SEARCH · PubMed Health

Results for “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.

At least 19 recordsLinked to original sources

PubMed1979

Structure and dynamics of neural network oscillators.

Techniques are given to represent oscillating neural networks by asynchronous logical switching networks, and to analyze the oscillating networks using a directed graph called a state transition diagram. Consideration is restricted to network oscillators containing no rhythm determining pacemaker neurons, and no neurons exhibiting self-limiting properties such as post-inhibitory rebound or accumulating refractoriness. In the state transition diagrams, stable oscillations are associated with a particular geometric configuration called a cyclic attractor (the heavy cycle in Fig. 2). We show that given the network connectivity it is possible to predict autonomous dynamic behaviour, as well as behaviour following hyperpolarizing or depolarizing inputs to neurons of the network. Conversely, given information about patterns of firing activity during cycles and transients of neural networks, the network connectivity can be predicted. The theoretical techniques can be used to generate a census of network structures capable of generating stable oscillations. Several representative network oscillators are discussed in the context of previous theoretical and experimental studies of the structure of neural network oscillators. Although the number of theoretically possile network oscillators capable of generating sustained oscillations is very large, the techniques which are given should be useful in the design of experiments capable of distinguishing between equally plausible hypotheses.

Action Potentials↗

PubMed2026

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

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

Graph Neural Networks↗

PubMed2025

Detecting Interspecific Positive Selection Using Convolutional Neural Networks.

Traditional statistical methods using maximum likelihood and Bayesian inference can detect positive selection from an interspecific phylogeny and a codon sequence alignment based on model assumptions, but they are prone to false positives due to alignment errors and can lack power. These problems are particularly pronounced when faced with high levels of indels and divergence. To address these issues, we trained and tested convolutional neural network models on simulated data and achieved higher accuracy in detecting selection across a specific range of phylogenetic scenarios and evolutionary modes. This advantage is particularly evident when performing inference on noisy data prone to misalignments. Our method shows some ability to account for these errors, where most statistical frameworks fail to do so in a tractable manner. We explore the generalizability of our convolutional neural network models to unseen evolutionary scenarios and identify future avenues to achieve broader utility. Once trained, our convolutional neural network model is faster at test time, making it a scalable alternative to traditional statistical methods for large-scale, multigene analyses. In addition to binary classification (inference of the presence or absence of positive selection during the evolution of the sequences), we use saliency maps to understand what the model learns and observe how this could be leveraged for sitewise inference of positive selection.

Neural Networks, Computer↗

PubMed1979

Effect of boundaries on the response of a neural network.

The effect an abrupt boundary has upon the dynamical response of a neural network is investigated. The retina of the Limulus eye is used as a model system for studying this effect. A theoretical technique is presented for the quantitative prediction of the manner in which this neural network responds in the vicinity of its boundary. Corresponding experimental measurements of the response to moving stimuli by single optic neurons located near retinal boundaries are presented. Theory and experiment show detailed quantitative agreement.

Animals↗

PubMed2025

Comparing artificial and convolutional neural networks with traditional models for Genomic prediction in wheat.

With the rapid development of sequencing technology, the application of genomic prediction has become more and more common in breeding schemes of livestocks and crops. Selecting an appropriate statistical model is of central importance to achieve high prediction accuracy. Recently, machine learning models have been expected to upgrade genomic prediction into a new era. However, the perspective still suffers from lack of evidence that machine learning models can generally outperform the traditional ones on empirical data sets. In this study, we compared two machine learning models based on artificial neural network (ANN) and convolutional neural network (CNN) with four traditional models, including genomic best linear unbiased prediction (GBLUP), Bayesian ridge regression (BRR), BayesA and BayesB, using three published data sets for grain yield in wheat. For each model, we considered two variants: modeling and ignoring the genotype-by-environment ([Formula: see text]) interaction. In the comparison, we considered two strategies of cross-validation: predicting genotypes that have not been evaluated in any environment (CV1) and predicting genotypes that have been tested in other environments (CV2). Our results showed that traditional Bayesian models (BayesA, BayesB, and BRR) outperformed GBLUP, ANN and CNN when considering [Formula: see text] interaction. The accuracies of ANN and CNN were higher than traditional models only in CV1 and when [Formula: see text] interaction was ignored. It was also found that the performance of the two machine learning models was significantly affected by the interaction between the CV strategy and the way of treating the [Formula: see text] interaction, while that of the four traditional models was only influenced by whether the [Formula: see text] interaction was considered or not. Thus, machine learning models can be a powerful complementary to the traditional ones and their superiority may depend on the prediction scenario. Among the two machine learning models, we observed that the accuracy of ANN was higher than CNN in most cases, indicating that it is still challenging to adapt complex machine learning models such as CNN to genomic prediction.

ANN↗

PubMed2025

Comparative analysis of convolutional neural network models for the histopathological differentiation of acinic cell carcinoma and secretory carcinoma.

OBJECTIVE: Although artificial intelligence tools show promise for enhancing the diagnosis of head and neck lesions, few studies have tested these resources for the microscopic diagnosis of salivary gland tumors. Specifically, the microscopic differentiation between acinic cell carcinoma and secretory carcinoma has never been addressed in this context. Therefore, this exploratory study aimed to comparatively evaluate the feasibility of applying convolutional neural networks for the microscopic differentiation between acinic cell carcinomas and secretory carcinomas. METHODS: A cross-sectional study using whole-slide images from 46 patients with acinic cell carcinoma (n = 26) or secretory carcinoma (n = 20) was conducted. Eight CNNs (ResNet-50, InceptionV3, VGG16, Xception, MobileNet, DenseNet121, EfficientNetB0, and EfficientNetV2B0) were trained and evaluated for accuracy, sensitivity, specificity, F1-score, and AUC. Performance was measured in training, validation, and test subsets. Accuracy and loss curves were also presented. RESULTS: InceptionV3 demonstrated the best overall performance, with the lowest loss (1.39), highest accuracy (0.81), sensitivity (0.90), and F1-score (0.81). VGG16 achieved the highest AUC (0.86) and precision (0.77). DenseNet121 showed the lowest performance in terms of accuracy (0.65) and F1-Score (0.52), but the highest specificity (0.85). CONCLUSION: This proof-of-concept study suggests that convolutional neural networks may be feasible tools to support the microscopic differentiation between acinic cell carcinoma and secretory carcinoma. The performance of these models critically depends on the size of the dataset and the quality of annotations. The findings should be interpreted cautiously given the limited dataset and potential sources of bias. Further validation with larger, multicenter datasets is needed before any clinical application can be considered.

Humans↗

PubMed2026

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

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

Neural Networks, Computer↗

PubMed2025

CASTER-DTA: Equivariant Graph Neural Networks for Predicting Drug-Target Affinity.

Accurately determining the binding affinity of a ligand with a protein is important for drug design, development, and screening. With the advent of accessible protein structure prediction methods such as AlphaFold, predicted protein 3D structures are readily available; however, methods for predicting binding affinity currently do not take full advantage of 3D protein information. Here, we present CASTER-DTA (Cross-Attention with Structural Target Equivariant Representations for Drug-Target Affinity), which uses an equivariant graph neural network to learn more robust protein representations alongside a standard graph neural network to learn molecular representations to predict drug-target affinity. We augment these representations by incorporating an attention-based mechanism between protein residues and drug atoms to improve interpretability. We show that CASTER-DTA represents a state-of-the-art improvement on multiple benchmarks for predicting drug-target affinity and that it generates novel insights for several related tasks. We then apply CASTER-DTA to create a large resource of the binding affinities of every FDA-approved drug against every protein in the human proteome and make these predictions freely available for download. We also make available a web server for researchers to apply a pretrained CASTER-DTA model for predicting binding affinities between arbitrary proteins and drugs.

deep learning↗

PubMed1979

Electrophysiological studies on the neural networks among estrogen and progesterone effective brain areas on lordosis behavior of the rat.

The present study was performed in an attempt to elucidate the possible neural networks and their functional modification by progesterone among estrogen and progesterone effective brain areas for lordosis behavior of the rat. Single and multiple unit activities were recorded in the medial preoptic area (MPO), dorsomedial thalamic nucleus (MD), interpeduncular nucleus (IP) and ventral part of midbrain reticular formation (MRF), and single or train pulse stimulation was applied to the MPI, MD, IP, MRF, caudate-putamen (CP), habenular nucleus (HB), dorsal hippocampus (HPC), medial and lateral septum (m- and 1-SEPT) and lateral amygdala (1-AMYG). Unit activity was recorded under urethane anesthesia in ovariectomized rats pretreated with estrogen or with estrogen and progesterone. MPO units showed facilitatory responses to stimulation in the MRF, HB and 1-SEPT, and inhibitory responses to stimulation in the MD, HPC, m-SEPT and 1-AMYG in ovariectomized estrogen-primed rats. CP stimulation inhibited the MD unit activity. Stimulation in the IP had no effect on the MPO or MD units, while the IP units were affected by stimulation in the MPO, MD, CP and HB. MRF unit was accelerated by the MD and CP and inhibited by the MPO stimulation. In the ovariectomized, estrogen and progesterone-treated rat, the MPO unit responses to the MRF and MD stimulation, and the MD unit responses to the MRF and CP stimulation were different from those in the rat with only estrogen treatment. In addition, in the ovariectomized estrogen-primed rat, local application of progesterone to the MD prevented the inhibitory effect of the MD on the MPO unit. Progesterone, when given to the stimulated brain area, accelerated the MPO unit which was activated by the MRF stimulation, and inhibited the MD neuron which was inhibited by the CP stimulation. Multiple unit recordings showed similar results. Moreover, multi-unit activity in the HB and IP was elevated following a systemic progesterone application. On the basis of these results, the possible neural networks in the brain which participate in the lordosis control mechanisms are discussed.

Animals↗

PubMed2026

BioNeuralNet: a graph neural network based Multi-Omics network data analysis tool.

SUMMARY: Multi-omics data offer unprecedented insights into complex biological systems, yet their high dimensionality, sparsity, and intricate interactions pose significant analytical challenges. Network-based approaches have advanced multi-omics research by effectively capturing biologically relevant relationships among molecular features (e.g., genes, proteins, metabolites). While these methods are powerful for representing molecular interactions, there remains a need for tools specifically designed to effectively utilize these network representations across diverse downstream analyses. To fulfill this need, we introduce BioNeuralNet, a flexible and modular Python framework tailored for end-to-end network-based multi-omics data analysis. BioNeuralNet leverages Graph Neural Networks (GNNs) to learn biologically meaningful low-dimensional representations from multi-omics networks, converting these complex molecular networks into versatile embeddings. BioNeuralNet supports all major stages of multi-omics network analysis, including several network construction techniques, generation of low-dimensional representations, and a broad range of downstream analytical tasks. Its extensive utilities, including diverse GNN architectures, and compatibility with established Python packages (e.g., scikit-learn, PyTorch, NetworkX), enhance usability and facilitate quick adoption. BioNeuralNet is an open-source, user-friendly, and extensively documented framework designed to support flexible and reproducible multi-omics network analysis in precision medicine. AVAILABILITY AND IMPLEMENTATION: The BioNeuralNet library is available via The Python Package Index (PyPI). Source code, documentation, tutorials, and workflows are hosted at https://bioneuralnet.readthedocs.io. Code archived at https://doi.org/10.5281/zenodo.17503083.

Graph Neural Networks↗

PubMed2025

Transfer learning with multiomics integration and deep neural networks reveals drug resistance mechanisms in cancer.

Drug resistance remains one of the primary challenges in effective cancer therapy. In this study, we employed a deep neural network (DNN)-based transfer learning (TL) approach to predict drug response and uncover drug resistance mechanisms. We integrated gene expression, somatic mutation, and copy number aberration (CNA) data with drug response profiles using multi-omics integration (MI). We used the Genomics of Drug Sensitivity in Cancer (GDSC) data for training and incorporated drugs with same pathways into the training models. We then evaluated drug response predictions on independent in-vivo PDX Encyclopedia (PDX) and ex-vivo the Cancer Genome Atlas (TCGA) datasets. In addition, we conducted pathway enrichment analyses to elucidate the mechanisms underlying drug resistance for paclitaxel, 5-fluorouracil (5-FU), gemcitabine, and cetuximab. We also applied Fisher's exact test (FET) to assess potential associations between drug resistance and the presence of mutations or CNAs. Our pan-drug models outperformed other methods based on the area under the precision-recall curve (AUCPR). Our pathway enrichment analyses revealed LDHB-mediated pyruvate metabolism and FYN-mediated focal adhesion might have pivotal roles in paclitaxel resistance, while PINK1-mediated mitophagy might be critical in 5-FU resistance. In addition to transcriptional activation, FET suggested that CNAs in LDHB and PINK1 may also be associated with resistance to paclitaxel and 5-FU, respectively. Furthermore, enrichment results for paclitaxel and cetuximab indicated shared resistance mechanisms between the two drugs. Importantly, our findings are consistent with prior experimental studies, providing literature-based validation of our results. Overall, our DNN-based TL approach achieved strong predictive performance across PDX & TCGA datasets and enrichment analyses provided valuable biological insights into drug resistance mechanisms.

Humans↗

PubMed2025

Development and validation of a deep learning model based on cascade mask regional convolutional neural network to noninvasively and accurately identify human round spermatids.

INTRODUCTION: The difficulty of identifying human round spermatids (hRSs) has impeded applications of the human round spermatid injection (ROSI) technique. RSs can be accurately screened through flow cytometric analysis utilizing the Hoechst fluorescence profile reflecting DNA, but this method is not suitable for isolating hRSs due to the toxicity associated with Hoechst staining. OBJECTIVE: To evaluate the capacity of a deep learning model grounded in a cascade mask region-based convolutional neural network (R-CNN) for the noninvasive and accurate identification of hRSs. METHODS: In this study, we presented the development and validation of a deep learning model for identifying hRSs through the analysis of 3457 optical light microscope images of sorted hRSs obtained via flow cytometric analysis. The model's accuracy and specificity were evaluated by calculating the mean average precision (mAP). Furthermore, a double-blind experiment was conducted to access the reliability of the proposed model in accurately identifying hRSs. It detected the expression of protamine (PRM1) and/or peanut lectin (PNA), which are established markers for RSs. RESULTS: Our deep learning-based model demonstrated a high precision, achieving a mAP of over 0.80 for isolating hRSs in test datasets. The expression of PRM1 and/or PNA was observed in all cells noninvasively selected by our AI model during an independent double-blind test. This phenomenon confirmed the accuracy and effectiveness of the proposed model. The model's capability for noninvasive and accurate isolation of hRSs among spermatogenic cells highlighted its robustness and generalizability for clinical applications. CONCLUSION: The deep learning AI model based on a cascade R-CNN has the ability to accurately identify hRSs among spermatogenic cells. The application of this noninvasive method, which requires no additional procedures in clinical practice, is able to facilitate the widespread implementation of ROSI technique. Therefore, it can provide patients with spermatogenic arrest the opportunity to become biological fathers.

Humans↗

PubMed2026

Non-destructive prediction of lead content in oilseed rape leaves by fluorescence hyperspectral technology based on neural network.

Based on fluorescence hyperspectral imaging (FHSI), this study targeted rapid, non-destructive quantification of lead (Pb) content in oilseed rape leaves treated with varying silicon (Si) concentrations, acquiring fluorescence spectra over the 484.43-1001.61 nm wavelength range. To optimize spectral data quality, preprocessing methods (Savitzky-Golay smoothing, first derivative, detrending) were comprehensively compared. Characteristic wavelengths were then selected via interval variable iterative shrinkage, which effectively compressed data dimensionality and reduced computational load. A hybrid SE-CL1DA model, fusing a 1D convolutional neural network, a long short-term memory network and SE attention mechanism was constructed, with Bayesian optimization tuning hyperparameters to boost stability. The BO-SE-CL1DA outperformed both traditional machine learning and insufficiently optimized deep learning model (Rp2=0.9609, RMSE = 0.0377 mg/kg, RPD = 5.1736), thus enabling accurate Pb estimation, supporting Si-regulated heavy metal stress management and facilitating agricultural contamination monitoring.

Plant Leaves↗

PubMed2026

Artificial neural network data fusion-mediated dual-mode sensor based on Fe3O4@PdIr for Salmonellatyphimurium detection in food.

Salmonella Typhimurium (S. typhimurium) is a major foodborne pathogen that poses a serious threat to public health. In this study, a colorimetric/electrochemical dual-mode biosensor assisted by artificial neural network (ANN) was developed for the sensitive detection of S. typhimurium. Fe3O4@PdIr nanocomposites with enhanced peroxidase-like activity and electrochemical performance were prepared and conjugated with an aptamer specific to S. typhimurium to obtain Fe3O4@PdIr-Apt. Through the sandwich binding of Fe3O4@PdIr-Apt and Apt to the target, the nanocomposites were attached to microplates or Au electrodes, thereby generating colorimetric and electrochemical signals. The ANN model deeply resolved the complex nonlinear relationship between the dual signals, enabling mutual correction and ultimately performing data fusion to output a single detection result, which significantly reduced the mean square error while improving detection sensitivity and reliability. This sensor exhibited a wide linear range of 2.7-2.7 × 108 CFU/mL and a low detection limit of 1.66 CFU/mL. Additionally, this method was successfully applied to the detection of S. typhimurium in pork and milk, with a recovery rate of 95.19% ∼ 104.07%. It indicated that the constructed sensor holds great practical potential for S. typhimurium detection.

Neural Networks, Computer↗

PubMed2025

HallmarkGraph: a cancer hallmark informed graph neural network for classifying hierarchical tumor subtypes.

MOTIVATION: Accurate tumor subtype diagnosis is crucial for precision oncology, yet current methodologies face significant challenges. These include balancing model accuracy with interpretability and the high costs of generating multi-omics data in clinical settings. Moreover, there is a lack of validated models capable of classifying hierarchical tumor subtypes across a comprehensive pan-cancer cohort. RESULTS: We present a graph neural network, HallmarkGraph, the first biologically informed model developed to classify hierarchical tumor subtypes in human cancer. Inspired by cancer hallmarks, the model's architecture integrates transcriptome profiles and gene regulatory interactions to perform multi-label classification. We evaluate the model on a comprehensive pan-cancer cohort comprising 11 476 samples from 26 primary cancers with 405 subtypes up to eight levels. The model demonstrates exceptional performance, achieving 5-fold cross-validation accuracy between 85% and 99% for tumor subtypes labeled with increasing details of genomic information. It also shows good generalizability on a validation dataset of 887 samples, assessed using three metrics that consider tumor subtypes at individual, combined, and sample levels. Benchmarking and ablation experiments show that hallmark-based embeddings slightly influence model performance, while the integrated multilayer perceptron plays a significant role in determining classifier accuracy. Additionally, we use the SHAP method to link cancer hallmarks with genes, identifying key features that influence model decisions. Our findings present a biologically informed machine learning framework capable of tracking tumor transcriptomic trajectories and distinguishing inter- and intra-tumor heterogeneity in pan-cancer. This approach holds promise for enhancing cancer diagnostics. AVAILABILITY AND IMPLEMENTATION: HallmarkGraph is accessible at https://github.com/laixn/HallmarkGraph.

Humans↗

PubMed2025

HINN: Hierarchical Input Neural Network identifies multi-omics biomarker for cognitive decline.

Understanding complex diseases requires models that can integrate diverse layers of biological data while yielding insights that are biologically interpretable. Although multi-omics integration with machine learning (ML) has advanced disease prediction and biomarker discovery, most existing approaches overlook the hierarchical and regulatory relationships that connect these molecular layers. Here, we present the Hierarchical Input Neural Network (HINN), a deep learning framework that incorporates known cross-omics relationships directly into its architecture, capturing the flow of information from genomics to epigenomics, transcriptomics, and downstream biological processes. By embedding these relationships, HINN improves both predictive performance and biological interpretability. We applied HINN to blood-derived multi-omics data from individuals with Alzheimer's disease or mild cognitive impairment to predict cognitive scores from standardized assessments. HINN outperformed both baseline and state-of-the-art models and pinpointed multi-omics biomarkers-including SNPs and promoter-region CpG sites in ATP6V1C1 and RCHY1 -that were significantly correlated with plasma p-Tau181 levels. These features map to biologically relevant processes with potential implications for cognitive decline. Our findings demonstrate how combining deep learning with biological knowledge can uncover interpretable, blood-based biomarkers for cognitive decline due to complex diseases such as Alzheimer's. All code and data are openly available at https://github.com/bozdaglab/HINN.

Alzheimer’s disease↗

PubMed1979

Studies on human finger tapping neural networks by phase transition curves.

The human finger tapping was studied psychologically by the phase transition curves. We assumed that some oscillatory neural network controls the tapping. One of our future works on the human finger tapping is to devise a method to change the magnitude of perturbation continuously in phase resetting experiments of a constant tapping interval with a same kind of task. If this is achieved, we can obtain a phase transition surface (i.e. the new phase as a function of the old phase and the magnitude of perturbation). From the shape of a phase transition surface, the intrinsic properties of the oscillatory network which controls the tapping can be studied (Kawato et al., 1978).

Conditioning, Psychological↗

PubMed1979

Mathematical model for the self-organization of neural networks.

Mutual inhibition between neurons combined with a learning principle similar to that proposed by Hebb is shown to secure a powerful self-organizing property for neural networks. Numerical analysis reveals that the system investigated always organizes itself into the same final state from any arbitrarily chosen initial state.

Action Potentials↗