GLESKit: an MCP-based system for gene-level biomedical investigation and evidence synthesis
- 1Faculty of Sciences of the University of Porto
Abstract
Biomedical investigation at the gene level requires researchers to combine expression data, functional annotations, pathways, interaction networks, genetic associations, drug evidence and literature. Accessing these resources involves databases, analysis tools and scripts that require bioinformatics expertise, complicating the production of clear, reviewable reports. We present GLESKit, a gene centred system that connects these steps through the Model Context Protocol and retains data, analyses, sources and reports within a study workspace. We evaluated report production with 15 author curated GeneReportBench tasks and question answering with a gene level subset of BixBench, a reference biology benchmark for agentic systems. GLESKit completed all 15 reports with a mean committee score of 0.904, although evidence quality varied, and earned positive credit on 35 of 39 scored human BixBench questions with a mean of 0.438. In paired tests, configurations with skills scored 0.145 higher across 20 questions and 0.085 higher across five reports.
Related
- Facilitating Valid Statistical Inference in Biomedical Image Synthesis
- HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge
- Acetylated PLIN2 coordinates the innate immune system and oxylipin synthesis on lipid droplets to propagate inflammation
- Mapping human genetic associations to drug targets in valvular heart disease: an integrative evidence synthesis
- Coordinated RNA- and protein-templated synthesis of double-stranded DNA by a dual reverse transcriptase immune system
BibTeX
@misc{moraes2026gleskit,
title = {{GLESKit: an MCP-based system for gene-level biomedical investigation and evidence synthesis}},
author = {A. Moraes and P. G. Ferreira},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.25.761689},
url = {https://www.biorxiv.org/content/10.64898/2026.10.25.761689v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - GLESKit: an MCP-based system for gene-level biomedical investigation and evidence synthesis
AU - A. Moraes
AU - P. G. Ferreira
PY - 2026
DA - 2026/10/25
PB - bioRxiv
DO - 10.64898/2026.10.25.761689
UR - https://www.biorxiv.org/content/10.64898/2026.10.25.761689v1
AB - Biomedical investigation at the gene level requires researchers to combine expression data, functional annotations, pathways, interaction networks, genetic associations, drug evidence and literature. Accessing these resources involves databases, analysis tools and scripts that require bioinformatics expertise, complicating the production of clear, reviewable reports. We present GLESKit, a gene centred system that connects these steps through the Model Context Protocol and retains data, analyses, sources and reports within a study workspace. We evaluated report production with 15 author curated GeneReportBench tasks and question answering with a gene level subset of BixBench, a reference biology benchmark for agentic systems. GLESKit completed all 15 reports with a mean committee score of 0.904, although evidence quality varied, and earned positive credit on 35 of 39 scored human BixBench questions with a mean of 0.438. In paired tests, configurations with skills scored 0.145 higher across 20 questions and 0.085 higher across five reports.
ER -