Machine-Learning-Based Late Fusion on Multi-Omics and Multi-Scale Data for Non-Small-Cell Lung Cancer Diagnosis.

Machine-Learning-Based Late Fusion on Multi-Omics and Multi-Scale Data for Non-Small-Cell Lung Cancer Diagnosis.
复制标题

基于机器学习的多维多尺度数据融合在非小细胞肺癌诊断中的应用

DOI:
10.3390/jpm12040601
复制
发表时间:
2022-04-08
影响因子:
--
通讯作者:
--
中科院分区:
医学4区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

区分不同的非小细胞肺癌亚型对于为患者提供有效的治疗至关重要。为此,近年来,机器学习技术被用于处理来自患者的可用生物数据。然而,在大多数情况下,这个问题是用单一模式方法处理的,没有探索癌症数据的多尺度和多组学性质用于分类的潜力。在这项工作中,我们利用后期融合策略和机器学习技术,研究了五种多尺度多基因组模式(RNA-Seq、miRNA-Seq、全片成像、拷贝数变化和DNA甲基化)的融合。我们为每个通道训练一个独立的机器学习模型,并通过使用一种新的优化方法来计算后期融合的参数,来探索通过以增加的方式融合它们的输出可以获得的相互作用和收益。使用所有模态的最终分类模型获得F1分数、AUC和AUPRC,改进了每个独立模型获得的结果和文献中针对该问题提出的结果。这些结果表明,利用癌症数据的多尺度和多组学性质,可以提高个性化医疗中单通道临床决策支持系统的性能,从而提高患者的诊断水平。
Differentiation between the various non-small-cell lung cancer subtypes is crucial for providing an effective treatment to the patient. For this purpose, machine learning techniques have been used in recent years over the available biological data from patients. However, in most cases this problem has been treated using a single-modality approach, not exploring the potential of the multi-scale and multi-omic nature of cancer data for the classification. In this work, we study the fusion of five multi-scale and multi-omic modalities (RNA-Seq, miRNA-Seq, whole-slide imaging, copy number variation, and DNA methylation) by using a late fusion strategy and machine learning techniques. We train an independent machine learning model for each modality and we explore the interactions and gains that can be obtained by fusing their outputs in an increasing manner, by using a novel optimization approach to compute the parameters of the late fusion. The final classification model, using all modalities, obtains an F1 score of , an AUC of , and an AUPRC of , improving those results that each independent model obtains and those presented in the literature for this problem. These obtained results show that leveraging the multi-scale and multi-omic nature of cancer data can enhance the performance of single-modality clinical decision support systems in personalized medicine, consequently improving the diagnosis of the patient.
DOI: 10.1186/s12859-016-1421-y
发表时间: 2017-01-13
期刊: BMC bioinformatics
影响因子: 3
作者:
Cheerla N;Gevaert O
通讯作者: Gevaert O
实现癌症基因组数据的共同愿景。
DOI: 10.1056/nejmp1607591
发表时间: 2016-09-22
期刊: The New England journal of medicine
影响因子: --
作者:
Grossman RL;Heath AP;Ferretti V;Varmus HE;Lowy DR;Kibbe WA;Staudt LM
通讯作者: Staudt LM
DOI: 10.1038/s41598-020-66333-x
发表时间: 2020-06-09
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Kanavati, Fahdi;Toyokawa, Gouji;Tsuneki, Masayuki
通讯作者: Tsuneki, Masayuki
DOI: 10.1016/j.compbiomed.2021.104387
发表时间: 2021-04-19
影响因子: 7.7
作者:
Castillo-Secilla, Daniel;Galvez, Juan Manuel G.;Rojas, Ignacio
通讯作者: Rojas, Ignacio
DOI: 10.1162/089976603321891855
发表时间: 2003-07-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
Keerthi, SS;Lin, CJ
通讯作者: Lin, CJ