The accessible human surfaceome
- 1Deliverome Bio, Inc.
- 2Coral Biosciences, LLC
Abstract
Proteins associated with the extracellular face of the plasma membrane ("surface proteins" or the "surfaceome") are important therapeutic targets because they can direct therapeutics to specific cell types and deliver them into cells. However, experimental and computational databases disagree substantially on which proteins make up the human plasma membrane proteome, and none focus specifically on the set of accessible surface proteins that would be useful for therapeutic applications. Here, we used an agentic LLM pipeline to curate the accessible human surfaceome from literature. To assess performance, we built SurfaceBench, a manually curated benchmark of 147 proteins on which five reference databases frequently disagree. Our LLM triage agent classified surface status more accurately than existing databases and recovered 1,108 candidate surface proteins not present in any of them. On held-out clinical and viral-entry surface targets, the pipeline recovered 98–100% of established surface antigens. A literature-anchored deep-dive pipeline run on over 5,000 candidates then returned 1,783 canonical surface proteins and 1,252 with weaker or context-dependent surface evidence. Each queryable record contains 24 LLM-based annotation fields — including confidence, primary localization, and expression breadth — and seven deterministic structural and topological features. Unlike existing databases, our records trace every claim to the agent's reasoning and to exact quotes from the full-text literature it could access. All records can be browsed in an open-source viewer. These results show that LLMs reasoning over unstructured scientific text can build updatable, bespoke databases that outperform expert-curated resources, although performance remains limited by agent access to full-text literature.
Author-deposited copy of the bioRxiv preprint doi:10.64898/2026.10.18.759859: the PDF as submitted to bioRxiv, plus JATS XML and the figure files it references. Authors are listed in alphabetical order.
Related
- Developing an accessible judgement bias task for non-human primates
- ConfUSIus: an accessible and scalable toolkit for functional ultrasound imaging analysis
- KSTAR v1.2: A faster and more and accessible KSTAR for kinase activity inference
- INTOXICOM Workshop Report: Making toxicology tools more accessible and interoperable
- iFLiP: accessible and low-cost lifetime fiber photometry for robust longitudinal and quantitative measurements of neural dynamics
BibTeX
@misc{carlson2026accessible,
title = {{The accessible human surfaceome}},
author = {Rebecca J. Carlson and L. Robert Hollingsworth and Michael J. Smallegan},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.18.759859},
url = {https://www.biorxiv.org/content/10.64898/2026.10.18.759859v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - The accessible human surfaceome
AU - Rebecca J. Carlson
AU - L. Robert Hollingsworth
AU - Michael J. Smallegan
PY - 2026
DA - 2026/10/18
PB - bioRxiv
DO - 10.64898/2026.10.18.759859
UR - https://www.biorxiv.org/content/10.64898/2026.10.18.759859v1
AB - Proteins associated with the extracellular face of the plasma membrane ("surface proteins" or the "surfaceome") are important therapeutic targets because they can direct therapeutics to specific cell types and deliver them into cells. However, experimental and computational databases disagree substantially on which proteins make up the human plasma membrane proteome, and none focus specifically on the set of accessible surface proteins that would be useful for therapeutic applications. Here, we used an agentic LLM pipeline to curate the accessible human surfaceome from literature. To assess performance, we built SurfaceBench, a manually curated benchmark of 147 proteins on which five reference databases frequently disagree. Our LLM triage agent classified surface status more accurately than existing databases and recovered 1,108 candidate surface proteins not present in any of them. On held-out clinical and viral-entry surface targets, the pipeline recovered 98–100% of established surface antigens. A literature-anchored deep-dive pipeline run on over 5,000 candidates then returned 1,783 canonical surface proteins and 1,252 with weaker or context-dependent surface evidence. Each queryable record contains 24 LLM-based annotation fields — including confidence, primary localization, and expression breadth — and seven deterministic structural and topological features. Unlike existing databases, our records trace every claim to the agent's reasoning and to exact quotes from the full-text literature it could access. All records can be browsed in an open-source viewer. These results show that LLMs reasoning over unstructured scientific text can build updatable, bespoke databases that outperform expert-curated resources, although performance remains limited by agent access to full-text literature. Author-deposited copy of the bioRxiv preprint doi:10.64898/2026.10.18.759859: the PDF as submitted to bioRxiv, plus JATS XML and the figure files it references. Authors are listed in alphabetical order.
ER -