynamic biological systems. To address these limitations, we propose ORBIT (Oncogenic Representation Learning via Bi-Prototype Contrastive Learning in Hyperbolic Space). Our framework synergistically fuses multi-omics profiles with functional network data using a context-adaptive graph reweighting mechanism to capture cancer-specific dynamics. The model employs a bi-prototype contrastive learning strategy within hyperbolic space, which aligns gene representations around distinct driver and non-driver semantic anchors while preserving the intrinsic hierarchy of biological networks. Comprehensive evaluations demonstrate that ORBIT achieves highly competitive stability in pan-cancer analysis while consistently outperforming state-of-the-art methods in cancer-specific predictions. Furthermore, functional enrichment analysis confirms that the model effectively segregates core cancer pathways, and drug sensitivity profiling validates the clinical relevance of the identified drivers. By integrating hyperbolic geometry with context-adaptive learning, ORBIT offers a robust and interpretable paradigm for precision medicine. The source codes and datasets are publicly accessible at https://github.com/spcho-dev/ORBIT.

Humans↗

PubMed2026

NeuroOmics-Net: An interpretable multimodal deep learning framework for Alzheimer's disease diagnosis and progression prediction using neuroimaging, EEG, and genomic data.

Accurate diagnosis and progression prediction of Alzheimer's disease (AD) remain challenging due to the heterogeneous nature of the disease, which involves structural brain degeneration, electrophysiological dysfunction, and molecular dysregulation. Most existing deep learning approaches rely on a single modality or limited multimodal combinations, thereby failing to capture the complex cross-domain interactions underlying AD progression. Furthermore, the scarcity of large-scale datasets containing synchronized neuroimaging, electrophysiological, and genomic measurements restricts the development of comprehensive multimodal diagnostic systems. To address these challenges, this study proposes NeuroOmics-Net, a multimodal deep learning framework for Alzheimer's disease analysis that integrates structural magnetic resonance imaging (sMRI), electroencephalography (EEG), and gene expression data. The proposed framework combines a Hierarchical Multi-View Encoder (HME) for modality-specific feature extraction, a Cross-Omics Attention Fusion (CAF) module for adaptive integration of complementary biomarkers, and a Disease Progression Graph Learning (DPGL) module for modeling progression-related relationships across biological domains. To facilitate cross-modal integration from independent cohorts, Regularized Canonical Correlation Analysis (RCCA) is employed to align heterogeneous feature representations within a shared latent space. Experiments were conducted using publicly available datasets from ADNI, PhysioNet, and GEO repositories comprising 1120 diagnosis-aligned samples. The proposed framework achieved 94.3% classification accuracy and an AUC of 0.975 for distinguishing normal controls (NC), mild cognitive impairment (MCI), and Alzheimer's disease subjects, while attaining 93.7% accuracy for predicting conversion from stable mild cognitive impairment (sMCI) to progressive mild cognitive impairment (pMCI). However, a fairness sensitivity analysis using stratified demographic reweighting revealed accuracy ranging from 90.8% (low-education, high-comorbidity proxy subgroup) to 96.1% (low-risk, high-reserve proxy subgroup), a demographic parity gap of 5.3 percentage points, indicating that overall accuracy reflects a performance ceiling in a relatively homogeneous research cohort rather than a realistic estimate for demographically diverse clinical populations. Comparative evaluations demonstrated consistent improvements over state-of-the-art unimodal and multimodal deep learning models. Interpretability analysis further identified clinically relevant biomarkers, including hippocampal and entorhinal atrophy, theta-alpha EEG alterations, and APOE-associated molecular pathways. Because sMRI, EEG, and gene expression data were sourced from separate, unpaired cohorts with no subjects possessing all three synchronized measurements, all reported cross-modal associations reflect population-level statistical correspondence across diagnosis-matched groups rather than within-subject physiological coupling; no claim of intra-individual causal cross-modal interaction is made. These findings demonstrate that NeuroOmics-Net provides an effective computer-aided framework for multimodal biomedical data processing and Alzheimer's disease analysis. By integrating neuroimaging, electrophysiological, and genomic information, the proposed approach enables accurate diagnosis, progression prediction, and biologically interpretable decision support for clinical and translational applications.

Humans↗

PubMed2005

Self-organizing maps for learning the edit costs in graph matching.

Although graph matching and graph edit distance computation have become areas of intensive research recently, the automatic inference of the cost of edit operations has remained an open problem. In the present paper, we address the issue of learning graph edit distance cost functions for numerically labeled graphs from a corpus of sample graphs. We propose a system of self-organizing maps (SOMs) that represent the distance measuring spaces of node and edge labels. Our learning process is based on the concept of self-organization. It adapts the edit costs in such a way that the similarity of graphs from the same class is increased, whereas the similarity of graphs from different classes decreases. The learning procedure is demonstrated on two different applications involving line drawing graphs and graphs representing diatoms, respectively.

Algorithms↗

PubMed2006

Teaching skeletal muscle adaptations to aerobic exercise using an American Physiological Society classic paper by Dr. Philip Gollnick and colleagues.

The use of primary research in the classroom enhances the critical thinking abilities of students. The present article describes a strategy for using the American Physiological Society classic paper "Enzyme activity and fiber composition in skeletal muscle of untrained and trained men" by Dr. Philip D. Gollnick and colleagues to enhance the students' ability to understand research, increase their knowledge of the adaptations to exercise, and learn computer skills in data analysis and presentation. By having students read, study, prepare graphs, and discuss the data from a classic paper, they gain an improved understanding of the factors that influence aerobic exercise ability. This study is especially useful for illuminating the exercise-specific differences in bioenergetic enzymes, muscle fiber type, and fitness characteristics that exist between untrained and trained individuals.

Adaptation, Physiological↗

PubMedDate not supplied

Automatic generation of complementary descriptors with molecular graph networks.

We describe a method for the automatic generation of weakly correlated descriptors for molecular data sets. The method can be regarded as a statistical learning procedure that turns the molecular graph, representing the 2D formula of the compound, into an adaptive whole molecule composite descriptor. By translating the molecular graph structure into a dynamical system, the algorithm can compute an output value that is highly sensitive to the molecular topology. This system can be trained by gradient descent techniques, which rely on the efficient calculation of the gradient by back-propagation. We present computational experiments concerning the classification of the Developmental Therapeutics Program AIDS antiviral screen data set on which the performance of the method compares with that of approaches based on substructure comparison.

Algorithms↗

PubMed2025

PLNMFG: Pseudo-label guided non-negative matrix factorization model with graph constraint for single-cell multi-omics data clustering.

The development of single-cell multi-omics sequencing technologies has enabled the simultaneous analysis of multi-omics data within the same cell. Accurate clustering of these cells is crucial for downstream analyses of complex biological functions. Despite significant advances in multi-omics integration approaches, current methodologies exhibit two major limitations. First, they inadequately incorporate prior biological knowledge from various omic layers. Second, these methods often conduct independent dimensionality reduction on individual omic datasets, thereby failing to capture the intrinsic complementary information and potentially overlooking crucial cross-platform interactions. Motivated by these, this study investigates a non-negative matrix factorization model called PLNMFG, which integrates the unified latent representation learning that retains the features between and within omics and the cluster structure learning that retains the intrinsic structure of the data into one joint framework. Specially, PLNMFG performs adaptive imputation to handle dropout events and uses prior pseudo-labels as constraints during the process of collective non-negative matrix factorization, as a result, a more robust latent representation that preserves the double similarity information is obtained. Graph Laplacian constraint is applied during clustering which further preserves structure characteristic of multi-omics data. In addition, the weight of each omic is adaptively learned based on the omic contribution. A series of experiments on 8 benchmark datasets show that our model performs well in terms of clustering accuracy and computational efficiency.

Single-Cell Analysis↗

PubMed1996

Radiographic skills learning: procedure simulation using adaptive hypermedia.

The design and development of a simulation tool supporting learning of radiographic skills is reported. This tool has by textual, graphical and iconic resources, organized according to a building-block, adaptive hypermedia approach, which is described and supported by an image base of radiographs. It offers interactive user-controlled simulation of radiographic imaging procedures. The development is based on a commercially available environment (Toolbook 3.0, Asymetrix Corporation). The core of the system is an attributed precedence (priority) graph, which represents a task outline (concept and resources structure), which is dynamically adjusted to selected procedures. The user interface imitates a conventional radiography system, i.e. operating console, tube, table, patient and cassette. System parameters, such as patient positioning, focus-to-patient distance, magnification, field dimensions, tube voltage and mAs are under user control. Their effects on image quality are presented, by means of an image base acquired under controlled exposure conditions. Innovative use of hypermedia, computer based learning and simulation principles and technology in the development of this tool resulted in an enhanced interactive environment providing radiographic parameter control and visualization of parameter effects on image quality.

Computer Simulation↗

PubMed2005

Comparison of Colvard pupillometer and infrared digital photography for measurement of the dark-adapted pupil diameter.

PURPOSE: To investigate the accuracy of pupil diameter measurement using the Colvard pupillometer and to determine the learning curve for inexperienced examiners. SETTING: Texas Tech University Health Sciences Center, Lubbock, Texas, USA. METHODS: In this population study, subjects with normal pupillary behavior were tested by 1 of 2 investigators (examiner A, examiner B). After 5 minutes of dark adaptation at 1 lux, digital infrared pupil photography of the right eye was performed, followed by measurement of the horizontal pupil diameter and vertical pupil diameter with the Colvard pupillometer. The photographs were digitally analyzed to determine the horizontal and vertical pupil diameters. During phase I of the study, examiners were masked to the results of infrared pupil photography; during phase II, they reviewed the infrared pupil photography results after each testing session. Bland-Altman plots were created to detect measurement bias; results were graphed by subject test sequence to assess learning. A test difference of less than +/-0.5 mm was considered clinically acceptable. RESULTS: Fifty-nine subjects were tested in phase I, of whom 39 had adequate infrared pupil photography for analysis; 40 were tested in phase II, of whom 34 were included. The mean age of the analyzed subjects was 27 years (range 18 to 44 years). For all subjects, the infrared pupil photography median horizontal pupil diameter was 7.09 mm +/- 0.75 (SD) (range 5.44 to 8.79 mm); the median vertical pupil diameter was 7.22 +/- 0.79 mm (range 5.45 to 9.10 mm). Examiner A initially had a negative bias (Colvard pupillometer value less than infrared pupil photography value) for both horizontal and vertical pupil diameter measurements, which resolved during phase I after 23 subjects were tested; 18 of the final 19 subjects tested (11 phase I, 8 phase II) showed a test difference of less than 0.5 mm for all readings. The pupil diameter did not affect the bias. Examiner B had a strong positive bias that persisted throughout the study. Testing 26 subjects in 5 sessions during phase II did not improve the accuracy. During the final testing session, 3 of 8 subjects had a test difference of 0.5 mm or more in at least 1 dimension. The pupil diameter did not affect the bias. CONCLUSION: The Colvard pupillometer is susceptible to user errors causing unidirectional bias and seems to have a steep and variable learning curve.

Adolescent↗

PubMed1994

Mixed Bayesian networks: a mixture of Gaussian distributions.

Mixed Bayesian networks are probabilistic models associated with a graphical representation, where the graph is directed and the random variables are discrete or continuous. We propose a comprehensive method for estimating the density functions of continuous variables, using a graph structure and a set of samples. The principle of the method is to learn the shape of densities from a sample of continuous variables. The densities are approximated by a mixture of Gaussian distributions. The estimation algorithm is a stochastic version of the Expectation Maximization algorithm (Stochastic EM algorithm). The inference algorithm corresponding to our model is a variant of junction three method, adapted to our specific case. The approach is illustrated by a simulated example from the domain of pharmacokinetics. Tests show that the true distributions seem sufficiently fitted for practical application.

Algorithms↗

PubMed2006

Discovering functional gene expression patterns in the metabolic network of Escherichia coli with wavelets transforms.

BACKGROUND: Microarray technology produces gene expression data on a genomic scale for an endless variety of organisms and conditions. However, this vast amount of information needs to be extracted in a reasonable way and funneled into manageable and functionally meaningful patterns. Genes may be reasonably combined using knowledge about their interaction behaviour. On a proteomic level, biochemical research has elucidated an increasingly complete image of the metabolic architecture, especially for less complex organisms like the well studied bacterium Escherichia coli. RESULTS: We sought to discover central components of the metabolic network, regulated by the expression of associated genes under changing conditions. We mapped gene expression data from E. coli under aerobic and anaerobic conditions onto the enzymatic reaction nodes of its metabolic network. An adjacency matrix of the metabolites was created from this graph. A consecutive ones clustering method was used to obtain network clusters in the matrix. The wavelet method was applied on the adjacency matrices of these clusters to collect features for the classifier. With a feature extraction method the most discriminating features were selected. We yielded network sub-graphs from these top ranking features representing formate fermentation, in good agreement with the anaerobic response of hetero-fermentative bacteria. Furthermore, we found a switch in the starting point for NAD biosynthesis, and an adaptation of the l-aspartate metabolism, in accordance with its higher abundance under anaerobic conditions. CONCLUSION: We developed and tested a novel method, based on a combination of rationally chosen machine learning methods, to analyse gene expression data on the basis of interaction data, using a metabolic network of enzymes. As a case study, we applied our method to E. coli under oxygen deprived conditions and extracted physiologically relevant patterns that represent an adaptation of the cells to changing environmental conditions. In general, our concept may be transferred to network analyses on biological interaction data, when data for two comparable states of the associated nodes are made available.

Algorithms↗

PubMed1993

Integrated cardiovascular physiology: a laboratory exercise.

Examining the hemodynamic responses to exercise provides a unique opportunity to analyze and integrate cardiovascular physiology because more is learned about how a system operates when it is forced to perform than when it is idle. We designed a laboratory exercise that examines the cardiovascular responses to exercise in a sedentary individual, an athlete, an individual with quadriplegia, and an individual with heart transplantation. The special populations were chosen because of their unique limitations and adaptations, which directly influence cardiovascular function. Basic anatomic and physiological data about the special populations are provided, and the students are challenged to analyze and assimilate information from figures, answer questions, make calculations, and plot graphs. The answers to the questions are provided in the APPENDIX. This laboratory exercise should be attempted in a group to foster discussions and interactions. The laboratory does not require any equipment or software. This exercise should be attempted after the cardiovascular section of the physiology course so that the students can integrate and apply the information presented during the course.

Adult↗

PubMed1995

[Glossary of terms used by radiologists in image processing].

We give the definition of 166 words used in image processing. Adaptivity, aliazing, analog-digital converter, analysis, approximation, arc, artifact, artificial intelligence, attribute, autocorrelation, bandwidth, boundary, brightness, calibration, class, classification, classify, centre, cluster, coding, color, compression, contrast, connectivity, convolution, correlation, data base, decision, decomposition, deconvolution, deduction, descriptor, detection, digitization, dilation, discontinuity, discretization, discrimination, disparity, display, distance, distorsion, distribution dynamic, edge, energy, enhancement, entropy, erosion, estimation, event, extrapolation, feature, file, filter, filter floaters, fitting, Fourier transform, frequency, fusion, fuzzy, Gaussian, gradient, graph, gray level, group, growing, histogram, Hough transform, Houndsfield, image, impulse response, inertia, intensity, interpolation, interpretation, invariance, isotropy, iterative, JPEG, knowledge base, label, laplacian, learning, least squares, likelihood, matching, Markov field, mask, matching, mathematical morphology, merge (to), MIP, median, minimization, model, moiré, moment, MPEG, neural network, neuron, node, noise, norm, normal, operator, optical system, optimization, orthogonal, parametric, pattern recognition, periodicity, photometry, pixel, polygon, polynomial, prediction, pulsation, pyramidal, quantization, raster, reconstruction, recursive, region, rendering, representation space, resolution, restoration, robustness, ROC, thinning, transform, sampling, saturation, scene analysis, segmentation, separable function, sequential, smoothing, spline, split (to), shape, threshold, tree, signal, speckle, spectrum, spline, stationarity, statistical, stochastic, structuring element, support, syntaxic, synthesis, texture, truncation, variance, vision, voxel, windowing.

Diagnostic Imaging↗

PubMed1994

An educational tool for understanding the cardiopulmonary changes associated with aging.

Normal aging is associated with cardiac, vascular, and pulmonary adaptations that significantly affect the individual's ability to maintain homeostasis. To understand the changes associated with aging, we developed a laboratory exercise that compares and contrasts the cardiopulmonary responses to exercise in a young and an older individual. We also developed this interactive tool because it is our experience that learning is better facilitated when students are encouraged, and required, to become an active and integral part of the educational process. This exercise provides a unique opportunity to analyze, integrate, and interpret the changes associated with aging because more is learned about how a system operates when it is forced to perform than when it is idle. In this laboratory exercise, basic anatomical and physiological data about aging are provided. Subsequently, figures are presented that illustrate the responses of specific cardiopulmonary variables during exercise (e.g., heart rate, cardiac output, blood pressure), and the students are challenged to analyze and assimilate information from the figures, answer questions, make calculations, and plot graphs. The laboratory does not require equipment or software, only rules and pencils. Questions, and answers to them, are provided in the appendix. The emphasis is on the application of basic science principles, interpretation of pictorial or tabular material, and problem solving skills. In addition, an evaluation instrument was developed to assess the effectiveness of this instructional tool in an academic setting. Specifically, the evaluation instrument addressed four major components, including aims and objectives, content of materials, components and organization, and summary and recommendations.

Adult↗

PubMedDate not supplied

Immune system learning and memory quantified by graphical analysis of B-lymphocyte phylogenetic trees.

The immune system learns from its encounters with pathogens and memorizes its experiences. One of the mechanisms it uses for this purpose is the intra-individual evolution of antigen receptors on B lymphocytes, achieved via hypermutation and selection of antigen receptor variable region genes during an immune response. We have developed a novel method for analyzing the graphical properties of phylogenetic trees of receptor genes which have been mutated and selected during an immune response. In the study presented here, we address the artifacts introduced by experimental methods of cell collection for DNA analysis, the meaning of each parameter measured on the tree graphs, and the differences between the dynamics of the humoral immune response in different lymphoid tissues.

Adaptation, Physiological↗

PubMed2000

A signal-flow-graph approach to on-line gradient calculation.

A large class of nonlinear dynamic adaptive systems such as dynamic recurrent neural networks can be effectively represented by signal flow graphs (SFGs). By this method, complex systems are described as a general connection of many simple components, each of them implementing a simple one-input, one-output transformation, as in an electrical circuit. Even if graph representations are popular in the neural network community, they are often used for qualitative description rather than for rigorous representation and computational purposes. In this article, a method for both on-line and batch-backward gradient computation of a system output or cost function with respect to system parameters is derived by the SFG representation theory and its known properties. The system can be any causal, in general nonlinear and time-variant, dynamic system represented by an SFG, in particular any feedforward, time-delay, or recurrent neural network. In this work, we use discrete-time notation, but the same theory holds for the continuous-time case. The gradient is obtained in a straightforward way by the analysis of two SFGs, the original one and its adjoint (obtained from the first by simple transformations), without the complex chain rule expansions of derivatives usually employed. This method can be used for sensitivity analysis and for learning both off-line and on-line. On-line learning is particularly important since it is required by many real applications, such as digital signal processing, system identification and control, channel equalization, and predistortion.

Algorithms↗

PubMed2003

Coastal seas as a context for science teaching: a lesson from Chesapeake Bay.

Lessons that employ authentic environmental data can enhance the ability of students to understand fundamental science concepts. This differs from traditional "environmental education" in that school curricula need not set aside time for educators to teach only environmental topics. Rather, the "environment" is used to advance student learning in science and technology. The success of this approach depends on programs that encourage scientists to communicate more effectively with teachers at all education levels. The expanding diversity of research and monitoring activities on the world's marine waters constitutes an outstanding potential education resource. Many of these projects involve remote sensing with sophisticated instrumentation and employ Internet technology to compile measurements, interpret data using graphs and satellite imagery, and share the results among scientific colleagues and the general public alike. Unfortunately, these resources, which constitute a much shortened path between research findings and textbook presentation, are seldom interpreted for use by K-12 educators. We have developed an example that uses the Chesapeake Bay as a paradigm to demonstrate how such interpretation can assist educators in teaching important principles in physical oceanography and marine ecology. We present this example using PowerPoint to conduct a virtual tour of selected Internet sources. Our example begins with the conceptual "salt wedge" circulation model of Chesapeake Bay as a partially mixed estuary. Teachers have the opportunity to explore this model using salinity, temperature, and dissolved oxygen data taken from a research vessel platform during summer professional development programs. This source of authentic data, originally obtained by teachers themselves, clearly demonstrates the presence of a picnocline and deep-water anoxia. Our lesson plan proceeds to interpret these data using additional Internet-based resources at increasing scales of time and space. The "salt wedge," picnocline, and anoxia are examined using graphics derived from data taken by researchers using "ScanFish," a towed instrument that samples temperature, salinity, and dissolved oxygen at a resolution of only a few meters vertically and horizontally. The seasonal dynamics of these parameters at a given location are interpreted using biweekly monitoring data obtained as part of the state-federal Chesapeake Bay Program. The influence of annual variations in freshwater input is examined using stream flow data from US. Geological Survey gauging stations. Satellite remote sensing images from the TOPEX/Poseidon project are used to show how El Niño and La Niña events in the mid-Pacific affect the Chesapeake Bay system via rainfall on its watershed. Finally, the life cycle of the blue crab (Callinectes sapidus) is presented to show how an estuarine organism has adapted to this truly unique and dynamic coastal environment.

Animals↗