Meta-matching as a simple framework to translate phenotypic predictive models from big to small data. He, T., An, L., Chen, P., Chen, J., Feng, J., Bzdok, D., Holmes, A. J., Eickhoff, S. B., & Yeo, B. T. T. Nature Neuroscience, May, 2022. Publisher: Nature Publishing Group![Meta-matching as a simple framework to translate phenotypic predictive models from big to small data [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 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.
@article{he_meta-matching_2022,
title = {Meta-matching as a simple framework to translate phenotypic predictive models from big to small data},
copyright = {2022 The Author(s), under exclusive licence to Springer Nature America, Inc.},
issn = {1546-1726},
url = {https://www.nature.com/articles/s41593-022-01059-9},
doi = {10.1038/s41593-022-01059-9},
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.},
language = {en},
urldate = {2022-05-19},
journal = {Nature Neuroscience},
author = {He, Tong and An, Lijun and Chen, Pansheng and Chen, Jianzhong and Feng, Jiashi and Bzdok, Danilo and Holmes, Avram J. and Eickhoff, Simon B. and Yeo, B. T. Thomas},
month = may,
year = {2022},
note = {Publisher: Nature Publishing Group},
keywords = {Cognitive neuroscience, Network models},
pages = {1--10},
}
Downloads: 0
{"_id":"PDedb7DYfEQBP3baM","bibbaseid":"he-an-chen-chen-feng-bzdok-holmes-eickhoff-etal-metamatchingasasimpleframeworktotranslatephenotypicpredictivemodelsfrombigtosmalldata-2022","author_short":["He, T.","An, L.","Chen, P.","Chen, J.","Feng, J.","Bzdok, D.","Holmes, A. J.","Eickhoff, S. B.","Yeo, B. T. T."],"bibdata":{"bibtype":"article","type":"article","title":"Meta-matching as a simple framework to translate phenotypic predictive models from big to small data","copyright":"2022 The Author(s), under exclusive licence to Springer Nature America, Inc.","issn":"1546-1726","url":"https://www.nature.com/articles/s41593-022-01059-9","doi":"10.1038/s41593-022-01059-9","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.","language":"en","urldate":"2022-05-19","journal":"Nature Neuroscience","author":[{"propositions":[],"lastnames":["He"],"firstnames":["Tong"],"suffixes":[]},{"propositions":[],"lastnames":["An"],"firstnames":["Lijun"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Pansheng"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Jianzhong"],"suffixes":[]},{"propositions":[],"lastnames":["Feng"],"firstnames":["Jiashi"],"suffixes":[]},{"propositions":[],"lastnames":["Bzdok"],"firstnames":["Danilo"],"suffixes":[]},{"propositions":[],"lastnames":["Holmes"],"firstnames":["Avram","J."],"suffixes":[]},{"propositions":[],"lastnames":["Eickhoff"],"firstnames":["Simon","B."],"suffixes":[]},{"propositions":[],"lastnames":["Yeo"],"firstnames":["B.","T.","Thomas"],"suffixes":[]}],"month":"May","year":"2022","note":"Publisher: Nature Publishing Group","keywords":"Cognitive neuroscience, Network models","pages":"1–10","bibtex":"@article{he_meta-matching_2022,\n\ttitle = {Meta-matching as a simple framework to translate phenotypic predictive models from big to small data},\n\tcopyright = {2022 The Author(s), under exclusive licence to Springer Nature America, Inc.},\n\tissn = {1546-1726},\n\turl = {https://www.nature.com/articles/s41593-022-01059-9},\n\tdoi = {10.1038/s41593-022-01059-9},\n\tabstract = {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.},\n\tlanguage = {en},\n\turldate = {2022-05-19},\n\tjournal = {Nature Neuroscience},\n\tauthor = {He, Tong and An, Lijun and Chen, Pansheng and Chen, Jianzhong and Feng, Jiashi and Bzdok, Danilo and Holmes, Avram J. and Eickhoff, Simon B. and Yeo, B. T. Thomas},\n\tmonth = may,\n\tyear = {2022},\n\tnote = {Publisher: Nature Publishing Group},\n\tkeywords = {Cognitive neuroscience, Network models},\n\tpages = {1--10},\n}\n\n","author_short":["He, T.","An, L.","Chen, P.","Chen, J.","Feng, J.","Bzdok, D.","Holmes, A. J.","Eickhoff, S. B.","Yeo, B. T. T."],"key":"he_meta-matching_2022","id":"he_meta-matching_2022","bibbaseid":"he-an-chen-chen-feng-bzdok-holmes-eickhoff-etal-metamatchingasasimpleframeworktotranslatephenotypicpredictivemodelsfrombigtosmalldata-2022","role":"author","urls":{"Paper":"https://www.nature.com/articles/s41593-022-01059-9"},"keyword":["Cognitive neuroscience","Network models"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/groups/4553800/items?key=BfP7bN7FF9dJwtyiLBORewdg&format=bibtex&limit=100","dataSources":["5EcJ4DjTLGyJLTga3"],"keywords":["cognitive neuroscience","network models"],"search_terms":["meta","matching","simple","framework","translate","phenotypic","predictive","models","big","small","data","he","an","chen","chen","feng","bzdok","holmes","eickhoff","yeo"],"title":"Meta-matching as a simple framework to translate phenotypic predictive models from big to small data","year":2022}