Wang Shijie, Linsley Jeremy W, Linsley Drew A, Lamstein Josh, Finkbeiner Steven
Center for Systems and Therapeutics, Gladstone Institutes, San Francisco, CA, United States.
Robert J. and Nancy D. Carney Institute for Brain Science, Brown University, Providence, RI, United States.
Front Toxicol. 2022 Aug 24;4:935438. doi: 10.3389/ftox.2022.935438. eCollection 2022.
Neurotoxicity can be detected in live microscopy by morphological changes such as retraction of neurites, fragmentation, blebbing of the neuronal soma and ultimately the disappearance of fluorescently labeled neurons. However, quantification of these features is often difficult, low-throughput, and imprecise due to the overreliance on human curation. Recently, we showed that convolutional neural network (CNN) models can outperform human curators in the assessment of neuronal death from images of fluorescently labeled neurons, suggesting that there is information within the images that indicates toxicity but that is not apparent to the human eye. In particular, the CNN's decision strategy indicated that information within the nuclear region was essential for its superhuman performance. Here, we systematically tested this prediction by comparing images of fluorescent neuronal morphology from nuclear-localized fluorescent protein to those from freely diffused fluorescent protein for classifying neuronal death. We found that biomarker-optimized (BO-) CNNs could learn to classify neuronal death from fluorescent protein-localized nuclear morphology (mApple-NLS-CNN) alone, with super-human accuracy. Furthermore, leveraging methods from explainable artificial intelligence, we identified novel features within the nuclear-localized fluorescent protein signal that were indicative of neuronal death. Our findings suggest that the use of a nuclear morphology marker in live imaging combined with computational models such mApple-NLS-CNN can provide an optimal readout of neuronal death, a common result of neurotoxicity.
通过实时显微镜观察，神经毒性可通过形态学变化检测出来，如神经突回缩、碎片化、神经元胞体起泡，最终荧光标记的神经元消失。然而，由于过度依赖人工筛选，对这些特征进行量化往往困难、低通量且不准确。最近，我们发现卷积神经网络（CNN）模型在根据荧光标记神经元的图像评估神经元死亡方面表现优于人工筛选，这表明图像中存在指示毒性但人眼无法察觉的信息。特别是，CNN的决策策略表明核区域内的信息对其超人般的表现至关重要。在此，我们通过比较核定位荧光蛋白和自由扩散荧光蛋白的荧光神经元形态图像来分类神经元死亡，系统地测试了这一预测。我们发现生物标志物优化（BO-）的CNN仅从荧光蛋白定位的核形态（mApple-NLS-CNN）就能学会以超人般的准确率对神经元死亡进行分类。此外，利用可解释人工智能的方法，我们在核定位荧光蛋白信号中识别出了指示神经元死亡的新特征。我们的研究结果表明，在实时成像中使用核形态标记物并结合mApple-NLS-CNN等计算模型，可以为神经元死亡（神经毒性的常见结果）提供最佳读数。
