Harness automates optical screening pipeline to improve gene analysis
Harness-Driven Agentic Operation of Optical Pooled Screen Analysis
Human-Computer Interaction
Summary
Analyzing images from experiments that change genes in cells can take many days and lots of manual work. The authors created a tool called Brieflow-auto that uses an AI assistant to run and manage this analysis automatically. It checks for problems, fixes common errors, and even suggests improvements to the software. Their tests showed this approach found more useful data and handled unexpected issues better than humans working by hand. This method could make these complex experiments easier and faster for scientists to use.
What this means in practice
- •For cell biology labs: Automate processing of microscopy data from genetic screens to improve data quality and reduce manual parameter tuning.
- •For bioinformatics platform developers: Integrate AI-driven orchestration and error handling into complex biological data pipelines to enhance robustness and maintainability.
- •For data science teams in pharmaceuticals: Use AI-managed pipelines to speed up morphological data analysis for drug discovery screens, reducing time and errors.$Commercial implications: Enables commercial software products that automate complex biological imaging analyses for pharmaceutical companies seeking faster candidate evaluation.
Authors
Matteo Di Bernardo, Claire Peterson, Ege Topkoc, Matt Might, Iain M. Cheeseman
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.