Machine learning approaches based on fibroblast morphometry do not predict ALS.
Machine learning approaches based on fibroblast morphometry do not predict ALS.
复制标题
基于成纤维细胞形态测量的机器学习方法不能预测 ALS。
DOI：
10.1016/j.neurobiolaging.2023.06.010
复制
发表时间：
2023
影响因子：
4.2
通讯作者：
Konrad,Csaba
中科院分区：
文献类型：
--
作者：
Woo,Evan;Bredvik,Kirsten;Liu,Bangyan;Fuchs,ThomasJ;Manfredi,Giovanni;Konrad,Csaba
肌萎缩侧索硬化症（ALS）是一种具有破坏性的神经肌肉疾病，治疗选择有限。早期疾病检测、临床试验设计和个性化医疗都需要生物标志物。早期的证据表明，ALS原发性皮肤成纤维细胞的特定形态特征可用作生物标志物;然而，这一假设尚未在最终的大型成纤维细胞群体中进行严格测试。在这里，我们成像ALS相关的细胞器（线粒体，内质网，溶酶体）和蛋白质（TAR DNA结合蛋白43，Ras GTP酶激活蛋白结合蛋白1，热休克蛋白60）在基线和应激扰动下，并测试了他们的预测能力对一组443人成纤维细胞系ALS和健康人。机器学习方法能够自信地预测应激扰动状态（ROC-AUC <0.99），但不能预测疾病组或临床特征（ROC-AUC <0.58-0.64）。我们的研究结果表明，使用患者来源的成纤维细胞形态测量的多变量模型可以准确地预测不同的压力源，但不足以开发可行的ALS生物标志物。
Amyotrophic lateral sclerosis (ALS) is a devastating neuromuscular disease with limited therapeutic options. Biomarkers are needed for early disease detection, clinical trial design, and personalized medicine. Early evidence suggests that specific morphometric features in ALS primary skin fibroblasts may be used as biomarkers; however, this hypothesis has not been rigorously tested in conclusively large fibroblast populations. Here, we imaged ALS-relevant organelles (mitochondria, endoplasmic reticulum, lysosomes) and proteins (TAR DNA-binding protein 43, Ras GTPase-activating protein-binding protein 1, heat-shock protein 60) at baseline and under stress perturbations and tested their predictive power on a total set of 443 human fibroblast lines from ALS and healthy individuals. Machine learning approaches were able to confidently predict stress perturbation states (ROC-AUC ∼0.99) but not disease groups or clinical features (ROC-AUC 0.58–0.64). Our findings indicate that multivariate models using patient-derived fibroblast morphometry can accurately predict different stressors but are insufficient to develop viable ALS biomarkers.