PerTurboAgent: An LLM-based Agent for Designing Iterative Perturb-Seq Experiments

Minsheng Hao, yongju lee, Hanchen Wang, Gabriele Scalia, Aviv Regev
Proceedings of the 20th Machine Learning in Computational Biology meeting, PMLR 311:44-64, 2025.

Abstract

Understanding how genetic interventions alter cell phenotypes is crucial for uncovering gene regulatory mechanisms and identifying drug targets. Methods like Perturb-seq assess the impact of many genetic interventions on cellular profiles (e.g., RNA). However, exhaustively testing all perturbations, especially combinations, is infeasible. Iterative experimental design offers a solution. By using gene circuit modularity, sparsity, and prior knowledge, we can predict the effects of unseen perturbations and group genes into co-functional modules. Subsequent Perturb-seq rounds test these predictions, refining the model. This cycle prioritizes gene testing, maximizing knowledge from limited resources, and enabling general predictive models. Designing these experiments is complex, requiring a system to analyze data, integrate knowledge, use statistical tools, predict outcomes, and prioritize perturbations. We developed PerTurboAgent, an LLM-based agent for designing iterative Perturb-seq experiments. It excels at predicting candidate gene panels through self-directed data analysis and knowledge retrieval. We evaluated its ability to identify genes affecting gene expression upon perturbation using genome-scale data. PerTurboAgent surpasses existing agent-based and active learning strategies, providing an efficient, understandable method for designing sequential perturbation experiments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v311-hao25b, title = {PerTurboAgent: An LLM-based Agent for Designing Iterative Perturb-Seq Experiments}, author = {Hao, Minsheng and lee, yongju and Wang, Hanchen and Scalia, Gabriele and Regev, Aviv}, booktitle = {Proceedings of the 20th Machine Learning in Computational Biology meeting}, pages = {44--64}, year = {2025}, editor = {Knowles, David A and Koo, Peter K}, volume = {311}, series = {Proceedings of Machine Learning Research}, month = {10--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v311/main/assets/hao25b/hao25b.pdf}, url = {https://proceedings.mlr.press/v311/hao25b.html}, abstract = {Understanding how genetic interventions alter cell phenotypes is crucial for uncovering gene regulatory mechanisms and identifying drug targets. Methods like Perturb-seq assess the impact of many genetic interventions on cellular profiles (e.g., RNA). However, exhaustively testing all perturbations, especially combinations, is infeasible. Iterative experimental design offers a solution. By using gene circuit modularity, sparsity, and prior knowledge, we can predict the effects of unseen perturbations and group genes into co-functional modules. Subsequent Perturb-seq rounds test these predictions, refining the model. This cycle prioritizes gene testing, maximizing knowledge from limited resources, and enabling general predictive models. Designing these experiments is complex, requiring a system to analyze data, integrate knowledge, use statistical tools, predict outcomes, and prioritize perturbations. We developed PerTurboAgent, an LLM-based agent for designing iterative Perturb-seq experiments. It excels at predicting candidate gene panels through self-directed data analysis and knowledge retrieval. We evaluated its ability to identify genes affecting gene expression upon perturbation using genome-scale data. PerTurboAgent surpasses existing agent-based and active learning strategies, providing an efficient, understandable method for designing sequential perturbation experiments.} }
Endnote
%0 Conference Paper %T PerTurboAgent: An LLM-based Agent for Designing Iterative Perturb-Seq Experiments %A Minsheng Hao %A yongju lee %A Hanchen Wang %A Gabriele Scalia %A Aviv Regev %B Proceedings of the 20th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2025 %E David A Knowles %E Peter K Koo %F pmlr-v311-hao25b %I PMLR %P 44--64 %U https://proceedings.mlr.press/v311/hao25b.html %V 311 %X Understanding how genetic interventions alter cell phenotypes is crucial for uncovering gene regulatory mechanisms and identifying drug targets. Methods like Perturb-seq assess the impact of many genetic interventions on cellular profiles (e.g., RNA). However, exhaustively testing all perturbations, especially combinations, is infeasible. Iterative experimental design offers a solution. By using gene circuit modularity, sparsity, and prior knowledge, we can predict the effects of unseen perturbations and group genes into co-functional modules. Subsequent Perturb-seq rounds test these predictions, refining the model. This cycle prioritizes gene testing, maximizing knowledge from limited resources, and enabling general predictive models. Designing these experiments is complex, requiring a system to analyze data, integrate knowledge, use statistical tools, predict outcomes, and prioritize perturbations. We developed PerTurboAgent, an LLM-based agent for designing iterative Perturb-seq experiments. It excels at predicting candidate gene panels through self-directed data analysis and knowledge retrieval. We evaluated its ability to identify genes affecting gene expression upon perturbation using genome-scale data. PerTurboAgent surpasses existing agent-based and active learning strategies, providing an efficient, understandable method for designing sequential perturbation experiments.
APA
Hao, M., lee, y., Wang, H., Scalia, G. & Regev, A.. (2025). PerTurboAgent: An LLM-based Agent for Designing Iterative Perturb-Seq Experiments. Proceedings of the 20th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 311:44-64 Available from https://proceedings.mlr.press/v311/hao25b.html.

Related Material