瑞士洛桑联邦理工学院Maria Brbi?小组在研究中取得进展。他们研制了Systema：一个评估系统变异外遗传扰动响应预测的框架。2025年8月25日出版的《自然—生物技术》杂志发表了这项成果。

研究团队表明，目前的方法很难概括出系统变异之外的情况，即由选择偏差或混杂因素引起的受干扰细胞和对照细胞之间一致的转录差异。课题组研究人员在10个数据集中量化了这种差异，涵盖了三种技术和五种细胞系，并表明常见的指标容易受到这些偏差的影响，从而导致高估的性能。为了解决这个问题，研究团队介绍了Systema，这是一个评估框架，强调扰动特定的影响，并确定正确重建扰动景观的预测。使用这个框架，研究人员揭示了对现有方法的预测能力的见解，并表明预测对看不见的扰动的响应比标准指标所表明的要困难得多。他们的工作强调了异质基因面板的重要性，并将预测性能从系统效应中分离出来，使扰动响应建模在生物学上有意义。

据悉，在功能基因组学中，预测基因扰动的转录反应是具有挑战性的。虽然最近的方法旨在推断未经测试的扰动的影响，但它们真正的预测能力仍不清楚。

附：英文原文

Title: Systema: a framework for evaluating genetic perturbation response prediction beyond systematic variation

Author: Vias Torn, Ramon, Wiatrak, Maciej, Piran, Zoe, Fan, Shuyang, Jiang, Liangze, Teichmann, Sarah A., Nitzan, Mor, Brbi, Maria

Issue&Volume: 2025-08-25

Abstract: Predicting transcriptional responses to genetic perturbations is challenging in functional genomics. While recent methods aim to infer effects of untested perturbations, their true predictive power remains unclear. Here, we show that current methods struggle to generalize beyond systematic variation, the consistent transcriptional differences between perturbed and control cells arising from selection biases or confounders. We quantify this variation in ten datasets, spanning three technologies and five cell lines, and show that common metrics are susceptible to these biases, leading to overestimated performance. To address this, we introduce Systema, an evaluation framework that emphasizes perturbation-specific effects and identifies predictions that correctly reconstruct the perturbation landscape. Using this framework, we uncover insights into the predictive capabilities of existing methods and show that predicting responses to unseen perturbations is substantially harder than standard metrics suggest. Our work highlights the importance of heterogeneous gene panels and disentangles predictive performance from systematic effects, enabling biologically meaningful developments in perturbation response modeling.

DOI: 10.1038/s41587-025-02777-8

Source: https://www.nature.com/articles/s41587-025-02777-8