bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2025.11.26.690887

MARRVEL-MCP enables natural language variant interpretation through autonomous workflow construction

Everton, Z. J.·Botas, J.·Kim, S. Y.·Liu, Z.·Jeong, H.-H.
View original source ↗Export metadata ↓

Abstract

AO_SCPLOWBSTRACTC_SCPLOWRare disease variant interpretation requires navigating multiple genomic databases with strict input formats and synthesizing heterogeneous evidence, creating barriers for non-experts and cognitive burdens even for specialists. MARRVEL exemplifies this challenge by requiring precise queries (e.g., HGVS notation) and returning complex, difficult-to-synthesize outputs. To address this input-output asymmetry, we developed MARRVEL-MCP, a natural language interface enabling large language models (LLMs) to perform end-to-end variant interpretation via structured tool access. This work demonstrates the impact of context engineering--the deliberate design of domain-aware tool environments and information scaffolding--in reshaping the role of model scale in genomics. MARRVEL-MCP equips LLMs with 39 tools spanning gene and variant utilities, pathogenicity databases, phenotype resources, expression atlases, ortholog data, and literature APIs. Without hard-coded pipelines, LLMs autonomously infer workflows, performing named-entity recognition, identifier normalization, and multi-database synthesis from narrative queries. Using 45 expert-curated questions, lightweight models (3B-20B parameters) with MARRVEL-MCP matched or outperformed larger models lacking tool access. A 20B-parameter model (gpt-oss-20b) achieved a 95% pass rate versus 33% without MARRVEL-MCP, approaching state-of-the-art proprietary performance. Although accuracy remains below the 100% required for autonomous diagnosis and token usage is considerable, these results show that well-designed context can compensate for limited model capacity. These findings establish context engineering as a core principle for biomedical AI, enabling efficient, scalable integration of LLMs with curated genomic resources. MARRVEL-MCP is available at https://github.com/hyunhwan-bcm/MARRVEL_MCP/.

Source connections

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Everton, Z. J., Botas, J., Kim, S. Y., Liu, Z., Jeong, H.-H.. 2025-11-28. MARRVEL-MCP enables natural language variant interpretation through autonomous workflow construction. https://doi.org/10.1101/2025.11.26.690887

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states

Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.

bioinformatics↗
bioRxiv2026

Benchmarking single-cell foundation models for aging biology

Single cell foundation models (scFMs) provide representations of cellular states, but their utility across biological questions in aging research remains unclear. We established a benchmark of cellular representations for aging research, evaluating ten general-purpose scFMs, three aging-specific models and conventional methods across five biological questions using more than 2.5 million single cell transcriptomes. Using frozen pretrained representations, Geneformer performed best among scFMs for chronological age prediction and age pseudotime concordance, although 2,000 highly variable genes achieved higher mean performance. Several scFMs captured positive molecular age shifts across three disease contexts, consistent with reported aging-associated changes. SCimilarity performed well for rare cellular state identification across out-of-distribution datasets, exceeding aging specific models and conventional baselines. At the gene level, scGPT showed the highest recovery of reference TF target interactions, including aging-related regulatory hubs. Overall, scFMs supported diverse aging analyses, but performance depended on the biological question, highlighting their utility for rare cellular state identification and regulatory analysis.

bioinformatics↗
bioRxiv2026

CryoMV: Structure-Prior-Guided Modeling and Real-Particle Validation of Continuous Conformational Transitions in Cryo-EM

Continuous protein conformations are essential for understanding fundamental biological processes and supporting drug discovery. Although cryo-EM can resolve individual states at high resolution, recovering continuous heterogeneity from 2D particle images remains challenging. High noise, motion blur, and limited structural priors make it difficult to accurately generate and validate high-resolution continuous conformations using raw particle data. Here, we introduce cryoMV, a framework that integrates structure-prior-guided modeling with real-particle validation for continuous conformational transitions. CryoMV uses reference density maps to establish structural anchors and motion priors, models candidate transition paths between selected conformations, and transfers the learned representation to raw 2D cryo-EM particle images. Each candidate conformation is subsequently evaluated using the estimated particle poses and contrast transfer functions. Supported conformations are reconstructed through raw particle back-projection and assessed using canonical half-maps and Fourier shell correlation. On EMPIAR-10516 and EMPIAR-10345, cryoMV achieves excellent performance in terms of robustness, verifiability, and reconstruction resolution. By incorporating structure-prior modeling and evidence from the raw particles, cryoMV offers an explicit mechanism for assessing whether generated conformations are supported by experimental data and provides a practical approach to reducing model-induced artifacts in continuous cryo-EM heterogeneity analysis.

bioinformatics↗