SEARCH · PubMed Health

Results for “Dynamic 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.

At least 19 recordsLinked to original sources

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↗

PubMed2004

Win-stay, lose-shift in language learning from peers.

Traditional language learning theory explores an idealized interaction between a teacher and a learner. The teacher provides sentences from a language, while the learner has to infer the underlying grammar. Here, we study a new approach by considering a population of individuals that learn from each other. There is no designated teacher. We are inspired by the observation that children grow up to speak the language of their peers, not of their parents. Our goal is to characterize learning strategies that generate "linguistic coherence," which means that most individuals use the same language. We model the resulting learning dynamics as a random walk of a population on a graph. Each vertex represents a candidate language. We find that a simple strategy using a certain aspiration level with the principle of win-stay, lose-shift does extremely well: stay with your current language, if at least three others use that language; otherwise, shift to an adjacent language on the graph. This strategy guarantees linguistic coherence on all nearly regular graphs, in the relevant limit where the number of candidate languages is much greater than the population size. Moreover, for many graphs, it is sufficient to have an aspiration level demanding only two other individuals to use the same language.

Algorithms↗

PubMed1988

A graph-dynamic model of the power law of practice and the problem-solving fan-effect.

Numerous human learning phenomena have been observed and captured by individual laws, but no unified theory of learning has succeeded in accounting for these observations. A theory and model are proposed that account for two of these phenomena: the power law of practice and the problem-solving fan-effect. The power law of practice states that the speed of performance of a task will improve as a power of the number of times that the task is performed. The power law resulting from two sorts of problem-solving changes, addition of operators to the problem-space graph and alterations in the decision procedure used to decide which operator to apply at a particular state, is empirically demonstrated. The model provides an analytic account for both of these sources of the power law. The model also predicts a problem-solving fan-effect, slowdown during practice caused by an increase in the difficulty of making useful decisions between possible paths, which is also found empirically.

Decision Making↗

PubMed2004

Spread of two linked social norms on complex interaction networks.

In this paper, we study the spread of social norms, such as rules and customs that are components of human cultures. We consider the spread of two social norms, which are linked through individual behaviors. Spreading social norms depend not only on the social network structure, but also on the learning system. We consider four social network structures: (1) complete mixing, in which each individual interacts with the others at random, (2) lattice, in which each individual interacts with its neighbors with some probability and with the others at random, (3) power-law network, in which a few influential people have more social contacts than the others, and (4) random graph network, in which the number of contacts follows a Poisson distribution. Using the lattice model, we also investigate the effect of the small-world phenomenon on the dynamics of social norms. In our models, each individual learns a social norm by trial and error (individual learning) and also imitates the other's social norm (social learning). We investigate how social network structure and learning systems affect the spread of two linked social norms. Our main results are: (1) Social learning does not lead to coexistence of social norms. Individual learning produces coexistence, and the dynamics of coexistence depend on which social norms are learned individually. (2) Social norms spread fastest in the power-law network model, followed by the random graph model, the complete mixing model, the two-dimensional lattice model and the one-dimensional lattice. (3) We see a "small world effect" in the one-dimensional model, but not in two dimensions.

Computer Simulation↗

PubMed2006

Probabilistic fusion of stereo with color and contrast for bilayer segmentation.

This paper describes models and algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from color/contrast or from stereo alone is known to be error-prone. Here, color, contrast, and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, Layered Dynamic Programming (LDP), solves stereo in an extended six-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive color model that is learned on-the-fly and stereo disparities are obtained by dynamic programming. The second algorithm, Layered Graph Cut (LGC), does not directly solve stereo. Instead, the stereo match likelihood is marginalized over disparities to evaluate foreground and background hypotheses and then fused with a contrast-sensitive color model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar performance, substantially better than either stereo or color/ contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output.

Algorithms↗

PubMed2005

Dynamic algorithms for the shortest path routing problem: learning automata-based solutions.

This paper presents the first Learning Automaton-based solution to the dynamic single source shortest path problem. It involves finding the shortest path in a single-source stochastic graph topology where there are continuous probabilistic updates in the edge-weights. The algorithm is significantly more efficient than the existing solutions, and can be used to find the "statistical" shortest path tree in the "average" graph topology. It converges to this solution irrespective of whether there are new changes in edge-weights taking place or not. In such random settings, the proposed learning automata solution converges to the set of shortest paths. On the other hand, the existing algorithms will fail to exhibit such a behavior, and would recalculate the affected shortest paths after each weight-change. The important contribution of the proposed algorithm is that all the edges in a stochastic graph are not probed, and even if they are, they are not all probed equally often. Indeed, the algorithm attempts to almost always probe only those edges that will be included in the shortest path graph, while probing the other edges minimally. This increases the performance of the proposed algorithm. All the algorithms were tested in environments where edge-weights change stochastically, and where the graph topologies undergo multiple simultaneous edge-weight updates. Its superiority in terms of the average number of processed nodes, scanned edges and the time per update operation, when compared with the existing algorithms, was experimentally established. The algorithm can be applicable in domains ranging from ground transportation to aerospace, from civilian applications to military, from spatial database applications to telecommunications networking.

Algorithms↗

PubMed2026

Unveiling tumor heterogeneity by single cell RNA-sequencing: From basic considerations to clinical applications.

Tumor heterogeneity-encompassing diverse cellular phenotypes, genomic alterations, and microenvironmental contexts-is a principal barrier to effective cancer therapy. Single-cell RNA sequencing (scRNA-seq) has transformed our ability to resolve this complexity by capturing transcriptomes at single-cell resolution. Here, we review the technical foundations required for high-quality scRNA-seq studies. We then trace the evolution of scRNA-seq platforms from manual micromanipulation to high-throughput systems, and describe the computational pipelines that enable reliable data interpretation. The application of scRNA-seq is exemplarily shown in the context of lung cancer, where single-cell profiling has revealed (i) the clonal and sub-clonal architecture of tumors, (ii) extensive remodeling of the immune microenvironment, iii) key mechanisms underlying resistance to targeted agents and immune-checkpoint blockade, and (iv) the dynamics of neo-antigen-specific T-cell responses. Integrating machine-learning techniques-such as deep-learning classifiers and graph-based models-with single-cell transcriptomic data has markedly sped up biomarker discovery, produced more accurate risk-stratification scores, and enabled the generation of patient-specific therapeutic predictions. We surveyed the major trial registry ClinicalTrials.gov and identified ∼380 ongoing or completed studies that explicitly incorporate scRNA-seq as a correlative or pharmacodynamic endpoint. Overall, the analysis shows that scRNA-seq becomes an increasingly important component of modern trials, providing high-resolution cellular and molecular readouts that complement conventional imaging and bulk-omics endpoints. While key challenges remain, ranging from costs, scalability and need for rigorous validation before routine clinical deployment, ongoing technological advances continue to expand the potential of scRNA-seq as a cornerstone of precision medicine.

Humans↗

PubMed2026

Decoding spatiotemporal fibrotic and cellular immunosuppression of therapeutic T cells in live pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDA) is profoundly immunosuppressive. To help define this behavior, we present integrated experimental and computational frameworks to elucidate therapeutic T cell dynamics. Through the development of TME-CARTographer (TME-CART), a computational pipeline integrating high-dimensional data, graph theory, behavior analysis, and deep learning (DL), we present quantitative insights on 4D T cell-TME interactions in live PDA tumors. Mapping physical immunosuppression demonstrates that collagen fiber architectures direct migration while concomitantly limiting off-axis movement, creating immune exclusion zones. Expanding these findings, we establish that the collagen matrix harbors and spatially organizes immunosuppressive myeloid cells to serve as cooperative co-modulators of T cell behaviors, including migration, sampling, repulsion, and sequestration. Consistent with these findings, DL defines both linear and nonlinear collagen matrix and cellular neighborhood interactions as drivers of T cell behavior. The TME-CART DL framework also accurately predicts shifts in immunosuppression following depletion of myeloid cells. Overall, we identify synergistic barriers impeding anti-tumor T cell behaviors and present TME-CART as a discovery platform for interpreting complex 4D data to enhance the understanding and design of immunotherapies.

Journal Article↗

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↗

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↗

PubMed2025

An image-based protein-ligand binding representation learning framework via multi-level flexible dynamics trajectory pre-training.

MOTIVATION: Accurate prediction of protein-ligand binding (PLB) relationships plays a crucial role in drug discovery, which helps identify drugs that modulate the activity of specific targets. Traditional biological assays for measuring PLB relationships are time consuming and costly. In addition, models for predicting PLB relationships have been developed and widely used in drug discovery tasks. However, learning more accurate PLB representations is essential to meet the stringent standards required for drug discovery. RESULTS: We propose an image-based PLB representation learning framework, called ImagePLB, which equips ligand representation learner (LRL) and protein representation learner (PRL) to accept 3D multi-view ligand images and protein graphs as input, respectively, and learns rich interaction information between ligand and protein through a binding representation learner (BRL). Considering the scarcity of protein-ligand pairs, we further propose a multi-level next trajectory prediction (MLNTP) task to pre-train ImagePLB on the 4D flexible dynamics trajectory of 16 972 complexes, including ligand level, protein level, and complex level, to learn information related to trajectories. Besides, by introducing trajectory regularization (TR), we effectively alleviate the problem of high (even almost identical) feature similarity caused by adjacent trajectories. Compared with the current state-of-the-art methods, ImagePLB has achieved competitive improvements on PLB-related prediction tasks, including protein-ligand affinity and efficacy prediction tasks. This study opens the door to the image-based PLB learning paradigm. AVAILABILITY AND IMPLEMENTATION: All data and implementation details of code can be obtained from https://github.com/HongxinXiang/ImagePLB.

Ligands↗

PubMed2005

On the use of qualitative reasoning to simulate and identify metabolic pathways.

MOTIVATION: Perhaps the greatest challenge of modern biology is to develop accurate in silico models of cells. To do this we require computational formalisms for both simulation (how according to the model the state of the cell evolves over time) and identification (learning a model cell from observation of states). We propose the use of qualitative reasoning (QR) as a unified formalism for both tasks. The two most commonly used alternative methods of modelling biochemical pathways are ordinary differential equations (ODEs), and logical/graph-based (LG) models. RESULTS: The QR formalism we use is an abstraction of ODEs. It enables the behaviour of many ODEs, with different functional forms and parameters, to be captured in a single QR model. QR has the advantage over LG models of explicitly including dynamics. To simulate biochemical pathways we have developed 'enzyme' and 'metabolite' QR building blocks that fit together to form models. These models are finite, directly executable, easy to interpret and robust. To identify QR models we have developed heuristic chemoinformatics graph analysis and machine learning procedures. The graph analysis procedure is a series of constraints and heuristics that limit the number of ways metabolites can combine to form pathways. The machine learning procedure is generate-and-test inductive logic programming. We illustrate the use of QR for modelling and simulation using the example of glycolysis. AVAILABILITY: All data and programs used are available on request.

Algorithms↗

PubMed2026

GenOT: generative optimal transport enables spatiotemporal interpolation and generation in cross-platform spatial transcriptomics.

Spatial transcriptomics technologies have revolutionized the analysis of spatial gene expression, yet integrating spatial information and generating data across heterogeneous samples remain challenging. We present GenOT, a generative framework combining multi-scale graph self-supervised contrastive learning with optimal transport barycenter theory for efficient cross-slice and cross-platform spatiotemporal interpolation. The core innovation of GenOT lies in introducing an optimal transport barycenter-based interpolation algorithm, which mathematically models spatial distribution differences across heterogeneous samples to reconstruct spatiotemporal gene expression dynamics. Extensive evaluations demonstrate that GenOT consistently outperforms existing approaches in spatial domain identification, cross-platform interpolation, and developmental trajectory reconstruction.

Spatial Transcriptomics↗

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

CLUE: cluster-based retrieval of images by unsupervised learning.

In a typical content-based image retrieval (CBIR) system, target images (images in the database) are sorted by feature similarities with respect to the query. Similarities among target images are usually ignored. This paper introduces a new technique, cluster-based retrieval of images by unsupervised learning (CLUE), for improving user interaction with image retrieval systems by fully exploiting the similarity information. CLUE retrieves image clusters by applying a graph-theoretic clustering algorithm to a collection of images in the vicinity of the query. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. CLUE can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus, it may be embedded in many current CBIR systems, including relevance feedback systems. The performance of an experimental image retrieval system using CLUE is evaluated on a database of around 60,000 images from COREL. Empirical results demonstrate improved performance compared with a CBIR system using the same image similarity measure. In addition, results on images returned by Google's Image Search reveal the potential of applying CLUE to real-world image data and integrating CLUE as a part of the interface for keyword-based image retrieval systems.

Algorithms↗

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↗

PubMed1989

An approach to the teaching of host/parasite population modelling.

Computer-aided learning is considered to be useful in the teaching of host/parasite population modelling. The STELLA programme for the Apple Macintosh microcomputer allows dynamic models to be developed by drawing a diagram of the interactions and then defining the relationships between variables in terms of simple mathematics or as graphs. Our experience in using this programme for project-based teaching is described.

Animals↗

PubMed1996

New approaches in molecular structure prediction.

In the past years, much effort has been put on the development of new methodologies and algorithms for the prediction of protein secondary and tertiary structures from (sequence) data; this is reviewed in detail. New approaches for these predictions such as neural network methods, genetic algorithms, machine learning, and graph theoretical methods are discussed. Secondary structure prediction algorithms were improved mostly by considering families of related proteins; however, for the reliable tertiary structure modeling of proteins, knowledge-based techniques are still preferred. Methods and examples with more or less successful results are described. Also, programs and parameterizations for energy minimisations, molecular dynamics, and electrostatic interactions have been improved, especially with respect to their former limits of applicability. Other topics discussed in this review include the use of traditional and on-line databases, the docking problem and surface properties of biomolecules, packing of protein cores, de novo design and protein engineering, prediction of membrane protein structures, the verification and reliability of model structures, and progress made with currently available software and computer hardware. In summary, the prediction of the structure, function, and other properties of a protein is still possible only within limits, but these limits continue to be moved.

Chemical Phenomena↗