ScProteoAgent enables natural-language-driven single-cell proteomics analysis and interpretation
Single-cell proteomics requires computational choices to remain aligned with experimental design as research questions evolve. Here we present ScProteoAgent, which translates natural-language requests into domain-specific calculations and preserves research intent, analysis design, matrix-processing history and statistical outputs as reusable analytical state. Follow-up requests reuse applicable…
Single-cell proteomics analysis and interpretation can now be driven by natural language with the help of ScProteoAgent. This innovative tool transforms human requests into complex calculations while preserving the original research intent. It maintains analysis design, matrix-processing history, and statistical outputs as reusable analytical states, allowing for seamless follow-up requests.
A comprehensive benchmark created by the researchers featured 55 tasks and 33 reference conclusions from 11 published studies, covering various biological and analytical settings. When compared to 88 archived outputs from eight existing systems, ScProteoAgent scored the highest at 93.67 under a standard six-dimensional rule-based evaluation.
The tool's effectiveness was demonstrated in practical scenarios, such as HeLa migration studies, liver zonation research, and investigations into brain development, sample preservation, and hematopoiesis. ScProteoAgent bridges the gap between research questions and statistical results, ensuring that the analytical context remains intact and supports more targeted biological investigations.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
