SEARCH · PubMed Health

Results for “Deep generative models”

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 37 records · Page 2Linked to original sources

PubMedDate not supplied

[Is the implantation of hinged knee joint prostheses still justifiable today? 15 years' experience using the Blauth knee joint prosthesis].

In objection to knee hinge prostheses there is often mentioned a higher complication rate. An increased load impact on the bone-cement interface results from the close connection of tibial and femoral components. This is assumed to cause bad results, as reported from early artificial knee joint replacements, characterised by weight bearing axes and direct contact metal to metal. These are contrasted to long term results of the Blauth hinge prosthesis. The Blauth prosthesis is constructed according to the low friction principle without a weightbearing axis. A prospective multicentric long term follow-up study reports on 556 prostheses. 463 (83%) were controlled between 1 and 15 years after operation (average: 43 months). Aseptic loosenings had to be confirmed in 1.3% of the patients, deep infections in 2.6%. The survival analysis did not show an erratic deterioration in dependence of the observation period. After 10 years there is still a probability of 89% that a prosthesis does not show a deep infection or loosening. The efficiency of artificial knee joint replacement by hinge joints should therefore not be judged on the results of the first generation of these models.

Adult↗

PubMed2025

Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control.

Core promoters are essential regulatory elements that control transcription initiation, but accurately predicting and designing their strength remains challenging due to complex sequence-function relationships and the limited generalizability of existing AI-based approaches. To address this, we developed a modular platform integrating rational library design, predictive modelling, and generative optimization into a closed-loop workflow for end-to-end core promoter engineering. Conserved and spacer region of core promoters exert distinct effects on transcriptional strength, with the former driving large-scale variation and the latter enabling finer gradation. Based on this insight, Mutation-Barcoding-Reverse Sequencing approach was used and constructed a synthetic promoter library comprising 112 955 variants with minimal redundancy and a 16 226-fold expression range. A Transformer-based model trained on this dataset achieved a Pearson correlation of 0.87 with experimentally measured promoter strengths. When combined with a conditional diffusion model, the system enabled de novo generation of promoter sequences with defined strengths, achieving a design-to-measurement correlation of 0.95 and maintaining high accuracy (R = 0.93) across varied sequence contexts. The designed promoters consistently preserved their intended strength gradients, demonstrating robust plug-and-play functionality. This work establishes a scalable and extensible platform (www.yudenglab.com) for deep learning-guided programmable design of Escherichia coli core promoters, enabling precise transcriptional control.

Promoter Regions, Genetic↗

PubMed2026

Peptide-phosphorodiamidate morpholino oligomer therapy for dysferlinopathy induces pseudoexon skipping and restoration of functional protein.

The dysferlinopathies are a spectrum of autosomal recessive muscle diseases caused by mutations in the dysferlin gene (DYSF). Clinical manifestations vary from asymptomatic hyperCKemia to severe muscle pathology and loss of muscle function. These are designated as limb-girdle muscular dystrophy type 2R (LGMDR2; formerly LGMD2B or Miyoshi myopathy). Among other functions, dysferlin is crucial for plasma membrane repair and maintenance of intracellular calcium homeostasis. In previous studies, we identified 2 independent point mutations deep within introns that cause aberrant DYSF mRNA splicing and the inclusion of pseudoexons within transcripts that diminish protein expression. In this study, we generated and characterized a mouse model for 1 of these mutations (within DYSF intron 44). In these mice, a segment of human DYSF DNA containing the mutant intronic sequence flanked by surrounding human exon sequences replaced the normal homologous mouse DNA. These mice exhibited aberrant Dysf pre-mRNA splicing, pseudoexon inclusion, loss of DYSF protein expression, and muscle pathology similar to that observed in patients. Using this model, we identified antisense oligonucleotides and a peptide-phosphorodiamidate morpholino oligomer that blocks the mouse Dysf pre-mRNA splicing complexes from binding the mutant pre-mRNA, thereby restoring nearly normal muscle pathology and function.

Animals↗

PubMed1989

Creation of realistic appearing simulated patient cases using the INTERNIST-1/QMR knowledge base and interrelationship properties of manifestations.

The Internist-1/Quick Medical Reference (QMR) knowledge base (KB) describes the clinical manifestations of some 600 diseases in the domain of internal medicine. This KB, while not representing deep causal modelling of disease processes, is nonetheless effective in providing medical diagnostic assistance through the QMR medical decision support system. One potential application of this extensive KB is the generation of simulated patient cases for use in educating health professionals. However, the "flat" KB is not adequate for this because the clinical manifestations used in the disease descriptions are not mutually independent. While it is theoretically possible to construct disease descriptions which embody pathophysiologic mechanisms of disease causality, it is not practical from the standpoint of resource utilization. Short of constructing a causal knowledge base, the authors herein describe the generation of realistic appearing simulated patient case data using existing information in the knowledge base. This existing information in the KB is in the form of properties which represent a shallow form of interrelationships of the manifestations. The authors conclude that this ability to generate simulated cases represents another view in which to look at an extensive knowledge base, as well as having application to constructing intelligent tutoring systems for health professionals in training.

Artificial Intelligence↗

PubMed2026

Machine Learning in Hyperlipidaemia Research: Screening and Experimental Insights into Lipid Metabolism Modulators.

Hyperlipidemia, characterized by elevated blood lipid levels, represents a major global health concern due to its strong association with cardiovascular disease, diabetes, and metabolic syndrome. While current therapies - such as statins, fibrates, bile acid sequestrants, and PCSK9 inhibitors - are effective in controlling hyperlipidemia, they are often associated with adverse effects, potential drug resistance, and suboptimal efficacy in certain patient populations. All of the above underscore the urgent need for safer and more effective therapeutic alternatives. Among the major molecular targets involved in the regulation of lipid metabolism are HMG-CoA reductase, PCSK9, peroxisome proliferator-activated receptors (PPARs), cholesteryl ester transfer protein (CETP), and nuclear receptors, including the liver X receptor (LXR) and farnesoid X receptor (FXR), which are also targets for future antihyperlipidemic drug development. Recent advancements in artificial intelligence (AI) and machine learning (ML) have significantly transformed and accelerated drug discovery by enabling the processing of vast amounts of genomic, proteomic, and chemical data. Furthermore, ML tools such as quantitative structure-activity relationship (QSAR) modelling, deep learning, random forest, and support vector machines (SVM) have proven predictive and effective in identifying novel lipid metabolism modulators, thereby enhancing the efficacy and accuracy of virtual screening. Meanwhile, molecular docking has become an integral part of structure-based drug design (SBDD), and software such as AutoDock, Glide, and GOLD have proven effective in generating accurate ligand-target docking models. Molecular docking, together with ML-based approaches, enables the identification of potent and selective drug candidates. Overall, the combination of ML and molecular docking offers an efficient and accurate platform for antihyperlipidemic drug discovery, helping to overcome the limitations of currently available therapeutic strategies.

HMG-CoA reductase↗

PubMed1986

Architecture of the masticatory apparatus in eastern raccoons (Procyon lotor lotor).

The structure and function of the masticatory apparatus of raccoons resemble those found in carnivores. In this study, the architecture of the skull, dentition, and masticatory apparatus is described, and a model is proposed that suggests a mechanism used by raccoons to reduce different foods. The model suggests that jaw movements are similar to those of cats, the posterior regions of the superficial and deep parts of the temporalis and the anterior region of the medial pterygoid generate horizontal jaw movements, and the anterior portions of the superficial and deep temporalis as well as portions of the masseteric complex generate vertical closing movement. The distributions of slow, fast fatigable, and fast fatigue-resistant fibers for the temporalis and masseteric complex are related to the possible actions of these muscles during mastication, as are the regional cross-sectional areas of the masticatory muscles.

Animals↗

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↗

PubMed2025

DiCARN-DNase: enhancing cell-to-cell Hi-C resolution using dilated cascading ResNet with self-attention and DNase-seq chromatin accessibility data.

MOTIVATION: The spatial organization of chromatin is fundamental to gene regulation and essential for proper cellular function. The Hi-C technique remains the leading method for unraveling 3D genome structures, but the limited availability of high-resolution (HR) Hi-C data poses significant challenges for comprehensive analysis. Deep learning models have been developed to predict HR Hi-C data from low-resolution counterparts. Early Convolutional Neural Network (CNN)-based models improved resolution but struggled with issues like blurring and capturing fine details. In contrast, Generative Adversarial Network (GAN)-based methods encountered difficulties in maintaining diversity and generalization. Additionally, most existing algorithms perform poorly in cross-cell line generalization, where a model trained on one cell type is used to enhance HR data in another cell type. RESULTS: In this work, we propose Dilated Cascading Residual Network (DiCARN) to overcome these challenges and improve Hi-C data resolution. DiCARN leverages dilated convolutions and cascading residuals to capture a broader context while preserving fine-grained genomic interactions. Additionally, we incorporate DNase-seq data into our model, providing a robust framework that demonstrates superior generalizability across cell lines in HR Hi-C data reconstruction. AVAILABILITY AND IMPLEMENTATION: DiCARN is publicly available at https://github.com/OluwadareLab/DiCARN.

Chromatin↗

PubMed1991

The influence of model parameter values on the prediction of skin surface temperature: II. Contact problems.

A model of heat transfer and temperature distribution in the skin and superficial tissues which is based on a finite difference numerical solution of the one-dimensional multilayer coupled bioheat equation is presented. The model is used to investigate the influence of the values chosen to represent the physiological and thermal properties of the tissues on the skin surface temperature after contact with an external medium. It was found that the skin blood flow and dermal conductivity were the main cutaneous parameters which influence the contact response, but in terms of normalized temperature the response was little influenced by cutaneous metabolic heat generation and deep dermal temperature. For contact with a good conductor, the transient behaviour was sensitive to the heat transfer coefficient on the outer surface and the thickness of the contact material, but insensitive to the conductivity of the material.

Humans↗

PubMed2025

Caenorhabditis diversity on Pohnpei, Micronesia, provides evidence that the Elegans Supergroup has its roots in the Americas and diversified in the Pacific en route to Asia.

The microscopic nematode Caenorhabditis elegans stands unrivaled as a model for developmental biology, neurobiology, and genetics, but fundamental aspects of its ecology, biogeography, and natural history remain unknown. Leveraging recent findings that place its center of diversity in the cool, high-elevation forests of Hawaii, we performed an intensive survey of the Caenorhabditis fauna of Pohnpei, a high island in Micronesia that is home to the largest patch of high-elevation forest between Hawaii and East Asia. We found nine species of Caenorhabditis, five of them new, but not C. elegans. Most species were limited to the hot lowlands but three spanned the elevational range and one was found only in the cloudforest. Using the distribution of Caenorhabditis nematodes among habitat patches - individual rotting fruits or flowers - we parameterized simple models that capture key aspects of the population biology of these animals. We generated transcriptomes for the new species and inferred a phylogeny for 70 species of Caenorhabditis, based on 2955 genes. This phylogeny allowed us to perform the first quantitative biogeographic analysis for the group. Our analysis suggests that the deep ancestors of the Elegans Supergroup of species lived in the Americas, and that the Supergroup's subsequent diversification occurred in Remote Oceania. The ancestors of the Supergroup gave rise to a diverse Oceanian fauna and ultimately to multiple lineages that moved into Asia, Africa, Australasia, and back into the Americas. Though biogeographic inferences are limited by the lack of information from key regions of the southwest Pacific, the data are consistent with a model of trans-Pacific migration, with the islands of Oceania serving as sources rather than sinks for biodiversity.

Caenorhabditis↗

PubMed1987

Role of platelets in atherogenesis: relevance to coronary arterial restenosis after angioplasty.

There is now considerable evidence to suggest that some aspects of early lesion formation and later lesion growth are a reaction to injury. Hemodynamic factors are important in determining the site of injury and may produce injury directly. Injury can lead to atherogenesis in animal models as well as in humans. Superficial injury exposes the subendothelium, allowing platelet adhesion, which at high shear rates is dependent on vWF. Platelet adhesion and degranulation release PDGF, which stimulates smooth muscle cell proliferation, synthetic functions, and vasoconstriction. LDL stimulates smooth muscle cell growth as well as damages endothelium in some experimental systems. Thus, a link is provided between platelet and lipid involvement in atherosclerosis. Direct evidence for a role of platelets in atherogenesis comes from studies in which animals were treated to reduce platelet number or function or in which platelet function is genetically impaired (pigs with von Willebrand's disease). In these models, reduced platelet function is associated with less atherosclerosis. Deeper injury exposes collagen, with subsequent platelet aggregation, thrombin and fibrin generation. The role of reduced production of PGI2 and fibrinolytic agents following severe damage is unknown. Deep injury to the vessel occurs during plaque fissuring, the pathologic process underlying most cases of myocardial infarction, unstable angina, and some cases of sudden death. Angioplasty produces amelioration of many patients' symptoms and is safe. However, acute occlusion occurs occasionally, and restenosis in the first year occurs in some 30 percent of patients treated. Angioplasty damages the arterial wall, with endothelial denudation and intimal and medial splitting. Why does this, and plaque injury, by stimulating platelet deposition, not produce more restenosis? Changes in arterial anatomy are likely to be important: the increase in vessel diameter and in blood flow produce conditions less favorable for thrombotic or arteriosclerotic restenosis.

Angioplasty, Balloon↗

PubMed2026

[Applications and Challenges of Deep Learning in Human Genome Research].

In recent years, the advent of high-throughput omics technologies has fueled an explosive growth in human genomic data. Uncovering the latent functions within this vast data has become a significant challenge in functional genomics research. While traditional statistical methods have proved successful for analyzing smaller-scale datasets in the past, they exhibit clear limitations in analytical efficiency and integrating multi-dimensional data, struggling to meet the escalating demands of contemporary genomic analysis. The introduction of deep learning (DL) technologies offers a novel paradigm for this field. This review systematically examines the advances in applying deep learning to human genomics research. Studies demonstrate that when ample labeled data is available, discriminative DL computational methods-such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs)-achieve high accuracy and efficiency in genomic variant discovery tasks. Furthermore, generative DL methods, particularly Large Language Models (LLMs) leveraging self-supervised pre-training strategies, effectively integrate complex genomic information and exhibit superior performance in functional genomic sequence annotation and gene regulation studies. This review also explores the application of LLMs in multi-omics data integration and prediction. Looking ahead, the continued accumulation of long-read sequencing and high-dimensional data is expected to enable DL technologies to integrate increasingly complex and heterogeneous genomic information, playing an increasingly crucial role in human genomics research.

Deep Learning↗

PubMed2024

Nanopore sequencing to detect A-to-I editing sites.

Adenosine-to-inosine (A-to-I) RNA editing, mediated by the ADAR family of enzymes, is pervasive in metazoans and functions as an important mechanism to diversify the proteome and control gene expression. Over the years, there have been multiple efforts to comprehensively map the editing landscape in different organisms and in different disease states. As inosine (I) is recognized largely as guanosine (G) by cellular machineries including the reverse transcriptase, editing sites can be detected as A-to-G changes during sequencing of complementary DNA (cDNA). However, such an approach is indirect and can be confounded by genomic single nucleotide polymorphisms (SNPs) and DNA mutations. Moreover, past studies rely primarily on the Illumina platform, which generates short sequencing reads that can be challenging to map. Recently, nanopore direct RNA sequencing has emerged as a powerful technology to address the issues. Here, we describe the use of the technology together with deep learning models that we have developed, named Dinopore (Detection of inosine with nanopore sequencing), to interrogate the A-to-I editome of any organism.

Inosine↗

PubMed1978

Neuronal mechanisms of the late N-wave induced in vitro in thin sections of the olfactory cortex of rats.

Experiments were done to elucidate properties of the late N-wave which was induced in vitro in thin sections of the olfactory cortex of the rat in response to stimulation of the lateral olfactory tract. The late N-wave decreased in size at a stimulation rate of more than once every 90 sec or at temperatures higher than 27 degrees C. The late N-wave was suppressed in the presence of GABA, picrotoxin or bicuculline or in the Cl-free medium. Penicillin or pentylenetetrazol, which blocked actions of GABA on the presynaptic potential, also suppressed the late N-wave. The late N-wave first appeared at postnatal ages of 18--25 days. The late N-wave reversed in polarity when recorded from the deep layers of the sections or from the cut surface of the sections. Single cells in the deep portions of the sections discharged during the late N-wave. Cells in the superficial layers fired just before or after the late N-wave. In order to explain these observations, a neuronal model for generation of the late N-wave was presented.

Action Potentials↗

PubMed2023

Active learning of enhancer and silencer regulatory grammar in photoreceptors.

Cis-regulatory elements (CREs) direct gene expression in health and disease, and models that can accurately predict their activities from DNA sequences are crucial for biomedicine. Deep learning represents one emerging strategy to model the regulatory grammar that relates CRE sequence to function. However, these models require training data on a scale that exceeds the number of CREs in the genome. We address this problem using active machine learning to iteratively train models on multiple rounds of synthetic DNA sequences assayed in live mammalian retinas. During each round of training the model actively selects sequence perturbations to assay, thereby efficiently generating informative training data. We iteratively trained a model that predicts the activities of sequences containing binding motifs for the photoreceptor transcription factor Cone-rod homeobox (CRX) using an order of magnitude less training data than current approaches. The model's internal confidence estimates of its predictions are reliable guides for designing sequences with high activity. The model correctly identified critical sequence differences between active and inactive sequences with nearly identical transcription factor binding sites, and revealed order and spacing preferences for combinations of motifs. Our results establish active learning as an effective method to train accurate deep learning models of cis-regulatory function after exhausting naturally occurring training examples in the genome.

Journal Article↗

PubMed2021

Deep generative neural network for accurate drug response imputation.

Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational autoencoder (VAE) model to compress thousands of genes into latent vectors in a low-dimensional space. We then demonstrate that these encoded vectors could accurately impute drug response, outperform standard signature-gene based approaches, and appropriately control the overfitting problem. We apply rigorous quality assessment and validation, including assessing the impact of cell line lineage, cross-validation, cross-panel evaluation, and application in independent clinical data sets, to warrant the accuracy of the imputed drug response in both cell lines and cancer samples. Specifically, the expression-regulated component (EReX) of the observed drug response achieves high correlation across panels. Using the well-trained models, we impute drug response of The Cancer Genome Atlas data and investigate the features and signatures associated with the imputed drug response, including cell line origins, somatic mutations and tumor mutation burdens, tumor microenvironment, and confounding factors. In summary, our deep learning method and the results are useful for the study of signatures and markers of drug response.

Antineoplastic Agents↗

PubMed2025

Smarter stomata: emergent technologies unlocking yield potential in a changing climate.

Stomata, the gatekeepers of leaf gas exchange, regulate carbon dioxide uptake and water loss, functions increasingly critical as crops face more frequent, intense heat and drought. Under dry conditions, stomatal conductance (g s) typically decreases, limiting carbon assimilation and yield. Heat stress, in contrast, elicits variable g S responses: sometimes increasing to facilitate transpirational cooling, while at other times decreasing, especially when combined with drought. Heat and drought also induce complex, context-dependent shifts in stomatal anatomy. Smaller, denser stomata improve drought resilience in some cases, while reduced density confers greater tolerance in others. The optimal stomatal ideotype remains unknown, and different or even opposing traits may confer resilience dependent on the environmental scenario. Substantial genotypic variation in g s and stomatal anatomy, high heritability and co-localized quantitative trait loci for stomatal traits and yield highlight their untapped potential as breeding targets for climate-resilient crops. However, stomatal traits remain largely absent from breeding pipelines due to challenges of phenotyping at scale. This is changing rapidly. Advances in deep learning, porometry, digital microscopy, and remote sensing now enable high-throughput measurement of stomatal physiology and anatomy. Next-generation breeding technologies including clustered regularly interspaced short palindromic repeats (CRISPR), multi-omics approaches, and artificial intelligence-driven ideotype selection models could revolutionize breeding, allowing precise engineering of stomatal traits for resilience to environmental stress. The time has come to move beyond characterizing stomatal traits and start actively incorporating them into breeding strategies. By leveraging these technologies, stomatal traits can become high value targets, unlocking their potential to enhance crop performance in a hotter, drier future.

abiotic stress↗

PubMed1985

Influence of hypothermia and circulatory arrest on cerebral temperature distributions.

A finite element model of the bioheat transfer equation has been developed to simulate the temperature distribution in the head of a subhuman primate. Simulations were made of the induction of deep hypothermia and of subsequent hypothermic circulatory arrest (HCA). Simulations of the circulatory arrest phase were performed with different values of surface heat transfer coefficient and tissue metabolic heat generation. Numerical results were compared with experimental data for the same procedure. The simulations indicate the brain cools rapidly to a near isothermal condition in response to an infusion of cold arterial blood. However, extracerebral structures cool much more slowly. The bulk of heat gain by the brain during HCA is due to heat transfer from these warmer extra-cerebral tissues. These results suggest extended cooling by cardiopulmonary bypass (CPB) combined with surface cooling pads should reduce or even prevent the rise of brain temperatures during HCA.

Animals↗