Search Results (77)

The rapid advancement of sequencing technologies has led to the generation of complex multi-omics data, which are often high-dimensional, noisy, and imbalanced, posing significant challenges for traditional machine learning methods. The novelty of this work resides in the architecture-level integration of autoencoders with Generative Adversarial Network (GAN) and Conditional Tabular Generative Adversarial Network (CTGAN) models, where the autoencoder is employed for latent feature extraction and noise reduction, while GAN-based models are used for realistic sample generation and class imbalance mitigation in multi-omics cancer datasets. This study proposes a novel framework that combines an autoencoder for dimensionality reduction and a CTGAN for generating synthetic samples to balance underrepresented classes. The process starts with selecting the most discriminative features, then extracting latent representations for each omic type, merging them, and generating new minority samples. Finally, all samples are used to train a neural network to predict specific cancer outcomes, defined here as clinically relevant biomarkers or patient characteristics. In this work, the considered outcome in the bladder cancer is Tumor Mutational Burden (TMB), while the breast cancer outcome is menopausal status, a key factor in treatment planning. Experimental results show that the proposed model achieves high precision, with an average precision of 0.9929 for TMB prediction in bladder cancer and 0.9748 for menopausal status in breast cancer, and reaches perfect precision (1.000) for the positive class in both cases. In addition, the proposed AE–CTGAN framework consistently outperformed an autoencoder combined with a standard GAN across all evaluation metrics, achieving average accuracies of 0.9929 and 0.9748, recall values of 0.9846 and 0.9777, and F1-scores of 0.9922 for bladder and breast cancer datasets, respectively. A comparative fidelity analysis in the latent space further demonstrated the superiority of CTGAN, reducing the average Euclidean distance between real and synthetic samples by approximately 72% for bladder cancer and by up to 84% for breast cancer compared to a standard GAN. These findings confirm that CTGAN generates high-fidelity synthetic samples that preserve the structural characteristics of real multi-omics data, leading to more reliable class balancing and improved predictive performance. Overall, the proposed framework provides an effective and robust solution for handling class imbalance in multi-omics cancer data and enhances the accuracy of clinically relevant outcome prediction. Full article

Sepsis is a life-threatening syndrome characterized by marked clinical heterogeneity and complex host–pathogen interactions. Although traditional mechanistic studies have identified key molecular pathways, they remain insufficient to capture the highly dynamic, multifactorial, and systems-level nature of this condition. The advent of high-throughput omics technologies—particularly integrative multi-omics approaches encompassing genomics, transcriptomics, proteomics, and metabolomics—has profoundly reshaped sepsis research by enabling comprehensive profiling of molecular perturbations across biological layers. However, the unprecedented scale, dimensionality, and heterogeneity of multi-omics datasets exceed the analytical capacity of conventional statistical methods, necessitating more advanced computational strategies to derive biologically meaningful and clinically actionable insights. In this context, artificial intelligence (AI) has emerged as a powerful paradigm for decoding the complexity of sepsis. By leveraging machine learning and deep learning algorithms, AI can efficiently process ultra-high-dimensional and heterogeneous multi-omics data, uncover latent molecular patterns, and integrate multilayered biological information into unified predictive frameworks. These capabilities have driven substantial advances in early sepsis detection, molecular subtyping, prognosis prediction, and therapeutic target identification, thereby narrowing the gap between molecular mechanisms and clinical application. As a result, the convergence of AI and multi-omics is redefining sepsis research, shifting the field from descriptive analyses toward predictive, mechanistic, and precision-oriented medicine. Despite these advances, the clinical translation of AI-driven multi-omics approaches in sepsis remains constrained by several challenges, including limited data availability, cohort heterogeneity, restricted interpretability and causal inference, high computational demands, difficulties in integrating static molecular profiles with dynamic clinical data, ethical and governance concerns, and limited generalizability across populations and platforms. Addressing these barriers will require the establishment of standardized, multicenter datasets, the development of explainable and robust AI frameworks, and sustained interdisciplinary collaboration between computational scientists and clinicians. Through these efforts, AI-enabled multi-omics research may progress toward reproducible, interpretable, and equitable clinical implementation. Ultimately, the synergy between artificial intelligence and multi-omics heralds a new era of intelligent discovery and precision medicine in sepsis, with the potential to transform both research paradigms and bedside practice. Full article

Omics research is changing the way medicine develops new strategies for diagnosis, prevention, and treatment. With the surge of advanced machine learning models tailored for omicss analysis, recent research has shown improved results and pushed the progress towards personalized medicine. The dissection of multiple layers of genetic information has provided new insights into precision medicine, at the same time raising issues related to data abundance. Studies focusing on single-cell scale have upgraded the knowledge about gene expression, revealing the heterogeneity that governs the functioning of multicellular organisms. The amount of information gathered through such sequencing techniques often exceeds the human capacity for analysis. Understanding the underlying network of gene expression regulation requires advanced computational tools that can deal with the complex analytical data provided. The recent emergence of artificial intelligence-based frameworks, together with advances in quantum algorithms, has the potential to enhance multiomicsc analyses, increasing the efficiency and reliability of the gene expression profile prediction. The development of more accurate computational models will significantly reduce the error rates in interpreting large datasets. By making analytical workflows faster and more precise, these innovations make it easier to integrate and interrogate multi-omics data at scale. Deep learning (DL) networks perform well in terms of recognizing complex patterns and modeling non-linear relationships that enable the inference of gene expression profiles. Applications range from direct prediction of DNA sequence-informed predictive modeling to transcriptomic and epigenetic analysis. Quantum computing, particularly through quantum machine learning methods, is being explored as a complementary approach for predictive modeling, with potential applications to complex gene interactions in increasingly large and high-dimensional biological datasets. Together, these tools are reshaping the study of complex biological data, while ongoing innovation in this field is driving progress towards personalized medicine. Overall, the combination of high-resolution omics and advanced computational tools marks an important shift toward more precise and data-driven clinical decision-making. Full article

Background: Pituitary neuroendocrine tumours (PitNETs) are clinically and biologically heterogeneous neoplasms that remain challenging to diagnose, prognosticate, and treat. Although recent WHO classifications using transcription-factor-based markers have refined pathological categorisation, histopathology alone still fails to predict tumour behaviour or support individualised therapy. Objective: This systematic review aimed to evaluate how machine learning (ML) and knowledge extraction approaches can complement pathology by integrating multi-dimensional omics datasets to generate predictive and clinically meaningful insights in PitNETs. Methods: The review followed the PRISMA 2020 statement for systematic reviews. Searches were conducted in PubMed, Google Scholar, arXiv, and SciSpace up to June 2025 to identify omics studies applying ML or computational data integration in PitNETs. Eligible studies included original research using genomic, transcriptomic, epigenomic, proteomic, or liquid biopsy data. Data extraction covered study design, ML methodology, data accessibility, and clinical annotation. Study quality and validation strategies were also assessed. Results: A total of 726 records were identified. After the reviewing process, 98 studies met inclusion criteria. PitNET research employed unsupervised clustering or regularised regression methods reflecting their suitability for high-dimensional omics datasets and the limited sample sizes. In contrast, deep learning approaches were rarely implemented, primarily due to the scarcity of large, clinically annotated cohorts required to train such models effectively. To support future research and model development, we compiled a comprehensive catalogue of all publicly available PitNET omics resources, facilitating reuse, methodological benchmarking, and integrative analyses. Conclusions: Although omics research in PitNETs is increasing, the lack of standardised, clinically annotated datasets remains a major obstacle to the development and deployment of robust predictive models. Coordinated efforts in data sharing and clinical harmonisation are required to unlock its full potential. Full article

Background: In high-dimensional, small-sample omics studies such as metabolomics, feature selection not only determines the discriminative performance of classification models but also directly affects the reproducibility and translational value of candidate biomarkers. However, most existing methods primarily optimize classification accuracy and treat stability as a post hoc diagnostic, leading to considerable fluctuations in selected feature sets under different data splits or mild perturbations. Methods: To address this issue, this study proposes FRL-TSFS, a feature selection framework synergistically driven by filter-based Robust Rank Aggregation and L1-sparse modeling. Five complementary filter methods—variance thresholding, chi-square test, mutual information, ANOVA F test, and ReliefF—are first applied in parallel to score features, and Robust Rank Aggregation (RRA) is then used to obtain a consensus feature ranking that is less sensitive to the bias of any single scoring criterion. An L1-regularized logistic regression model is subsequently constructed on the candidate feature subset defined by the RRA ranking to achieve task-coupled sparse selection, thereby linking feature selection stability, feature compression, and classification performance. Results: FRL-TSFS was evaluated on six representative metabolomics and gene expression datasets under a mildly perturbed scenario induced by 10-fold cross-validation, and its performance was compared with multiple baselines using the Extended Kuncheva Index (EKI), Accuracy, and F1-score. The results show that RRA substantially improves ranking stability compared with conventional aggregation strategies without degrading classification performance, while the full FRL-TSFS framework consistently attains higher EKI values than the other feature selection schemes, markedly reduces the number of selected features to several tens of metabolites or genes, and maintains competitive classification performance. Conclusions: These findings indicate that FRL-TSFS can generate compact, reproducible, and interpretable biomarker panels, providing a practical analysis framework for stability-oriented feature selection and biomarker discovery in untargeted metabolomics. Full article

Organoids are self-organizing three-dimensional (3D) cellular structures derived from stem cells. They can mimic the anatomical and functional properties of real organs. They have transformed in vitro disease modeling by closely replicating the structural and functional characteristics of human tissues. The complexity and variability of organoid-derived data pose significant challenges for analysis and clinical translation. Artificial Intelligence (AI) has emerged as a crucial enabler, offering scalable and high-throughput tools for interpreting imaging data, integrating multi-omics profiles, and guiding experimental workflows. This review aims to discuss how AI is reshaping organoid-based research by enhancing morphological image analysis, enabling dynamic modeling of organoid development, and facilitating the integration of genomics, transcriptomics, and proteomics for disease classification. Moreover, AI is increasingly used to support drug screening and personalize therapeutic strategies by analyzing patient-derived organoids. The integration of AI with organoid-on-chip systems further allows for real-time feedback and physiologically relevant modeling. Drawing on peer-reviewed literature from the past decade, Furthermore, CNNs have been used to analyze colonoscopy and histopathological images in colorectal cancer with over 95% diagnostic accuracy. We examine key tools, innovations, and case studies that illustrate this evolving interface. As this interdisciplinary field matures, the future of AI-integrated organoid platforms depends on establishing open data standards, advancing algorithms, and addressing ethical and regulatory considerations to unlock their clinical and translational potential. Full article

Integration of multi-omics data provides a comprehensive perspective on complex biological systems, facilitating advances in disease classification and biomarker discovery. However, the heterogeneity and high dimensionality of omics data present significant analytical challenges. To achieve effective and interpretable multi-omics integration, we propose a novel deep learning framework named MOGOLA(Multi-Omics integration by Gating and Omics-Linked Attention). MOGOLA consists of three core components: (1) A hybrid graph learning module that integrates Graph Convolutional Networks and Graph Attention Networks for intra-omics feature extraction. (2) A gating and confidence mechanism that adaptively weighs feature importance across different omics types. (3) A cross-omics attention-based fusion module that captures inter-omics relationships. Comprehensive evaluations on four benchmark datasets (BRCA, KIPAN, ROSMAP, and LGG) demonstrate that MOGOLA consistently outperforms eleven state-of-the-art approaches. Ablation studies further validate the contribution of each module, while biomarkers identification highlight the framework’s clinical potential. These results show that MOGOLA is a robust and interpretable approach for multi-omics data integration and a contribution to advances in computational biology and precision medicine. Full article

Animal breeding has undergone profound transformations from its origins in phenotypic observation to the integration of genomic and machine learning techniques. This review paper explores the progression of livestock breeding, tracing its roots to the domestication of animals during the Neolithic Revolution. Gregor Mendel’s foundational work with pea plants established key principles of Mendelian genetics, which initially focused on discrete qualitative traits. However, the advancement of quantitative genetics has shifted the focus to continuous traits, such as body weight and milk yield, which are influenced by multiple genes. QTL mapping revolutionized breeding by shifting from phenotype- to genotype-based selection, enhancing accuracy through genomic predictions like GEBV under GBLUP. The strongest QTL associations on chromosome 18 linked local GEBV with FUK and DDX19B expression. In recent years, machine learning and artificial intelligence have transformed genomic prediction into livestock breeding by efficiently handling high-dimensional data and capturing complex genetic relationships. Notably, a deployed deep learning model achieved an average correlation of up to 0.643 between actual and predicted values. This review highlights the integration of machine learning approaches in animal breeding, showcasing advancements in milk and meat production, and the improvement of disease management through multi-omics strategies. The paper underscores the shift towards innovative methods and their impact on advancing animal breeding practices, offering insights into prospects for enhancing productivity, health, and welfare in livestock. Full article

Radiomics has emerged as a promising tool for non-invasive tumour phenotyping in breast cancer, providing valuable insights into tumour heterogeneity, response prediction, and risk stratification. However, traditional radiomic approaches often rely on correlative patterns of image analysis to clinical data and lack direct biological interpretability. Combining information provided by radiomics with genomics or other multi-omics data can be important to personalise diagnostic and therapeutic work up in breast cancer management. This review aims to explore the current progress in integrating radiomics with multi-omics data—genomics and transcriptomics—to establish biologically grounded, multidimensional models for precision management of breast cancer. We will review recent advances in integrative radiomics and radiogenomics, highlight the synergy between imaging and molecular profiling, and discuss emerging machine learning methodologies that facilitate the integration of high-dimensional data. Applications of radiogenomics, including breast cancer subtype and molecular mutation prediction, radiogenomic mapping of the tumour immune microenvironment, and response forecasting to immunotherapy and targeted therapies, as well as lymph nodes involvement, will be evaluated. Challenges in technical limitations including imaging modalities harmonization, interpretability, and advancing machine learning methodologies will be addressed. This review positions integrative radiogenomics as a driving force for next-generation breast cancer care. Full article

Objectives: Cancer, characterized by its profound complexity and heterogeneity, arises from a multitude of molecular disruptions. The pursuit of identifying distinct cancer subtypes is driven by the need to stratify patients into clinically coherent subgroups, each exhibiting unique prognostic outcomes. The integration of multi-omics datasets enhances the precision of subtyping and advances precision medicine. Methods: Considering the high-dimensional nature inherent to various multi-omics data types, we introduce an innovative deep learning framework, DAE-MKL, which integrates denoising autoencoders with multi-kernel learning for identifying cancer subtypes. Leveraging the capabilities of DAE, we extract non-linearly transformed features that retain pertinent information while mitigating noise and redundancy. These refined data representations are then funneled into the MKL framework, thereby enhancing the accuracy of subtype identification. We applied the DAE-MKL framework to both simulated studies and empirical datasets derived from two distinct cancer types, low-grade glioma (LGG, $n$ = 86) and kidney renal clear cell carcinoma (KIRC, $n$ = 285), thereby validating its utility and feasibility. Results: In simulations, DAE-MKL achieved superior performance with NMI gains up to 0.78 compared to other state-of-the-art methods. For real datasets, DAE-MKL identified three LGG subtypes and three KIRC subtypes, showing significant survival differences (KIRC log-rank $p$ = 3.33 × 10⁻⁸, LGG log-rank $p$ = 3.99 × 10⁻⁸). Additionally, we explored potential cancer-related biomarkers. Conclusions: The DAE-MKL effectively identifies molecular subtypes, reduces data dimensionality, and improves prognostic stratification in multi-omics cancer datasets, providing an effective tool for precision oncology. Full article

Classifying brain tumour transcriptomic data is crucial for precision medicine but remains challenging due to high dimensionality and limited interpretability of conventional models. This study benchmarks three image-based deep learning approaches, DeepInsight, Fotomics, and a novel saliency-guided convolutional neural network (CNN), for transcriptomic classification. DeepInsight utilises dimensionality reduction to spatially arrange gene features, while Fotomics applies Fourier transforms to encode expression patterns into structured images. The proposed method transforms each single-cell gene expression profile into an RGB image using PCA, UMAP, or t-SNE, enabling CNNs such as ResNet to learn spatially organised molecular features. Gradient-based saliency maps are employed to highlight gene regions most influential in model predictions. Evaluation is conducted on two biologically and technologically different datasets: single-cell RNA-seq from glioblastoma GSM3828672 and bulk microarray data from medulloblastoma GSE85217. Outcomes demonstrate that image-based deep learning methods, particularly those incorporating saliency guidance, provide a robust and interpretable framework for uncovering biologically meaningful patterns in complex high-dimensional omics data. For instance, ResNet-18 achieved the highest accuracy of 97.25% on the GSE85217 dataset and 91.02% on GSM3828672, respectively, outperforming other baseline models across multiple metrics. Full article

Neurodevelopmental disorders (NDDs), including autism spectrum disorder, intellectual disability, and attention-deficit/hyperactivity disorder, are genetically and phenotypically heterogeneous conditions affecting millions worldwide. High-throughput omics technologies—transcriptomics, proteomics, metabolomics, and epigenomics—offer a unique opportunity to link genetic variation to molecular and cellular mechanisms underlying these disorders. However, the high dimensionality, sparsity, batch effects, and complex covariance structures of omics data present significant statistical challenges, requiring robust normalization, batch correction, imputation, dimensionality reduction, and multivariate modeling approaches. This review provides a comprehensive overview of statistical frameworks for analyzing high-dimensional omics datasets in NDDs, including univariate and multivariate models, penalized regression, sparse canonical correlation analysis, partial least squares, and integrative multi-omics methods such as DIABLO, similarity network fusion, and MOFA. We illustrate how these approaches have revealed convergent molecular signatures—synaptic, mitochondrial, and immune dysregulation—across transcriptomic, proteomic, and metabolomic layers in human cohorts and experimental models. Finally, we discuss emerging strategies, including single-cell and spatially resolved omics, machine learning-driven integration, and longitudinal multi-modal analyses, highlighting their potential to translate complex molecular patterns into mechanistic insights, biomarkers, and therapeutic targets. Integrative multi-omics analyses, grounded in rigorous statistical methodology, are poised to advance mechanistic understanding and precision medicine in NDDs. Full article

Transcriptomic profiling is a powerful tool for dissecting the cellular and molecular complexity of ocular tissues, providing insights into retinal development, corneal disease, macular degeneration, and glaucoma. With the expansion of microarray, bulk RNA sequencing (RNA-seq), and single-cell RNA-seq technologies, artificial intelligence (AI) has emerged as a key strategy for analyzing high-dimensional gene expression data. This review synthesizes AI-enabled transcriptomic studies in ophthalmology from 2019 to 2025, highlighting how supervised and unsupervised machine learning (ML) methods have advanced biomarker discovery, cell type classification, and eye development and ocular disease modeling. Here, we discuss unsupervised techniques, such as principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), uniform manifold approximation and projection (UMAP), and weighted gene co-expression network analysis (WGCNA), now the standard in single-cell workflows. Supervised approaches are also discussed, including the least absolute shrinkage and selection operator (LASSO), support vector machines (SVMs), and random forests (RFs), and their utility in identifying diagnostic and prognostic markers in age-related macular degeneration (AMD), diabetic retinopathy (DR), glaucoma, keratoconus, thyroid eye disease, and posterior capsule opacification (PCO), as well as deep learning frameworks, such as variational autoencoders and neural networks that support multi-omics integration. Despite challenges in interpretability and standardization, explainable AI and multimodal approaches offer promising avenues for advancing precision ophthalmology. Full article

The evolving paradigm of precision medicine is redefining the landscape of orthobiologic therapies by moving beyond traditional diagnosis-driven approaches toward biologically tailored interventions. This review synthesizes current evidence supporting precision orthobiologics, emphasizing the significance of individualized treatment strategies in musculoskeletal regenerative medicine. This narrative review synthesized literature from PubMed, Embase, and Web of Science databases (January 2015–December 2024) using search terms, including ‘precision medicine,’ ‘orthobiologics,’ ‘regenerative medicine,’ ‘biomarkers,’ and ‘artificial intelligence’. Biological heterogeneity among patients with ostensibly similar clinical diagnoses—reflected in diverse inflammatory states, genetic backgrounds, and tissue degeneration patterns—necessitates patient stratification informed by molecular, genetic, and multi-omics biomarkers. These biomarkers not only enhance diagnostic accuracy but also improve prognostication and monitoring of therapeutic responses. Advanced imaging modalities such as T2 mapping, DTI, DCE-MRI, and molecular PET offer non-invasive quantification of tissue health and regenerative dynamics, further refining patient selection and treatment evaluation. Simultaneously, bioengineered delivery systems, including hydrogels, nanoparticles, and scaffolds, enable precise and sustained release of orthobiologic agents, optimizing therapeutic efficacy. Artificial intelligence and machine learning approaches are increasingly employed to integrate high-dimensional clinical, imaging, and omics datasets, facilitating predictive modeling and personalized treatment planning. Despite these advances, significant challenges persist—ranging from assay variability and lack of standardization to regulatory and economic barriers. Future progress requires large-scale multicenter validation studies, harmonization of protocols, and cross-disciplinary collaboration. By addressing these limitations, precision orthobiologics has the potential to deliver safer, more effective, and individualized care. This shift from generalized to patient-specific interventions holds promise for improving outcomes in degenerative and traumatic musculoskeletal disorders through a truly integrative, data-informed therapeutic framework. Full article

Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies—including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks—are advancing cancer research. Specifically, we highlight three major applications of ML–metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies. Full article