SEARCH · PubMed Health

Results for “Representation 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

PubMed2026

Representation learning for multi-modal spatially resolved transcriptomics data.

MOTIVATION: Spatial transcriptomics enables in-depth molecular characterization of samples on a morphology and RNA level while preserving spatial location. Integrating the resulting multi-modal data is an unsolved problem, and developing new solutions in precision medicine depends on improved methodologies. RESULTS: We introduce AESTETIK, a convolutional deep learning model that jointly integrates spatial, transcriptomics, and morphology information to learn accurate spot representations. AESTETIK yielded substantially improved cluster assignments on widely adopted technology platforms (e.g. 10x Genomics™, NanoString™) across multiple datasets. We achieved performance enhancement on structured tissues (e.g. brain) with a 21% increase in median ARI over previous state-of-the-art methods. Notably, AESTETIK also demonstrated superior performance on cancer tissues with heterogeneous cell populations, showing a 2-fold increase in breast cancer, 79% in melanoma, and 21% in liver cancer. We expect that these advances will enable a multi-modal understanding of key biological processes. AVAILABILITY AND IMPLEMENTATION: AESTETIK is implemented in Python 3 and is available as open source software at http://www.github.com/ratschlab/aestetik. The Snakemake pipeline for reproducing the results is available at http://www.github.com/ratschlab/st-rep.

Spatial Transcriptomics↗

PubMed2026

ORBIT: Oncogenic Representation Learning via Bi-Prototype Contrastive Learning in Hyperbolic Space for cancer driver gene identification.

Accurate identification of cancer driver genes is crucial for precision oncology but remains challenging due to the complexity of integrating heterogeneous data and modeling dynamic biological systems. To address these limitations, we propose ORBIT (Oncogenic Representation Learning via Bi-Prototype Contrastive Learning in Hyperbolic Space). Our framework synergistically fuses multi-omics profiles with functional network data using a context-adaptive graph reweighting mechanism to capture cancer-specific dynamics. The model employs a bi-prototype contrastive learning strategy within hyperbolic space, which aligns gene representations around distinct driver and non-driver semantic anchors while preserving the intrinsic hierarchy of biological networks. Comprehensive evaluations demonstrate that ORBIT achieves highly competitive stability in pan-cancer analysis while consistently outperforming state-of-the-art methods in cancer-specific predictions. Furthermore, functional enrichment analysis confirms that the model effectively segregates core cancer pathways, and drug sensitivity profiling validates the clinical relevance of the identified drivers. By integrating hyperbolic geometry with context-adaptive learning, ORBIT offers a robust and interpretable paradigm for precision medicine. The source codes and datasets are publicly accessible at https://github.com/spcho-dev/ORBIT.

Humans↗

PubMed2026

Integrating histology and spatial transcriptomics via multimodal transformers and contrastive representation learning for accurate gene expression prediction.

Predicting spatial gene expression from Histological images is a fundamental task in understanding tissue organization and molecular phenotypes. However, existing methods often rely on single-model representations or lack effective alignment between image and transcriptomic features. To address these limitations, we propose a unified multimodal learning framework that integrates histological imaging and spatial transcriptomics through a shared latent representation space. Specifically, histological H&E images are encoded by a ResNet50-based convolutional stem and a MobileViT Transformer backbone to extract hierarchical visual representations. Both modalities are projected into a shared latent space via linear-GELU-dropout transformation blocks, enabling cross-modal alignment through a contrastive learning objective that maximizes agreement between the corresponding image and the spot embeddings. Experimental results on the 10x Genomics Visium dataset of human liver tissue demonstrate that MViTGene achieves significantly higher prediction accuracy than existing methods across multiple gene subsets, with improvements of 20%, 33%, and 12% in predicting marker genes, highly expressed genes, and highly variable genes, respectively. The significant improvement in relevance indicates that the model can more accurately capture the true correspondence between tissue morphology and gene expression, therefore enabling more reliable biological interpretation. It provides a computational tool for high-throughput spatial gene expression prediction that balances performance and interpretability.

Humans↗

PubMed1992

IPSA-Inductive Protein Structure Analysis.

The Inductive Structure Protein Analysis (IPSA) project presents a new method for investigating protein structure. IPSA includes the creation of a new database which was designed specifically for the analysis of protein structure by statistics and machine learning. The Protein Representation Language (PRL) database includes explicit and symbolic representations of geometrical, topological and chemophysical information about secondary structures and the relationships between secondary structures. The IPSA methodology consists of: the use of PRL information to produce a new database of examples of secondary structures which associate together (examples of possible super-secondary structures); then the use of a variety of clustering techniques to produce a consensus clustering of these examples (super-secondary structures); these super-secondary structures are finally examined to uncover any biological features of significance. We have applied this method to find simple super-secondary structures consisting of pairs of alpha-helices. We found four well-defined super-secondary structures, one formed exclusively by long range interactions, and another in association with an additional element of secondary structure (alpha t alpha-motif). Examinations were carried out using homologous pairs and conformational fits which confirm our clustering.

Cluster Analysis↗

PubMed2026

CAKR: commutative algebra k-mer representations for genomics.

Despite the availability of various sequence analysis models, comparative genomic analysis remains a challenge in genomics, genetics, and phylogenetics. Commutative algebra, a fundamental tool in algebraic geometry and number theory, has rarely been used in data and biological sciences. In this study, we introduce commutative algebra k-mer representations as a nonlinear algebraic framework for analyzing genomic sequences. This representation bridges commutative algebra, algebraic topology, combinatorics, and machine learning to establish a mathematical framework for comparative genomic analysis. We evaluate its effectiveness on three tasks including genetic variant classification, phylogenetic tree reconstruction, and viral classification, typically requiring alignment-based, alignment-free, and machine-learning approaches, respectively. In this work, we show that commutative algebra k-mer representations outperform five state-of-the-art sequence analysis methods across twelve primary datasets, with two additional supplementary fragment-placement benchmarks, especially in viral classification, and maintain relatively stable predictive accuracy as dataset size increases, underscoring scalability and robustness.

Genomics↗

PubMed2025

Tomtom-lite: accelerating Tomtom enables large-scale and real-time motif similarity scoring.

SUMMARY: Pairwise sequence similarity is a core operation in genomic analysis, yet most attention has been given to sequences made up of discrete characters. With the growing prevalence of machine learning, calculating similarities for sequences of continuous representations, e.g. frequency-based position-weight matrices (PWMs) and attribution-based contribution-weight matrices, is taking on newfound importance. Tomtom has previously been proposed as an algorithm for identifying pairs of PWMs whose similarity is statistically significant, but the implementation remains inefficient for both real-time and large-scale analysis. Accordingly, we have re-implemented Tomtom as a numba-accelerated Python function that is natively multi-threaded, avoids cache misses, more efficiently caches intermediate values, and uses approximations at compute bottlenecks. Here, we provide a detailed description of the original Tomtom method and present results demonstrating that our re-implementation can achieve over a 1000-fold speedup compared with the original tool on reasonable tasks. AVAILABILITY AND IMPLEMENTATION: Our implementation of Tomtom is freely available as a Python package at https://github.com/jmschrei/memesuite-lite, which can be downloaded via pip install memelite or at https://zenodo.org/records/17008952.

Software↗

PubMed1985

A program for machine learning of counting criteria: empirical induction of logic-based classification rules.

A program has been developed which derives classification rules from empirical observations and expresses these rules in a knowledge representation format called 'counting criteria'. Decision rules derived in this format are often more comprehensible than rules derived by existing machine learning programs such as AQ11. Use of the program is illustrated by the inference of discrimination criteria for certain types of bacteria based upon their biochemical characteristics. The program may be useful for the conceptual analysis of data and for the automatic generation of prototype knowledge bases for expert systems.

Artificial Intelligence↗

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↗

PubMed2026

A transcription factor regulatory atlas for activity inference and perturbation prediction.

Inferring transcription factor (TF) activity from transcriptomes and predicting transcriptome-wide responses to TF perturbations remain challenging, in part because available TF-mRNA resources often face a trade-off between precision and coverage and typically lack signed regulatory information. Here, we present TFActProfiler, a TF-mRNA resource and computational framework that learns signed, quantitative TF-mRNA regulatory coefficients by integrating heterogeneous prior evidence (ChIP-based, motif-based, and curated TF-mRNA annotations) with large-scale bulk and single-cell RNA-seq atlases. TFActProfiler contains 2 606 176 signed TF-mRNA interactions and improves TF activity inference in TF knockdown benchmarks relative to widely used regulon resources while retaining broad TF and target coverage. In addition, because the same learned regulatory coefficients can be used to model downstream transcriptional effects, TFActProfiler enables prediction of transcriptome-wide gene expression responses to TF knockdown without training on task-matched perturbation data. When perturbation datasets are available, TFActProfiler can be further refined to achieve performance comparable to state-of-the-art machine-learning baselines. By providing a direction-aware representation of TF-mRNA regulation for both activity inference and perturbation-response modeling, TFActProfiler supports systematic dissection of gene regulatory programs across diverse cellular contexts.

Transcription Factors↗

PubMed2025

Exercise Therapy in Down Syndrome: A Systematic Review and Meta-Analysis Focused on Muscle Strength, Redox Balance, and Inflammatory Profile.

OBJECTIVE: This study systematically reviewed and meta-analyzed randomized and quasi-randomized controlled trials investigating the impact of exercise therapy on muscle strength, redox balance, and inflammatory profile in individuals with Down syndrome. DESIGN: Systematic review and meta-analysis. DATA SOURCES: Cochrane Central Register of Controlled Trials, MEDLINE, CINAHL, SPORTDiscus, EMBASE, and PEDro. ELIGIBILITY CRITERIA FOR SELECTING STUDIES: Randomized and quasi-randomized controlled trials exploring exercise therapy effects on muscle strength and redox balance in individuals with Down syndrome. Although no initial restrictions on age, gender, or health condition were applied during the search process, all included studies focused on adult participants (>18 yr old). No language restrictions were applied, and the search covered the period from 1970 to 2021. RESULTS: We assessed the abstract of 1964 studies. Of the 46 studies meeting the inclusion criteria for the period 2004-2021, 32 focused on muscle strength, and 14 examined redox balance and inflammation. A total of 1611 participants with a mean age of 27 yr were included. This review confirmed that different exercise modalities are prone to improve muscle strength (random effect (95% confidence interval): 0.66, 0.54 to 0.78), redox balance and inflammatory profile (random effect (95% confidence interval): -1.04, -1.31 to -0.76) in this population. The multimodel inference suggested that the frequency of training (times per week) might play a significant role in the main effect. Unsupervised machine learning algorithms displayed a pattern-based graphic representation to assess heterogeneity. CONCLUSIONS: Exercise training demonstrated a positive impact on muscle strength in adults with Down syndrome. The review provides valuable insights into the effects of exercise therapy on individuals with Down syndrome, emphasizing the need for tailored training prescriptions.

Humans↗

PubMed2026

A leakage-aware genomic prediction pipeline for meropenem resistance in Klebsiella pneumoniae using transformer-based resistome representation learning.

MOTIVATION: Antimicrobial resistance (AMR) in Klebsiella pneumoniae, particularly to carbapenems such as meropenem, is a major global health problem. Machine learning is increasingly used to predict resistance from genomic markers; however, many models fail to capture high-level gene-gene interactions and may exhibit inflated performance due to lineage-biased prediction. Existing genomic prediction models largely rely on flat feature representations that fail to capture epistatic gene interactions, and commonly suffer from inflated performance estimates due to phylogenetic data leakage. To address these limitations simultaneously, a leakage-aware hybrid TabTransformer-CatBoost pipeline was developed, combining self-attention-based resistome representation learning with gradient boosting classification under clade-aware data partitioning. A self-attention encoder converts sparse gene presence-absence profiles into contextualized latent embeddings, which are subsequently classified using gradient boosting to capture lineage-aware AMR patterns. RESULTS: The proposed architecture outperformed classical baselines including Logistic Regression, Random Forest, XGBoost, and optimized CatBoost models. Internal accuracy reached 92.59% for the Chained Hybrid configuration (area under the receiver operating characteristic curve, AUROC = 0.8670, F1 = 0.8537). Performance gains primarily originated from the embedding stage, as confirmed by ablation analysis. External validation across independent multinational cohorts (n = 305) demonstrated generalizability (AUROC = 0.8105; F1 = 0.7552). Permutation testing produced near-zero Matthews Correlation Coefficient (MCC) = 0.0091, indicating predictions reflect genuine biological signal rather than noise. These results establish attention-based genomic embedding with gradient boosting as a scalable, interpretable, and leakage-aware framework for clinical AMR prediction. AVAILABILITY AND IMPLEMENTATION: The source code for the TabTransformer-CatBoost framework, including preprocessing pipelines and pre-trained embeddings, is available at https://github.com/SibelKervanci/kp-meropenem-tabtransformer.

Journal Article↗

PubMed2025

Whole-genome phenotype prediction with machine learning: open problems in bacterial genomics.

MOTIVATION: How can we identify causal genetic mechanisms governing bacterial traits? Initial efforts entrusting machine learning models to handle the task of predicting phenotype from genotype yield high accuracy scores. However, attempts to extract meaningful interpretations from the predictive models are found to be corrupted by falsely identified 'causal' features. Relying solely on pattern recognition and correlations is unreliable, significantly so in bacterial genomics settings where high-dimensionality and spurious associations are the norm. Though it is not yet clear whether we can overcome this hurdle, significant efforts are being made towards discovering potential high-risk bacterial genetic variants. In view of this, we set up open problems surrounding phenotype prediction from bacterial whole-genome datasets and extending those approaches to learning causal effects, and discuss challenges that impact the reliability of a machine's decision-making when faced with datasets of this nature. RESULTS: We identify major sources of non-injectivity in the formulation of the genotype-to-phenotype mapping function-linkage-disequilibrium, limited sampling, information loss in representations, unmeasured confounders and observational noise-and analyse their implications for machine learning applications. Using a collection of 4,140 Staphylococcus aureus isolates, we illustrate challenges surrounding the defined open problems. AVAILABILITY AND IMPLEMENTATION: Raw sequencing data are available from the European Nucleotide Archive (ENA) under project accessions ERP001012, PRJEB3174, PRJEB2655, PRJEB2756, and PRJEB2944. Assemblies and annotations were generated with the Sanger bacterial pipeline (https://github.com/sanger-pathogens/vr-codebase) and unitigs extracted using DBGWAS (https://gitlab.com/leoisl/dbgwas).

Machine Learning↗

PubMed2026

DNA methylation biomarkers for early detection of ovarian cancer.

Ovarian cancer (OC) remains difficult to detect at an early stage, and current screening approaches using CA125 and transvaginal ultrasonography have not demonstrated sufficient benefit for population screening. DNA methylation is a promising biomarker class because epigenetic alterations may arise early in tumourigenesis, can be detected in circulating cell-free DNA (cfDNA), and may provide tissue-of-origin information. This review critically evaluates recent evidence on DNA methylation biomarkers for early OC detection. PubMed/MEDLINE, Web of Science, and Scopus were searched for studies published between January 2020 and September 2025, supplemented by selected earlier studies of biological or methodological relevance. Evidence was synthesised across single-gene biomarkers, multi-locus panels, genome-wide signatures, assay platforms, and machine-learning classifiers, with emphasis on early-stage performance, histological representation, comparator populations, analytical methodology, and validation design. Single-gene markers such as BRCA1, RASSF1A, OPCML, HOXA9, and HIC1 show variable performance, while multi-gene and classifier-based approaches generally provide stronger discrimination. However, many studies remain limited by retrospective case-control designs, small FIGO stage I-II subsets, predominance of serous disease, and insufficient prospective validation. Integration with CA125 may improve sensitivity but can reduce specificity, which is critical in low-prevalence screening. Clinical translation will therefore require minimal and reproducible methylation signatures, standardised low-input cfDNA workflows, rigorous external validation, and prospective longitudinal evaluation in intended-use populations.

Humans↗

PubMed2025

The signed two-space proximity model for learning representations in protein-protein interaction networks.

MOTIVATION: Accurately predicting complex protein-protein interactions (PPIs) is crucial for decoding biological processes, from cellular functioning to disease mechanisms. However, experimental methods for determining PPIs are computationally expensive. Thus, attention has been recently drawn to machine learning approaches. Furthermore, insufficient effort has been made toward analyzing signed PPI networks, which capture both activating (positive) and inhibitory (negative) interactions. To accurately represent biological relationships, we present the Signed Two-Space Proximity Model (S2-SPM) for signed PPI networks, which explicitly incorporates both types of interactions, reflecting the complex regulatory mechanisms within biological systems. This is achieved by leveraging two independent latent spaces to differentiate between positive and negative interactions while representing protein similarity through proximity in these spaces. Our approach also enables the identification of archetypes representing extreme protein profiles. RESULTS: S2-SPM's superior performance in predicting the presence and sign of interactions in SPPI networks is demonstrated in link prediction tasks against relevant baseline methods. Additionally, the biological prevalence of the identified archetypes is confirmed by an enrichment analysis of Gene Ontology (GO) terms, which reveals that distinct biological tasks are associated with archetypal groups formed by both interactions. This study is also validated regarding statistical significance and sensitivity analysis, providing insights into the functional roles of different interaction types. Finally, the robustness and consistency of the extracted archetype structures are confirmed using the Bayesian Normalized Mutual Information (BNMI) metric, proving the model's reliability in capturing meaningful SPPI patterns. AVAILABILITY: S2-SPM is implemented and freely available under the MIT license at https://github.com/Nicknakis/S2SPM.

Protein Interaction Mapping↗

PubMed2026

Assessing Metal Ion Assignment Accuracy in Protein Data Bank Models via Elemental Spectroscopy.

Accurate representation of metal ions in macromolecular structures is critical for chemical interpretation, computational modeling, and machine-learning methods that rely on Protein Data Bank (PDB) entries. However, the elemental identity of metals modeled in crystallographic structures is often inferred indirectly and rarely validated experimentally. Here, we combine Particle Induced X-ray Emission (PIXE) and X-ray Fluorescence Spectroscopy (XRFS) to determine the elemental composition of protein samples used to generate 70 deposited metalloprotein crystal structures. By analyzing the original protein material employed for crystallization, but before the addition of crystallization buffer solutions, we assess whether the modeled metal ions in deposited structures are consistent with experimentally detectable elemental content. We find that in a majority of cases, the metals modeled in the corresponding PDB entries are inconsistent with the metals present in the protein samples before crystallization, or that additional metals are present but not represented in the structural models. Spectroscopic results were integrated with automated crystallographic validation metrics, including real-space Z-difference (RSZD) analysis and systematic rerefinement, to evaluate atomic-number mismatch at metal sites. PIXE and XRFS show strong agreement for dominant elemental signals and provide complementary, scalable approaches for identifying suspect metal assignments. This work does not address physiological or functional metalation but instead highlights a widespread data integrity issue in deposited macromolecular structures, PDB-wide. These results establish an experimentally corroborated link between elemental identity and crystallographic validation metrics, enabling the large-scale detection of chemically inconsistent annotations in structural databases used for computational modeling and machine learning.

Databases, Protein↗

PubMed2025

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models.

Reasoning about hypotheses and updating knowledge through empirical observations are central to scientific discovery. In this work, we applied logic-based machine learning methods to drive biological discovery by guiding experimentation. Genome-scale metabolic network models (GEMs) - comprehensive representations of metabolic genes and reactions - are widely used to evaluate genetic engineering of biological systems. However, GEMs often fail to accurately predict the behaviour of genetically engineered cells, primarily due to incomplete annotations of gene interactions. The task of learning the intricate genetic interactions within GEMs presents computational and empirical challenges. To efficiently predict using GEM, we describe a novel approach called Boolean Matrix Logic Programming (BMLP) by leveraging Boolean matrices to evaluate large logic programs. We developed a new system, [Formula: see text], which guides cost-effective experimentation and uses interpretable logic programs to encode a state-of-the-art GEM of a model bacterial organism. Notably, [Formula: see text] successfully learned the interaction between a gene pair with fewer training examples than random experimentation, overcoming the increase in experimental design space. [Formula: see text] enables rapid optimisation of metabolic models to reliably engineer biological systems for producing useful compounds. It offers a realistic approach to creating a self-driving lab for biological discovery, which would then facilitate microbial engineering for practical applications.

Active learning↗

PubMed2026

Integrative dual-track transcriptomics reveals stage-specific coordination, regulatory divergence, and HSP90AA1-associated remodeling in human folliculogenesis.

Human folliculogenesis depends on coordinated yet non-identical developmental remodeling in the oocyte and its surrounding granulosa cells. When these two compartments remain synchronized and when they diverge into lineage-specific regulatory states, however, remains incompletely resolved. Here we performed an integrative dual-track re-analysis of the human RNA-seq dataset GSE107746, modeling oocytes and granulosa cells as distinct but developmentally linked compartments across follicular progression. Analysis of 148 sequencing libraries showed that compartment identity was the dominant source of transcriptomic variation, supporting compartment-aware downstream interpretation. Within this framework, oocytes followed a relatively continuous developmental trajectory, with substantial transcriptional remodeling already evident across adjacent stages, whereas granulosa cells showed weaker early-stage contrasts but markedly stronger late-stage reorganization, particularly around the antral and preovulatory transitions. Functional enrichment indicated that oocyte maturation was associated with RNA-processing and broader genome-regulatory remodeling, whereas granulosa maturation was dominated by progressive mitochondrial and bioenergetic activation. Co-expression analysis showed that both compartments contained strong late-stage programmes together with inverse early-state modules, indicating a shared systems-level architecture of maturation, although the hub-gene composition and biological content of these programmes were largely compartment-specific. Machine-learning validation reinforced this asymmetry: oocyte stage classification was best recovered from a compact eigengene-based representation, whereas granulosa stage discrimination was better resolved by a broader differential-expression-derived feature set. At the gene level, HSP90AA1 emerged as a stage-associated marker with compartment-specific behavior, showing progressive attenuation across oocyte development, assignment to the selected oocyte blue module, and sharper transitional dynamics in granulosa cells. Together, these findings support a model in which human folliculogenesis proceeds through coordinated but non-equivalent transcriptomic remodeling, with shared developmental logic at the systems level but distinct molecular execution in germline and somatic compartments.

Co-expression networks↗

PubMed2025

Rapid assessment of clinical severity for salmonellosis cases via protein family domain analysis and machine learning.

Salmonella is a common pathogen, infecting more than a million people yearly. Rapid assessment of clinical case severity is essential for improving patient outcomes and optimizing healthcare resources. Advancements in genome sequencing technologies have enabled the analysis of bacterial genomes from many clinical cases, opening up new opportunities for precise and timely diagnosis. This study proposes a genome-based framework for identifying critical Salmonella cases before the onset of critical symptoms and facilitating early medical intervention. By leveraging protein family (Pfam) domains as the representation for genomic data, the complex genetic profiles of Salmonella cases are simplified into interpretable features. The severity levels of cases were investigated through rigorous data analysis, resulting in a set of 70 Pfam domains that could be potentially used as biomarkers. Machine Learning was employed to assess the predictive power of the curated Pfam biomarkers, achieving high accuracy (~93%) in sorting cases into critical, moderate, and mild categories. The results demonstrate the efficacy of the proposed approach. This framework highlights the potential of using bacterial genomic data in clinical decision-making, opening the window for timely personalized interventions for Salmonella infection management.

Domains of unknown function (DUFs)↗