Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
BaseCamp decouples deterministic bioinformatics execution from pipeline decision-making by deploying six domain-specialized, locally hosted LLM agents governed by a central reasoning coordinator to manage quality control, parameter selection, and borderline variant arbitration. Restricting language models strictly to configuration, interpretation, and anomaly diagnosis circumvents common hallucination and reproducibility pitfalls while keeping sensitive genomic data on-premise. Across standard sequencing benchmarks, the framework achieves expert-level configuration concordance, surfaces cross-stage anomalies missed by traditional workflow engines, and generates an auditable ledger for previously untracked filtering decisions.
Bioinformatics pipelines already have robust tools for crunching raw sequencing reads; BaseCamp proves that a consortium of small, local LLMs can automate the brittle human judgment layer that configures them without ever exposing the underlying genomic data.
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.