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 19 recordsLinked to original sources

PubMed2026

Deep generative models in biological sequence and structure analysis and design.

Deep generative models have transformed biological sequence modeling from predictive analysis toward increasingly controllable design. Early biological applications of Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) established latent representation learning and sequence synthesis, while recent advances in transformer-based language models, discrete diffusion, flow-matching, and multimodal generative frameworks have substantially expanded the scope of biological design. This review examines generative models for DNA, RNA, and protein sequence design, emphasizing how different model classes represent biological constraints, operate over discrete and continuous spaces, and integrate sequence, structure, and function. We compare VAEs, GANs, autoregressive and masked language models, diffusion models, and flow-based approaches across genomics, transcriptomics, and proteomics, with particular attention to controllability, long-range dependency modeling, structural grounding, generalization, and experimental utility. We further examine evaluation strategies, out-of-distribution generalization, and closed-loop design-build-test-learn workflows that connect in silico generation with empirical validation. We distinguish fundamental modality-dependent constraints including sequence discreteness, context length, structural coupling, and physical or thermodynamic requirements from architecture-dependent advantages that reflect the current state of the field. Current studies suggest that long-context models are particularly useful for genome-scale representation and sequence modeling, whereas structure-aware diffusion, flow-based, and inverse-folding approaches provide better frameworks for geometry-constrained RNA and protein design. This perspective provides a critical framework for understanding the present capabilities, limitations, and convergence of generative approaches toward reliable and experimentally grounded biological design.

Biological sequence analysis↗

PubMed2026

scSurv: a deep generative model for single-cell survival analysis.

MOTIVATION: Single-cell omics analysis has unveiled the heterogeneity of various cell types within tumors. However, no methodology currently reveals how this heterogeneity influences cancer patient survival at single-cell resolution. Here, we introduce scSurv, combining a Cox proportional hazards model with a deep generative model of single-cell transcriptome, to estimate individual cellular contributions to clinical outcomes. RESULTS: The accuracy of scSurv was validated using both simulated and real datasets. This method identifies cells associated with favorable or adverse prognoses and extracts genes correlated with their contribution levels. In melanoma, scSurv reproduces known prognostic macrophage classifications and facilitates hazard mapping through spatial transcriptomics in renal cell carcinoma. We also identified genes consistently associated with prognosis across multiple cancers and demonstrated the applicability of this method to infectious diseases. scSurv is a novel framework for quantifying the heterogeneity of individual cellular effects on clinical outcomes. AVAILABILITY: The implementation of scSurv is available on GitHub (https://github.com/3254c/scSurv) and Zenodo (https://doi.org/10.5281/zenodo.17793054).

Humans↗

PubMed2026

CRISPGen: A deep generative framework for multi-objective CRISPR/Cas9 guide RNA design via Conditional Latent Diffusion and Dual-Critic Reinforcement Learning.

MOTIVATION: The CRISPR-Cas9 system offers transformative potential for precision genome editing, yet its clinical translation remains constrained by the risk of unintended off-target double-strand breaks. While current discriminative models excel at evaluating pre-specified candidate guides, resolving the fundamental antagonism between on-target cleavage efficiency and off-target specificity within a fixed sequence search space remains a major challenge. RESULTS: We present CRISPGen, a unified deep generative framework that reframes sgRNA design as a multi-objective constrained sequence synthesis problem. It integrates (i) DNABERT-2 genomic-language embeddings, (ii) a conditional latent diffusion generator conditioned on a user-specified on-target efficiency target, and (iii) a dual-critic reinforcement-learning (RL) stage that couples a frozen on-target efficiency critic with a cross-attention off-target discriminator (validation Pearson R=0.8157) trained on a unified corpus of experimental off-target events from six detection platforms. Across 1000 generated sgRNAs, CRISPGen reduces the mean off-target discriminator score by 99.7% relative to the pre-RL baseline and, under an exhaustive whole-genome screen of all 302,631,056 NGG PAM sites in GRCh38, yields zero perfect-match and only 55 one-mismatch genomic hits. We further show, transparently, that the internal on-target critic saturates under RL optimization - an instance of Goodhart's Law - and therefore assess on-target viability using an independent external CRISPRon screen (mean 47.10/100). Repeating the RL fine-tuning stage under three random seeds (with the diffusion generator, DNABERT-2 embeddings, and off-target discriminator held fixed) yields a stable operating point across seeds. Full diversity, per-mismatch, and reproducibility statistics are reported in the Results. AVAILABILITY: Source code is available at https://github.com/malekpouri/CRISPGen; the pre-trained checkpoints and the 3,000,000-sequence library are hosted on Hugging Face (https://huggingface.co/malekpouri/CRISPGen-Checkpoints) and archived on Zenodo under DOI 10.5281/zenodo.21428641.

CRISPR-Cas9↗

PubMed1991

Bursting-induced epileptiform EPSPs in slices of piriform cortex are generated by deep cells.

Previous study revealed that bursting activity generated by a variety of means in slices of piriform cortex induces persistent epileptiform EPSPs in superficial pyramidal cells by an NMDA-dependent process. The present study was undertaken to test the hypothesis that the observed epileptiform EPSPs in superficial pyramidal cells are driven by deep cells. This hypothesis was suggested by recent findings from in vitro studies of the properties of deep cells and in vivo studies indicating that the deep part of the piriform cortex or neighboring deep structures are involved in the generation of seizure activity in animal models of epilepsy. Results from simultaneous cell-pair recordings, examination of subdivided slices, and local application of excitatory and inhibitory agents provided strong evidence in support of this hypothesis. It was concluded that the endopiriform nucleus, a collection of cells immediately deep to the piriform cortex, plays a central role in generation, but that cells in the deep part of layer III and the claustrum may also contribute. Furthermore, it was found that generation of prolonged ictal-like activity only occurs in slices of piriform cortex in which the endopiriform nucleus is present. Implications of these findings for epileptogenesis are discussed.

Animals↗

PubMed2025

Soffritto: a deep learning model for predicting high-resolution replication timing.

MOTIVATION: Replication timing (RT) refers to the order in which DNA loci are replicated during S phase. RT is cell-type specific and implicated in cellular processes including transcription, differentiation, and disease. RT is typically quantified genome-wide using two-fraction assays (e.g. Repli-Seq) which sort cells into early and late S phase fractions followed by DNA sequencing, yielding a ratio as the RT signal. While two-fraction RT data are widely available in multiple cell lines, it is limited in its ability to capture high-resolution RT features. To address this, high-resolution Repli-Seq, which quantifies RT across 16 fractions, was developed, but it is costly and technically challenging with very limited data generated to date. RESULTS: Here, we developed Soffritto, a deep learning model that predicts high-resolution RT data using two-fraction RT data, histone ChIP-seq data, GC content, and gene density as input. Soffritto is composed of a Long Short-Term Memory (LSTM) module and a prediction module. The LSTM module learns long- and short-range interactions between genomic bins, while the prediction module is composed of a fully connected layer that outputs a 16-fraction probability vector for each bin using the LSTM module's embeddings as input. By performing both within cell line and cross-cell line training and testing for five human and mouse cell lines, we show that Soffritto is able to capture experimental 16-fraction RT signals with high accuracy, and the predicted signals allow detection of high-resolution RT patterns. AVAILABILITY AND IMPLEMENTATION: Soffritto is available at https://github.com/ay-lab/Soffritto.

Deep Learning↗

PubMed2025

Carafe enables high quality in silico spectral library generation for data-independent acquisition proteomics.

Data-independent acquisition (DIA)-based mass spectrometry is becoming an increasingly popular mass spectrometry acquisition strategy for carrying out quantitative proteomics experiments. Most of the popular DIA search engines make use of in silico generated spectral libraries. However, the generation of high-quality spectral libraries for DIA data analysis remains a challenge, particularly because most such libraries are generated directly from data-dependent acquisition (DDA) data or are from in silico prediction using models trained on DDA data. In this study, we developed Carafe, a tool that generates high-quality experiment-specific in silico spectral libraries by training deep learning models directly on DIA data. We demonstrate the performance of Carafe on a wide range of DIA datasets, where we observe improved fragment ion intensity prediction and peptide detection relative to existing pretrained DDA models. To make Carafe more accessible to the community, we have integrated Carafe into the widely used Skyline tool.

Journal Article↗

PubMed2026

Prediction of bacterial protein-compound interactions with only positive samples.

MOTIVATION: Prediction of Compound-Protein Interactions (CPI) in bacteria is crucial to advance various pharmaceutical and chemical engineering fields, including biocatalysis, drug discovery, and industrial processing. However, current CPI models cannot be applied for bacterial CPI prediction due to the lack of curated negative interaction samples. RESULTS: We propose a novel Positive-Unlabeled (PU) learning framework, named BIN-PU, to address this limitation. BIN-PU generates pseudo positive and negative labels from known positive interaction data, enabling effective training of deep learning models for CPI prediction. We also propose a weighted positive loss function that weights to truly positive samples. We have validated BIN-PU coupled with multiple CPI backbone models, comparing the performance with the existing PU models using bacterial cytochrome P450 (CYP) data. Extensive experiments demonstrate the superiority of BIN-PU over the benchmark models in predicting CPIs with only truly positive samples. Furthermore, we have validated BIN-PU on additional bacterial proteins obtained from literature review, human CYP datasets, and uncurated data for its reproducibility. We have also validated the CPI prediction for the uncurated CYP data with biological and biophysical experiments. BIN-PU represents a significant advancement in CPI prediction for bacterial proteins, opening new possibilities for improving predictive models in related biological interaction tasks. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/datax-lab/CYP.

Bacterial Proteins↗

PubMed2026

Artificial Intelligence for Natural Products Discovery and Development.

Natural products (NPs) remain a cornerstone of modern drug discovery, offering stereochemical complexity and diverse bioactivities that precisely modulate therapeutic targets, refined through billions of years of evolution. However, their research has long been hindered by inefficient, empirical workflows, high resource consumption, structural complexity, and the "multicomponent, multi-target" nature of their mechanisms. The exponential growth of genomic, metabolomic, and spectral data has overwhelmed conventional analytical methods, exposing critical bottlenecks in handling high-dimensional, heterogeneous datasets that exceed human interpretive capacity. Artificial intelligence (AI) is emerging as a transformative paradigm to address these challenges, integrating multi-omics and chemical data to shift NP research from fragmented empiricism toward mechanism-driven, precision-oriented development. By leveraging deep learning architectures- including graph neural networks, Transformers, and diffusion-based generative models-AI enables systematic decoding of NP biosynthesis, automated structure elucidation, rational target identification, knowledge extraction from vast unstructured scientific literature, and de novo molecular design. This review comprehensively surveys recent advances in AI applications across the full NP discovery and development pipeline, encompassing genome mining, structure-based and ligand-based virtual screening, multimodal structural characterization, lead optimization, and biosynthetic pathway engineering. We further examine the emerging roles of protein-centric, molecule- centric, and multimodal foundation models, as well as large language models, in bridging genotype-to-chemotype gaps and unlocking unstructured scientific knowledge. Finally, we discuss critical challenges including data scarcity, representational limitations for complex stereochemistry, physical plausibility in generative models, and the urgent need for experimental validation, while outlining future directions toward autonomous experimentation, closed-loop optimization, and human-AI collaborative discovery.

Artificial intelligence↗

PubMed2026

Mutational signatures in blood-brain barrier: mechanisms, computational insights, and clinical applications in precision oncology.

The blood - brain barrier (BBB) plays a central role in maintaining central nervous system (CNS) homeostasis, and its disruption is a defining feature of malignant brain tumors such as glioblastoma. Emerging evidence indicates that BBB dysfunction not only alters the tumor microenvironment but also shapes the mutational processes that drive genomic instability in CNS malignancies. This review synthesizes current understanding of the biological mechanisms linking BBB breakdown with distinct mutational signatures, including those arising from oxidative stress, hypoxia-induced replication stress, lipid peroxidation, inflammation, and metabolic reprogramming. Advances in next-generation sequencing, coupled with computational tools such as non-negative matrix factorization, Bayesian modeling, and deep learning, have enabled precise extraction of these signatures and their integration with multi-omics data. Clinically, BBB-associated mutational signatures offer significant promise for therapeutic stratification, prediction of treatment response, and noninvasive monitoring through cerebrospinal fluid - derived circulating tumor DNA. Despite these advances, challenges persist due to limited tissue accessibility, low-yield CSF samples, incomplete mechanistic models, and the lack of CNS-specific analytical frameworks. A deeper understanding of BBB-driven mutational processes, supported by improved computational approaches and integrative datasets, holds potential to advance precision oncology in neuro-oncology.

Humans↗

PubMed1992

Physiological interaction processes and radio-frequency energy absorption.

Because exposure to microwave fields at the resonant frequency may generate heat deep in the body, hyperthermia may result. This problem has been examined in an animal model to determine both the thresholds for response change and the steady-state thermoregulatory compensation for body heating during exposure at resonant (450 MHz) and supra-resonant (2,450 MHz) frequencies. Adult male squirrel monkeys, held in the far field of an antenna within an anechoic chamber, were exposed (10 min or 90 min) to either 450-MHz or 2,450-MHz CW fields (E polarization) in cool environments. Whole-body SARs ranged from 0-6 W/kg (450 MHz) and 0-9 W/kg (2,450 MHz). Colonic and several skin temperatures, metabolic heat production, and evaporative heat loss were monitored continuously. During brief RF exposures in the cold, the reduction of metabolic heat production was directly proportional to the SAR, but 2,450-MHz energy was a more efficient stimulus than was the resonant frequency. In the steady state, a regulated increase in deep body temperature accompanied exposure at resonance, not unlike that which occurs during exercise. Detailed analyses of the data indicate that temperature changes in the skin are the primary source of the neural signal for a change in physiological interaction processes during RF exposure in the cold.

Animals↗

PubMed2025

HIV-phyloTSI: subtype-independent estimation of time since HIV-1 infection for cross-sectional measures of population incidence using deep sequence data.

BACKGROUND: Estimating the time since HIV infection (TSI) at population level is essential for tracking changes in the global HIV epidemic. Most methods for determining TSI give a binary classification of infections as recent or non-recent within a window of several months, and cannot assess the cumulative impact of an intervention. RESULTS: We developed a Random Forest Regression model, HIV-phyloTSI, which combines measures of within-host diversity and divergence to generate continuous TSI estimates directly from viral deep-sequencing data, with no need for additional variables. HIV-phyloTSI provides a continuous measure of TSI up to 9 years, with a mean absolute error of less than 12 months overall and less than 5 months for infections with a TSI of up to a year. It performs equally well for all major HIV subtypes based on data from African and European cohorts. CONCLUSIONS: We demonstrate how HIV-phyloTSI can be used for incidence estimates on a population level.

HIV Infections↗

PubMed1990

The influence of model parameter values on the prediction of skin surface temperature: I. Resting and surface insulation.

A model is presented of heat transfer and temperature distributions in the skin and superficial tissues. It is based on a finite difference numerical solution of the one-dimensional multilayer coupled bioheat equation. In this paper, the model is used to investigate the influence of the values of parameters chosen to represent the physiological and heat transfer processes on the temperature of the skin under resting conditions and after insulation of the skin surface. Equilibrium resting temperatures were strongly influenced by deep body temperature especially at lower heat transfer coefficients on the skin surface, but slightly affected by the values chosen for skin blood flow and metabolic heat generation; both the heat transfer coefficients and environmental temperature strongly influenced the surface temperature. After surface insulation the temperature elevation was strongly influenced by the thermal conductivities of tissues, skin blood flow and deep boundary temperature; metabolic heat generation was only significantly at unphysiologically high values.

Humans↗

PubMed2026

A multi-scale fusion model based on multi-phase contrast-enhanced CT for predicting pancreatic cancer resectability.

Purpose.Develop a multi-scale fusion model (MSFM) based on multi-phase contrast-enhanced computed tomography (CECT) to predict pancreatic cancer (PC) resectability, thereby assisting expert decision-making.Methods.This retrospective study enrolled 280 patients with PC from four institutions, which were randomly divided into a training cohort (202 patients) and an independent test cohort (78 patients). Three-phase CECT images (arterial, venous, and delayed phases) were used for modeling. The MSFM comprises two sub-networks: (1) a multi-phase fusion network for extracting cross-phase shared fusion features, (2) a phase-specific branch network for capturing phase-specific features; and a post-fusion strategy to generate the final predictive score by integrating the shared fusion features and three groups of phase-specific features. Additionally, a human-machine fusion deep learning model (HMfDL) was constructed by fusing the predictive score of the MSFM with expert assessments.Results.In the independent test, the MSFM achieved an AUC (area under the receiver operating characteristic curve) of 0.8385 (95% CI: 0.7521-0.9249), accuracy of 84.62%, sensitivity of 72.00%, and specificity of 90.57%. This performance outperformed single-phase models (AUC range: 0.7638-0.7781), two-phase models (AUC range: 0.7826-0.7864), and ten states-of-the-art classifiers (AUC range: 0.7404-0.7796). The HMfDL further improved the performance, reaching an AUC of 0.8626 (95% CI: 0.7853-0.9400), accuracy of 91.03%, sensitivity of 80.00%, and specificity of 96.23%. Notably, the HMfDL corrected 58.82% of misdiagnosis made by experts.Conclusions. The MSFM effectively fuses multi-phase CECT to enable highly accurate predictions of PC resectability, and provides valuable support for expert decision-making through HMfDL.

Humans↗

PubMed2025

SHICEDO: single-cell Hi-C data enhancement with reduced over-smoothing.

MOTIVATION: Single-cell Hi-C (scHi-C) technologies have significantly advanced our understanding of the 3D genome organization. However, scHi-C data are often sparse and noisy, leading to substantial computational challenges in downstream analyses. RESULTS: In this study, we introduce SHICEDO, a novel deep-learning model specifically designed to enhance scHi-C contact matrices by imputing missing or sparsely captured chromatin contacts through a generative adversarial framework. SHICEDO leverages the unique structural characteristics of scHi-C matrices to derive customized features that enable effective data enhancement. Additionally, the model incorporates a channel-wise attention mechanism to mitigate the over-smoothing issue commonly associated with scHi-C enhancement methods. Through simulations and real-data applications, we demonstrate that SHICEDO outperforms the state-of-the-art methods, achieving superior quantitative and qualitative results. Moreover, SHICEDO enhances key structural features in scHi-C data, thus enabling more precise delineation of chromatin structures such as A/B compartments, TAD-like domains, and chromatin loops. AVAILABILITY AND IMPLEMENTATION: SHICEDO is publicly available at https://github.com/wmalab/SHICEDO.

Single-Cell Analysis↗

PubMed2025

APNet, an explainable sparse deep learning model to discover differentially active drivers of severe COVID-19.

MOTIVATION: Computational analyses of bulk and single-cell omics provide translational insights into complex diseases, such as COVID-19, by revealing molecules, cellular phenotypes, and signalling patterns that contribute to unfavourable clinical outcomes. Current in silico approaches dovetail differential abundance, biostatistics, and machine learning, but often overlook nonlinear proteomic dynamics, like post-translational modifications, and provide limited biological interpretability beyond feature ranking. RESULTS: We introduce APNet, a novel computational pipeline that combines differential activity analysis based on SJARACNe co-expression networks with PASNet, a biologically informed sparse deep learning model, to perform explainable predictions for COVID-19 severity. The APNet driver-pathway network ingests SJARACNe co-regulation and classification weights to aid result interpretation and hypothesis generation. APNet outperforms alternative models in patient classification across three COVID-19 proteomic datasets, identifying predictive drivers and pathways, including some confirmed in single-cell omics and highlighting under-explored biomarker circuitries in COVID-19. AVAILABILITY AND IMPLEMENTATION: APNet's R, Python scripts, and Cytoscape methodologies are available at https://github.com/BiodataAnalysisGroup/APNet.

COVID-19↗

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↗

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↗