Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “genomic foundation models”

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

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

At least 19 recordsLinked to original sources
PubMed2025

MutBERT: probabilistic genome representation improves genomics foundation models.

MOTIVATION: Understanding the genomic foundation of human diversity and disease requires models that effectively capture sequence variation, such as single nucleotide polymorphisms (SNPs). While recent genomic foundation models have scaled to larger datasets and multi-species inputs, they often fail to account for the sparsity and redundancy inherent in human population data, such as those in the 1000 Genomes Project. SNPs are rare in humans, and current masked language models (MLMs) trained directly on whole-genome sequences may struggle to efficiently learn these variations. Additionally, training on the entire dataset without prioritizing regions of genetic variation results in inefficiencies and negligible gains in performance. RESULTS: We present MutBERT, a probabilistic genome-based masked language model that efficiently utilizes SNP information from population-scale genomic data. By representing the entire genome as a probabilistic distribution over observed allele frequencies, MutBERT focuses on informative genomic variations while maintaining computational efficiency. We evaluated MutBERT against DNABERT-2, various versions of Nucleotide Transformer, and modified versions of MutBERT across multiple downstream prediction tasks. MutBERT consistently ranked as one of the top-performing models, demonstrating that this novel representation strategy enables better utilization of biobank-scale genomic data in building pretrained genomic foundation models. AVAILABILITY AND IMPLEMENTATION: https://github.com/ai4nucleome/mutBERT.

Humans↗
PubMed2025

NextVir: Enabling classification of tumor-causing viruses with genomic foundation models.

MOTIVATION: Oncoviruses, pathogens known to cause or increase the risk of cancer, include both common viruses such as human papillomaviruses and rarer pathogens such as human T-lymphotropic viruses. Computational methods for detecting viral DNA from data acquired by modern DNA sequencing technologies have enabled studies of the association between oncoviruses and cancers. Those studies are rendered particularly challenging when multiple species of oncovirus are present in a tumor sample. In such scenarios, merely detecting the presence of a sequencing read of viral origin is insufficiently informative-instead, a more precise characterization of the viral content in the sample is required. RESULTS: We address this need with NextVir, to our knowledge the first multi-class viral classification framework that adapts genomic foundation models to detecting and classifying sequencing reads of oncoviral origin. Specifically, NextVir explores several foundation models-DNABERT-S, Nucelotide Transformer, and HyenaDNA-and efficiently fine-tunes them to enable accurate identification of the sequencing reads' origin. The results demonstrate superior performance of the proposed framework over existing deep learning methods and suggest downstream potential for foundational models in genomics.

Humans↗
PubMed2025

Orthrus: Towards Evolutionary and Functional RNA Foundation Models.

In the face of rapidly accumulating genomic data, our ability to accurately predict key mature RNA properties that underlie transcript function and regulation remains limited. Pre-trained genomic foundation models offer an avenue to adapt learned RNA representations to biological prediction tasks. However, existing genomic foundation models are trained using strategies borrowed from textual domains that do not leverage biological domain knowledge. Here, we introduce Orthrus, a Mamba-based mature RNA foundation model pre-trained using a novel self-supervised contrastive learning objective with biological augmentations. Orthrus is trained by maximizing embedding similarity between curated pairs of RNA transcripts, where pairs are formed from splice isoforms of 10 model organisms and transcripts from orthologous genes in 400+ mammalian species from the Zoonomia Project. This training objective results in a latent representation that clusters RNA sequences with functional and evolutionary similarities. We find that the generalized mature RNA isoform representations learned by Orthrus significantly outperform genomic foundation models on mRNA property prediction tasks, and requires only a fraction of fine-tuning data to do so. Finally, we show that Orthrus is capable of capturing divergent biological function of individual transcript isoforms.

Journal Article↗
PubMed2026

Accelerating inference in genomic and proteomic foundation models via speculative decoding.

MOTIVATION: Genomic and protein foundation models (GFMs and PFMs) have demonstrated strong performance in learning the language of DNA and proteins, but their use in large-scale sequence generation is limited by the latency of autoregressive decoding. Because every token triggers a forward pass of a large Transformer, whose inference is relatively slow, long-sequence generation quickly becomes costly. RESULTS: In this work we adapt speculative decoding to a representative GFM: the DNA model DNAGPT and two representative PFMs: ProGen2 and ProtGPT2. We implement a probabilistic variant of speculative decoding, in which a lightweight draft model proposes short token spans and a larger target model verifies or corrects them in parallel, while preserving the target model's sampling distribution. Across all three models we systematically study the effect of speculation window length, temperature, draft architecture and prompt length, and we benchmark tokens per second over multiple runs per configuration. Speculative decoding yields consistent speedups over standard key-value cached decoding, with maximum observed speedup reaching 100% increase, while average gains across models ranging between 20% and 40% (e.g. 1.2×-1.4×), without changing the underlying target model predictions. Our results show that speculative decoding is a practical and model-agnostic strategy for accelerating genomic and proteomic sequence generation without sacrificing prediction quality. AVAILABILITY AND IMPLEMENTATION: All code and results are freely available at https://github.com/Georgakopoulos-Soares-lab/BioSpecDec.

Genomics↗
PubMed2026

RP3Net: a deep learning model for predicting recombinant protein production in Escherichia coli.

MOTIVATION: Recombinant protein expression can be a limiting step in the production of protein reagents for drug discovery and other biotechnology applications. We introduce RP3Net (Recombinant Protein Production Prediction Network), an AI model of small-scale heterologous soluble protein expression in Escherichia coli. RP3Net utilizes the most recent protein and genomic foundational models. A curated dataset of internal experimental results from AstraZeneca and publicly available data from the Structural Genomics Consortium was used for training, validation and testing of RP3Net. RESULTS: RP3Net achieves an increase in area under the receiver operator curve (AUROC) of 0.15, compared to a baseline model. When experimentally validated on an independent, prospective, manually selected set of 97 constructs, RP3Net outperformed currently available models, with an AUROC of 0.83, delivering accurate predictions in 77% of the cases, and correctly identifying successfully expressing constructs in 92% of cases. AVAILABILITY AND IMPLEMENTATION: The model, along with installation and running instructions, is available under an MIT licence at https://github.com/RP3Net/RP3Net, DOI 10.5281/zenodo.17243498.

Escherichia coli↗
PubMed2025

DNABERT-S: pioneering species differentiation with species-aware DNA embeddings.

SUMMARY: We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e. DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 28 diverse datasets show DNABERT-S's effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline's performance in 10-shot species classification with just a 2-shot training. AVAILABILITY AND IMPLEMENTATION: Model, codes, and data are publically available at https://github.com/MAGICS-LAB/DNABERT_S.

Sequence Analysis, DNA↗
PubMed2024

DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings.

We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e., DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 23 diverse datasets show DNABERT-S's effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline's performance in 10-shot species classification with just a 2-shot training. Model, codes, and data is publicly available at https://github.com/MAGlCS-LAB/DNABERT_S.

Journal Article↗
PubMed2026

Bridging Ancestry Gaps in Genomic Risk Prediction with Tabular Foundation Models.

MOTIVATION: Models deployed for genomic prediction of diseases perform unevenly across populations, limiting clinical utility. Two factors drive this limitation: large imbalances in sample availability across ancestry groups and non-stationarity of genotype-phenotype effect sizes across the ancestry continuum. While tabular foundation models with in-context learning (ICL) have shown strong sample efficiency in other domains, their effectiveness for genotype-to-phenotype prediction and their robustness to ancestry-driven effect heterogeneity remain unclear. RESULTS: Using large, ancestrally diverse biobank data, we show that ICL-capable tabular foundation models reduce performance degradation in under-sampled ancestry groups compared to conventional supervised approaches. However, we find that prevailing models trained on existing synthetic tabular tasks fail when allele effect sizes vary across ancestry space. Treating genetic ancestry as a continuous variable, we introduce an instruction-tuning framework that exposes models to synthetic tasks with ancestry-dependent non-stationary effects. Instruction-tuned models achieve improved and more stable predictive performance across the genetic ancestry continuum, including for individuals distant from in-context exemplars in ancestry space. AVAILABILITY AND IMPLEMENTATION: All code for instruction-tuning models, synthetic task generation, data wrangling, and model evaluation, is publicly available at https://github.com/ai4pm/Bridging-Ancestry-Gaps-in-Genomic-Risk-Prediction-with-Tabular-Foundation-Models. The final instruction-tuned model (ICL-NS-G2P-proto) is also released in this repository. Detailed documentation is provided, including environment setup instructions and guidelines for running various parts. The instruction-tuning task datasets are available at https://zenodo.org/records/18309187.

Ancestry Continuum↗
PubMed2026

Bridging ancestry gaps in genomic risk prediction with tabular foundation models.

MOTIVATION: Models deployed for genomic prediction of diseases perform unevenly across populations, limiting clinical utility. Two factors drive this limitation: large imbalances in sample availability across ancestry groups and non-stationarity of genotype-phenotype effect sizes across the ancestry continuum. While tabular foundation models with in-context learning (ICL) have shown strong sample efficiency in other domains, their effectiveness for genotype-to-phenotype prediction and their robustness to ancestry-driven effect heterogeneity remain unclear. RESULTS: Using large, ancestrally diverse biobank data, we show that ICL-capable tabular foundation models reduce performance degradation in under-sampled ancestry groups compared to conventional supervised approaches. However, we find that prevailing models trained on existing synthetic tabular tasks fail when allele effect sizes vary across ancestry space. Treating genetic ancestry as a continuous variable, we introduce an instruction-tuning framework that exposes models to synthetic tasks with ancestry-dependent non-stationary effects. Instruction-tuned models achieve improved and more stable predictive performance across the genetic ancestry continuum, including for individuals distant from in-context exemplars in ancestry space. AVAILABILITY AND IMPLEMENTATION: All code for instruction-tuning models, synthetic task generation, data wrangling, and model evaluation, is publicly available at https://github.com/ai4pm/Bridging-Ancestry-Gaps-in-Genomic-Risk-Prediction-with-Tabular-Foundation-Models. The final instruction-tuned model (ICL-NS-G2P-proto) is also released in this repository. Detailed documentation is provided, including environment setup instructions and guidelines for running various parts. The instruction-tuning task datasets are available at https://zenodo.org/records/18309187.

Humans↗
PubMed2026

Biological Foundation Models for Complex Disease Research and Clinical Translation.

Complex diseases, including cancer, rare genetic disorders, neurodevelopmental and psychiatric conditions, and neurodegenerative diseases, arise from interactions among genetic variation, gene regulation, and cellular states that are difficult to capture using a single data type or biological scale. Biological foundation models address this challenge by treating nucleotides and genes as tokens and learning representations that can be transferred to downstream biomedical and clinical tasks. In this review, we examine two major model classes, genomic sequence foundation models and cell foundation models, and compare their tokenization strategies, model architectures, pretraining objectives, and adaptation methods. We summarize their emerging applications in regulatory variant interpretation, disease-associated cell-state analysis, drug-response prediction, and therapeutic target discovery across complex diseases. We distinguish applications supported by experimental or retrospective validation from those that remain primarily computational or conceptual. We further discuss key challenges to clinical translation, including multimodal data integration, model interpretability, benchmarking, patient-specific prediction, and privacy protection. We highlight future opportunities to integrate biological foundation models with emerging frameworks of medical digital twins, agentic AI, and federated learning. By linking model design to translational goals, this review provides a practical framework for evaluating biological foundation models and their readiness for complex disease research and clinical use.

biological foundation model↗
PubMed2026

Jingjing Zhai and Edward S. Buckler.

Dr. Laura Zahn asked the authors, Dr. Jingjing Zhai and Dr. Edward (Ed) S. Buckler, to tell us about their research relating to their Cell Genomics paper, "PlantCAD2: A DNA foundation model for interpreting genomes across flowering plants."

Genomics↗
PubMed2026

Artificial intelligence agents and agentic artificial intelligence applied to precision medicine.

Precision medicine seeks to individualise care by integrating multimodal biomedical data, yet most deployed clinical artificial intelligence (AI) remains assistive, providing predictions without managing workflows or adapting autonomously. Agentic AI, built on large language models (LLMs), has emerged as a paradigm characterised by autonomy, goal-directed reasoning, memory, planning and tool use. This review synthesises evidence on agentic AI and LLMs applied to precision medicine, encompassing drug discovery, genomics, oncology, rare disease diagnostics and clinical pharmacology. This review also examines architectural components, recent validation milestones and emerging challenges, including hallucination, sociodemographic bias and evolving regulatory frameworks across the FDA, the EU AI Act and the WHO.

agentic AI↗
PubMed2026

The Continuity Trap in Data Science Health Research.

Secondary use is now the ordinary condition of data science health research rather than an exception to it. Electronic health records collected for clinical care become prediction tools and inputs for generative AI; imaging archives become foundation-model corpora; genomic datasets become resources for polygenic risk scores; and legacy biospecimens become renewable, indefinitely distributable cell lines. Governance has responded by emphasizing verifiable instruments such as provenance logs, repository approvals, broad-consent forms, data-use agreements, model cards, records of processing, and locality-preserving architectures. These instruments are necessary, and they answer real questions about lineage, privacy, institutional responsibility, and accountability, but they are not sufficient to establish that a present use remains ethically justified. We define ethical continuity as the persistence of normatively relevant relationships between the original conditions of data generation or material collection and subsequent downstream uses, such that current uses remain justifiable in light of the expectations, permissions, meanings, and relational obligations present at entrustment. We then define the Continuity Trap as a review-stage governance error in which a salient signal of continuity in one domain is treated as sufficient evidence of ethical continuity overall, causing inquiry into the remaining domains to close prematurely. The trap is not ordinary noncompliance, ethics creep, or a demand for universal rereview; it is a cross-domain inference error that can arise even in careful, good-faith review. We distinguish it from proxy closure, of which it is a continuity-specific subtype, and from Goodhart's and Campbell's laws, which describe how measures degrade once they become targets. We operationalize ethical continuity across 4 domains: provenance, semantics, authorization, and relational standing, developed in our Representational Veracity framework, and we show that these domains can diverge as data are linked, transformed, modeled, and redeployed. We identify the institutional mechanisms-provenance privilege, descriptor sedimentation, authorization fossilization, and community effacement-that cause auditable signals to be overread, and we examine how the US Health Insurance Portability and Accountability Act (HIPAA) of 1996, the General Data Protection Regulation, the European Health Data Space, US Food and Drug Administration guidance, the US National Institute of Standards and Technology (NIST) AI Risk Management Framework, and federated-learning governance can reduce risk while still inducing continuity traps. We apply the framework to consent and nonconsent settings, including public health, immunization, syndromic, and wastewater surveillance, polygenic risk scores, induced pluripotent stem cells, federated learning, and health-related large language models. The policy implication is trigger-based continuity review: rather than rereviewing every reuse, investigators and reviewers should identify the weakest continuity domain at the present data stage and impose a domain-matched safeguard, recorded in a short continuity statement. This reframing is intended for the committees, repositories, funders, and governance bodies that decide whether reuse may proceed, and it matters most in cross-border and low-resource settings. Provenance should begin ethical review; it should not end it.

Data Science↗
PubMed2025

Flashzoi: an enhanced Borzoi for accelerated genomic analysis.

MOTIVATION: Accurately predicting how DNA sequence drives gene regulation and how genetic variants alter gene expression is a central challenge in genomics. Borzoi, which models over ten thousand genomic assays including RNA-seq coverage from over half a megabase of sequence context alone promises to become an important foundation model in regulatory genomics, both for massively annotating variants and for further model development. However, the currently used relative positional encodings limit Borzoi's computational efficiency. RESULTS: We present Flashzoi, an enhanced Borzoi model that leverages rotary positional encodings and FlashAttention-2. This achieves over 3-fold faster training and inference and up to 2.4-fold reduced memory usage, while maintaining or improving accuracy in modeling various genomic assays including RNA-seq coverage, predicting variant effects, and enhancer-promoter linking. Flashzoi's improved efficiency facilitates large-scale genomic analyses and opens avenues for exploring more complex regulatory mechanisms and modeling. AVAILABILITY AND IMPLEMENTATION: The Flashzoi model architecture is part of the MIT-licensed borzoi-pytorch package, can be found at https://github.com/johahi/borzoi-pytorch and installed via pip. Model weights for all four Flashzoi and Borzoi replicates are available at https://huggingface.co/johahi under the MIT license. The code has been archived at https://zenodo.org/records/15669913.

Genomics↗
PubMed2026

Episode clustering in phylogenetic networks.

MOTIVATION: The classical duplication episode clustering (EC) model introduced by Guigó et al. in the 1990s provides a foundational approach for inferring genomic duplication events crucial to understanding genome evolution. This model clusters single gene duplications from a collection of gene trees at locations in the species tree to minimize the total number of such locations, called duplication episodes. However, it does not capture reticulate evolutionary histories. RESULTS: Here, we introduce NetEC, a novel extension of this problem to phylogenetic networks. To solve NetEC, we first develop a polynomial-time dynamic programming (DP) algorithm for testing whether a given set of network nodes can serve as episode locations. We then propose a main inference algorithm that utilizes this DP component to optimize the episode count; while the feasibility test runs in polynomial time, the full optimization has exponential worst-case complexity, and an optional heuristic mode is provided for larger instances. We also propose an extended episode analysis procedure that identifies additional genomic duplication candidates below reticulation nodes, complementing the main algorithm by resolving potential upward clustering of duplications induced by reticulation. We evaluate our method on simulated data and on an empirical Pandanales dataset comprising over 29 000 gene trees, demonstrating exact and accurate inference of genomic duplication events even in the presence of multiple reticulations. AVAILABILITY AND IMPLEMENTATION: All experiments were conducted using the NetEC tool (https://github.com/ppgorecki/netec), with all input data, scripts, and parameter settings for reproduction available in the same repository.

Phylogeny↗
PubMed2025

Knowledge-guided Contextual Gene Set Analysis Using Large Language Models.

Gene set analysis (GSA) is a foundational approach for interpreting genomic data of diseases by linking genes to biological processes. However, conventional GSA methods overlook clinical context of the analyses, often generating long lists of enriched pathways with redundant, nonspecific, or irrelevant results. Interpreting these requires extensive, ad-hoc manual effort, reducing both reliability and reproducibility. To address this limitation, we introduce cGSA, a novel AI-driven framework that enhances GSA by incorporating context-aware pathway prioritization. cGSA integrates gene cluster detection, enrichment analysis, and large language models to identify pathways that are not only statistically significant but also biologically meaningful. Benchmarking on 102 manually curated gene sets across 19 diseases and ten disease-related biological mechanisms shows that cGSA outperforms baseline methods by over 30%, with expert validation confirming its increased precision and interpretability. Two independent case studies in melanoma and breast cancer further demonstrate its potential to uncover context-specific insights and support targeted hypothesis generation.

Journal Article↗
PubMed2026

Knowledge-guided contextual gene set analysis with large language models.

MOTIVATION: Gene set analysis (GSA) is a foundational approach for interpreting genomic data of diseases by linking genes to biological processes. However, conventional GSA methods overlook clinical context of the analyses, often generating long lists of enriched pathways with redundant, nonspecific, or irrelevant results. Interpreting these requires extensive, ad-hoc manual effort, reducing both reliability and reproducibility. RESULTS: We introduce cGSA, a novel AI-driven framework that enhances GSA by incorporating context-aware pathway prioritization. cGSA integrates gene cluster detection, enrichment analysis, and large language models to identify pathways that are not only statistically significant but also biologically meaningful. Benchmarking on 102 curated gene sets across 19 diseases and ten disease-related biological mechanisms shows that cGSA outperforms baseline methods by over 30%, with expert validation confirming its increased precision and interpretability. Two independent case studies in melanoma and breast cancer further demonstrate its potential to uncover context-specific insights and support targeted hypothesis. AVAILABILITY AND IMPLEMENTATION: The demo website is publicly available at https://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/cGSA/, while the data and code can be accessed at https://github.com/ncbi-nlp/cGSA.

Large Language Models↗
PubMed2026

Molecular biomarker profiling in noninfectious uveitis: a chronological review of discovery.

PURPOSE OR REVIEW: Noninfectious uveitis (NIU) encompasses a heterogeneous group of immune-mediated intraocular inflammatory diseases whose complexity has driven systematic molecular biomarker discovery. This review presents NIU molecular biomarkers organized by biological category; autoantigens, human leukocyte antigens (HLA) and genetic markers, cellular immune subsets, cytokines, chemokines, and multiomics platforms including proteomics, microbiome metagenomics, metabolomics, and single-cell transcriptomics with each category presented in strict chronological order of landmark discovery. RECENT FINDINGS: We present a review organized along two nested timelines. Categories are presented in the order they historically emerged in the field, and within each category, landmark discoveries appear in chronological sequence. This allows the reader to trace how each biomarker category evolved: from foundational autoantigen identification in experimental uveitis models, through the genomic revolution of HLA association studies, into cellular immunophenotyping, cytokine profiling of aqueous humor, chemokine mapping of intraocular trafficking, and finally the emerging omics platforms that may potentially anchor precision medicine in NIU. Each biomarker is paired in line with its linked targeted therapeutic. SUMMARY: Biomarker research has transformed the understanding of NIU from a clinically defined syndrome into a group of molecularly distinct immune disorders. Advances spanning autoantigens, genetics, immune-cell profiling, cytokines, chemokines, and multiomics have revealed novel pathogenic mechanisms and therapeutic targets. Integration of these biomarkers with targeted therapies may accelerate the transition toward precision medicine in uveitis care.

cytokines↗