A multimodal graph neural network framework for cancer molecular subtype classification.
A multimodal graph neural network framework for cancer molecular subtype classification.
复制标题
DOI：
10.1186/s12859-023-05622-4
复制
发表时间：
2024-01-15
影响因子：
3
通讯作者：
中科院分区：
文献类型：
--
作者：
近年来高通量测序技术的发展，为研究人员提供了大量的多组学数据，使他们能够更好地研究癌症分子谱和基于分子亚型的癌症分类。整合多组学数据已被证明是建立更精确的分类模型的有效方法。大多数当前的多组学整合模型使用串联形式的早期融合或对每个组学使用单独的特征提取器的后期融合，其主要基于深度神经网络。由于生物系统的性质，图是生物医学数据的更好的结构表示。虽然很少有基于图神经网络（GNN）的多组学整合方法被提出，但它们有三个共同的缺点。一是它们中的大多数只使用一种类型的连接，要么是组间连接，要么是组内连接;第二，它们只考虑一种GNN层，要么是图卷积网络（GCN），要么是图注意力网络（GAT）;第三，这些方法中的大多数还没有在更复杂的分类任务（如癌症分子亚型）上进行测试。在这项研究中，我们提出了一种新的端到端多组学GNN框架，用于准确和强大的癌症亚型分类。所提出的模型利用多组学数据的异构多层图的形式，其中联合收割机结合两个组学间和组学内的连接，从建立生物知识。该模型结合了学习的图特征和全局基因组特征，以实现准确的分类。我们分别在癌症基因组图谱（TCGA）泛癌症数据集和TCGA乳腺浸润癌（BRCA）数据集上测试了所提出的模型的分子亚型和癌症亚型分类。该模型在准确率、F1得分、精确度和召回率方面优于目前最先进的四种基线模型。对基于GAT模型和基于GCN模型的比较分析表明，基于GAT的模型适用于信息较少的小图，而基于GCN的模型适用于信息较多的大图。在线版本包含补充材料，可通过10.1186/s12859-023-05622-4获得。
The recent development of high-throughput sequencing has created a large collection of multi-omics data, which enables researchers to better investigate cancer molecular profiles and cancer taxonomy based on molecular subtypes. Integrating multi-omics data has been proven to be effective for building more precise classification models. Most current multi-omics integrative models use either an early fusion in the form of concatenation or late fusion with a separate feature extractor for each omic, which are mainly based on deep neural networks. Due to the nature of biological systems, graphs are a better structural representation of bio-medical data. Although few graph neural network (GNN) based multi-omics integrative methods have been proposed, they suffer from three common disadvantages. One is most of them use only one type of connection, either inter-omics or intra-omic connection; second, they only consider one kind of GNN layer, either graph convolution network (GCN) or graph attention network (GAT); and third, most of these methods have not been tested on a more complex classification task, such as cancer molecular subtypes. In this study, we propose a novel end-to-end multi-omics GNN framework for accurate and robust cancer subtype classification. The proposed model utilizes multi-omics data in the form of heterogeneous multi-layer graphs, which combine both inter-omics and intra-omic connections from established biological knowledge. The proposed model incorporates learned graph features and global genome features for accurate classification. We tested the proposed model on the Cancer Genome Atlas (TCGA) Pan-cancer dataset and TCGA breast invasive carcinoma (BRCA) dataset for molecular subtype and cancer subtype classification, respectively. The proposed model shows superior performance compared to four current state-of-the-art baseline models in terms of accuracy, F1 score, precision, and recall. The comparative analysis of GAT-based models and GCN-based models reveals that GAT-based models are preferred for smaller graphs with less information and GCN-based models are preferred for larger graphs with extra information. The online version contains supplementary material available at 10.1186/s12859-023-05622-4.
登录
查看更多内容
影响因子：
3
作者：
Wang T;Bai J;Nabavi S
通讯作者：
Nabavi S
影响因子：
4.4
作者：
Ma, Tianle;Zhang, Aidong
通讯作者：
Zhang, Aidong
影响因子：
64.5
作者：
Hoadley KA;Yau C;Wolf DM;Cherniack AD;Tamborero D;Ng S;Leiserson MDM;Niu B;McLellan MD;Uzunangelov V;Zhang J;Kandoth C;Akbani R;Shen H;Omberg L;Chu A;Margolin AA;Van't Veer LJ;Lopez-Bigas N;Laird PW;Raphael BJ;Ding L;Robertson AG;Byers LA;Mills GB;Weinstein JN;Van Waes C;Chen Z;Collisson EA;Cancer Genome Atlas Research Network;Benz CC;Perou CM;Stuart JM
通讯作者：
Stuart JM
影响因子：
82.9
作者：
Mateo, Joaquin;Steuten, Lotte;Voest, Emile
通讯作者：
Voest, Emile
DOI：
10.1109/tnnls.2020.2978386
发表时间：
2021-01-01
影响因子：
10.4
作者：
Wu, Zonghan;Pan, Shirui;Yu, Philip S.
通讯作者：
Yu, Philip S.