MetaClaw: an auditable AI agent for end-to-end, multi-directional metagenomic and multi-omics analysis
- 1Huazhong University of Science and Technology
Abstract
End-to-end omics analysis requires more than selecting tools: a usable agent must bind data correctly, execute long workflows without blocking, preserve provenance and recover the biological conclusions that motivate an analysis. Existing LLM-driven bioinformatics agents automate parts of this process, but their operational dependencies and conclusion-level validity are often unclear. Here we present MetaClaw, an auditable agent that maps a user request to a registered workflow, executes standardized upstream processing on FlowHub, and runs study-specific downstream analyses in network-isolated OpenClaw containers. A YAML registry and an explicit plan-submit-poll-finalise lifecycle record file bindings, parameters, scripts, environments and outputs in per-job bundles. Across the full cohorts of four published studies (769 metagenomic profiles), MetaClaw recovered 4/4 sorghum marker groups, 3/3 RRMS features, 4/5 canonical CRC markers among the top 20 classifier features and 5/5 permafrost marker groups. In 45 model-by-prompt runs, upstream completion was consistent whereas downstream validity depended on the backend and instruction detail; three decoy-tested endpoints showed no significant differences. In 48 ablation sessions, removing the registry, planning loop or manifest caused distinct losses, with registry removal increasing time, tool calls and token cost. MetaClaw therefore connects standardized upstream execution, local analytical flexibility and conclusion-level validation in a rerunnable framework for metagenomic and microbiome multi-omics analysis.
Related
- Codon-aware multi-scale feature fusion for metagenomic sequence classification
- A closed-loop language-model agent for target-specific multi-objective hit-to-lead optimization
- A progressive ODE model of seasonal allergic rhinitis: from core Th2 axis to 21-dimensional multi- pathway integration with seasonal dynamics and directional assessment
- Multi-agent game theory for precision psychiatry
- An immune world model with multi-agent orchestration for peptide vaccines
BibTeX
@misc{zhang2026metaclaw,
title = {{MetaClaw: an auditable AI agent for end-to-end, multi-directional metagenomic and multi-omics analysis}},
author = {H. Zhang and Z. Li and P. N. P. Lagniton and Z. Wang and L. Zhao and W. Li and p. Duan and X. Jiang and K. Ning},
howpublished = {bioRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.21.739769},
url = {https://www.biorxiv.org/content/10.64898/2026.07.21.739769v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - MetaClaw: an auditable AI agent for end-to-end, multi-directional metagenomic and multi-omics analysis
AU - H. Zhang
AU - Z. Li
AU - P. N. P. Lagniton
AU - Z. Wang
AU - L. Zhao
AU - W. Li
AU - p. Duan
AU - X. Jiang
AU - K. Ning
PY - 2026
DA - 2026/07/21
PB - bioRxiv
DO - 10.64898/2026.07.21.739769
UR - https://www.biorxiv.org/content/10.64898/2026.07.21.739769v2
AB - End-to-end omics analysis requires more than selecting tools: a usable agent must bind data correctly, execute long workflows without blocking, preserve provenance and recover the biological conclusions that motivate an analysis. Existing LLM-driven bioinformatics agents automate parts of this process, but their operational dependencies and conclusion-level validity are often unclear. Here we present MetaClaw, an auditable agent that maps a user request to a registered workflow, executes standardized upstream processing on FlowHub, and runs study-specific downstream analyses in network-isolated OpenClaw containers. A YAML registry and an explicit plan-submit-poll-finalise lifecycle record file bindings, parameters, scripts, environments and outputs in per-job bundles. Across the full cohorts of four published studies (769 metagenomic profiles), MetaClaw recovered 4/4 sorghum marker groups, 3/3 RRMS features, 4/5 canonical CRC markers among the top 20 classifier features and 5/5 permafrost marker groups. In 45 model-by-prompt runs, upstream completion was consistent whereas downstream validity depended on the backend and instruction detail; three decoy-tested endpoints showed no significant differences. In 48 ablation sessions, removing the registry, planning loop or manifest caused distinct losses, with registry removal increasing time, tool calls and token cost. MetaClaw therefore connects standardized upstream execution, local analytical flexibility and conclusion-level validation in a rerunnable framework for metagenomic and microbiome multi-omics analysis.
ER -