Graph Neural Networks in Cancer and Oncology Research: Emerging and Future Trends.
Graph Neural Networks in Cancer and Oncology Research: Emerging and Future Trends.
复制标题
癌症与肿瘤学研究中的图神经网络：新兴趋势与未来趋势
DOI：
10.3390/cancers15245858
复制
发表时间：
2023-12-15
期刊：
影响因子：
5.2
通讯作者：
Rodin, Andrei S.
中科院分区：
文献类型：
--
作者：
Gogoshin, Grigoriy;Rodin, Andrei S.
图神经网络正在成为结构化数据分析和大规模多模态数据集预测建模的强大工具。在这篇综述中，我们调查了最近的应用程序的图形神经网络在癌症和肿瘤学研究的设置。我们确定了当前的主要研究领域，并将图神经网络与非图深度学习方法以及概率图模型进行了比较。最后，我们强调了新出现的趋势和紧迫的挑战，例如制定独立和全面的基准框架。这篇评论是针对癌症和肿瘤学的研究人员，临床医生和医生，科学家谁是有兴趣应用图形为中心的二级数据分析方法，结构化的多模态数据。下一代癌症和肿瘤学研究需要充分利用多模态结构化或图形信息，图形数据类型从分子结构到空间分辨成像和数字病理学，生物网络和知识图。图神经网络（GNN）有效地将图结构表示与深度学习的高预测性能（尤其是在大型多模态数据集上）联合收割机相结合。在这篇评论文章中，我们回顾了最近（2020年至今）GNN在癌症和肿瘤学研究背景下的应用前景，并描绘了目前主要的六个研究领域。然后，我们确定了未来研究的最有前途的方向。我们将GNN与图形模型和“非结构化”深度学习进行了比较，并为癌症和肿瘤学研究人员或医生科学家制定了指导方针，询问他们是否应该在研究管道中采用GNN方法。
Graph Neural Networks are emerging as a powerful tool for structured data analysis, and predictive modeling in massive multimodal datasets. In this review, we survey recent applications of graph neural networks in the setting of cancer and oncology research. We identify currently predominant research areas, and compare graph neural networks with non-graph deep learning methods as well as probabilistic graphical models. We conclude by highlighting emerging trends and pressing challenges, such as developing independent and comprehensive benchmarking frameworks. This review is aimed at cancer and oncology researchers, clinicians and physician-scientists who are interested in applying graph-centered secondary data analysis methods to structured multimodal data. Next-generation cancer and oncology research needs to take full advantage of the multimodal structured, or graph, information, with the graph data types ranging from molecular structures to spatially resolved imaging and digital pathology, biological networks, and knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on large multimodal datasets. In this review article, we survey the landscape of recent (2020–present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. We then identify the most promising directions for future research. We compare GNNs with graphical models and “non-structured” deep learning, and devise guidelines for cancer and oncology researchers or physician-scientists, asking the question of whether they should adopt the GNN methodology in their research pipelines.
登录
查看更多内容
用多模态图神经网络预测癌症患者的生存期
DOI：
10.1109/tcbb.2021.3083566
发表时间：
2022-03-01
影响因子：
4.5
作者：
Gao, Jianliang;Lyu, Tengfei;Li, Zhao
通讯作者：
Li, Zhao
用于预测人类癌症综合致死率的双丢失图卷积网络
影响因子：
5.8
作者：
Cai, Ruichu;Chen, Xuexin;Hao, Yuexing
通讯作者：
Hao, Yuexing
影响因子：
3
作者：
通讯作者：
--
DOI：
10.1109/tcbb.2023.3290394
发表时间：
2023-09-01
影响因子：
4.5
作者：
Furtney, Isaac;Bradley, Ray;Kabuka, Mansur R.
通讯作者：
Kabuka, Mansur R.
影响因子：
6
作者：
Chang, Yuzhou;He, Fei;Wang, Juexin;Chen, Shuo;Li, Jingyi;Liu, Jixin;Yu, Yang;Su, Li;Ma, Anjun;Allen, Carter;Lin, Yu;Sun, Shaoli;Liu, Bingqiang;Otero, Jose Javier;Chung, Dongjun;Fu, Hongjun;Li, Zihai;Xu, Dong;Ma, Qin
通讯作者：
Ma, Qin