Harness-Driven Agentic Operation of Optical Pooled Screen Analysis
Abstract
Optical pooled screens connect genetic perturbations to changes in cell morphology and behavior, but turning the microscopy data into interpretable results takes complex, multi-day analyses. Established pipelines process this data, yet researchers still select parameters, inspect outputs, and resolve failures for each experiment. Here, we present Brieflow-auto, a pipeline-specific harness implemented as a Claude Code plugin that lets a coding large language model (LLM) operate Brieflow, an open-source end-to-end pipeline for optical pooled screening data. A researcher supplies experimental facts and approves the launch. An agent tunes parameters in an interactive notebook, and the harness validates the configuration, monitors execution, recovers from common failures, and checks output quality. For pipeline defects, the agent opens upstream issues proposing backward-compatible fixes for the broader community. In five previously analyzed screens, harness runs yielded more cells with a confident single-gene assignment than the original hand analyses. On a screen the pipeline was not designed for, the harness turned each failure into a reviewed upstream fix. More broadly, we propose that wrapping an established pipeline in a harness can substantially accelerate its use and the long-term reliability of its codebase.
Related
- LifeLong Digital Twin: A Unified Modeling Paradigm and Agent Harness for Event-Driven Lifelong Health State Trajectories
- Archetype analysis of multiplexed antibody imaging reveals interpretable morphological programs in optical pooled screens
- Design and Operation of Photovoltaic‐Driven Electrocatalytic Water Splitting for Hydrogen Production
- Debate, Not Voting: Agentic Arbitration over Weak Optical Chemical Structure Recognition Models
- A Shared-Task-State-Driven Multi-Agent Framework for Knowledge Graph Construction in Substation Operation and Maintenance
BibTeX
@misc{bernardo2026harnessdriven,
title = {{Harness-Driven Agentic Operation of Optical Pooled Screen Analysis}},
author = {Matteo Di Bernardo and Claire Peterson and Ege Topkoc and Matt Might and Iain M. Cheeseman},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.22617},
eprint = {2610.22617},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.22617},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Harness-Driven Agentic Operation of Optical Pooled Screen Analysis
AU - Matteo Di Bernardo
AU - Claire Peterson
AU - Ege Topkoc
AU - Matt Might
AU - Iain M. Cheeseman
PY - 2026
DA - 2026/10/15
PB - arXiv
DO - 10.48550/arxiv.2610.22617
UR - https://arxiv.org/abs/2610.22617
AB - Optical pooled screens connect genetic perturbations to changes in cell morphology and behavior, but turning the microscopy data into interpretable results takes complex, multi-day analyses. Established pipelines process this data, yet researchers still select parameters, inspect outputs, and resolve failures for each experiment. Here, we present Brieflow-auto, a pipeline-specific harness implemented as a Claude Code plugin that lets a coding large language model (LLM) operate Brieflow, an open-source end-to-end pipeline for optical pooled screening data. A researcher supplies experimental facts and approves the launch. An agent tunes parameters in an interactive notebook, and the harness validates the configuration, monitors execution, recovers from common failures, and checks output quality. For pipeline defects, the agent opens upstream issues proposing backward-compatible fixes for the broader community. In five previously analyzed screens, harness runs yielded more cells with a confident single-gene assignment than the original hand analyses. On a screen the pipeline was not designed for, the harness turned each failure into a reviewed upstream fix. More broadly, we propose that wrapping an established pipeline in a harness can substantially accelerate its use and the long-term reliability of its codebase.
ER -