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.

28 records · Page 2Linked to original sources

PubMed2026

SurvGRN: a multi-feature fusion framework for bladder cancer survival prediction.

Bladder cancer survival outcomes exhibit significant heterogeneity, influenced by multifaceted factors. While digital pathology-based survival models leveraging artificial intelligence show promise, they often overlook complementary data sources. Conversely, imaging lacks cellular detail, and genomics/proteomics entail complexity and cost. To integrate multidimensional data for enhanced survival prediction, we propose SurvGRN, a multi-feature fusion framework. SurvGRN synergistically combines clinical variables, transcriptomics, and digital pathology slides using a gated residual network architecture. Pathological features are extracted via multiple instance learning, while clinical and transcriptomic data are processed as static inputs. These features are dynamically fused using a long short-term memory (LSTM) network for comprehensive survival risk assessment. Evaluated on 400 bladder cancer patients, SurvGRN significantly outperformed existing methods: improving the C-index by 12.6% over DeepMISL; 20.6% and 7.1% over graph-based models (DeepGraphConv and Patch-GCN); and 5.4% and 4.0% over attention-based approaches (Surformer and HVTSurv). Ablation studies confirmed the contributions of pathology features (extracted via ResNet-50 pre-trained on bladder tissue), clinical/transcriptomic data, and the LSTM fusion. SurvGRN also enabled significant stratification of patients into distinct risk cohorts. This work demonstrates that holistic integration of multi-source data through tailored fusion architectures substantially improves bladder cancer survival prediction.

bladder cancer↗

PubMed2026

Decoding the spatiotemporal patterns of food spoilage microbial communities: Integrating multi-omics and artificial intelligence to enable precision preservation.

In the global food supply chain, food wastage caused by spoilage has resulted in significant economic losses, food shortages, and environmental pressure. This process is fundamentally driven by the spatiotemporal dynamics of microbial communities. However, traditional research methods struggle to elucidate the complex mechanisms of spatial heterogeneity, interspecies interactions, and functional succession. This limits the development of effective preservation strategies. This review systematically reviews the cutting-edge progress of integrating multi-omics technologies and artificial intelligence (AI) to study food spoilage microbial communities, breaking through this bottleneck. We propose an intelligent theoretical framework that could potentially analyze microbial metabolic activities and predict dynamic shelf life if implemented. The conceptual framework integrates multidimensional data, including spatial metabolomics, temporal metatranscriptomics, single-cell transcriptomics, and longitudinal metagenomics. It can also be combined with AI models, such as graph neural networks. The article elaborates on the principles and applications of spatio-temporal monitoring technologies, such as nano secondary ion mass spectrometry, hyperspectral imaging, and the Internet of Things sensing. Through illustrative cases of typical perishable foods, it also explores how such a multi-omics - AI system might be applied to spoilage warning and precise intervention. Additionally, the article addresses the current challenges in data coverage, model generalization, and federated learning implementation. Then the research further explores emerging areas such as engineered probiotics, edge AI, and microfluidic sensing. These areas are targeted at transforming food preservation from an empirical control approach to a data-driven, precise regulatory framework. This transformation provides theoretical support and technical approaches for developing a smart, sustainable food preservation system.

Multiomics↗

PubMed2000

Animat navigation using a cognitive graph.

This article describes a computational model of the hippocampus that makes it possible for a simulated rat to navigate in a continuous environment containing obstacles. This model views the hippocampus as a "cognitive graph", that is, a hetero-associative network that learns temporal sequences of visited places and stores a topological representation of the environment. Calling upon place cells, head direction cells, and "goal cells", it suggests a biologically plausible way of exploiting such a spatial representation for navigation that does not require complicated graph-search algorithms. Moreover, it permits "latent learning" during exploration, that is, the building of a spatial representation without the need of any reinforcement. When the rat occasionally discovers some rewarding place it may wish to rejoin subsequently, it simply records within its cognitive graph, through a series of goal and sub-goal cells, the direction in which to move from any given start place. Accordingly, the model implements a simple "place-recognition-triggered response" navigation strategy. Two implementations of place cell management are studied in parallel. The first one associates place cells with place fields that are given a priori and that are uniformly distributed in the environment. The second one dynamically recruits place cells as exploration proceeds and adjusts the density of such cells to the local complexity of the environment. Both implementations lead to identical results. The article ends with a few predictions about results to be expected in experiments involving simultaneous recordings of multiple cells in the rat hippocampus.

Animals↗

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↗

PubMed2026

Accurately Deciphering Tissue Heterogeneity From Spatial Multi-Modal and Multi-Omics With STransformer.

Advances in spatially resolved technologies enable the simultaneous acquisition of diverse data modalities within a tissue slice while preserving critical spatial context, which presents unprecedented opportunities to decipher intricate tissue heterogeneity. However, existing computational approaches lack the intrinsic flexibility to universally process both spatial multi-modal and multi-omics data. Here, we introduce STransformer, a unified deep learning framework designed to seamlessly accommodate a comprehensive landscape of spatial data. By simultaneously capturing short-range cellular interactions and tissue-wide semantic patterns, it extracts robust representations to accurately dissect complex tissue heterogeneity. Systematic evaluations across diverse species, tissue types, and data modalities highlight its profound versatility. For spatial multi-modal data, STransformer delineates intricate anatomical structures in the human cortex, uncovers pathological mechanisms in Alzheimer's disease, and characterizes dynamic spatiotemporal developmental trajectories during chicken cardiogenesis. Scaling to spatial multi-omics data, STransformer synergizes spatial transcriptomic and proteomic profiles to decipher intricate immune microenvironments within the human tonsil, and jointly analyzes spatial epigenomic and transcriptomic data to infer regulatory mechanisms in the mouse embryonic brain. Consequently, STransformer serves as a highly versatile and robust analytical framework for advancing our understanding of tissue heterogeneity and disease pathogenesis.

Multiomics↗

PubMed2026

Decoding TnsC Filament Assembly in CRISPR-Associated Transposons Using Interpretable Deep Learning and Molecular Simulations.

CRISPR-associated transposons (CASTs) enable programmable DNA integration, yet how the TnsC regulator forms processive filaments on DNA to coordinate RNA-guided transposition in type V-K CAST systems remains unknown. Here, we integrate large-scale molecular simulations, interpretable deep learning using graph attention networks (GATs), and causal inference analyses to define the molecular determinants of TnsC filament nucleation and elongation. We show that TnsC nucleates by inducing localized DNA deformation that propagates along extended filaments, with Granger causality revealing that TnsC motions precede and predict DNA deformation. Interpretable GAT models demonstrate that elongation is determined during early recognition between incoming and DNA-bound subunits, followed by structural reorganization that regenerates the recruitment interface and enables processive assembly. These results elucidate the molecular mechanism of processive TnsC filament assembly and explain why isolated TnsC filaments preferentially elongate in the 5' → 3' direction, while accessory transposition factors can reshape the interaction landscape and alter filament growth polarity. Together, these findings advance our understanding of CAST function and inform the engineering of programmable DNA integration platforms. Beyond CAST systems, this work introduces an interpretable GAT approach as a general and transferable deep learning strategy for uncovering molecular mechanisms in biological systems, while demonstrating the power of causal inference for dissecting directional relationships in molecular dynamics.

Deep Learning↗

PubMed2006

Automated semantic analysis of changes in image sequences of neurons in culture.

Quantitative studies of dynamic behaviors of live neurons are currently limited by the slowness, subjectivity, and tedium of manual analysis of changes in time-lapse image sequences. Challenges to automation include the complexity of the changes of interest, the presence of obfuscating and uninteresting changes due to illumination variations and other imaging artifacts, and the sheer volume of recorded data. This paper describes a highly automated approach that not only detects the interesting changes selectively, but also generates quantitative analyses at multiple levels of detail. Detailed quantitative neuronal morphometry is generated for each frame. Frame-to-frame neuronal changes are measured and labeled as growth, shrinkage, merging, or splitting, as would be done by a human expert. Finally, events unfolding over longer durations, such as apoptosis and axonal specification, are automatically inferred from the short-term changes. The proposed method is based on a Bayesian model selection criterion that leverages a set of short-term neurite change models and takes into account additional evidence provided by an illumination-insensitive change mask. An automated neuron tracing algorithm is used to identify the objects of interest in each frame. A novel curve distance measure and weighted bipartite graph matching are used to compare and associate neurites in successive frames. A separate set of multi-image change models drives the identification of longer term events. The method achieved frame-to-frame change labeling accuracies ranging from 85% to 100% when tested on 8 representative recordings performed under varied imaging and culturing conditions, and successfully detected all higher order events of interest. Two sequences were used for training the models and tuning their parameters; the learned parameter settings can be applied to hundreds of similar image sequences, provided imaging and culturing conditions are similar to the training set. The proposed approach is a substantial innovation over manual annotation and change analysis, accomplishing in minutes what it would take an expert hours to complete.

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↗

PubMed2002

The three-stage concept to optimize the results of microsurgical reanimation of the paralyzed face.

From the authors three-dimensional video analyses they had to learn that the advantages of a one-stage procedure is outweighed by far by the disadvantages. A three-stage concept to a one-stage procedure was preferred for the following reasons: 1. Safety of having a cross-face nerve graft to cover the distance from the healthy facial nerve to the nerve of the muscle transplant without problems and without the danger of tension on the nerve suture line because of shortage of the muscle nerve. 2. Independence of anatomical variations like a very proximal muscle hilus in the latissimus dorsi muscle e.g., resulting in a too short muscle nerve. 3. Only face-lift incisions are necessary without the need of an additional incision in the nasolabial fold while using a cross-face nerve graft. 4. Freedom of positioning the muscle graft on the paralyzed side with free choice of the position of the transplant hilus. 5. The superficial temporal vessels can be used for microvascular anastomoses. 6. Prevention of a scar in the submandibular region with its tendency of hypertrophy, especially if it is connected to the preauricular incision. Different functional territories of one muscle transplant for eye closure and for smile is only possible in combination with two cross-face nerve grafts. Further on the three-dimensional video analysis showed clearly that Final surgical corrections for improvement of the static and dynamic symmetry should be performed. when the muscle transplant or the transposed muscle have gained their final functional result, which is often not before one or one and a half year after muscle transplantation. Therefore a three-stage concept is needed for the majority of patients. Detailed analyses of the movements in the different regions and the comparison of both sides clarify preoperatively the indication for the operative techniques to be used, and describe exactly the improvement of the overall result. It is not only possible to show, eg, the better positioning of the alar of the nose by a nasolabial dermal suspension plasty on the paralyzed side in millimeter, but also the influence on the relation of all the different points in the face (Fig. 5). The comparison of the right and the left side gives exact data on the symmetry of the face on rest and during the different movements. Of course, also qualities of facial reanimation like prevention of mass movements or synkinesias are detected in the three-dimensional graphs of all the points at the same time or in the repeated reviews of the original movement in the original video sequence. In conclusion, three-dimensional video analysis of facial movements became an important tool for online planning of operative procedures for the individual patient, and an excellent tool for comparative studies of different operative concepts and alternative operative techniques within a standardized registry of one center treating facial palsy or within international multicenter studies.

Adult↗