Prompt-as-a-Protocol with Agentic Research Automation: A Validated Methodology for AI-Native Biomedical Data Science Producing Peer-Reviewed Findings Across Genomics and Biosensor Domains

Abstract

Recent advances in large language model (LLM)-driven agentic systems have demonstrated capabilities for automating biomedical data analysis workflows. However, existing systems are predominantly validated on synthetic benchmarks or retrospective tasks, without demonstrated production of novel, peer-reviewed biological findings. Here we describe Prompt-as-a-Protocol (PaaP), a methodology that converts natural-language research questions into structured, executable analytical protocols, coupled with an agentic Generative Research Automation (GRA) layer that executes these protocols with integrated quality assurance. We validate PaaP+GRA through two prospective case studies in distinct biomedical domains. In single-cell transcriptomics, the pipeline identified KIF3A as the sole genome-wide significant correlate of ciliation status in human striatal parvalbumin interneurons (adjusted p = 1.37 x 10-14), while autonomously detecting and correcting a sex composition confound (p = 8.1 x 10-44) that would have produced spurious results. In biosensor analytics, the pipeline achieved calibrated PPG-to-ECG heart rate variability classification matching gold-standard ECG performance (ROC AUC = 0.85) for stress-state discrimination relevant to alcohol use disorder relapse monitoring. Both studies have been submitted for peer review. To our knowledge, PaaP+GRA is the first prompt-to-protocol methodology validated by prospective production of novel biological findings across multiple domains, including autonomous confound detection, rather than benchmark performance alone.