SEARCH · PubMed Health

Results for “convolutional neural network”

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.

87 records · Page 5Linked to original sources

PubMed2001

Principles underlying mammalian neocortical scaling.

The neocortex undergoes a complex transformation from mouse to whale. Whereas synapse density remains the same, neuron density decreases as a function of gray matter volume to the power of around -1/3, total convoluted surface area increases as a function of gray matter volume to the power of around 8/9, and white matter volume disproportionately increases as a function of gray matter volume to the power of around 4/3. These phylogenetic scaling relationships (including others such as neuron number, neocortex thickness, soma radius, and number of cortical areas) are clues to understanding the principles driving neocortex organization, but there is currently no theory that can explain why these neocortical quantities scale as they do. Here I present a two-part model that explains these neocortical allometric scaling laws. The first part of the model is a special case of the physico-mathematical model recently put forward to explain the quarter power scaling laws in biology. It states that the neocortex is a space-filling neural network through which materials are efficiently transported, and that synapse sizes do not vary as a function of gray matter volume. The second part of the model states that the neocortex is economically organized into functionally specialized areas whose extent of area-interconnectedness does not vary as a function of gray matter volume. The model predicts, among other things, that the number of areas and the soma radius increase as a function of gray matter volume to the power of 1/3 and 1/9, respectively, and empirical support is demonstrated for each. Also, the scaling relationships imply that, although the percentage of the total number of neurons to which a neuron connects falls as a function of gray matter volume with exponent -1/3, the network diameter of the neocortex is invariant at around two. Finally, I discuss how a similar approach may have promise in explaining the scaling relationships for the brain and other organs as a function of body mass.

Animals↗

PubMed2005

Uncertainty of data, fuzzy membership functions, and multilayer perceptrons.

Probability that a crisp logical rule applied to imprecise input data is true may be computed using fuzzy membership function (MF). All reasonable assumptions about input uncertainty distributions lead to MFs of sigmoidal shape. Convolution of several inputs with uniform uncertainty leads to bell-shaped Gaussian-like uncertainty functions. Relations between input uncertainties and fuzzy rules are systematically explored and several new types of MFs discovered. Multilayered perceptron (MLP) networks are shown to be a particular implementation of hierarchical sets of fuzzy threshold logic rules based on sigmoidal MFs. They are equivalent to crisp logical networks applied to input data with uncertainty. Leaving fuzziness on the input side makes the networks or the rule systems easier to understand. Practical applications of these ideas are presented for analysis of questionnaire data and gene expression data.

Algorithms↗

PubMed1975

Dispersion along fiber tracts and in the coupling between tracts and a cortical network.

Dispersion in a neuronal coritcal network was modeled using CSMP, a Continuous Systems Modeling Program. The signal dispersion over pathways was simulated by use of a serial product approximating the convolution integral. The program was written in a sufficiently general format to be applied to a variety of biological signals. Calculated signals from a fiber tract and activation of a cortical network were compared with experimental data from cats. The network consists of excitatory cells in a forward limb which send collaterals to interneurons that, once excited, feed back to inhibit the excitatory cells. The model was consistent with data from neuronal assemblies in the prepyriform cortex and fibers in the lateral olfactory tract.

Action Potentials↗

PubMed1993

Examining the volume efficiency of the cortical architecture in a multi-processor network model.

The convoluted form of the sheet-like mammalian cortex naturally raises the question whether there is a simple geometrical reason for the prevalence of cortical architecture in the brains of higher vertebrates. Addressing this question, we present a formal analysis of the volume occupied by a massively connected network or processors (neurons) and then consider the pertaining cortical data. Three gross macroscopic features of cortical organization are examined: the segregation of white and gray matter, the circumferential organization of the gray matter around the white matter, and the folded cortical structure. Our results testify to the efficiency of cortical architecture.

Animals↗

PubMed2000

Randomly connected sigma-pi neurons can form associator networks.

A set of sigma-pi units randomly connected to two input vectors forms a type of hetero-associator related to convolution- and matrix-based associative memories. Associations are represented as patterns of activity rather than connection strengths. Decoding the associations requires another network of sigma-pi units, with connectivity dependent on the encoding network. Learning the connectivity of the decoding network involves setting n3 parameters (where n is the size of the vectors), and can be accomplished in approximately 3e n log n presentations of random patterns. This type of network encodes information in activation values rather than in weight values, which makes the information about relationships accessible to further processing. This accessibility is essential for higher-level cognitive tasks such as analogy processing. The fact that random networks can perform useful operations makes it more plausible that these types of associative network could have arisen in the nervous systems of natural organisms during the course of evolution.

Animals↗

PubMed1993

TODAM2: a model for the storage and retrieval of item, associative, and serial-order information.

This article presents an extended version of the convolution-correlation memory model TODAM (theory of distributed associative memory) that not only eliminates some of the inadequacies of previous versions but also provides a unified treatment of item, associative, and serial-order information. The chunking model extended the basic convolution-correlation formalism by using multiple convolutions, n-grams (multiple autoassociations of sums of item vectors), and chunks (sums of n-grams) to account for chunking and serial organization. TODAM2 extends the chunking model by including rn-grams (reduced n-grams), labels, and "lebals" (the involution or mirror image of a label) to provide a general model for episodic memory. For paired associates, it is assumed that subjects store only labeled n-grams and lebaled rn-grams. It is shown that the model is broadly consistent with a number of major empirical paired-associate and serial-order effects.

Humans↗

PubMed2026

GraphyloVar: predicting the impact of non-coding variants using a multi-species sequence model.

MOTIVATION: Understanding the functional impact of genetic variants is a key problem for precision medicine. Tools like CADD, PhyloP, and PhastCons are useful, but they often look at each position in the genome in isolation. This means they can miss important information from the evolutionary history that connects different species. In this paper, we extend our previous model, Graphylo, to predict the effects of variants. Our new model, GraphyloVar, is built to directly utilize the phylogenetic tree that relates the species. RESULTS: GraphyloVar is a deep learning model that considers both DNA sequence and evolutionary patterns from many species. It uses two main components: Graph Convolutional Networks (GCNs) to process the phylogenetic tree, and Transformer encoders to extract features from the DNA sequences. Pre-trained to predict population-level allele frequencies on the TOPMed whole-genome sequencing cohort, GraphyloVar achieves an AUROC of 0.6246 zero-shot on ∼149M held-out variants, and an ensemble with CADD reaches 0.6442 (+0.020, P<10-15). Fine-tuned GraphyloVar achieves the highest AUROC across all 13 MPRA benchmark datasets. By integrating deep learning with explicit phylogenetic input, GraphyloVar offers a powerful and complementary approach to variant effect prediction that utilizes the full evolutionary history from many species to better identify and prioritize important non-coding variants. AVAILABILITY AND IMPLEMENTATION: Code and datasets are available at https://github.com/DongjoonLim/GraphyloVar under DOI: 10.5281/zenodo.20616818.

Phylogeny↗

PubMed2000

A fast fixed-point algorithm for independent component analysis of complex valued signals.

Separation of complex valued signals is a frequently arising problem in signal processing. For example, separation of convolutively mixed source signals involves computations on complex valued signals. In this article, it is assumed that the original, complex valued source signals are mutually statistically independent, and the problem is solved by the independent component analysis (ICA) model. ICA is a statistical method for transforming an observed multidimensional random vector into components that are mutually as independent as possible. In this article, a fast fixed-point type algorithm that is capable of separating complex valued, linearly mixed source signals is presented and its computational efficiency is shown by simulations. Also, the local consistency of the estimator given by the algorithm is proved.

Algorithms↗

PubMed2026

PEARL: integrative multi-omics classification and omics feature discovery via deep graph learning.

MOTIVATION: Integrating multi-omics data provides valuable insights into biological processes by capturing information across multiple molecular layers, enabling a comprehensive understanding of complex diseases and driving advancements in precision medicine. However, existing computational methods for multi-omics integration face significant challenges, such as low reliability and poor generalizability, due to the high dimensionality and low sample size nature of omics data. RESULTS: To address these challenges, we present PEARL (Pearson-Enhanced spectrAl gRaph convoLutional networks), a novel deep graph learning method for biomedical classification and functional important omics features identification. PEARL leverages a simple yet effective learning architecture to achieve superior and robust performance in high-dimensional, low-sample-size multi-omics settings. Our results demonstrate that PEARL significantly outperforms existing state-of-the-art methods on both synthetic and real biomedical datasets. Furthermore, applied to Alzheimer's disease (AD) brain multi-omics data, features prioritized by PEARL lead to functionally important genes that demonstrate significant enrichment in AD-related pathways. These findings highlight PEARL's practical utility in biomedical research and its potential to enhance biological interpretability in multi-omics studies. AVAILABILITY AND IMPLEMENTATION: The source code of our computational framework is available at https://github.com/zqq121017/PEARL.

Multiomics↗

PubMedDate not supplied

Separate neural definitions of visual consciousness and visual attention; a case for phenomenal awareness.

What is the relation between visual attention and visual awareness? It is difficult to imagine being aware of something without attending to it, and by some, visual consciousness is simply equated to what is in the focus of attention. However, findings from psychological as well as from neurophysiological experiments argue strongly against equating attention and visual consciousness. From these experiments clearly separate neural definitions of visual attention and visual consciousness emerge. In the model proposed here, visual attention is defined as a convolution of sensori-motor processing with memory. Consciousness, however, is generated by recurrent activity between cortical areas. The extent to which these recurrent interactions involve areas in executive or mnemonic space depends on attention and determines whether a conscious report is possible about the sensory experience, not whether the sensory experience is there. This way, a strong case can be made for a pure non-cognitive form of seeing, independent of attentional selection, called phenomenal awareness. This can be dissociated from the reportable form, depending on attention, called access awareness. The hypothesis explains why attention and consciousness seem so intricately related, even though they are fully separate phenomena.

Attention↗

PubMed2026

GiGCN: a network-based framework for uncovering synthetic lethal and viable genetic interactions.

Genetic interactions (GIs) underpin the functional connectivity of genes and pathways, and are important for dissecting genotype-phenotype relationships and identifying therapeutic targets for diseases. However, the scale of the human genome restricts systematic experimental interrogation of GIs. Existing computational tools focus on predicting synthetic lethality (SL) and synthetic viability (SV), the two primary forms of GIs, yet their accuracy and biological interpretability are compromised by inadequate modeling of the molecular mechanisms behind positive and negative interactions, as well as the limitation of negative samples. To overcome these challenges, we developed Genetic Interaction Graph Convolutional Network (GiGCN), a signed network modeling framework for the joint identification of gene pairs with SL and SV. We built a high-confidence signed genetic network by integrating verified GIs, and non-interacting gene pairs, together with gene semantic similarity derived from biological processes. By leveraging disentangled subspace decomposition, this framework separately models distinct functional dimensions within gene networks, enabling robust representation of context-dependent regulatory relationships and accurate discrimination of SL and SV events. Benchmark experiments demonstrate that GiGCN outperforms state-of-the-art approaches (area under receiver operating-characteristic curve: 0.978, and area under precision-recall curve: 0.944). Further analyses reveal biologically meaningful insights, including known and novel SL interactions centered on the oncogene MYC Proto-Oncogene (MYC), as well as SV interactions linked to autophagy and mitophagy pathways. This study provides a robust and interpretable network-based strategy for systematically exploring GIs. The GiGCN framework not only improves the precision of SL and SV prediction, but also offers mechanistic insights into gene functional relationships, thereby supporting the discovery of actionable therapeutic targets for cancer and other human diseases.

Humans↗

PubMed2026

Artificial Intelligence-Driven Multi-Omics Analysis Reveals Hydroxytyrosol Targeting of the TXNIP-NLRP3 Inflammasome Axis in Traumatic Brain Injury.

Traumatic brain injury (TBI) induces secondary neuroinflammation driven by oxidative stress, inflammasome activation, and immune remodeling, yet specific mechanism-guided pharmacological interventions remain limited. This study established an artificial intelligence (AI)-integrated network pharmacology and multi-omics framework to evaluate whether hydroxytyrosol (HT), an olive-derived natural polyphenol, may regulate TBI-related neuroinflammatory targets centered on the TXNIP/NLRP3 inflammasome axis. Starting from the SMILES structure of HT, potential targets were predicted using PharmMapper, SwissTargetPrediction, and the Similarity Ensemble Approach and were standardized to UniProt identifiers. TBI-associated genes were integrated from GeneCards, DisGeNET, OMIM, and the Therapeutic Target Database. The overlapping target set was analyzed using STRING-based protein-protein interaction (PPI) networks, MCODE, CytoHubba, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment. Public GEO transcriptomic datasets (GSE123831 and GSE104687) were used for cross-platform expression validation, differential expression analysis, and exploratory CIBERSORT-based immune infiltration estimation. Random forest (RF), multilayer perceptron (MLP), graph convolutional network (GCN), graph attention network (GAT), SHAP/LIME explainability analysis, LASSO inflammatory-risk scoring, and two-sample Mendelian randomization (MR) were further applied for target prioritization, immune phenotype mapping, and genetic association analysis. Seventy-three overlapping HT-TBI targets were identified. PPI and topology analyses prioritized TXNIP, NLRP3, CASP1, MAPK1, and TP53 as key hubs enriched in inflammasome activation, oxidative stress, apoptosis, and NOD-like receptor signaling. TXNIP, NLRP3, and CASP1 were consistently upregulated in both TBI transcriptomic datasets. LM22-based immune deconvolution suggested increased pro-inflammatory immune signatures and a positive TXNIP-M1 macrophage association (r = 0.63, p < 0.001), which should be interpreted as a transcriptome-derived hypothesis rather than validated murine immune-cell proportions. AI-based models consistently ranked TXNIP/NLRP3 as high-contribution features under internal validation, and removal of these targets reduced model performance. A five-gene inflammatory score achieved an internally evaluated AUC of 0.87, while two-sample MR supported positive genetic associations involving TXNIP expression, TBI risk, NLRP3 and IL-1β expression. Collectively, these findings prioritize the TXNIP/NLRP3/CASP1 module as a computationally supported candidate mechanism through which HT may influence oxidative stress-inflammasome-immune coupling in TBI. This study provides an interpretable drug-target-pathway-phenotype framework and identifies TXNIP, NLRP3, and CASP1 as priority nodes for future experimental validation.

Artificial Intelligence↗

PubMed2026

A nonlinear multi-omics data integration and classification model based on pathway self-attention and graph convolutional networks.

The abundance of omics data has significantly advanced the development of multi-omics data integration techniques. Non-linear embedding approaches for data integration have gradually become the mainstream in multi-omics research, as these approaches can substantially improve cancer analysis by enhancing the quality of the embeddings. However, current multi-omics data integration methods are typically confined to omics measurements, neglecting domain-specific prior knowledge encompassing biological pathways. In this study, we proposed a multi-omics integrated classification model, PathTransGCN, based on pathway self-attention and graph convolutional networks (GCN). The model integrated biological pathway information into multi-omics data analysis with the aim of enhancing the accuracy of cancer classification. Multi-omics data for breast cancer (BRCA), non-small cell lung cancer (NSCLC), and low-grade glioma (LGG) were obtained from The Cancer Genome Atlas (TCGA) and UCSC Xena databases. These data included gene mutations, DNA methylation, copy number variations, and gene expression, and were used to assess the model's generalizability across different cancers. First, PathTransGCN employed a pathway self-attention module to learn latent representations of samples across different pathways, thereby obtaining multi-omics integration vectors. Concurrently, a patient similarity network (PSN) was constructed using the similarity network fusion (SNF) approach. Second, the integrated vectors and the PSN were jointly fed into a GCN for end-to-end training, enabling precise classification of cancer subtypes. Through multi-omics data analysis of the BRCA dataset, PathTransGCN outperformed several popular algorithms (such as MoGCN and DeePathNet) in the five-class classification of cancer subtypes, achieving an accuracy rate of 87.6% and an F1 score of 86.4%. Moreover, the model demonstrated robust generalization capabilities across both NSCLC and LGG datasets, while effectively identifying key disease-associated biomarkers at the pathway level. Experimental results demonstrate that PathTransGCN exhibits outstanding performance in integrating omics data and delivering interpretable classification outcomes, presenting significant potential for clinical applications.

Humans↗

PubMed1982

The distribution and origin of serotonin-containing fibers in the septal area: a combined immunohistochemical and fluorescent retrograde tracing study in the rat.

The distribution of 5-hydroxytryptamine (serotonin, 5-HT)-containing nerve fibers and terminals in the septal area of the rat was studied by using immunohistochemistry with specific antibodies to 5-HT in combination with fluorescent retrograde tracing methods. The 5-HT innervation of the septum is heterogeneous with regard to both the morphology of individual processes and the density of distribution in different parts of the septum. Three major classes of 5-HT like immunoreactive processes can be distinguished: 1) thin, convoluted fibers with small, round or elongated varicosities; 2) thick and relatively straight fibers with few varicosities; and 3) pericellular plexuses with large varicosities in close association with perikarya in the lateral septum. Three areas of the septum receive a prominent innervation by 5-HT processes: the diagonal band of Broca, the ventral part of the lateral septum, and an area bordering the medial edge of the islands of Calleja (insula magna). Whereas the two latter areas contain dense terminal networks, the diagonal band of Broca is occupied primarily by 5-HT fibers en route to other parts of the septum. Intraseptal injections of HRP or fluorescent dyes (granular blue, propidium iodide) resulted in retrograde labeling of neuronal cell bodies in several nuclei of the brainstem which are known to contain 5-HT neurons: the dorsal raphe, the median raphe, the nucleus reticularis tegmenti pontis, the raphe pontis, and the raphe magnus. Where fluorescent retrograde tracing was performed with 5-HT immunohistochemistry on the same tissue section, a prominent 5-HT containing pathway and a non-5-HT-containing pathway from the raphe nuclei to the septum were revealed. Finally, double retrograde fluorescent labeling after injections of granular blue or propidium iodide into the septum and entorhinal area respectively of the same rat revealed extensive branching of the raphe efferents. Thus, individual raphe neurons may simultaneously connect with septum and the entorhinal area, two structures essential for normal hippocampal function.

Animals↗

PubMed2000

A programmable VLSI filter architecture for application in real-time vision processing systems.

An architecture is proposed for the realization of real-time edge-extraction filtering operation in an Address-Event-Representation (AER) vision system. Furthermore, the approach is valid for any 2D filtering operation as long as the convolutional kernel F(p,q) is decomposable into an x-axis and a y-axis component, i.e. F(p,q)=H(p)V(q), for some rotated coordinate system [p,q]. If it is possible to find a coordinate system [p,q], rotated with respect to the absolute coordinate system a certain angle, for which the above decomposition is possible, then the proposed architecture is able to perform the filtering operation for any angle we would like the kernel to be rotated. This is achieved by taking advantage of the AER and manipulating the addresses in real time. The proposed architecture, however, requires one approximation: the product operation between the horizontal component H(p) and vertical component V(q) should be able to be approximated by a signed minimum operation without significant performance degradation. It is shown that for edge-extraction applications this filter does not produce performance degradation. The proposed architecture is intended to be used in a complete vision system known as the Boundary-Contour-System and Feature-Contour-System Vision Model, proposed by Grossberg and collaborators. The present paper proposes the architecture, provides a circuit implementation using MOS transistors operated in weak inversion, and shows behavioral simulation results at the system level operation and electrical simulation and experimental results at the circuit level operation of some critical subcircuits.

Computer Simulation↗