SEARCH · Search PubMed

Results for “Machine learning.”

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

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 649 records · Page 36Linked to original sources

PubMed2004

Learning to discriminate between ligand-bound and disulfide-bound cysteines.

We present a machine learning method to discriminate between cysteines involved in ligand binding and cysteines forming disulfide bridges. Our method uses a window of multiple alignment profiles to represent each instance and support vector machines with a polynomial kernel as the learning algorithm. We also report results obtained with two new kernel functions based on similarity matrices. Experimental results indicate that binding type can be predicted at significantly higher accuracy than using PROSITE patterns.

Algorithms↗

PubMed2003

Analyzing tumor gene expression profiles.

A brief introduction to high throughput technologies for measuring and analyzing gene expression is given. Various supervised and unsupervised data mining methods for analyzing the produced high-dimensional data are discussed. The main emphasis is on supervised machine learning methods for classification and prediction of tumor gene expression profiles. Furthermore, methods to rank the genes according to their importance for the classification are explored. The approaches are illustrated by exploratory studies using two examples of retrospective clinical data from routine tests; diagnostic prediction of small round blue cell tumors (SRBCT) of childhood and determining the estrogen receptor (ER) status of sporadic breast cancer. The classification performance is gauged using blind tests. These studies demonstrate the feasibility of machine learning-based molecular cancer classification.

Adult↗

PubMed2026

Biological Parts in Yeast Synthetic Biology: From Regulatory Elements to Predictive Design Platforms.

Yeasts, particularly Saccharomyces cerevisiae, are important eukaryotic chassis for synthetic biology because of their tractable genetics, versatile toolkits, and broad utility in metabolic engineering and functional genomics. Progress in this field has been driven by biological parts that enable programmable control of gene expression and cellular behavior. Early efforts focused mainly on promoters, terminators, and other regulatory elements for tuning individual genes. However, as engineering expanded to multigene pathways, genetic circuits, and dynamic regulatory systems, the limits of part-centric design became clear. Part performance is often shaped by genomic context, chromatin state, host physiology, and interactions with other components, which restricts modularity and predictability. In response, yeast synthetic biology is shifting toward integrated design frameworks combining multilayer regulation, standardized assembly, automated experimentation, and computational modeling. This review provides an integrated perspective on the evolution of biological parts across DNA-, RNA-, and protein-level regulation, connecting these advances with assembly frameworks, biofoundries, and machine learning to trace the trajectory from part-centric engineering toward predictive, system-level design in yeast synthetic biology.

Biofoundry↗

PubMed2025

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

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

DNA Methylation↗

PubMed2025

HINN: Hierarchical Input Neural Network identifies multi-omics biomarker for cognitive decline.

Understanding complex diseases requires models that can integrate diverse layers of biological data while yielding insights that are biologically interpretable. Although multi-omics integration with machine learning (ML) has advanced disease prediction and biomarker discovery, most existing approaches overlook the hierarchical and regulatory relationships that connect these molecular layers. Here, we present the Hierarchical Input Neural Network (HINN), a deep learning framework that incorporates known cross-omics relationships directly into its architecture, capturing the flow of information from genomics to epigenomics, transcriptomics, and downstream biological processes. By embedding these relationships, HINN improves both predictive performance and biological interpretability. We applied HINN to blood-derived multi-omics data from individuals with Alzheimer's disease or mild cognitive impairment to predict cognitive scores from standardized assessments. HINN outperformed both baseline and state-of-the-art models and pinpointed multi-omics biomarkers-including SNPs and promoter-region CpG sites in ATP6V1C1 and RCHY1 -that were significantly correlated with plasma p-Tau181 levels. These features map to biologically relevant processes with potential implications for cognitive decline. Our findings demonstrate how combining deep learning with biological knowledge can uncover interpretable, blood-based biomarkers for cognitive decline due to complex diseases such as Alzheimer's. All code and data are openly available at https://github.com/bozdaglab/HINN.

Alzheimer’s disease↗

PubMed2024

Massively parallel approaches for characterizing noncoding functional variation in human evolution.

The genetic differences underlying unique phenotypes in humans compared to our closest primate relatives have long remained a mystery. Similarly, the genetic basis of adaptations between human groups during our expansion across the globe is poorly characterized. Uncovering the downstream phenotypic consequences of these genetic variants has been difficult, as a substantial portion lies in noncoding regions, such as cis-regulatory elements (CREs). Here, we review recent high-throughput approaches to measure the functions of CREs and the impact of variation within them. CRISPR screens can directly perturb CREs in the genome to understand downstream impacts on gene expression and phenotypes, while massively parallel reporter assays can decipher the regulatory impact of sequence variants. Machine learning has begun to be able to predict regulatory function from sequence alone, further scaling our ability to characterize genome function. Applying these tools across diverse phenotypes, model systems, and ancestries is beginning to revolutionize our understanding of noncoding variation underlying human evolution.

Humans↗

PubMed2025

Popcorn: prediction of short coding and noncoding genomic sequences in prokaryotes.

SUMMARY: The most challenging prokaryotic genes to identify often correspond to short ORFs (sORFs) encoding small proteins or to noncoding RNAs. RNA-seq experiments commonly evince small transcripts that do not correspond to annotated genes and are candidates for novel coding sORFs or small regulatory RNAs, but it can be difficult to accurately assess whether the numerous small transcripts are coding or not. We present Popcorn (PrOkaryotic Prediction of Coding OR Noncoding), a novel machine learning method for determining whether prokaryotic sequences are coding or noncoding. We find that Popcorn is effective in distinguishing coding from noncoding sequences, including coding sORFs and noncoding RNAs. AVAILABILITY AND IMPLEMENTATION: Freely available for use on the web at https://cs.wellesley.edu/∼btjaden/Popcorn. Source code available at https://github.com/btjaden/Popcorn and https://doi.org/10.5281/zenodo.15120075.

Open Reading Frames↗

PubMed2026

Functional neuroimaging subtypes of obsessive-compulsive disorder: A systematic review and meta-analysis.

Obsessive-compulsive disorder (OCD) exhibits substantial clinical heterogeneity that may reflect underlying neurobiological diversity. Neuroimaging-based subtyping may advance precision psychiatry by identifying biologically distinct subgroups with differential treatment responses. This study systematically synthesized evidence from functional neuroimaging subtyping studies in OCD to identify reproducible neurobiological subtypes, characterize their clinical profiles, and establish a consensus-based classification framework. We reviewed 40 original studies employing machine learning, clustering, normative modeling, or classification approaches, encompassing approximately 8,150 patients. Consensus clustering identified three reproducible neurobiological subtypes. The Limbic-Hyperactive subtype, comprising approximately 40% of patients, exhibited amygdala and insula hyperconnectivity, elevated anxiety levels, predominant contamination and washing symptoms, and favorable response to cognitive-behavioral therapy. The Fronto-Striatal-Hypoconnected subtype, comprising approximately 35% of patients, demonstrated reduced orbitofrontal-striatal connectivity, cognitive inflexibility, predominant checking and ordering symptoms, and a favorable response to selective serotonin reuptake inhibitors. The Global-Disrupted subtype, comprising approximately 25% of patients, exhibited widespread connectivity disruption, greater symptom severity, and poor treatment response. Support vector machine classification achieved 81.5% accuracy for subtype assignment, though classification of OCD versus healthy controls showed limited generalizability in multisite settings (AUC 0.567-0.673). These findings support a neuroimaging-based framework for personalized treatment selection but require prospective validation.

Humans↗

PubMed2026

Epigenetic profiling of circulating cell-free DNA for early detection and minimal residual disease assessment in lung cancer: a focus on DNA methylation.

Lung Cancer (LC) continues to be the biggest cause of cancer-related deaths around the world, mostly because of delayed diagnosis. Even if tissue biopsies and circulating tumor DNA (ctDNA) tests have revolutionized clinical management of LC patients, their effectiveness is restricted in settings with lower tumor burden, molecular heterogeneity, and bias in sampling approaches. In this scenario, the epigenetic profiling of cell-free DNA (cfDNA) stands out as a promising, less invasive approach, accurately detect cancer traces. Evidence from stage I-II disease and CT-detected pulmonary nodules supports the diagnostic potential of cfDNA methylation, although further validation in prospective screening cohorts remains necessary. Beyond genomic alterations, cfDNA epigenetic changes, including DNA methylation, chromatin organization, nucleosome positioning, and fragmentation patterns, reflect multi-dimensional complexity of tumor biology. These properties convey both the functional status and the origin of the circulating DNA fragments, accelerating for tumor integrating genomic analysis. Within this group, DNA methylation is the biologically robust and clinically well-established epigenetic marker, as alterations in methylation linked to cancer often occur in the early stages of tumorigenesis and are commonly found across different cancer cell types. Here, we explored the biological and clinical relevance of the epigenetic landscape of cfDNA in LC patients, particularly focusing on DNA methylation-based biomarkers and their evolving applications towards early diagnosis and post-surgical monitoring of minimal residual disease (MRD). We aimed to comprehensively overview analytical approaches for cfDNA methylation analysis, including targeted and genome-wide profiling strategies, and discuss their integration with machine learning (ML) and multi-omics frameworks in order to improve diagnostic performance and clinical applicability in LC management.

DNA methylation↗

PubMed2025

EDAmame: interactive exploratory data analyses with explainable models.

SUMMARY: Complex tabular datasets comprising many diverse features can require specific expertise to interpret, posing a barrier to researchers with minimal data science experience. EDAmame is an interactive tool that simplifies initial analysis and visualization of these datasets, providing insights into data quality and feature relationships. By leveraging open-source machine learning frameworks in R, EDAmame allows researchers to perform effective exploratory data analysis without command-line or coding requirements. AVAILABILITY AND IMPLEMENTATION: A limited online version can be accessed at https://edamame.org.au/ or can be downloaded from https://doi.org/10.5281/zenodo.15356492. The app is developed in R Shiny and implements tidyverse and tidymodels packages.

Machine Learning↗

PubMed2025

Properties Governing Native State Entanglements and Relationships to Protein Function.

Non-covalent lasso entanglements are structural motifs found in a majority of globular proteins, and their misfolding has been linked to a range of biological consequences. Here, we characterize these motifs' structural and physicochemical properties, sequence biases, functional site correlations, and universal features across E. coli, S. cerevisiae, and H. sapiens. We find that the crossing residues, which pierce the plane of the entanglement loop, are 11-times more likely to be a β-strand than an α-helix or random coil, and that around this position the protein sequence is 2.5-times more likely to be composed of a stretch of all hydrophobic residues (most often Val, Ile, or Phe) compared to other sequence motifs. Functionally, crossing residues are enriched at enzyme active sites in S. cerevisiae and small molecule binding residues across all species to degrees greater than expected by random chance. Metal binding residues are enriched in these entanglements in H. sapiens. Increasing statistical power by pooling together these species data, we find RNA-binding residues are enriched in these entanglement components. On the other hand, there is a spatial depletion of crossing residues at sites involved in protein binding. Using machine learning, we identified eight robust features predictive of these entanglements, achieving AUROC scores of 0.8 across species. These results are significant because they suggest a direct role for components of native entanglements in particular protein functions, as well as identifying strong secondary structure and sequence preferences in native entanglements.

Humans↗

PubMed2026

Ribo-ITP enables identification of translons from limited input samples.

In the last decade, an unexpectedly large number of translated regions (translons) have been discovered using ribosome profiling and proteomics. Translons can act as regulatory elements or encode functional micropeptides. However, identification of translons has been limited to cell lines or large organs due to high input requirements for conventional ribosome profiling and mass spectrometry. Here, we address this input limitation using Ribo-ITP on difficult-to-collect samples such as microdissected hippocampal tissues and single preimplantation embryos to identify thousands of translons. To test the translational capacity of the identified translons, we engineer a translon-dependent GFP reporter system and detect expression of translons initiating at ATG and near-cognate start codons in mouse embryonic stem cells (mESCs). We identify distinct expression patterns of translons using a comparative analysis of more than a thousand ribosome profiling datasets across a wide range of cell types. Further, using a machine learning model, we predict that specific upstream translons in synaptically enriched mRNAs regulate translation efficiency of the annotated coding region. Taken together, we present a proof-of-concept study to identify non-canonical translation events from low input samples which can be applied to cell and tissue types inaccessible to conventional methods.

Animals↗

PubMed2026

Artificial Intelligence for Colorectal Surgeons-Part II: Research Applications, Challenges in Adoption, and Practical Resources.

BACKGROUND: This is part II of a 2-part series examining artificial intelligence in colorectal surgery. Part I established foundational concepts and clinical applications. Implementation, however, requires understanding research methodologies, available resources, and the specific challenges currently limiting widespread adoption. These topics are the focus of part II. OBJECTIVE: To examine artificial intelligence's transformation of surgical research, provide practical implementation resources, address adoption challenges, and explore future directions in colorectal surgery. METHODS: Comprehensive literature review focusing on artificial intelligence research methodology, implementation barriers, educational resources, and emerging technologies relevant to colorectal surgeons. RESULTS: Artificial intelligence streamlines clinical trial design through predictive modeling and natural language processing, reducing enrollment challenges that contribute to failed or inadequate trial accrual. Machine learning enables heterogeneity analysis within clinical trials, identifying treatment-responsive subgroups. Foundation models unlock analysis of unstructured electronic health record data at scale. Professional societies and universities offer specialized artificial intelligence education programs, with open-access data sets facilitating research participation. However, implementation faces multifaceted challenges: technical infrastructure demands, with real-time processing requiring dedicated graphics processing unit clusters; regulatory frameworks struggling with continuously evolving algorithms; undefined liability distribution for artificial intelligence-assisted decisions; algorithmic bias risking health care disparities; and the "black box" problem limiting clinical trust. Economic barriers include substantial initial costs without clear reimbursement pathways. Future directions include multimodal artificial intelligence integrating imaging, genomics, and histopathology; cognitive robotic systems with real-time decision support; digital twin technology for patient-specific surgical simulation; and global surgical artificial intelligence networks enabling distributed learning across institutions. CONCLUSIONS: Although artificial intelligence offers transformative potential for colorectal surgery research and practice, successful implementation requires addressing technical, regulatory, ethical, and economic challenges. The surgeon's evolving role demands both traditional expertise and computational fluency. Future advances in multimodal integration, autonomous systems, and global collaboration will fundamentally reshape surgical practice but will require thoughtful implementation prioritizing patient benefit and clinical value.

Humans↗

PubMed2026

Knowledge-driven interpretable neural networks provide mechanistic insight.

Analyzing omics data in the context of pathway knowledge is critical for understanding the molecular mechanisms underlying pathological changes. However, current pathway analysis methods do not model the detailed mechanistic nature of biological interactions, limiting the understanding of pathway behavior to a relatively shallow level. To address this issue, we present a knowledge-driven machine learning framework that embeds features into pathway graphs and models reactions analytically, producing interpretable feature hierarchies and subnetworks in which functional associations are estimated to model biological interactions. The approach is agnostic to feature selection, enabling the use of full omics data sets without discarding weak signals. Applications to breast cancer microRNA-gene regulation data and COVID-19 metabolomic data highlight immune and metabolic pathways relevant to disease progression. This framework bridges predictive modeling with mechanistic interpretation and offers a foundation for integrative pathway analysis.

Humans↗

PubMed2025

GRUMB: a genome-resolved metagenomic framework for monitoring urban microbiomes and diagnosing pathogen risk.

SUMMARY: Urban infrastructure hosts dynamic microbial communities that complicate biosurveillance and AMR monitoring. Existing tools rarely combine genome-resolved reconstruction with ecological modeling and batch-aware analytics tailored to infrastructure-scale studies. We present GRUMB (Genome-Resolved Urban Microbiome Biosurveillance), an open-source, SLURM-compatible pipeline that reconstructs high-quality metagenome-assembled genomes (MAGs) from shotgun sequencing reads and integrates taxonomic/functional annotation (CARD, VFDB), batch-aware normalization, ecological diagnostics and machine learning classification of environment types with uncertainty and risk scoring. GRUMB accepts either SRA project accessions or paired-end FASTQ files with metadata, and produces assemblies, MAGs, taxonomic and functional profiles, ecological outputs and risk-informed classification. Its modular design enables reproducible, infrastructure-scale biosurveillance across diverse environments. AVAILABILITY AND IMPLEMENTATION: GRUMB is freely available under the MIT License at: https://github.com/SuleimanAminu/genome-resolved-urban-microbiome-biosurveillance; Zenodo DOI: https://doi.org/10.5281/zenodo.15505402. Requirements: Linux (Ubuntu 20.04+), Python 3.11, R 4.2+, SLURM. Issues and feature requests are tracked on GitHub.

Microbiota↗

PubMed2026

Decoding gene regulation in plant genomes with artificial intelligence.

One of the central goals of plant functional genomics is to uncover regulatory mechanisms that shape agriculturally important traits to inform crop improvement. Recent advances in machine learning (ML) and artificial intelligence (AI), especially Large Language Models (LLMs), have greatly transformed our ability to derive regulatory information from complex genomics data. This review starts with a brief introduction of recent advances in AI and ML. We then present a plant-focused synthesis of emerging applications of AI- and LLM tools to: (i) predict epigenomic features, regulatory DNA elements, and gene expressions; (ii) infer gene regulatory network; and (iii) estimate post-transcriptional regulation.

Artificial intelligence↗

PubMed2025

Conserved HSFA1-dependent chromatin dynamics drive heat stress responses in plants.

Eukaryotic organisms remodel chromatin landscapes to regulate gene expression in response to environmental stress. In plants, heat stress (HS) induces widespread chromatin changes, yet the role of heat shock transcription factors (HSFs) in chromatin remodeling and their evolutionary conservation remains unclear. Using Marchantia polymorpha Mphsf mutants and Arabidopsis thaliana Athsfa1s mutants, we identify HSFA1 as a key regulator of HS-induced cis-regulatory element (CRE) accessibility, a mechanism conserved across land plants, mice, and humans. Gene regulatory network modeling reveals parallel transcription factor subnetworks, with MpWRKY10 and MpABI5B acting as indirect and negative HS regulators. We further showed that ABA modulates gene expression in an HSFA1-dependent manner without inducing chromatin remodeling. Finally, we develop a machine learning framework integrating chromatin accessibility and CRE information to predict gene expression across species, revealing stress-responsive regulatory logic at the transcriptional level. These findings provide insights into how TFs coordinate chromatin architecture to drive stress adaptation.

Heat-Shock Response↗

PubMed2026

SeqQC-former: A sequence-quality fusion framework for QC-aware review prioritization of candidate somatic SNVs in cancer genomics.

The accurate prioritization of candidate somatic single-nucleotide variants (SNVs) remains a challenge due to the substantial variability in sequencing quality across genomic loci. SeqQC-Former is a sequence-quality fusion framework that integrates the local nucleotide context with read-level quality-control (QC) covariates derived from matched tumor-normal sequencing data. This integration generates QC-aware prioritization scores for the downstream review of candidate variants. Unlike conventional variant callers, SeqQC-Former is designed not to infer biological truth but to support post-calling review and prioritization under heterogeneous sequencing conditions. The framework was trained and evaluated on a SEQC2-derived dataset comprising 89,447 candidate loci, including 1378 positive and 88,069 negative loci. In chromosome-held-out validation, which aims to reduce potential genomic-position leakage, SeqQC-Former demonstrated strong discrimination (AUROC = 0.9479; AUPRC = 0.9448), indicating good generalization to previously unseen chromosomes. Given that the SEQC2-derived labels contain QC-associated information; these results should be interpreted as an evaluation of QC-aware prioritization capability rather than an independent validation of biological variant correctness. Ablation analyses revealed that structured QC covariates provided the dominant predictive signal under the current SEQC2-derived labeling regime. SeqQC-Former achieved a significantly higher AUROC than classical machine-learning baselines, as determined by DeLong's test (p < 0.01). Application to 53,164 glioblastoma variants demonstrated that external predictions were sensitive to QC scaling and threshold selection, underscoring that model outputs should be interpreted as QC-dependent prioritization scores rather than calibrated probabilities or definitive biological classifications. Overall, SeqQC-Former offers a reproducible post-calling QC-aware prioritization framework for large-scale somatic SNV review and underscores the importance of explicitly modeling sequencing-quality information when interpreting structured cancer genomics datasets.

Humans↗