GEOMeta provides a scalable resource and reproducible framework for metadata curation in the Gene Expression Omnibus, and benchmarked transcriptome representation models for predicting sex, age, tissue and disease from transcriptome embeddings.
Abstract
Public transcriptomic repositories contain millions of samples, yet their large-scale reuse is hindered by heterogeneous and inconsistently reported metadata. In the Gene Expression Omnibus (GEO), key biological information is often distributed across study- and sample-level records, requiring context-dependent interpretation. Here we present GEOMeta, a large language model (LLM)-based multi-stage workflow with task-specialized agents for automated GEO metadata curation. The pipeline separates metadata retrieval, task-specific information extraction, field standardization, ontology mapping and quality control. Using GEOMeta, we generated standardized annotations for approximately 600,000 human bulk RNA-seq samples. To demonstrate its utility, we benchmarked transcriptome representation models for predicting sex, age, tissue and disease from transcriptome embeddings. We further prospectively annotated newly submitted GEO studies and evaluated 22 frontier LLMs. Recent open-source Flash models achieved annotation quality comparable to leading reasoning models while reducing costs by an order of magnitude. GEOMeta provides a scalable resource and reproducible framework for metadata curation.
We describe an automated software tool to accomplish data curation tasks previously performed by humans for the Gemma genomics data re-analysis resource. Gemma is a hand-curated database of reprocessed transcriptomic studies, currently covering over 23,000 human, mouse and rat data sets largely drawn from the Gene Expression Omnibus (GEO). We developed a pipeline that uses both traditional (mechanical) and large-language models to produce detailed ontology-anchored, sample- and experiment-level annotations in accordance with our established curation guidelines. In this report, we describe benchmarking the pipeline and investigations aimed at evaluating readiness of the v1.1 Gemma curation agent for production use. Overall, performance is near that of human curators, at approximately 1/20th the cost and at least 100 times the speed. We also present preliminary exploration of triage methods for identifying agent curations that are more likely to contain errors, and thus can be forwarded for human review. We discuss the potential place of such curation approaches in bioinformatics ecosystems. Besides the software, our deliverables include the benchmark set of 500 studies and an evaluation framework that can be used to further develop the pipeline or compare to other approaches.
P. Pavlidis, B. O. Mancarci, A. Mãximo et al.· bioRxiv· 0 citations
Public transcriptomic repositories contain thousands of gene perturbation experiments, a valuable resource for understanding gene function, but perturbation metadata are not structured, which blocks systematic reuse. Existing perturbation atlases depend on expert manual curation, so they are costly to maintain and infrequently updated, while automated grouping approaches neither identify which samples form the perturbation arm nor recover the perturbed gene. Here we develop an automated pipeline that uses large language models to find single-gene perturbation experiments in NCBI-GEO and reconstruct their case-control sample groupings, along with the perturbed gene, perturbation type and cell line as structured, ontology-normalised fields. We manually curated 3,300 GEO experiments with sample-level case-control assignments and release these as an open benchmark (2,400 training, 600 validation, 300 temporally held-out test). Reasoning models and task-specific finetuning substantially improved identification of valid perturbation groups, with the best model reaching precision 0.925 and recall 0.836 on the test set. Applied at scale, the pipeline generated an atlas of 6,802 gene perturbation expression signatures from 4,453 GEO experiments, covering 2,907 uniquely perturbed genes. An R package, perturbMatch, supports exploration of the atlas and querying of user-supplied expression signatures against it using similarity scoring, so users can identify experiments that recapitulate a transcriptional state of interest.
GenesetGPT is proposed, an efficient, LLM-based framework that emphasizes both curated biological context and iterative prompt construction, thus enabling realistic summarization of heterogeneous gene sets at scale.
Jack R. Leary, Samantha Pattey, Rhonda L. Bacher· bioRxiv· 0 citations
MKMC (Multi-sample Kmer Counter), a scalable, reference-free toolkit for RNA-seq analysis that leverages k-mer–based statistics to detect biological variation without requiring alignment, is presented.
L. Mboning, Maciej Dlugosz, Marek Kokot et al.· bioRxiv· 0 citations
FEDKEA, an enzyme annotation tool leveraging protein language models, and a user-friendly, FEDKEA-based metagenomic pipeline, MEnzMap, which encompasses the entire analysis workflow—from raw data quality control to function prediction and downstream analyses are designed.
Lei Zheng, Bowen Li, Siqi Xu et al.· Science Advances· 0 citations
Motivation The rapid expansion of single-cell RNA sequencing (scRNA-seq) atlases has generated datasets comprising millions of cells annotated with increasingly rich metadata, including tissue, cell type, disease status, sex, age, treatment, and temporal information. Biological questions frequently require simultaneous interrogation of multiple metadata dimensions, such as identifying specific cell populations within defined tissues, disease states, demographic groups, and time points. While existing interactive platforms facilitate visualization and analysis of scRNA-seq data, deep metadata-driven exploration and downstream analysis of atlas-scale datasets remain insufficiently supported. Results We developed AtlasLens, an open-source R/Shiny application for interactive exploration of scRNA-seq datasets and integrated cellular atlases. AtlasLens enables iterative filtering across arbitrary metadata combinations, allowing users to define biologically meaningful cellular subsets and immediately perform downstream analyses. The platform integrates interactive visualization, differential expression analysis, Gene Ontology enrichment with redundancy reduction, temporal expression analysis, and context-dependent gene function profiling through GeneCOCOA. AtlasLens additionally records analysis history and automatically generates corresponding R code to enhance reproducibility. The application is distributed through Docker for simple local deployment, preserving data privacy and eliminating dependency-management challenges. We demonstrate AtlasLens using the Tabula Muris and a time-resolved whole-lung single-cell atlas of bleomycin-induced lung injury and fibrosis, highlighting its ability to support complex metadata-driven biological investigations. Availability Source code is available at https://github.com/SchulzLab/AtlasLens. Contact marcel.schulz@em.uni-frankfurt.de
Shamim Ashrafiyan, Iaroslav Kosaretskii, Marcel H. Schulz· bioRxiv· 0 citations