RADAgent: Automating RADseq Pipelines with Private Open-Source LLMs
Abstract
Restriction site-associated DNA sequencing (RADseq) is a family of reduced-representation sequencing methods. It uses restriction enzymes to sample subsets of the genome, therefore allowing multiple individuals to be sequenced and genotyped together at low cost. RADseq is widely used for population genomics, evolutionary biology, marker discovery, and the development of SNP panels, but complete analysis still requires expert coordination across multiple tools and processing stages. Traditional RADseq analysis requires expert coordination of heterogeneous bioinformatics tools, intermediate artifacts, quality-control checks, and parameter-dependent decisions across multiple stages. Although individual steps can be scripted, executing the complete workflow still requires human oversight for state tracking, result validation, and failure handling. To automate this expert-driven coordination, we present RADAgent, which introduces a modular agentic method for reliable RADseq workflow execution with an open-weight LLM. RADAgent maps the natural boundaries of the RADseq workflow into 16 independently executable and verifiable agent modules and uses a model-independent runtime for bounded tool execution, on-disk verification, and failure recovery. We evaluate RADAgent on a real population-genomics dataset containing 476 samples from 19 populations. The results demonstrate that RADAgent reliably automates the complete RADseq workflow with an open-weight LLM while keeping genomic data and model execution within the local computing environment. The code is publicly available at https://github.com/wenlu-lab/RADAgent.
Related
- BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
- AmPair: automating housekeeping-gene primer design for species-level metataxonomics
- Automating Observable Closure Analysis for Graph Transformation Models with MolFoundry
- Small-statured tomato plants for automating greenhouse production: opportunities, constraints, and research priorities
- Hidden assumptions in nascent RNA sequencing pipelines define reproducibility states
BibTeX
@misc{guo2026radagent,
title = {{RADAgent: Automating RADseq Pipelines with Private Open-Source LLMs}},
author = {Qiming Guo and Malaka Sudhakara Bava Sukruth Reddy and Honggang Zhao and Ye Wang and Chen Pan and Wenlu Wang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.33009},
eprint = {2610.33009},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.33009},
}
RIS
TY - UNPB
TI - RADAgent: Automating RADseq Pipelines with Private Open-Source LLMs
AU - Qiming Guo
AU - Malaka Sudhakara Bava Sukruth Reddy
AU - Honggang Zhao
AU - Ye Wang
AU - Chen Pan
AU - Wenlu Wang
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.33009
UR - https://arxiv.org/abs/2610.33009
AB - Restriction site-associated DNA sequencing (RADseq) is a family of reduced-representation sequencing methods. It uses restriction enzymes to sample subsets of the genome, therefore allowing multiple individuals to be sequenced and genotyped together at low cost. RADseq is widely used for population genomics, evolutionary biology, marker discovery, and the development of SNP panels, but complete analysis still requires expert coordination across multiple tools and processing stages. Traditional RADseq analysis requires expert coordination of heterogeneous bioinformatics tools, intermediate artifacts, quality-control checks, and parameter-dependent decisions across multiple stages. Although individual steps can be scripted, executing the complete workflow still requires human oversight for state tracking, result validation, and failure handling. To automate this expert-driven coordination, we present RADAgent, which introduces a modular agentic method for reliable RADseq workflow execution with an open-weight LLM. RADAgent maps the natural boundaries of the RADseq workflow into 16 independently executable and verifiable agent modules and uses a model-independent runtime for bounded tool execution, on-disk verification, and failure recovery. We evaluate RADAgent on a real population-genomics dataset containing 476 samples from 19 populations. The results demonstrate that RADAgent reliably automates the complete RADseq workflow with an open-weight LLM while keeping genomic data and model execution within the local computing environment. The code is publicly available at https://github.com/wenlu-lab/RADAgent.
ER -