Comparison of Cellular Morphological Descriptors and Molecular Fingerprints for the Prediction of Cytotoxicity- and Proliferation-Related Assays

Cell morphology features, such as those from the Cell Painting assay, can be generated at relatively low costs and represent versatile biological descriptors of a system and thereby compound response. In this study, we explored cell morphology descriptors and molecular fingerprints, separately and in combination, for the prediction of cytotoxicity- and proliferation-related in vitro assay endpoints. We selected 135 compounds from the MoleculeNet ToxCast benchmark data set which were annotated with Cell Painting readouts, where the relatively small size of the data set is due to the overlap of required annotations. We trained Random Forest classification models using nested cross-validation and Cell Painting descriptors, Morgan and ErG fingerprints, and their combinations. While using leave-one-cluster-out cross-validation (with clusters based on physicochemical descriptors), models using Cell Painting descriptors achieved higher average performance over all assays (Balanced Accuracy of 0.65, Matthews Correlation Coefficient of 0.28, and AUC-ROC of 0.71) compared to models using ErG fingerprints (BA 0.55, MCC 0.09, and AUC-ROC 0.60) and Morgan fingerprints alone (BA 0.54, MCC 0.06, and AUC-ROC 0.56). While using random shuffle splits, the combination of Cell Painting descriptors with ErG and Morgan fingerprints further improved balanced accuracy on average by 8.9% (in 9 out of 12 assays) and 23.4% (in 8 out of 12 assays) compared to using only ErG and Morgan fingerprints, respectively. Regarding feature importance, Cell Painting descriptors related to nuclei texture, granularity of cells, and cytoplasm as well as cell neighbors and radial distributions were identified to be most contributing, which is plausible given the endpoint considered. We conclude that cell morphological descriptors contain complementary information to molecular fingerprints which can be used to improve the performance of predictive cytotoxicity models, in particular in areas of novel structural space.细胞形态特征（cell morphology features），例如来自细胞绘画检测（Cell Painting assay）的特征，可通过相对较低的成本获取，且可作为系统及化合物应答的通用生物学描述符。本研究分别及联合探究了细胞形态描述符与分子指纹（molecular fingerprints），用于预测与细胞毒性（cytotoxicity）及细胞增殖（proliferation）相关的体外实验（in vitro assay）终点。我们从带有细胞绘画检测注释结果的MoleculeNet ToxCast基准数据集（MoleculeNet ToxCast benchmark data set）中选取了135种化合物；该数据集规模相对较小，系所需注释存在重叠所致。我们采用嵌套交叉验证（nested cross-validation），结合细胞绘画检测描述符、摩根指纹（Morgan fingerprints）与ErG指纹（ErG fingerprints）及其组合，训练了随机森林（Random Forest）分类模型。当采用留簇交叉验证（leave-one-cluster-out cross-validation，其中簇基于理化描述符（physicochemical descriptors）构建）时，相较于仅使用ErG指纹（平衡准确率0.55、马修斯相关系数0.09、受试者工作特征曲线下面积（AUC-ROC）0.60）或仅摩根指纹（平衡准确率0.54、马修斯相关系数0.06、受试者工作特征曲线下面积（AUC-ROC）0.56）的模型，使用细胞绘画检测描述符的模型在所有实验中的平均表现更优，其平衡准确率达0.65、马修斯相关系数为0.28、受试者工作特征曲线下面积为0.71。当采用随机打乱划分（random shuffle splits）时，细胞绘画检测描述符与ErG指纹、摩根指纹的联合使用，相较于仅使用ErG指纹或仅摩根指纹的模型，分别使平均平衡准确率提升了8.9%（12项实验中的9项）与23.4%（12项实验中的8项）。就特征重要性而言，与细胞核纹理、细胞颗粒度、细胞质以及细胞邻域和径向分布相关的细胞绘画检测描述符被确定为贡献度最高的特征，这与所考虑的实验终点相符。我们得出结论：细胞形态描述符包含与分子指纹互补的信息，可用于提升预测性细胞毒性模型的性能，尤其是在新型结构空间领域。