BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
Abstract
DNA sequencing pipelines, spanning quality control, alignment, variant calling, and annotation, are now reliably executed by workflow management systems that orchestrate established bioinformatics tools at scale. What remains manual is the decision layer surrounding that execution: selecting quality thresholds appropriate to a sample and platform, adjudicating borderline variant calls, diagnosing anomalies, and determining which findings warrant expert review. These decisions are repetitive, judgment-intensive, inconsistent across operators, and frequently undocumented. This paper introduces BaseCamp, a novel agentic AI framework for automating the decision layer of DNA sequencing pipelines. The framework decomposes the pipeline into six specialized AI agents, covering sample intake and quality control, alignment, variant calling, annotation, cross-stage monitoring, and reporting. Critically, BaseCamp agents do not perform sequence analysis: established tools execute alignment, calling, and annotation, while the agents select among them, configure them, interpret their output, and decide what follows. This confines language model reasoning to the judgment layer where it is reliable and preserves the reproducibility existing tooling guarantees. Agent reasoning is powered by a consortium of fine-tuned, domain-specialized large language models coordinated by a central reasoning LLM, executing locally so no sequencing data leaves the operating environment, under human-in-the-loop orchestration. Evaluation shows agent-generated configurations are concordant with expert practice, that an explicit filtering ledger renders inspectable what filtering otherwise removes without trace, and that cross-stage anomaly detection surfaces conditions execution monitoring misses. BaseCamp offers a generalizable blueprint for agentic automation of scientific data pipelines.
Related
- RADAgent: Automating RADseq Pipelines with Private Open-Source LLMs
- An end-to-end in silico framework for truth-based validation and regression testing of clinical genome sequencing pipelines, from simulated reads to reportable findings
- Hidden assumptions in nascent RNA sequencing pipelines define reproducibility states
- Systematic evaluation of transcript normalization methods and quantification pipelines across long-read sequencing platforms
- Taxonomic classification cost tracks neither sequencing depth nor community richness at single-sample scale: a measured resource protocol for 16S rRNA amplicon pipelines
BibTeX
@misc{bandara2026basecamp,
title = {{BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines}},
author = {Eranga Bandara and Xueping Liang and Asanga Gunaratna and Tharaka Hewa and Abdul Rahman and Peter Foytik and Safdar H. Bouk and Sachini Rajapakse and Isurunima Kularathna and Pramoda Karunarathna and Chalani Rajapakse and Ng Wee Keong and Kasun De Zoysa and Amin Hass and Wathsala Herath and Ross Gore and Ravi Mukkamala and Nihal Siriwardanagea and Gihan Siriwardanagea and Aruna Withanage and Nilaan Loganathan and Sachin Shetty},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28557},
eprint = {2609.28557},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28557},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
AU - Eranga Bandara
AU - Xueping Liang
AU - Asanga Gunaratna
AU - Tharaka Hewa
AU - Abdul Rahman
AU - Peter Foytik
AU - Safdar H. Bouk
AU - Sachini Rajapakse
AU - Isurunima Kularathna
AU - Pramoda Karunarathna
AU - Chalani Rajapakse
AU - Ng Wee Keong
AU - Kasun De Zoysa
AU - Amin Hass
AU - Wathsala Herath
AU - Ross Gore
AU - Ravi Mukkamala
AU - Nihal Siriwardanagea
AU - Gihan Siriwardanagea
AU - Aruna Withanage
AU - Nilaan Loganathan
AU - Sachin Shetty
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.28557
UR - https://arxiv.org/abs/2609.28557
AB - DNA sequencing pipelines, spanning quality control, alignment, variant calling, and annotation, are now reliably executed by workflow management systems that orchestrate established bioinformatics tools at scale. What remains manual is the decision layer surrounding that execution: selecting quality thresholds appropriate to a sample and platform, adjudicating borderline variant calls, diagnosing anomalies, and determining which findings warrant expert review. These decisions are repetitive, judgment-intensive, inconsistent across operators, and frequently undocumented. This paper introduces BaseCamp, a novel agentic AI framework for automating the decision layer of DNA sequencing pipelines. The framework decomposes the pipeline into six specialized AI agents, covering sample intake and quality control, alignment, variant calling, annotation, cross-stage monitoring, and reporting. Critically, BaseCamp agents do not perform sequence analysis: established tools execute alignment, calling, and annotation, while the agents select among them, configure them, interpret their output, and decide what follows. This confines language model reasoning to the judgment layer where it is reliable and preserves the reproducibility existing tooling guarantees. Agent reasoning is powered by a consortium of fine-tuned, domain-specialized large language models coordinated by a central reasoning LLM, executing locally so no sequencing data leaves the operating environment, under human-in-the-loop orchestration. Evaluation shows agent-generated configurations are concordant with expert practice, that an explicit filtering ledger renders inspectable what filtering otherwise removes without trace, and that cross-stage anomaly detection surfaces conditions execution monitoring misses. BaseCamp offers a generalizable blueprint for agentic automation of scientific data pipelines.
ER -