A cell-level discriminative neural network model for diagnosis of blood cancers.
A cell-level discriminative neural network model for diagnosis of blood cancers.
复制标题
DOI：
10.1093/bioinformatics/btad585
复制
发表时间：
2023-10-03
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
精确识别患者样本中的癌细胞对于准确诊断和临床监测至关重要，但这一直是癌症精准医学机器学习方法的重大挑战。在大多数情况下，训练数据仅在受试者或样本水平上具有疾病注释。传统的方法将分类过程分成多个独立优化的步骤。最近的方法要么专注于预测样本水平的诊断，而不识别单个病理细胞，要么对识别异质性癌细胞表型不太有效。我们开发了一种广义的端到端可区分模型，细胞评分神经网络（CSNN），它采用样本级训练数据，同时预测测试样本的诊断和样本中诊断细胞的身份。样本之间的细胞水平密度差异与样本诊断有关，这允许使用反向传播计算单个细胞被诊断的概率。我们将CSNN应用于两个独立的临床流式细胞术数据集进行白血病诊断。在定性和定量评估方面，CSNN在癌症诊断和细胞水平分类方面都优于现有的神经网络建模方法。生成事后决策树和2D点图用于解释所鉴定的癌细胞，显示所鉴定的细胞表型与临床上在患者群组中观察到的癌症内在型相匹配。独立的数据聚类分析证实了所鉴定的癌细胞群体。CSNN的源代码和实验中使用的数据集可在GitHub（http：//github.com/erobl/csnn）上公开获得。原始FCS文件可从FlowRepository（ID：FR-FCM-Z6 YK）下载。
Precise identification of cancer cells in patient samples is essential for accurate diagnosis and clinical monitoring but has been a significant challenge in machine learning approaches for cancer precision medicine. In most scenarios, training data are only available with disease annotation at the subject or sample level. Traditional approaches separate the classification process into multiple steps that are optimized independently. Recent methods either focus on predicting sample-level diagnosis without identifying individual pathologic cells or are less effective for identifying heterogeneous cancer cell phenotypes. We developed a generalized end-to-end differentiable model, the Cell Scoring Neural Network (CSNN), which takes sample-level training data and predicts the diagnosis of the testing samples and the identity of the diagnostic cells in the sample, simultaneously. The cell-level density differences between samples are linked to the sample diagnosis, which allows the probabilities of individual cells being diagnostic to be calculated using backpropagation. We applied CSNN to two independent clinical flow cytometry datasets for leukemia diagnosis. In both qualitative and quantitative assessments, CSNN outperformed preexisting neural network modeling approaches for both cancer diagnosis and cell-level classification. Post hoc decision trees and 2D dot plots were generated for interpretation of the identified cancer cells, showing that the identified cell phenotypes match the cancer endotypes observed clinically in patient cohorts. Independent data clustering analysis confirmed the identified cancer cell populations. The source code of CSNN and datasets used in the experiments are publicly available on GitHub (http://github.com/erobl/csnn). Raw FCS files can be downloaded from FlowRepository (ID: FR-FCM-Z6YK).
登录
查看更多内容
影响因子：
64.5
作者：
Levine JH;Simonds EF;Bendall SC;Davis KL;Amir el-AD;Tadmor MD;Litvin O;Fienberg HG;Jager A;Zunder ER;Finck R;Gedman AL;Radtke I;Downing JR;Pe'er D;Nolan GP
通讯作者：
Nolan GP
影响因子：
4.3
作者：
Finak G;Frelinger J;Jiang W;Newell EW;Ramey J;Davis MM;Kalams SA;De Rosa SC;Gottardo R
通讯作者：
Gottardo R
影响因子：
3.7
作者：
Ji, Disi;Putzel, Preston;Smyth, Padhraic
通讯作者：
Smyth, Padhraic
影响因子：
3.7
作者：
Aghaeepour, Nima;Nikolic, Radina;Hoos, Holger H.;Brinkman, Ryan R.
通讯作者：
Brinkman, Ryan R.
DOI：
10.1093/bioinformatics/bty768
发表时间：
2019-04-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Hu Z;Glicksberg BS;Butte AJ
通讯作者：
Butte AJ