小柯机器人

元匹配作为一个简单的框架可将表型预测模型从大数据转化为小数据
2022-05-22 01:28

新加坡国立大学B. T. Thomas Yeo团队发现,元匹配作为一个简单的框架可将表型预测模型从大数据转化为小数据。2022年5月16日,《自然—神经科学》杂志在线发表了这项成果。

研究人员提出了一个简单的框架,元匹配(Meta-matching),将大规模数据集的预测模型转化为小规模研究中新的未见过的非脑成像表型。关键的考虑是小型研究中的独特表型可能与一些大规模数据集中的相关表型相关(但不相同)。元匹配利用这些相关关系来提高小型研究的预测能力。研究人员应用元匹配来预测来自静止状态功能连接的非脑成像表型。

使用英国生物银行(N=36,848)和人类连接组项目(HCP)(N=1,019)数据集,研究人员证明了元匹配可以在许多情况下大大提升小型独立数据集新表型的预测。例如,将英国生物银行模型转化为100个HCP参与者,在35个表型中,产生了8倍的方差解释,平均绝对收益为4.0%(最小=-0.2%,最大=16.0%)。随着越来越多的大规模数据集收集越来越多样化的表型,这些结果代表了元匹配潜力的一个下限。

附:英文原文

Title: Meta-matching as a simple framework to translate phenotypic predictive models from big to small data

Author: He, Tong, An, Lijun, Chen, Pansheng, Chen, Jianzhong, Feng, Jiashi, Bzdok, Danilo, Holmes, Avram J., Eickhoff, Simon B., Yeo, B. T. Thomas

Issue&Volume: 2022-05-16

Abstract: We propose a simple framework—meta-matching—to translate predictive models from large-scale datasets to new unseen non-brain-imaging phenotypes in small-scale studies. The key consideration is that a unique phenotype from a boutique study likely correlates with (but is not the same as) related phenotypes in some large-scale dataset. Meta-matching exploits these correlations to boost prediction in the boutique study. We apply meta-matching to predict non-brain-imaging phenotypes from resting-state functional connectivity. Using the UK Biobank (N=36,848) and Human Connectome Project (HCP) (N=1,019) datasets, we demonstrate that meta-matching can greatly boost the prediction of new phenotypes in small independent datasets in many scenarios. For example, translating a UK Biobank model to 100 HCP participants yields an eight-fold improvement in variance explained with an average absolute gain of 4.0% (minimum=0.2%, maximum=16.0%) across 35 phenotypes. With a growing number of large-scale datasets collecting increasingly diverse phenotypes, our results represent a lower bound on the potential of meta-matching.

DOI: 10.1038/s41593-022-01059-9

Source: https://www.nature.com/articles/s41593-022-01059-9

Nature Neuroscience:《自然—神经科学》,创刊于1998年。隶属于施普林格·自然出版集团,最新IF:28.771
官方网址:https://www.nature.com/neuro/
投稿链接:https://mts-nn.nature.com/cgi-bin/main.plex


本期文章:《自然—神经科学》:Online/在线发表

分享到:

0