Large-scale drug discovery and repurposing is challenging. Identifying the mechanism of action (MOA) is crucial, yet current approaches are costly and low-throughput. Here we present an approach for MOA identification by profiling changes in mitochondrial phenotypes. By temporally imaging mitochondrial morphology and membrane potential, we established a pipeline for monitoring time-resolved mitochondrial images, resulting in a dataset comprising 570,096 single-cell images of cells exposed to 1,068 United States Food and Drug Administration-approved drugs. A deep learning model named MitoReID, using a re-identification (ReID) framework and an Inflated 3D ResNet backbone, was developed. It achieved 76.32% Rank-1 and 65.92% mean average precision on the testing set and successfully identified the MOAs for six untrained drugs on the basis of mitochondrial phenotype. Furthermore, MitoReID identified cyclooxygenase-2 inhibition as the MOA of the natural compound epicatechin in tea, which was successfully validated in vitro. Our approach thus provides an automated and cost-effective alternative for target identification that could accelerate large-scale drug discovery and repurposing.

大规模的药物发现和重新利用具有挑战性。确定作用机制 (MOA) 至关重要，但目前的方法成本高昂且通量低。在这里，我们提出了一种通过分析线粒体表型变化来识别 MOA 的方法。通过对线粒体形态和膜电位进行时间成像，我们建立了一个用于监测时间分辨线粒体图像的管道，生成了一个数据集，其中包含暴露于 1,068 种美国食品和药物管理局批准的药物的细胞的 570,096 个单细胞图像。开发了一种名为 MitoReID 的深度学习模型，该模型使用重新识别 (ReID) 框架和 Inflated 3D ResNet 主干。它在测试集上实现了 76.32% Rank-1 和 65.92% 平均精度，并根据线粒体表型成功识别了六种未经训练的药物的 MOA。此外，MitoReID 确定了茶中天然化合物表儿茶素的 MOA 抑制环氧合酶 2，并在体外得到了成功验证。因此，我们的方法为目标识别提供了一种自动化且经济高效的替代方案，可以加速大规模药物发现和重新利用。