Newest papers

Harness-Driven Agentic Operation of Optical Pooled Screen Analysis

Matteo Di Bernardo, Claire Peterson, Ege Topkoc, Matt Might, Iain M. Cheeseman · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.22617 · cited by 0 works (OpenAlex) · open-access PDF

French

Les écrans fixes optiques établis relient les perturbations génétiques aux changements de morphologie cellulaire et de comportement, mais la transformation des données de microscopie en résultats interprétables nécessite des analyses complexes et multi-jours. Les pipelines établies traitent ces données, mais les chercheurs choisissent toujours les paramètres, inspectent les sorties et résolvent les défaillances pour chaque expérience. Ici, nous présentons Brieflow-auto, un outil spécifique aux pipelines mis en œuvre sous la forme d'un plugin Claude Code qui permet à un modèle de langue de codage (LLM) d'exécuter Brieflow, un pipeline open-source end-to-end pour les données de dépistage optiques regroupées. Un chercheur four

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Pipeline (software), Coding (social sciences), Computer science, Process (computing), Reliability (semiconductor), Upstream (networking)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange