Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Ensemble methods”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the 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
PubMed2026

Development of a PCR-based technique for genotyping UGT1A1 gene and distribution of rs3064744 alleles in the Russian population.

BACKGROUND: Accurate determination of tandem thymine-adenine (TA) repeat numbers in the UGT1A1 promoter region (rs3064744) is essential for diagnosing Gilbert's syndrome and personalizing therapy with toxic agents like irinotecan and atazanavir. However, traditional polymerase chain reaction (PCR) assays face severe limitations due to the AT-rich sequence and overlapping melting temperatures (Tm) of the highly homologous 7TA and 8TA alleles. In this context, melting curve analysis (MCA) employing fluorophore-quencher systems has emerged as a promising alternative. The purpose of this study was to develop a novel genotyping approach combining optimized aPCR-MCA analysis with an automated classifier to overcome the limitations posed by the differentiation of highly homologous alleles and to demonstrate its practical application, providing the distribution of rs3064744 genotypes across four regional cohorts of the Russian population. METHODS: A specialized Dual Head 1D-convolutional neural network (1D-CNN) ensemble with Test-Time Augmentation (TTA) was developed. The model was trained and internally validated on 1,620 engineered plasmid samples, and independently evaluated on an external clinical test set of 440 unique patient genomic DNA specimens. Real-time PCR was performed on CFX96 and DTprime platforms. Additionally, population-wide screening was conducted on 997 archival clinical samples from Moscow, Sakha (Yakutia), Dagestan, and Rostov regions. RESULTS: While 5TA and 6TA alleles were easily separated, absolute Tm distributions of 7TA and 8TA alleles overlapped significantly, and non-uniform Tm shifts of 0.8 °C-1.4 °C occurred across platforms. Conventional absolute Tm thresholding was therefore inadequate. By assessing relative morphological curve divergence against co-amplified 7TA/7TA and 7TA/8TA reference anchors, the 1D-CNN ensemble neutralized instrument noise. It achieved 100% accuracy on internal validation and 100% concordance (440/440) with clinical reference pyrosequencing. Population screening revealed that Dagestan, Yakutia, and Rostov cohorts closely align with the European population. Rare 5TA and 8TA alleles were detected at low frequencies in Yakutia and Moscow. CONCLUSION: Combining LNA-modified aPCR-MCA with a comparative 1D-CNN model successfully circumvents thermodynamic limitations and eliminates human operator bias. This integrated system offers an accessible, high-throughput, and clinically valid solution for routine UGT1A1 pharmacogenetic testing.

1D-CNN↗
PubMed2026

Predicting enhancer-promoter interactions using a stacking-based ensemble strategy.

MOTIVATION: Enhancer-promoter interactions (EPIs) are essential for gene regulation and disease progression. Recent studies have shown that distal enhancers can regulate target genes through interactions with nearby promoters, providing important insights into transcriptional regulation mechanisms. Although high-throughput experimental techniques have enabled large-scale identification of EPIs, these methods are often costly and time-consuming. In addition, existing computational approaches still face challenges in effectively integrating heterogeneous feature representations from different cell lines. RESULTS: We propose a stacked ensemble framework for EPI prediction that integrates feature representations from diverse cell line datasets using multiple machine learning algorithms. The extracted complementary patterns are further combined by an XGBoost classifier to improve robustness against overfitting. Experiments on six independent datasets show that the proposed method achieves superior accuracy and generalization compared with existing EPI prediction models, with an average AUROC of 0.909 while maintaining computational efficiency. AVAILABILITY: The source code and its archived release are available at GitHub and Zenodo. The Zenodo archive provides a versioned snapshot of the repository: https://zenodo.org/records/19952998.

Promoter Regions, Genetic↗
PubMed2025

Noninvasive detection and differentiation of gastric malignancy using cell-free DNA biomarkers.

INTRODUCTION: Gastric cancer remains a major global health burden, with high mortality driven by late-stage diagnoses that limit treatment options and reduce survival. Current diagnostic methods such as endoscopy and biopsy are invasive, resource-intensive, and impractical for large-scale early detection. OBJECTIVES: This study aimed to develop and validate an ensemble machine learning model integrating four cell-free DNA (cfDNA) fragmentomic feature classes derived from 5 × whole genome sequencing (WGS) data to non-invasively differentiate malignant gastric cancer from benign gastric lesions in high-risk or symptomatic patients. METHODS: A total of 681 plasma samples were prospectively collected, comprising 329 from patients with gastric cancer or high-grade intraepithelial neoplasia (HGIN) and 352 from individuals with benign gastric conditions. The dataset was divided into a training cohort (n = 333) and a temporally independent validation cohort (n = 348). An external validation cohort of 305 participants was also included. RESULTS: The ensemble model achieved an AUROC of 0.920 in cross-validation testing on the training cohort, 0.912 in the independent validation cohort, and 0.896 (95% CI 0.860-0.932) in the external cohort. At a pre-specified prediction threshold of 0.402, the model demonstrated 93.3% sensitivity and 71.9% specificity in the validation cohort, yielding a PPV of 71.3% and an NPV of 93.5%. In the external cohort, sensitivity and specificity were 91.7% and 69.1%, respectively (PPV 75.7%, NPV 88.8%). Model scores correlated with clinical stage, tumor grade, and histopathological subtype. Approximately 71% of non-cancer patients could have been spared unnecessary endoscopy. CONCLUSIONS: The cfDNA fragmentomics-based ensemble model enables accurate, non-invasive differentiation between gastric cancer and benign gastric lesions in high-risk or symptomatic patients. This approach demonstrates strong potential as a pre-endoscopy triage tool, supporting earlier detection and more efficient use of diagnostic resources.

Humans↗
PubMed2026

MegaPlantTF: a machine learning framework for comprehensive identification and classification of plant transcription factors.

MOTIVATION: Understanding the role of transcription factors (TFs) in plants is essential for the study of gene regulation and various biological processes. However, both TF detection and classification remain challenging due to the great diversity and complexity of these proteins. Conventional approaches, such as BLAST, often suffer from high computational complexity and limited performance on less common TF families. RESULTS: We introduce MegaPlantTF, the first comprehensive machine learning and deep learning framework for the prediction (TF versus non-TF) and classification (family-level) of plant TFs. Our method employs k-mer-based protein representations and a two-stage architecture combining a deep feed-forward neural network with a stacking ensemble classifier. To ensure robust performance assessment, we report micro-, macro-, and weighted-average performance metrics, providing a holistic evaluation of both frequent and underrepresented TF families. Additionally, we employ threshold-based evaluation to calibrate confidence in TF detection. The results show that MegaPlantTF achieves strong accuracy and precision, particularly with a k-mer size of 3 and a classification threshold of 0.5, and maintains stable performance even under stringent thresholds. In addition to the standard cross-validation tests, a use case study on Sorghum bicolor confirms that our method performs strongly in the genome-wide analysis, making it highly suitable for large-scale TF identification and classification tasks. MegaPlantTF represents a novel contribution by integrating k-mer encoding, binary family-specific classifiers, and a two-stage stacking ensemble into a unified, reproducible framework for large-scale plant TF identification and classification. AVAILABILITY AND IMPLEMENTATION: MegaPlantTF is freely accessible through a public web server available at https://bioinformatics.um6p.ma/MegaPlantTF. The complete source code, including pretrained models and example datasets, is available at https://github.com/Bioinformatics-UM6P/MegaPlantTF.

Transcription Factors↗
PubMed2025

Structural basis of differential gene expression at eQTLs loci from high-resolution ensemble models of 3D single-cell chromatin conformations.

MOTIVATION: Techniques such as high-throughput chromosome conformation capture (Hi-C) have provided a wealth of information on nucleus organization and genome important for understanding gene expression regulation. Genome-Wide Association Studies have identified numerous loci associated with complex traits. Expression quantitative trait loci (eQTL) studies have further linked the genetic variants to alteration in expression levels of associated target genes across individuals. However, the functional roles of many eQTLs in noncoding regions remain unclear. Current joint analyses of Hi-C and eQTLs data lack advanced computational tools, limiting what can be learned from these data. RESULTS: We developed a computational method for simultaneous analysis of Hi-C and eQTL data, capable of identifying a small set of nonrandom interactions from all Hi-C interactions. Using these nonrandom interactions, we reconstructed large ensembles (×105) of high-resolution single-cell 3D chromatin conformations with thorough sampling, accurately replicating Hi-C measurements. Our results revealed many-body interactions in chromatin conformation at the single-cell level within eQTL loci, providing a detailed view of how 3D chromatin structures form the physical foundation for gene regulation, including how genetic variants of eQTLs affect the expression of associated eGenes. Furthermore, our method can deconvolve chromatin heterogeneity and investigate the spatial associations of eQTLs and eGenes at subpopulation level, revealing their regulatory impacts on gene expression. Together, ensemble modeling of thoroughly sampled single-cell chromatin conformations combined with eQTL data, helps decipher how 3D chromatin structures provide the physical basis for gene regulation, expression control, and aid in understanding the overall structure-function relationships of genome organization. AVAILABILITY AND IMPLEMENTATION: It is available at https://github.com/uic-liang-lab/3DChromFolding-eQTL-Loci.

Quantitative Trait Loci↗
PubMed2025

Granular Hydrogels as Brittle Yield Stress Fluids.

While granular hydrogels are increasingly used in biomedical applications, methods to capture their rheological behavior generally consider shear-thinning and self-healing properties or produce ensemble metrics (e.g., dynamic moduli) while neglecting transient yielding and unyielding processes. Combining oscillatory shear testing with Brittility (Bt) via the Kamani-Donley-Rogers (KDR) model, this work shows that granular hydrogels behave as brittle yield stress fluids. This work quantifies steady and transient rheology as a function of microgel properties and granular composition for polyethylene glycol and gelatin microgels. The KDR model with Bt captures granular hydrogel behavior for a wide range of design parameters, reducing the complex rheology to a determination of model parameters. In granular mixtures, this work observes monotonic dependencies of the elastic modulus, structural viscosity, and brittility upon granular composition, while the yield stress is lower for mixtures. Microgel size distribution and polymer fraction are the most influential parameters in monolithic granular hydrogels, while microgel size and packing density are less impactful. The model robustly captures self-healing behavior and reveals that granular hydrogel relaxation accelerates with an increased small-amplitude strain rate. This quantitative framework is an important step toward rational design of granular hydrogels for applications ranging from injection and in situ stabilization to 3D bioprinting.

brittility↗
PubMed2026

Physiological sub-typing of cold and freezing injury in Triticum turgidum subspecies with bioinformatic and expression characterization of glutathione reductase.

BACKGROUND: This study examined how different subspecies of Triticum turgidum (T. durum, T. polonicum, T. turanicum) respond to cold and freezing, assessing their water status, stress responses, and antioxidant system, with particular focus on the structure and function of glutathione reductase (TtGR). METHODS: TtGR genes were first identified from the T. turgidum genome using publicly available genomic resources such as Ensembl Plants. Promoter regions (~2 kb upstream) were analyzed to identify cis-regulatory elements using PlantCARE. Gene classification was performed based on predicted subcellular localization and conserved domain features. Plants were subjected to cold acclimation and freezing treatments, and physiological, biochemical, and enzymatic parameters were measured. RESULTS: Bioinformatics analyses identified four TtGR genes in the T. turgidum genome. The genes in two groups: cytosolic (Class I) and chloroplastic (Class II). Gene structure analysis showed a conserved exon-intron organization, while motif analysis confirmed the presence of Nicotinamide Adenine Dinucleotide Phosphate (NADPH)-binding and redox-active domains across all TtGR proteins. Several regulatory sequences in the promoters are involved in cold (DRE), abscisic acid (ABRE), and stress (STRE) responses, indicating that TtGR genes are dynamically regulated in response to environmental changes. Physiological analyses showed that freezing treatment reduces leaf water content in all genotypes, leading to turgor loss, hydrogen peroxide (H2O2) accumulation, and increased malondealdehyte (MDA) levels. However, tolerance mechanisms addressing water stress and membrane damage differ among genotypes. At the biochemical level, activation of the antioxidant defense system occurs in all genotypes. T. turanicum displays strong defense by significantly increasing enzyme activities, ensuring that the ascorbate-glutathione cycle continues under stress. By contrast, T. polonicum, although showing increased overall enzyme activities, experiences a dramatic drop in glutathione reductase (GR) activity at freezing temperatures, which restricts reduced glutathione (GSH) regeneration and creates a functional bottleneck in the antioxidant cycle. T. durum fails to sustain enzyme activities over the stress period, leading to an intermediate-sensitive response. Thus, whereas T. turanicum effectively maintains antioxidant function during freezing, T. polonicum and T. durum exhibit less efficient stress responses, either through enzymatic bottlenecks or a lack of sustained defense. CONCLUSIONS: One of the most striking findings of this study is the observed dissociation between TtGR gene expression levels and enzyme activities. Low temperature limits the link between transcription and enzyme function. The primary determinant of low-temperature tolerance in T. turgidum subspecies is the sustainability of GR enzyme activity and GSH regeneration under freezing conditions.

Triticum↗
PubMed2024

Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data.

UNLABELLED: Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor-type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole-genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a data set of 39,787 solid tumors sequenced using a clinically targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivaling the performance of WGS-based methods. GDD-ENS can also guide diagnoses of rare type and cancers of unknown primary and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows could provide clinically relevant tumor-type predictions to guide treatment decisions in real time. SIGNIFICANCE: We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.

Humans↗
PubMed1979

Estimation of signal and noise spectra by special averaging techniques with application to a posteriori "Wiener" filtering.

This paper deals with the problem of separating the spectra of signal and noise in ensembles where the signal can be considered as an invariant component and the noise as a stationary additive background. Several methods are discussed and compared on the basis of a statistical analysis of the first two moments of the estimators for signal and noise spectra. As a consequence a procedure is proposed which provides a flexible compromise between estimation accuracy and computational effort. The application of this procedure to a posteriori "Wiener" filtering is compared with a more common, but time consuming, technique.

Electronics, Medical↗
PubMed2025

A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits.

BACKGROUND: DNA methylation (DNAm) provides a window to characterize the impacts of environmental exposures and the biological aging process. Epigenetic clocks are often trained on DNAm using penalized regression of CpG sites, but recent evidence suggests potential benefits of training epigenetic predictors on principal components. METHODOLOGY/FINDINGS: We developed a pipeline to simultaneously train three epigenetic predictors; a traditional CpG Clock, a PCA Clock, and a SuperLearner PCA Clock (SL PCA). We gathered publicly available DNAm datasets to generate i) a novel childhood epigenetic clock, ii) a reconstructed Hannum adult blood clock, and iii) as a proof of concept, a predictor of polybrominated biphenyl exposure using the three developmental methodologies. We used correlation coefficients and median absolute error to assess fit between predicted and observed measures, as well as agreement between duplicates. The SL PCA clocks improved fit with observed phenotypes relative to the PCA clocks or CpG clocks across several datasets. We found evidence for higher agreement between duplicate samples run on alternate DNAm arrays when using SL PCA clocks relative to traditional methods. Analyses examining associations between relevant exposures and epigenetic age acceleration (EAA) produced more precise effect estimates when using predictions derived from SL PCA clocks. CONCLUSIONS: We introduce a novel method for the development of DNAm-based predictors that combines the improved reliability conferred by training on principal components with advanced ensemble-based machine learning. Coupling SuperLearner with PCA in the predictor development process may be especially relevant for studies with longitudinal designs utilizing multiple array types, as well as for the development of predictors of more complex phenotypic traits.

DNA Methylation↗
PubMed2026

Integrative Network Analysis of Bioactive Compounds from Punica granatum L. Peel: Multi-Target Mechanisms in Wound Healing.

BACKGROUND: Wound-healing agents often have limited efficacy and require prolonged recovery times, prompting growing interest in developing herbal-based formulations. Among these, Punica granatum L. has attracted considerable attention because of its high polyphenolic content. Despite its widespread use, the precise pharmacological targets underlying its wound-healing effects remain poorly understood and require systematic investigation. OBJECTIVES: This study aimed to elucidate the underlying pharmacological mechanisms of the topical wound-healing properties of P. granatum L. using a network pharmacology approach. METHODS: Bioactive compounds of P. granatum L. and their potential target genes were identified using the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP), Similarity Ensemble Approach (SEA), and SwissTargetPrediction databases. Wound healing-related genes were retrieved from the GeneCards database. Genes intersecting P. granatum L. targets and wound healing-associated genes were subjected to functional enrichment analyses, including protein-protein interaction (PPI), Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses. The PPI network was further analyzed using Cytoscape, and the phytoconstituent-target interaction network was visualized using Gephi. These findings were validated using molecular docking. RESULTS: A total of 40 intersecting genes were identified as potential P. granatum L. targets involved in wound healing. Among these, EGFR, PTPN11, HRAS, IGF1R, and ESR1 were identified as key hub genes. Functional enrichment analysis indicated that the most significantly enriched signaling pathways included the MAPK, PI3K-Akt, EGFR tyrosine kinase inhibitor resistance, focal adhesion, and FoxO signaling pathways. Molecular docking analysis confirmed favorable binding of quercetin and ellagic acid to the hub targets EGFR, IGF1R, and ESR1. CONCLUSIONS: These findings elucidate the pharmacological pathways underlying P. granatum-mediated wound healing and suggest that P. granatum L. acts as a multi-target modulator in the wound-healing process.

Focal Adhesion↗
PubMed2025

Annotation matters: the effect of structural gene annotation on orthology inference.

MOTIVATION: In silico gene annotation, the process of identifying the genes present in a genome, remains a challenging task. As genome assemblies rapidly increase, the corresponding gene models and repertoires often fall short in quality. Despite advances in annotation methods, a lack of community standards means that most published gene annotations result from ad hoc pipelines. As a result, only a few species have nearly complete and accurate gene models. This annotation quality is thought to affect downstream analyses, including orthology inference, often the first step of comparative genomics studies. RESULTS: We show that different annotation methods yield markedly distinct orthology inferences. We compared orthology assignments of gene models obtained by four prominent protein-coding gene model sources: the NCBI Eukaryotic Genome Annotation Pipeline, the Ensembl Gene Annotation System, the UniProt Reference Proteomes, and Augustus 3.4 (an ab initio pipeline). We observe significant discrepancies between sources, namely in the proportion of orthologous genes per genome, the completeness of Hierarchical Orthologous Groups, and the accuracy and recall of the predicted orthologs on a standard orthology benchmark.

Molecular Sequence Annotation↗
PubMed2025

In silico prediction method for plant Nucleotide-binding leucine-rich repeat- and pathogen effector interactions.

Plant Nucleotide-binding leucine-rich repeat (NLR) proteins play a crucial role in effector recognition and activation of Effector triggered immunity following pathogen infection. Genome sequencing advancements have led to the identification of a myriad of NLRs in numerous agriculturally important plant species. However, deciphering which NLRs recognize specific pathogen effectors remains challenging. Predicting NLR-effector interactions in silico will provide a more targeted approach for experimental validation, critical for elucidating function, and advancing our understanding of NLR-triggered immunity. In this study, NLR-effector protein complex structures were predicted using AlphaFold2-Multimer for all experimentally validated NLR-effector interactions reported in literature. Binding affinities- and energies were predicted using 97 machine learning models from Area-Affinity. We show that AlphaFold2-Multimer predicted structures have acceptable accuracy and can be used to investigate NLR-effector interactions in silico. Binding affinities for 58 NLR-effector complexes ranged between -8.5 and -10.6 log(K), and binding energies between -11.8 and -14.4 kcal/mol-1, depending on the Area-Affinity model used. For 2427 "forced" NLR-effector complexes, these estimates showed larger variability, enabling identification of novel NLR-effector interactions with 99% accuracy using an Ensemble machine learning model. The narrow range of binding energies- and affinities for "true" interactions suggest a specific change in Gibbs free energy, and thus conformational change, is required for NLR activation. This is the first study to provide a method for predicting NLR-effector interactions, applicable to all pathosystems. Finally, the NLR-Effector Interaction Classification (NEIC) resource can streamline research efforts by identifying NLRs important for plant-pathogen resistance, advancing our understanding of plant immunity.

Plant Proteins↗
PubMed2026

Seeing and Feeling DNA Methylation: Single-Molecule Biophysics Meets Machine Learning.

DNA methylation at 5-methylcytosine (5mC) is crucial for embryonic development and cellular function, while aberrant patterns strongly drive disease onset and progression. Its reversible nature offers substantial therapeutic potential, emphasizing the need for precise, context-specific genome wide 5mC mapping. Conventional techniques such as bisulfite sequencing and ensemble biosensor assays are hindered by DNA degradation, amplification bias, high cost, and inability to resolve single-molecule structural and mechanical effects of methylation. This review examines advances in single-molecule biophysical methods (nanopore sensing, smFRET, optical/magnetic tweezers, and AFM) that provide direct, label-free/minimally invasive 5mC detection, along with quantitative insights into DNA conformation, mechanics, and protein-DNA interactions. These techniques complement traditional methylome mapping by linking genomic localization to molecular mechanisms. Emerging machine-learning approaches are revolutionizing analysis, particularly in nanopore sensing, while promising applications in smFRET, tweezers, and AFM address throughput and reproducibility challenges. Their convergence promises scalable, high-resolution epigenetic profiling, advancing precision epigenomics toward clinical application.

DNA Methylation↗
PubMed2025

MaxComp: Predicting single-cell chromatin compartments from 3D chromosome structures.

The genome is organized into distinct chromatin compartments with at least two main classes, a transcriptionally active A and an inactive B compartment, broadly corresponding to euchromatin and heterochromatin. Chromatin regions within the same compartment preferentially interact with each other over regions in the opposite compartment. A/B compartments are traditionally identified from ensemble Hi-C contact frequency matrices using principal component analysis of their covariance matrices. However, defining compartments at the single-cell level from sparse single-cell Hi-C data is challenging, especially since homologous copies are often not resolved. To address this, we present MaxComp, an unsupervised method, for inferring single-cell A/B compartments based on 3D geometric considerations in single-cell chromosome structures-derived either from multiplexed FISH-omics imaging or 3D structure models derived from Hi-C data. By representing each 3D chromosome structure as an undirected graph with edge-weights encoding structural information, MaxComp reformulates compartment prediction as a variant of the Max-cut problem, solved using semidefinite graph programming (SPD) to optimally partition the graph into two structural compartments. Our results show that the population average of MaxComp single-cell compartment annotations closely matches those derived from ensemble Hi-C principal component analysis, demonstrating that compartmentalization can be recovered from geometric principles alone, using only the 3D coordinates and nuclear microenvironment of chromatin regions. Our approach reveals widespread cell-to-cell variability in compartment organization, with substantial heterogeneity across genomic loci. When applied to multiplexed FISH imaging data, MaxComp also uncovers relationships between compartment annotations and transcriptional activity at the single-cell level. In summary, MaxComp offers a new framework for understanding chromatin compartmentalization in single cells, connecting 3D genome architecture, and transcriptional activity with the cell-to-cell variations of chromatin compartments.

Chromatin↗
PubMed2026

Dynamic evolution of chaperone-mediated autophagy is associated with tumor microenvironment remodeling and prognostic stratification in lung adenocarcinoma: insights from single-cell transcriptomics, ensemble machine learning, and experimental validation.

BACKGROUND: Lung adenocarcinoma (LUAD) shows prognostic heterogeneity, and tumor-node-metastasis (TNM) staging is limited for individualized management. Chaperone-mediated autophagy (CMA) maintains proteostasis, but its role during adenocarcinoma in situ (AIS)-minimally invasive adenocarcinoma (MIA)-invasive adenocarcinoma (IAC) progression remains unclear. METHODS: Single-cell RNA sequencing (scRNA-seq) data from GSE189357 and bulk transcriptomes from The Cancer Genome Atlas (TCGA)-LUAD and Gene Expression Omnibus (GEO) cohorts were integrated. CMA activity, cell-cell communication, weighted gene co-expression network analysis (WGCNA), tumor-normal differential expression, machine-learning survival modeling, tumor microenvironment (TME) features, drug sensitivity, and EPC1 function were analyzed. RESULTS: CMA-high tumor epithelial cells increased from AIS (58.1%) to MIA (65.7%) but declined in IAC (44.4%; p < 0.001). CMA-low cells preferentially received fibroblast-derived extracellular matrix cues. A CMA-negatively correlated module identified 69 core genes. Random survival forest (RSF) performed best among 117 machine-learning combinations (mean concordance index > 0.873). High-risk patients had worse survival across cohorts, and the risk score was independently associated with overall survival (hazard ratio = 16.013, 95% confidence interval: 9.579-26.768, p < 0.001). High-risk tumors showed proliferative activation and M0 macrophage enrichment, whereas low-risk tumors showed stronger immune-related signaling. EPC1 overexpression suppressed malignant phenotypes in A549 cells. CONCLUSION: CMA dynamics are associated with stromal and immune remodeling during LUAD progression. A CMA-based model provides robust prognostic stratification and may offer a basis for future TME-guided studies.

Chaperone-mediated autophagy↗
PubMed2026

ViralQC: a tool for assessing completeness and contamination of predicted viral contigs.

MOTIVATION: Viruses represent the most abundant biological entities on Earth, playing vital roles in diverse ecosystems. Cataloging viruses across various environments is essential for understanding their properties and functions. Metagenomic sequencing has emerged as the most comprehensive method for virus discovery. However, distinguishing viral sequences from the vast background of microbial organisms in metagenomic data remains a significant challenge. Existing tools experience varying degrees of false positive rates due to noise in sequencing and assembly, and the integration of proviruses into microbial genomes. This highlights the urgent need for an accurate and efficient method to evaluate the quality of viral contigs. RESULTS: To address these challenges, we introduce ViralQC, a tool designed to assess the quality of viral contigs or bins. ViralQC identifies microbial contamination within putative viral sequences using an ensemble framework powered by DNA and protein foundation models and estimates completeness by analyzing protein organization. We evaluated ViralQC on multiple datasets and compared its performance against the state-of-the-art tool, CheckV. Leveraging both DNA and protein foundation models, ViralQC achieves higher sensitivity on contamination detection for contigs longer than 10 kbp while maintaining comparable accuracy. Additionally, ViralQC delivers more accurate estimation on contigs with completeness&#x2009;>&#x2009;50%. AVAILABILITY: The source code of ViralQC is available via: https://github.com/ChengPENG-wolf/ViralQC.

Software↗
PubMed2025

The Effect of Alcohol Intake on Brain White Matter Microstructural Integrity: A New Causal Inference Framework for Incomplete Phenomic Data.

Although substance use, such as alcohol intake, is known to be associated with cognitive decline during aging, its direct influence on the central nervous system remains incompletely understood. In this study, we investigate the influence of alcohol intake frequency on reduction of brain white matter microstructural integrity in the fornix, a brain region considered a promising marker of age-related microstructural degeneration, using a large UK Biobank (UKB) cohort with extensive phenomic data reflecting a comprehensive lifestyle profile. Two major challenges arise: (a) potentially nonlinear confounding effects from phenomic variables and (b) a limited proportion of participants with complete phenomic data. To address these challenges, we develop a novel ensemble learning framework tailored for robust causal inference and introduce a data integration step to incorporate information from UKB participants with incomplete phenomic data, improving estimation efficiency. Our analysis reveals that daily alcohol intake may significantly reduce fractional anisotropy, a neuroimaging-derived measure of white matter structural integrity, in the fornix and increase systolic and diastolic blood pressure levels. Moreover, extensive numerical studies demonstrate the superiority of our method over competing approaches in terms of estimation bias, while outcome regression-based estimators may be preferred when minimizing mean squared error is prioritized. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Brain aging↗