SEARCH · PubMed Health

Results for “Supervised Machine Learning”

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

PubMed2025

MyESL: A Software for Evolutionary Sparse Learning in Molecular Phylogenetics and Genomics.

Evolutionary sparse learning uses supervised machine learning to build evolutionary models where genomic sites loci are parameters. It uses the Least Absolute Shrinkage and Selection Operator with bi-level sparsity to connect a specific phylogenetic hypothesis with sequence variation across genomic loci. The MyESL software addresses the need for open-source tools to perform evolutionary sparse learning analyses, offering features to preprocess input phylogenomic alignments, post-process output models to generate molecular evolutionary metrics, and make Least Absolute Shrinkage and Selection Operator regression adaptable and efficient for phylogenetic trees and alignments. The core of MyESL, which constructs models with logistic regressions using bi-level sparsity, is written in C++. Its input data preprocessing and result post-processing tools are developed in Python. Compared to other tools, MyESL is more computationally efficient and provides evolution-friendly inputs and outputs. These features have already enabled the use of MyESL in two phylogenomic applications, one to identify outlier sequences and fragile clades in inferred phylogenies and another to build genetic models of convergent traits. In addition to the use in a Python environment, MyESL is available as a standalone executable compatible across multiple platforms, which can be directly integrated into scripts and third-party software. The source code, executable, and documentation for MyESL are openly accessible at https://github.com/kumarlabgit/MyESL.

Phylogeny↗

PubMed2026

Machine learning-enabled multi-omics discovery of prognostic biomarkers and signaling targets in pancreatic cancer.

Pancreatic ductal adenocarcinoma (PDAC) remains difficult to subtype using single omics layers. We conducted an exploratory investigation integrating reverse-phase protein array (RPPA) and DNA methylation data from the cancer genome atlas (TCGA)- pancreatic adenocarcinoma (PAAD) to assess the feasibility of multi-omics subtyping, alongside a supervised machine learning analysis of a small gene expression omnibus (GEO) transcriptomic cohort (n = 26) to identify candidate diagnostic genes. RPPA-based K-means clustering suggested a weak, possible two-subtype structure (silhouette ≈ 0.16) that remained unassociated with overall survival (log-rank p = 0.113) and lacked independent prognostic value. An independently performed similarity network fusion (SNF) analysis integrating RPPA and methylation data showed low concordance with RPPA-derived subtypes (Adjusted Rand Index (ARI) = 0.014), indicating limited convergence between molecular modalities. Supervised machine learning analysis of the GEO cohort using a fully nested leave-one-out cross-validation pipeline achieved a mean (area under the curve) AUC of 0.896 across four classifiers and identified four-fold-stable candidate genes (ESCO2, COL17A1, BCL2L14, and SOWAHB). However, this gene panel demonstrated limited external validity across two independent PDAC cohorts (log-rank p = 0.438 for both GSE62452 and GSE28735), indicating limited generalizability despite robust internal performance. Collectively, these findings provide limited evidence for a robust, prognostically significant multi-omics subtype or a validated diagnostic gene signature; instead, this study serves as a hypothesis-generating resource and highlights the importance of rigorous cross-validation and independent external validation in small-sample transcriptomic biomarker discovery.

Humans↗

PubMed2025

Federated learning for the pathogenicity annotation of genetic variants in multi-site clinical settings.

MOTIVATION: Rare diseases collectively affect 5% of the population. However, fewer than 50% of rare disease patients receive a molecular diagnosis after whole genome sequencing. Supervised machine learning is a valuable approach for the pathogenicity scoring of human genetic variants. However, existing methods are often trained on curated but limited central repositories, resulting in poor accuracy when tested on external cohorts. Yet, large collections of variants generated at hospitals and research institutions remain inaccessible to machine-learning purposes because of privacy and legal constraints. Federated learning (FL) algorithms have been recently developed enabling institutions to collaboratively train models without sharing their local datasets. RESULTS: Here, we present a proof-of-concept study evaluating the effectiveness of FL for the clinical classification of genetic variants. A comprehensive array of diverse FL strategies was assessed for coding and non-coding Single Nucleotide Variants as well as Copy Number Variants. Our results showed that federated models generally achieved comparable or superior performance to traditional centralized learning. In addition, federated models reached a robust generalization to independent sets with smaller data fractions as compared to their centralized model counterparts. Our findings support the adoption of FL to establish secure multi-institutional collaborations in human variant interpretation. AVAILABILITY AND IMPLEMENTATION: All source code required to reproduce the results presented in this article, implemented in Python, is available under the GNU General Public License v3 at https://github.com/RausellLab/FedLearnVar.

Humans↗

PubMed2026

Development and Validation of Machine Learning Models for Predicting Early Cognitive Decline Using Home Sensor-Derived Behavioral Data: Sensors in-Home for Elder Wellbeing (SINEW) Cohort Study.

BACKGROUND: As the global population continues to age, the prevalence of geriatric conditions, including dementia and frailty, is also increasing. Early identification of individuals at an elevated risk of these conditions, such as those presenting with mild cognitive impairment (MCI) or prefrailty, can provide a critical window for prompt intervention aimed at preventing or reversing disease progression. To promote such early identification, there is a burgeoning interest in the use of digital sensor technology and predictive modeling. OBJECTIVE: This study aimed to use a continuous, home-based monitoring sensor system for older adults to distinguish those exhibiting normal aging from those with MCI, early dementia, prefrailty, or frailty, and to predict their transition from normal aging to one of these conditions. METHODS: This longitudinal cohort study will recruit 200 community-dwelling adults aged ≥65 years with normal cognition or MCI at baseline. A multi-sensor system will be installed in participants' homes, including passive infrared motion sensors, door contact sensors, bed sensors, medication box sensors, wearable activity bands, and Bluetooth proximity beacons. These devices will continuously capture spatiotemporal activity patterns, mobility indicators, sleep behaviors, and medication-taking routines. Annual assessments will include standardized cognitive tests (eg, Montreal Cognitive Assessment, Mini-Mental State Examination, Rey Auditory-Verbal Learning Test, digit span, Color Trails Test, semantic fluency, Stroop), frailty measures (modified Fried phenotype, gait speed, grip strength), mental health scales, sleep quality, and psychosocial indicators. Sensor-derived features-such as gait variability, activity regularity, sleep fragmentation, and medication adherence patterns-will be integrated with clinical data to develop supervised machine learning models. Planned approaches include logistic regression, random forests, gradient boosting, and deep learning. Model performance will be evaluated using cross-validation and independent test sets. Primary metrics will include area under the receiver operating characteristic curve, sensitivity, specificity, precision, recall, and F1-score. Models will be benchmarked against gold-standard clinical diagnoses and validated using temporal subsets of the dataset. RESULTS: Enrollment for this study started in November 2019 and will continue until March 2030. As of June 2025, we have enrolled 138 participants. Full data analysis has yet to begin. CONCLUSIONS: We aim to develop a reliable and effective sensor system for in-home use that will facilitate the early detection of cognitive and physical decline. In so doing, it will add to our current understanding of digital biomarkers. It is common for older adults to seek clinical intervention only when their cognitive impairment has already reached an advanced stage. The implementation of readily deployable sensor systems within community settings presents us with opportunities for prompt intervention, which holds the potential for delaying or reversing disease progression and allowing for a greater number of functional and meaningful years.

Humans↗

PubMed2025

Alzheimer's subtypes A supervised, unsupervised, multimodal, multilayered embedded recursive (SUMMER) AI study.

Since Alzheimer's disease (AD) is a heterogeneous disease, different subtypes may have distinct biological, genetic, and clinical characteristics, requiring tailored interventions. While several proposed subtypes of AD exist, there is still no clear consensus on a definitive classification. By leveraging complementary AI approaches, including supervised and unsupervised learning, within a recursive pipeline (SUMMER) that integrates multimodal datasets encompassing MRI measurements, phenotypes, and genetic data, our goal was to generate robust scientific evidence for identifying AD subtypes. Data was downloaded from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and included neuroimaging data (MRI), genetics (SNPs), clinical diagnosis, and demographics. 1133 European American participants' images, aged 55-95, were included in this study. The analysis was multi-fold, where the first step involved applying an unsupervised application to a subset of the MRI sample (AD + cognitively normal (CN) aged matched groups, 100 men aged 68-85 years, and 76 women aged 68-85 years). The MRI brain gray matter was segmented into 44 regions of interest (ROIs) according to a standard atlas, and 618 features were extracted, including ROI voxel intensity measurements such as minimum, maximum, and histogram variables. Results identified a cluster of subtype AD men and a cluster of subtype AD women that were distinct from the rest of their respective samples. In the next step, the integrity of the identified subtype AD clusters was investigated using the XGBoost supervised machine learning application with genetic features (SNPs, N=36,724) and labels: the identified subtype AD cluster vs. the rest of the sample, stratified by sex. A significant AD subtype men model (accuracy=0.85, F1=0.72, AUC=0.83) and a significant women AD subtype model (accuracy=0.81, F1=0.81, AUC=0.81) were built, confirming the homogeneity of the isolated AD subtype clusters. Discriminative biomarkers were extracted from the significant models, including selected ROIs and SNPs. Finally, the subtype models were tested on an unseen subset of ADNI data. The genetic-based models identified clusters of AD subtype participants consisting of 34% of the men AD group and 47% of the women AD group. Phenotypic analysis indicates that lower body weight was associated with the women's AD subtype. Complex diseases like AD demand a sophisticated, multimodal approach for precise diagnosis. Effectively identifying disease subtypes enhances the potential for personalized treatment, ultimately improving patient outcomes.

Journal Article↗

PubMed2026

Social disconnection integrates genetic and proteomic risks in suicidal ideation and depression.

Suicidal ideation (SI) and major depressive disorder (MDD) are complex psychiatric conditions arising from the interplay of genetic liability, molecular processes, and psychosocial factors. While these dimensions have been extensively studied in isolation, their joint contribution to SI and MDD remains unclear. This study integrates multi-modal data to elucidate these synergistic effects and develop robust models for individual-level risk stratification. Leveraging longitudinal multi-modal data from 13,085 UK Biobank participants, we integrated genomic, proteomic, and social connection profiles. We developed interpretable risk scores using a rigorous supervised machine learning framework encompassing diverse linear and ensemble classifiers. Permutation importance was employed to quantify feature contributions and derive transparent, weighted risk metrics across diverse classifiers. These scores were validated through association, interaction, and mediation analyses. Social connection-based risk scores significantly differentiated cases and controls across the two suicidal ideation phenotypes at 2017 and 2023 with cross-sectional analyses (AUCs: 0.70 - 0.73), outperforming proteomic-only models. Functional dimensions of social connection emerged as the most informative predictors. Longitudinal analyses revealed that social risk scores at baseline predicted suicidal ideation onset six years later, independent of demographic covariates. Interaction analyses demonstrated that polygenic risk for suicide attempt significantly interacted with both social and proteomic risk features in relation to depression. Structural equation models further confirmed that social disconnection acts as a key mediator linking genetic predisposition to MDD and SI. Social disconnection is a critical risk factor mediating the impact of genetic vulnerability on psychiatric outcomes. Integrating social, genetic, and molecular data supports a multilevel framework for risk stratification and highlights the potential of socially oriented interventions to mitigate biological risk.

Humans↗

PubMed2026

An encyclopedia of human enhancer-gene regulatory interactions.

Identifying transcriptional enhancers and their target genes is essential for understanding gene regulation and the effect of human genetic variation on disease1-6. Here we create and evaluate a resource of more than 92 million enhancer-gene regulatory interactions across 1,458 biosamples covering 369 cell types and tissues, by integrating predictive models, chromatin states, three-dimensional contacts and large-scale genetic perturbations generated by the ENCODE Consortium7. We first create a systematic benchmarking pipeline to compare predictive models, assembling a dataset of 10,356 element-gene pairs measured in CRISPR perturbation experiments, more than 30,000 fine-mapped expression quantitative trait loci and 569 fine-mapped genome-wide association study (GWAS) variants linked to a probable causal gene. Using this framework, we develop ENCODE-rE2G, a predictive model achieving state-of-the-art performance across several prediction tasks, demonstrating that iterative perturbations and supervised machine learning can build increasingly accurate predictive models of enhancer regulation. Using ENCODE-rE2G, we build an encyclopedia of enhancer-gene regulatory interactions in the human genome, revealing global properties of enhancer networks, identifying differences in regulatory complexity across genes and improving analyses linking noncoding variants to target genes and cell types for common complex diseases. By interpreting the model, we find that beyond enhancer activity and three-dimensional enhancer-promoter contacts, additional features that guide enhancer-promoter communication include promoter class and enhancer-enhancer synergy. These genome-wide maps of enhancer-gene regulatory interactions, benchmarking software, predictive models and insights about enhancer function provide a valuable resource for future studies of gene regulation and human genetics.

Humans↗

PubMed2026

A validated, modifiable proteomic score from the EXSCEL trial predicts cardiovascular events in diabetes.

BACKGROUNDAdults with type 2 diabetes mellitus (T2DM) are at increased risk for stroke, myocardial infarction, and cardiovascular death, yet individual risk is heterogeneous and incompletely captured by clinical models.METHODSIn the Exenatide Study of Cardiovascular Event Lowering (EXSCEL), adults with T2DM were randomized to a GLP-1 RA (exenatide) or a placebo and followed longitudinally for major adverse cardiovascular events (MACE). High-throughput discovery proteomics was done in plasma collected at baseline and 12 months. Proteins associated with time to MACE were identified using multivariable regression and incorporated into supervised machine learning models. A multi-protein score was developed and externally validated in 2 independent population-based and trial cohorts.RESULTSThe proteomic score showed incremental improvement in cardiovascular risk discrimination beyond clinical factors alone, and several proteins were consistently prioritized across modeling approaches. The protein score and a top-ranked protein, tetranectin, were modified by GLP-1 RA treatment, and a decrease in protein score was associated with improved outcomes, supporting modifiability of MACE risk.CONCLUSIONExternal validation confirmed generalizability across cohorts with and without diabetes. Together, these findings demonstrate that plasma proteomic signatures can enhance cardiovascular risk stratification and identify treatment-responsive biomarkers in T2DM, supporting their potential role in precision prevention strategiesFUNDINGThe EXSCEL study was funded by Amylin Pharmaceuticals. This research was supported by contracts HHSN268201200036C, HHSN268200800007C, HHSN268201800001C, N01HC55222, N01HC85079, N01HC85080, N01HC85081, N01HC85082, N01HC85083, N01HC85086, 75N92021D00006, and grants R01HL146145, U01HL080295, U01HL130114, R01HL172803, and R01HL144483 from the National Heart, Lung, and Blood Institute, with additional contribution from the National Institute of Neurological Disorders and Stroke. Additional support was provided by R01AG023629 from the National Institute on Aging.

Aged↗

PubMed2025

Tumor-immune partitioning and clustering algorithm for identifying tumor-immune cell spatial interaction signatures within the tumor microenvironment.

BACKGROUND: Growing evidence supports the importance of characterizing the organizational patterns of various cellular constituents in the tumor microenvironment in precision oncology. Most existing data on immune cell infiltrates in tumors, which are based on immune cell counts or nearest neighbor-type analyses, have failed to fully capture the cellular organization and heterogeneity. METHODS: We introduce a computational algorithm, termed Tumor-Immune Partitioning and Clustering (TIPC), that jointly measures immune cell partitioning between tumor epithelial and stromal areas and immune cell clustering versus dispersion. As proof-of-principle, we applied TIPC to a prospective cohort incident tumor biobank containing 931 colorectal carcinoma cases. TIPC identified tumor subtypes with unique spatial patterns between tumor cells and T lymphocytes linked to certain molecular pathologic and prognostic features. T lymphocyte identification and phenotyping were achieved using multiplexed (multispectral) immunofluorescence. In a separate hepatocellular carcinoma cohort, we replaced the stromal component with specific immune cell types-CXCR3+CD68+ or CD8+-to profile their spatial relationships with CXCL9+CD68+ cells. RESULTS: Six unsupervised TIPC subtypes based on T lymphocyte distribution patterns were identified, comprising two cold and four hot subtypes. Three of the four hot subtypes were associated with significantly longer colorectal cancer (CRC)-specific survival compared to a reference cold subtype. Our analysis showed that variations in T-cell densities among the TIPC subtypes did not strictly correlate with prognostic benefits, underscoring the prognostic significance of immune cell spatial patterns. Additionally, TIPC revealed two spatially distinct and cell density-specific subtypes among microsatellite instability-high colorectal cancers, indicating its potential to upgrade tumor subtyping. TIPC was also applied to additional immune cell types, eosinophils and neutrophils, identified using morphology and supervised machine learning; here two tumor subtypes with similarly low densities, namely 'cold, tumor-rich' and 'cold, stroma-rich', exhibited differential prognostic associations. Lastly, we validated our methods and results using The Cancer Genome Atlas colon and rectal adenocarcinoma data (n = 570). Moreover, applying TIPC to hepatocellular carcinoma cases (n = 27) highlighted critical cell interactions like CXCL9-CXCR3 and CXCL9-CD8. CONCLUSIONS: Unsupervised discoveries of microgeometric tissue organizational patterns and novel tumor subtypes using the TIPC algorithm can deepen our understanding of the tumor immune microenvironment and likely inform precision cancer immunotherapy.

Humans↗

PubMed2026

Machine Learning and Metabolomics to Characterize Warburg-Like Metabolic Subtypes in Human Retinal Endothelial Cells Exposed to Risk Factors Associated With Proliferative Diabetic Retinopathy.

PURPOSE: High glucose (HG), hypoxia (Hyp), and their combination are major risk factors for proliferative diabetic retinopathy (PDR). Although these conditions induce features of the Warburg-like metabolic reprogramming in human retinal endothelial cells (HRECs), it remains unclear whether they produce distinct metabolic and angiogenic subtypes. This study aimed to characterize the Warburg-like-associated metabolic heterogeneity induced by these PDR-related risk factors and evaluate the ability of supervised machine-learning models to distinguish these subtypes. METHODS: HRECs were cultured under normoglycemic, HG, Hyp (2% O2), and combined HG-Hyp conditions. Untargeted LC-MS/MS metabolomics quantified metabolites spanning carbohydrates, amino acids, nucleotides, and lipids. Principal component analysis (PCA) assessed overall metabolic variation, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis identified metabolic pathways associated with angiogenesis. In vitro angiogenesis assays measured endothelial tube formation and branching. Nine supervised classifiers (decision tree, logistic regression, naïve Bayes, random forest, K-Nearest Neighbors, neural network, gradient boosting, AdaBoost, and Support Vector Machine) were trained on the highest-ranked metabolites selected by the Information Gain Ratio feature-ranking approach. Model performance was evaluated using 10-fold cross-validation, leave-one-out cross-validation (LOOCV), permutation testing, and a classifier stability analysis under biologically meaningful distributional shift using an independent chemically induced hypoxia model (CoCl2). RESULTS: PCA revealed partial separation of metabolic profiles across conditions, indicating different Warburg-like metabolic subtypes. The combined HG-Hyp condition exhibited enhanced angiogenic potential relative to either HG or Hyp alone. KEGG pathway enrichment analysis identified fatty acid biosynthesis and elongation among the most significantly enriched pathways in HRECs under combined HG-Hyp conditions, alongside amino sugar and nucleotide sugar metabolism, glycerophospholipid metabolism, the pentose phosphate pathway, and glycolysis/gluconeogenesis. Supervised machine-learning classifiers distinguished these metabolic subtypes, with AdaBoost and gradient Boosting showing the most balanced, reproducible performance across 10-fold cross-validation, LOOCV, and permutation testing, and remaining the most reliable classifiers under domain-shift testing (area under the curve = 0.88, P = 0.0061). CONCLUSIONS: In this exploratory analysis, HG, Hyp, and their combination drive metabolically and functionally distinct subtypes of Warburg-like metabolic reprogramming in HRECs, with HG-Hyp in combination producing a highly angiogenic phenotype. Boosting-based ensemble classifiers provide a promising framework for detecting these subtypes even under domain-shift conditions, warranting validation in larger independent datasets. TRANSLATIONAL RELEVANCE: Integrating metabolomics with machine-learning classification offers a strategy to identify Warburg-like metabolic subtypes in retinal endothelial cells, providing insights into angiogenic mechanisms and guiding the development of targeted diagnostics or therapeutics for PDR.

Humans↗

PubMed2026

NanoSSL: attention mechanism-based self-supervised learning method for protein identification using nanopores.

MOTIVATION: Nanopores are cutting-edge interdisciplinary tools that can analyze biomolecules at the single-molecule level for many applications, e.g. DNA sequencing. Efforts are underway to extend nanopores to proteomics, including the development of machine learning algorithms for protein sequencing and identification. However, single-molecule data are intrinsically noisy and hard to process. Moreover, the development and performance of machine learning for nanopore is jeopardized by data scarcity. Self-supervised learning is an emerging method that may yield advantages in nanopore scenarios. RESULTS: We propose and experimentally validate Nanopore analysis using Self-Supervised Learning (NanoSSL), a generative self-supervised learning framework based on attention mechanisms for the identification of protein signals from nanopores. Leveraging a two-step approach consisting of self-supervised pre-training and supervised fine-tuning, NanoSSL learns useful feature representations from empirical data to facilitate downstream classification tasks. Inspired by the concept of fragmentation in conventional protein sequencing technologies, during pretraining each translocation event is split into multiple non-overlapping fragments of equal size, some of which are randomly masked and reconstructed using a masked autoencoder. Learning the feature representations of the reconstructed nanopore events facilitates molecular identification in fine-tuning. In this study, we retested a publicly available nanopore multiplexed protein sensing dataset for model iteration, and subsequently measured Alzheimer's disease biomarker Aβ1-42 using homemade solid-state nanopores. Empirical results indicated NanoSSL achieved an unprecedented performance across four metrics: accuracy, precision, recall, and F1 score, when classifying two mutated Aβ1-42, E22G and G37R. The self-supervised learning and attention mechanism were verified as the source of performance gains. AVAILABILITY AND IMPLEMENTATION: The main program is available at https://doi.org/10.5281/zenodo.17172822.

Nanopores↗

PubMed2025

SIGEL: a context-aware genomic representation learning framework for spatial genomics analysis.

Spatial transcriptomics (ST) integrates spatial information into genomics, yet methods for generating spatially-informed gene representations are limited and computationally intensive. We present SIGEL, a cost-effective framework that derives gene manifolds from ST data by exploiting spatial genomic context. The resulting SIGEL-generated gene representations (SGRs) are context-aware, biologically meaningful, and robust across samples, making them highly effective for key downstream tasks, including imputing missing genes, detecting spatial expression patterns, identifying disease-related genes and interactions, and improving spatial clustering. Extensive experiments across diverse ST datasets validate SIGEL's effectiveness and highlight its potential in advancing spatial genomics research.

Genomics↗

PubMed2026

Fairness-aware supervised hierarchical contrastive semantic learning for sexual dimorphism analysis.

MOTIVATION: Sexual dimorphism is a fundamental biological determinant driving systematic differences in disease susceptibility, progression, and clinical outcomes. However, current sex-combined AI-based genomic models often exhibit algorithmic bias and fail to capture these sex-specific mechanisms, creating a critical barrier to unbiased precision medicine. Ensuring fairness in the context of sexual dimorphism requires understanding and addressing the distinct biological mechanisms functioning in each sex, rather than focusing solely on equalizing predictive performance. RESULTS: We propose a fairness-aware supervised hierarchical contrastive learning approach, called FairHICON, to discover unbiased sex-common and sex-specific predictive features. Evaluations on cancer and asthma transcriptomic datasets demonstrate that FairHICON significantly outperforms state-of-the-art benchmarks, improving predictive performance by up to 9% while effectively reducing the performance gap between male and female sexes. Furthermore, prognostic validation confirms that the identified sex-specific pathways stratify patient survival significantly better within their corresponding sex groups. This validates FairHICON to elucidate the molecular heterogeneity of sexual dimorphism, advancing inclusive precision medicine. AVAILABILITY AND IMPLEMENTATION: The source code and data is available at https://github.com/datax-lab/FairHICON.

Sex Characteristics↗

PubMed2026

Linking MRI radiomics to transcriptomics-based radiosensitivity in lower-grade glioma: A radiogenomic framework.

BACKGROUND: RSI is a transcriptomics-based biomarker associated with radiotherapy outcomes, but its clinical application is constrained by the requirement for tumor tissue and RNA sequencing. This study investigates whether MRI-derived radiomic features can reflect RSI-defined intrinsic radiosensitivity in lower-grade glioma.This addresses a critical gap arising from the limited availability of matched imaging and genomic data in routine clinical practice. METHODS: MRI-derived radiomic features were extracted from FLAIR images of lower-grade glioma patients obtained from TCIA and matched with transcriptomic data from TCGA. A total of 107 patients with both MRI and RNA sequencing data were included in the radiogenomic analysis. Radiomic features were ranked using a Borda-based ensemble feature selection strategy. Five supervised machine-learning classifiers were trained to predict RSI-based radiosensitivity classification, and model interpretability was assessed using SHAP within radiogenomic framework. RESULTS: Classification performance increased with feature number and stabilized at compact subset of 13 radiomic features. Logistic regression showed stable performance with an AUC of 0.82 (95 % CI: 0.71-0.93). SHAP analysis indicated that heterogeneity-related texture features were dominant contributors to model predictions, with many associated with the RR phenotype, while others were linked to the RS phenotype. CONCLUSION: An MRI-based radiomic signature enables non-invasive prediction of RSI-defined radiosensitivity in lower-grade glioma. Rather than offering an immediately deployable clinical tool, this study establishes a proof-of-concept radiogenomic framework demonstrating that intrinsic radiosensitivity, traditionally assessed through invasive molecular assays, can be approximated using quantitative imaging features. These findings highlight the potential of imaging-based radiosensitivity assessment and provide a foundation for future radiogenomic investigations.

Lower-grade glioma↗

PubMed2025

AncestryGeni: a novel genetic ancestry classification pipeline for small and noisy sequence data.

MOTIVATION: Efforts to address health disparities are often limited by the lack of robust computational tools for inferring genetic ancestry by calculating an individual's genetic similarity to continental groups. We have already shown that a preferred alternative to self-described race is using ancestry-informative markers (AIMs) that can be classified into ancestral components and used to estimate their similarity to those of known populations to identify continental groups. However, real-world genomic data can present challenges, including limited availability of germline DNA, a small number of AIMs for each sample, and the use of different variant calling software, limiting the application of existing solutions. RESULTS: Here, we describe a novel supervised machine-learning tool AncestryGeni, which infers genetic ancestry for samples with even a hundred markers and is applicable to any genomic data, including whole exome sequencing (WES) and RNA sequencing (RNA-Seq) data. Applying AncestryGeni to a real-world genomic dataset obtained from the Multiple Myeloma Research Foundation (MMRF) CoMMpass study, we show that it is more accurate than the commonly used FastNGSadmix when using nonstandard genomic material. We also demonstrate that when using AncestryGeni, the tumor-derived sequence obtained from WES and RNA-Seq can be a robust data source to accurately estimate an individual's genetic similarity to a continental group. AVAILABILITY AND IMPLEMENTATION: AncestryGeni pipeline is available at https://github.com/eelhaik/AncestryGeni/tree/main.

Humans↗

PubMed2026

GUANinE v1.1 reveals complementarity of supervised and genomic language models.

There has been much debate about the benefits of supervised versus unsupervised learning on genomes. Determining which is better in what contexts requires developing comprehensive benchmarks spanning functional and evolutionary tasks. Importantly, such benchmarks need large sample sizes to enable well-powered ranking of models. Having developed and applied such a benchmark here (GUANinE v1.1), we conclusively demonstrate each paradigm offers key advantages and outperforms on certain tasks. In accordance with training, supervised sequence-to-function models exhibit strong performance when annotating functional states characterized by chromatin accessibility or histone marks, while self-supervised language models outperform on evolutionary conservation. Our hundreds of new evaluations in this v1.1 expansion provide evidence for a tradeoff between input context size and model parameter count for a fixed compute budget, which we depict with new metrics such as kiloparameters/base pair. We also construct two new large-scale variant interpretation tasks in v1.1: cadd-snv measuring deleteriousness, and clinvar-snv measuring clinical pathogenicity. We find that conservation scores, and by extension, genomic language models, predict deleteriousness well, but successfully translating deleteriousness predictions to pathogenicity remains challenging. GUANinE v1.1 newly evaluates dozens of pretrained genomic models, and we conclude that moderate-context hybrid or post-trained language models may define the next era of machine learning in genomics.

Genomics↗

PubMed2025

Network Interactions of Circulating FGF23, HRG-HMGB1, and Cardiac Disease in CKD.

KEY POINTS: Multitrait analysis of genome-wide association study boosts the statistical power to identify novel genetic traits for fibroblast growth factor 23. A functional genomics approach aided network discovery to identify histidine-rich glycoprotein (HRG) and high-mobility group protein box 1 (HMGB1) as key regulators of cardiac disease in CKD. Integration of clinical and genetic data enhances the discovery power and is crucial for understanding the genetic underpinnings of mineral bone disorder related to CKD. BACKGROUND: Genome-wide association studies (GWAS) have identified numerous genetic loci associated with mineral metabolism markers but have exclusively focused on single-trait analysis. In this study, we performed a multitrait analysis of GWAS (MTAG) of mineral metabolism, exploring overlapping genetic architecture between traits to identify novel genetic associations for fibroblast growth factor 23 (FGF23). METHODS: We applied MTAG to variants common to GWAS of five genetically correlated mineral metabolism markers in participants of European ancestry. We integrated UK Biobank GWAS for blood levels for phosphate, 25-hydroxyvitamin D, and calcium (n=366,484) and Cohorts for Heart and Aging Research in Genetic Epidemiology GWAS for parathyroid hormone (n=29,155) and FGF23 (n=13,716). We then used supervised and unsupervised deep machine learning to identify novel associations between genetic traits and FGF23. RESULTS: MTAG increased the effective sample size for mineral metabolism markers to n=50,325 for FGF23. After clumping, MTAG identified independent genome-wide significant single-nucleotide polymorphisms for all traits, including 62 loci for FGF23. Many of these loci have not been previously reported in single-trait analyses. Through a functional genomics approach, we identified histidine-rich glycoprotein (HRG) and high-mobility group box 1 (HMGB1) as master regulators of downstream canonical pathways associated with circulating FGF23, and both genes were highly enriched in hypertrophied cardiac tissue of deceased hemodialysis patients. In addition, we found that DNMT3A was associated with uremic toxin, 8-hydroxy-2-deoxyguanosine, a biomarker of DNA damage. In silico gene perturbation analysis revealed that DNMT3A is protective in patients with heart failure caused by hypertrophied or dilated cardiomyopathy. CONCLUSIONS: Our findings highlight the importance of MTAG analysis of mineral metabolism markers to boost the number of genome-wide significant loci for FGF23 to identify novel genetic traits. Functional genomics revealed novel networks that inform unique cellular functions and identified HRG and HMGB1 as key master regulators of FGF23 and cardiovascular disease in CKD.

bones, stones, and mineral metabolism↗

PubMed2026

A weakly supervised deep learning-based recurrence prediction and risk stratification of lung adenocarcinoma from pathology whole-slide images.

BACKGROUND: Accurate prediction of postoperative recurrence in lung adenocarcinoma (LUAD) is essential for guiding clinical decision-making and improving patient outcomes. Although various predictive models have been developed, most rely on complex genomic analyses and high-dimensional clinical data. The complexity of these approaches substantially limits their feasibility for routine clinical use. To address this clinical challenge, this study aims to predict postoperative recurrence using routinely available hematoxylin and eosin (H&E)-stained images and characterize the associated biological features. METHODS: A total of 329 patients who underwent curative resection at the First Affiliated Hospital of Wenzhou Medical University (FHWMU) were retrospectively enrolled and randomly assigned to training and internal validation cohorts in a 7:3 ratio. An independent external validation cohort comprising 70 patients from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) was included. Three patch-level feature extractors (Inception_V3, ResNet18, and DenseNet121) were evaluated within a weakly supervised multiple-instance learning (MIL) framework incorporating automated region-of-interest (ROI) detection on segmented whole-slide images (WSIs). Model performance was assessed using the area under the receiver operating characteristic curve (AUC), Kaplan-Meier (KM) survival analysis, and multivariable Cox proportional hazards regression. Transcriptomic profiling and gene set enrichment analysis (GSEA) were conducted to investigate biological differences between risk groups. RESULTS: The model achieved AUCs of 0.923 in the training cohort, 0.891 in the internal validation cohort, and 0.847 in the external validation cohort. The model effectively stratified patients into high- and low-risk groups with significantly different recurrence-free survival (RFS) across all cohorts (all P < 0.001) and retained prognostic value within AJCC stages I-III. Transcriptomic analyses revealed consistent enrichment of cell cycle-related pathways and neutrophil extracellular trap (NET) formation in high-risk patients across both institutional and CPTAC cohorts, aligning with distinct biological profiles of the model-derived risk stratification. CONCLUSIONS: This weakly supervised deep learning framework enables accurate and externally validated prediction of postoperative recurrence in LUAD using routinely available histopathological images, and integration of histopathological features with molecular analyses enhances biological interpretability. This work provides a clinically accessible and cost-effective tool for postoperative risk assessment in LUAD patients.

Humans↗