SEARCH · PubMed Health

Results for “Long Short Term Memory”

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.

11 recordsLinked to original sources

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↗

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↗

PubMed2026

Whole-Genome Deep Learning Predicts Chemotherapy Response in Colorectal Cancer.

Chemotherapy response in colorectal cancer (CRC) exhibits significant heterogeneity, with current clinical predictors failing to capture complex genomic determinants of resistance. We developed a hybrid deep learning framework integrating convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) networks to analyze whole-genome somatic mutations, evolutionary conservation, chromatin accessibility, and 3D genome architecture in 2,546 TCGA patients. An attention mechanism identified predictive genomic regions. The model achieved an AUC of 0.92 (95% CI: 0.89-0.94) in cross-validation and 0.88 (95% CI: 0.85-0.91) in independent validation, outperforming clinical models (ΔAUC = +0.18, p < 0.001). Key predictors included non-coding variants in TP53, KRAS, and PIK3CA regulatory regions. Triple-positive patients (mutations in all 3 regions) had significantly worse progression-free survival (HR = 4.7, p < 0.001). Our framework enables accurate chemotherapy response prediction and reveals novel non-coding resistance mechanisms, advancing precision oncology in CRC.

Humans↗

PubMed2025

CNV-Finder: Streamlining Copy Number Variation Discovery.

Copy Number Variations (CNVs) play pivotal roles in the etiology of complex diseases and are variable across diverse populations. Understanding the association between CNVs and disease susceptibility is significant in disease genetics research and often requires analysis of large sample sizes. One of the most cost-effective and scalable methods for detecting CNVs is based on normalized signal intensity values, such as Log R Ratio (LRR) and B Allele Frequency (BAF), from Illumina genotyping arrays. In this study, we present CNV-Finder, a novel pipeline integrating deep learning techniques on array data, specifically a Long Short-Term Memory (LSTM) network, to expedite the large-scale identification of CNVs within predefined genomic regions. This facilitates efficient prioritization of samples for time-consuming or costly subsequent analyses such as Multiplex Ligation-dependent Probe Amplification (MLPA), short-read, and long-read whole genome sequencing. We incorporate four genes to establish our methods-Parkin (PRKN), Leucine Rich Repeat And Ig Domain Containing 2 (LINGO2), Microtubule Associated Protein Tau (MAPT), and alpha-Synuclein (SNCA)-which may be relevant to neurological diseases such as Alzheimer's disease (AD), Parkinson's disease (PD), Progressive Supranuclear Palsy (PSP), or related disorders such as essential tremor (ET). By training our models on expert-annotated samples and validating them across diverse cohorts, including those from the Global Parkinson's Genetics Program (GP2) and additional dementia-specific databases, we demonstrate the efficacy of CNV-Finder in accurately detecting deletions and duplications. Our pipeline outputs app-compatible files for visualization within CNV-Finder's interactive web application. This interface enables researchers to review predictions and filter displayed samples by model prediction values, LRR range, and variant count in order to explore or confirm results. Our pipeline integrates this human feedback to enhance model performance and reduce false positive rates. Through a series of comprehensive analyses and validations using visual inspection, MLPA, short-read, and long-read sequencing data, we demonstrate the robustness and adaptability of CNV-Finder in identifying CNVs with regions of varied size, probe density, and noise. Our findings highlight the significance of contextual understanding and human expertise in enhancing the precision of CNV identification, particularly in complex genomic regions like 17q21.31. The CNV-Finder pipeline is a scalable, publicly available resource for the scientific community, available on GitHub (https://github.com/GP2code/CNV-Finder; DOI 10.5281/zenodo.14182563). CNV-Finder not only expedites accurate candidate identification but also significantly reduces the manual workload for researchers, enabling future targeted validation and downstream analyses in regions or phenotypes of interest.

Copy Number Variation (CNV)↗

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

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

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

bladder cancer↗

PubMed2026

Downregulation of Trpv4 and Klf2 in brain microvessels is associated with the progression of neurovascular dysfunction and cognitive impairment in a model of heart failure with preserved ejection fraction.

Vascular cognitive impairment (VCI) shares major risk factors with heart failure with preserved ejection fraction (HFpEF), including obesity, diabetes and hypertension. Yet VCI research often relies on single-stimulus models, whereas patients experience combined risk factors. We therefore assessed cerebrovascular and cognitive phenotypes in an HFpEF model and investigated underlying mechanisms. Male Lean and Obese ZSF1 rats underwent longitudinal assessments of blood pressure, glucose, cardiac function and behavioural performance. Cerebral blood flow and neurovascular coupling were assessed by laser speckle contrast imaging. White matter integrity, blood-brain barrier (BBB) permeability and vascular density were analyzed by (immuno)histochemistry. Cortical microvessels were isolated for transcriptomic profiling, and selected targets were validated using multiplex in-situ hybridization. Obese rats exhibited neurovascular uncoupling and impaired short- and long-term memory and spatial learning, accompanied by brain atrophy and reduced myelin. BBB permeability increased at 22-23 weeks and vascular density at 34-35 weeks in Obese versus Lean rats. Transcriptomic analysis of brain microvessels revealed altered processes related to angiogenesis, vasoreactivity, immune mechanisms and vascular remodelling, with consistent downregulation of Trpv4 and Klf2. Obese ZSF1 rats develop progressive neurovascular dysfunction associated with HFpEF onset and reduced Trpv4 and Klf2 expression in cerebral microvessels, two key vasoprotective genes.

Diastolic dysfunction↗

PubMed2025

A comparative study highlights superiority of LSTM in crop genomic prediction.

We systematically evaluated three key determinants affecting prediction accuracy and the algorithm performance differences based on fifteen state-of-the-art GP methods, and found LSTM suitable for capturing additive and epistatic effects. Genomic prediction (GP) has been developed as an important method supporting crop breeding. By utilizing the phenotype values result from GP, breeders could make decisions in the seedling stage that consequently benefit for cost saving. In recent years, machine learning emerged as an efficient technology to solve modeling problems in many fields, including crop breeding. However, numerous modeling approaches have hindered the application of GP since breeders struggle to choose. Therefore, a comprehensively methodological research with guiding significance is extremely necessary. In the present study, we systematically evaluated three key determinants affecting prediction accuracy and the algorithm performance differences based on fifteen state-of-the-art GP methods. As for genomic feature processing, we found feature selection (SNP filtering approach) performed better than feature extraction (PCA method). Specifically, the feature relationship dependent methods (GBLUP, RNN, and LSTM) as well as DNN architecture showed superior performance with feature selection. Marker density analysis showed positive correlation with prediction accuracy in a limited threshold. Comparison on effect of population size demonstrated a positive correlation between trait genetic complexity and the optimal population size required. By testing fifteen modeling methods, we found LSTM network displayed superior performance, achieving the highest average STScore (0.967) across six datasets. Further research using all cell states or the latest cell states of LSTM inputs demonstrated its architecture particularly adept with capturing additive and epistatic QTL effects among SNPs. In conclusion, our findings provide basic principles for implementing GP in breeding project to maximize prediction accuracy while maintaining cost-effectiveness.

Plant Breeding↗

PubMed2026

Diving Deeper Into Mechanisms of Acrylamide-Induced Toxicity: RNA Sequencing Reveals Transcriptomic Alteration and Retrotransposon Expression in Drosophila melanogaster.

Given the inevitability of human and animal exposure to acrylamide, there is increasing concern regarding its potential health risks. While a number of molecular mechanisms have been proposed, the complexity of acrylamide toxicological pathways and interactions remains incompletely characterized. In this study, we employed a transcriptomic approach to investigate the transcriptional responses of Drosophila melanogaster following exposure to acrylamide (100 mg/kg). Our analysis identified 634 differentially expressed genes (DEGs), with 362 upregulated and 272 downregulated. Functional analysis revealed these DEGs are enriched in pathways related to reproduction, detoxification, cellular and metabolic processes, signaling, synaptic formation and organization. Notably, acrylamide exposure upregulated the expression of tau and beta-amyloid protein precursor-like genes, both implicated in Alzheimer's disease pathology. An aversive memory test further demonstrated that acrylamide impaired the short-term memory of treated flies. Additionally, acrylamide-induced toxicity altered the expression of nine long terminal repeat retrotransposons, belonging to the gypsy and pao superfamilies. By exploring the potential role of transposable element activity in acrylamide-mediated toxicity, this study provides novel insights into the molecular mechanisms underlying its effects. Collectively, these findings offer a more comprehensive understanding of the mechanisms and pathways associated with the toxic action and detoxification of acrylamide in D. melanogaster.

Animals↗

PubMed2026

Electromagnetic Radiation Stimulated Learning in Perovskite Nickelates.

Biological plasticity refers to the ability of synapses to strengthen or weaken over time. These adaptive properties play a fundamental role in learning and memory, spanning many orders of magnitude in timescales. Short-term plasticity (STP) arises from rapid correlative activity, while long-term plasticity (LTP) is governed by slower biochemical processes. Here, we investigate electromagnetically driven relaxation dynamics in perovskite nickelate thin films as an analogue of biological learning behaviors. By comparing radio frequency (RF), infrared (IR), visible, and ultraviolet (UV) radiation as stimuli, we find that RF excitation primarily induces STP, while visible and IR illumination lead to reversible relaxation on behavioral timescales. In contrast, UV illumination results in persistent, non-thermal changes in conductivity over extended timescales. Notably, UV-exposed nickelate films exhibit glass-like dynamics, characterized by stretched exponential relaxation and aging phenomena. The films display habituation to repeated stimuli, along with sensitization and spontaneous recovery under controlled environments. A minimal dynamical systems model captures key qualitative features of the UV-induced resistance changes. Our results demonstrate that electromagnetic frequency enables multi-timescale relaxation spanning nearly nine orders of magnitude, suggesting perovskite nickelates as promising platforms for adaptive optoelectronic hardware and for linking computational neuroscience with emerging quantum technologies.

electromagnetic radiation↗

PubMed2025

Intratumoral B cell and interferon signatures in newly diagnosed glioblastoma are associated with longer survival in patients treated with SurVaxM.

Glioblastoma (GBM) has proved difficult to treat, and there is dire need for more effective therapies. In a single arm phase IIa trial (NCT02455557), treatment of newly diagnosed GBM patients with the peptide vaccine SurVaxM resulted in promising median progression-free and overall survival. To investigate molecular features that associate with GBM responsiveness to SurVaxM, retrospective whole exome and RNA sequencing was performed on patient tumors (n = 34) collected prior to standard of care treatment plus SurVaxM. Differential gene expression and mutational profiles were characterized between patients with short-term (OS < 18 months) or long-term (OS ≥ 18 months) overall survival. Greater expression of interferon, complement, and humoral immunity signatures were associated with long-term survival. Deconvolution of transcriptomes identified enrichment of intratumoral memory B cell populations in long-term survivors that were validated by CD20 staining in matched samples. A five-gene expression signature and a B cell specific signature predicted survival within the SurVaxM-treated cohort, however, these signatures were not associated with improved outcomes in a similarly treated population obtained from The Cancer Genome Atlas (TCGA) that did not receive immunotherapeutic intervention. Although prospective validation is ongoing, the findings in this discovery cohort specify molecular features of GBM associated with better overall survival and potential responsiveness to immunotherapy with SurVaxM.

Humans↗