Curation at Scale with EPITOME: Extraction Pipeline for Immunological Texts and Open-Source Multimodal Enquiry

Richardson, E.; Lischwe, P.; Bennett, J.; Blazeska, N.; Greenbaum, J.; Harlan, B.; Lallmamode, N.; Marrama, D.; Talbott, M.; Vita, R.; Sette, A.; Kuether, K.; Peters, B.

doi:10.64898/2026.01.08.698331

bioRxiv · 10.64898/2026.01.08.698331

Curation at Scale with EPITOME: Extraction Pipeline for Immunological Texts and Open-Source Multimodal Enquiry

Richardson, E.·Lischwe, P.·Bennett, J.·Blazeska, N.·Greenbaum, J.·Harlan, B.·Lallmamode, N.·Marrama, D.·Talbott, M.·Vita, R.·Sette, A.·Kuether, K.·Peters, B.

View original source ↗Export metadata ↓

Abstract

The Immune Epitope Database (IEDB, iedb.org) has manually curated epitope data from over 26,000 publications across two decades. With PubMed adding [~]5,000 articles daily, traditional curation methods face scalability challenges. Given the multimodality of data contained in scientific papers, we have sought to build an open-source vision language model (VLM)-based tool that human curators can use to speed up and automate biological data curation. Here we present a multimodal document ingestion and Question-Answering (QnA) pipeline that ties traditional Optical Character Recognition (OCR) and text matching with Vision-Language Model (VLM) capabilities. The system, which we call EPITOME, implements three-stage processing: regex-based epitope and MHC molecule identification, visual element extraction from PDFs, and contextual indexing that links peptide sequences, MHC molecules, and assays to their locations across text, tables, and figures. This indexing is used to supply context for further VLM QnA. Our preliminary results from EPITOME demonstrate promising zero-shot performance of open-source VLMs that suggest promise for accelerating biocuration through a curator-in-the-loop process, with our evaluation identifying strategic points where curator-in-the-loop intervention can enhance overall system accuracy.

Explore related subjects

bioinformatics Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Richardson, E., Lischwe, P., Bennett, J., Blazeska, N., Greenbaum, J., Harlan, B., Lallmamode, N., Marrama, D., Talbott, M., Vita, R., Sette, A., Kuether, K., Peters, B.. 2026-01-09. Curation at Scale with EPITOME: Extraction Pipeline for Immunological Texts and Open-Source Multimodal Enquiry. https://doi.org/10.64898/2026.01.08.698331

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↗