Wen Gang, Li Limin
School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China.
Bioinformatics. 2024 Dec 26;41(1). doi: 10.1093/bioinformatics/btae684.
High-throughput techniques have produced a large amount of high-dimensional multi-omics data, which makes it promising to predict patient survival outcomes more accurately. Recent work has showed the superiority of multi-omics data in survival analysis. However, it remains challenging to integrate multi-omics data to solve few-shot survival prediction problem, with only a few available training samples, especially for rare cancers.
In this work, we propose a meta-learning framework for multi-omics few-shot survival analysis, namely MMOSurv, which enables to learn an effective multi-omics survival prediction model from a very few training samples of a specific cancer type, with the meta-knowledge across tasks from relevant cancer types. By assuming a deep Cox survival model with multiple omics, MMOSurv first learns an adaptable parameter initialization for the multi-omics survival model from abundant data of relevant cancers, and then adapts the parameters quickly and efficiently for the target cancer task with a very few training samples. Our experiments on eleven cancer types in The Cancer Genome Atlas datasets show that, compared to single-omics meta-learning methods, MMOSurv can better utilize the meta-information of similarities and relationships between different omics data from relevant cancer datasets to improve survival prediction of the target cancer with a very few multi-omics training samples. Furthermore, MMOSurv achieves better prediction performance than other state-of-the-art strategies such as multitask learning and pretraining.
MMOSurv is freely available at https://github.com/LiminLi-xjtu/MMOSurv.
高通量技术产生了大量高维多组学数据，这使得更准确地预测患者生存结果成为可能。近期研究表明了多组学数据在生存分析中的优势。然而，整合多组学数据以解决少样本生存预测问题仍然具有挑战性，因为可用的训练样本很少，尤其是对于罕见癌症。
在这项工作中，我们提出了一种用于多组学少样本生存分析的元学习框架，即MMOSurv，它能够从特定癌症类型的极少训练样本中学习有效的多组学生存预测模型，并利用来自相关癌症类型的跨任务元知识。通过假设一个具有多个组学的深度Cox生存模型，MMOSurv首先从相关癌症的丰富数据中学习多组学生存模型的自适应参数初始化，然后使用极少的训练样本快速有效地调整目标癌症任务的参数。我们在癌症基因组图谱数据集的11种癌症类型上进行的实验表明，与单组学元学习方法相比，MMOSurv可以更好地利用相关癌症数据集中不同组学数据之间的相似性和关系的元信息，以通过极少的多组学训练样本改善目标癌症的生存预测。此外，MMOSurv比其他诸如多任务学习和预训练等当前最先进的策略具有更好的预测性能。
