Standard

Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics. / Vilor-Tejedor, Natalia; Ikram, Mohammad Arfan; Roshchupkin, Gennady V.; Cáceres, Alejandro; Alemany, Silvia; Vernooij, Meike W.; Niessen, Wiro J.; van Duijn, Cornelia M.; Adams, Hieab H.; More Authors.

In: NeuroInformatics, Vol. 17, No. 4, 2019, p. 583-592.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Vilor-Tejedor, N, Ikram, MA, Roshchupkin, GV, Cáceres, A, Alemany, S, Vernooij, MW, Niessen, WJ, van Duijn, CM, Adams, HH & More Authors 2019, 'Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics' NeuroInformatics, vol. 17, no. 4, pp. 583-592. https://doi.org/10.1007/s12021-019-09416-z

APA

Vilor-Tejedor, N., Ikram, M. A., Roshchupkin, G. V., Cáceres, A., Alemany, S., Vernooij, M. W., ... More Authors (2019). Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics. NeuroInformatics, 17(4), 583-592. https://doi.org/10.1007/s12021-019-09416-z

Vancouver

Vilor-Tejedor N, Ikram MA, Roshchupkin GV, Cáceres A, Alemany S, Vernooij MW et al. Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics. NeuroInformatics. 2019;17(4):583-592. https://doi.org/10.1007/s12021-019-09416-z

Author

Vilor-Tejedor, Natalia ; Ikram, Mohammad Arfan ; Roshchupkin, Gennady V. ; Cáceres, Alejandro ; Alemany, Silvia ; Vernooij, Meike W. ; Niessen, Wiro J. ; van Duijn, Cornelia M. ; Adams, Hieab H. ; More Authors. / Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics. In: NeuroInformatics. 2019 ; Vol. 17, No. 4. pp. 583-592.

BibTeX

@article{d0a8f2b422a646afbaa707759fb7e4d0,
title = "Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics",
abstract = "Multivariate methods have the potential to better capture complex relationships that may exist between different biological levels. Multiple Factor Analysis (MFA) is one of the most popular methods to obtain factor scores and measures of discrepancy between data sets. However, singular value decomposition in MFA is based on PCA, which is adequate only if the data is normally distributed, linear or stationary. In addition, including strongly correlated variables can overemphasize the contribution of the estimated components. In this work, we introduced a novel method referred as Independent Multifactorial Analysis (ICA-MFA) to derive relevant features from multiscale data. This method is an extended implementation of MFA, where the component value decomposition is based on Independent Component Analysis. In addition, ICA-MFA incorporates a predictive step based on an Independent Component Regression. We evaluated and compared the performance of ICA-MFA with both, the MFA method and traditional univariate analyses, in a simulation study. We showed how ICA-MFA explained up to 10-fold more variance than MFA and univariate methods. We applied the proposed algorithm in a study of 4057 individuals belonging to the population-based Rotterdam Study with available genetic and neuroimaging data, as well as information about executive cognitive functioning. Specifically, we used ICA-MFA to detect relevant genetic features related to structural brain regions, which in turn were involved, in the mechanisms of executive cognitive function. The proposed strategy makes it possible to determine the degree to which the whole set of genetic and/or neuroimaging markers contribute to the variability of the symptomatology jointly, rather than individually. While univariate results and MFA combinations only explained a limited proportion of variance (less than 2{\%}), our method increased the explained variance (10{\%}) and allowed the identification of significant components that maximize the variance explained in the model. The potential application of the ICA-MFA algorithm constitutes an important aspect of integrating multivariate multiscale data, specifically in the field of Neurogenetics.",
keywords = "Data integration, ICA-MFA, Imaging genetics, Modelling, Neurogenetics",
author = "Natalia Vilor-Tejedor and Ikram, {Mohammad Arfan} and Roshchupkin, {Gennady V.} and Alejandro C{\'a}ceres and Silvia Alemany and Vernooij, {Meike W.} and Niessen, {Wiro J.} and {van Duijn}, {Cornelia M.} and Adams, {Hieab H.} and {More Authors}",
year = "2019",
doi = "10.1007/s12021-019-09416-z",
language = "English",
volume = "17",
pages = "583--592",
journal = "NeuroInformatics",
issn = "1539-2791",
publisher = "Humana Press",
number = "4",

}

RIS

TY - JOUR

T1 - Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics

AU - Vilor-Tejedor, Natalia

AU - Ikram, Mohammad Arfan

AU - Roshchupkin, Gennady V.

AU - Cáceres, Alejandro

AU - Alemany, Silvia

AU - Vernooij, Meike W.

AU - Niessen, Wiro J.

AU - van Duijn, Cornelia M.

AU - Adams, Hieab H.

AU - More Authors, null

PY - 2019

Y1 - 2019

N2 - Multivariate methods have the potential to better capture complex relationships that may exist between different biological levels. Multiple Factor Analysis (MFA) is one of the most popular methods to obtain factor scores and measures of discrepancy between data sets. However, singular value decomposition in MFA is based on PCA, which is adequate only if the data is normally distributed, linear or stationary. In addition, including strongly correlated variables can overemphasize the contribution of the estimated components. In this work, we introduced a novel method referred as Independent Multifactorial Analysis (ICA-MFA) to derive relevant features from multiscale data. This method is an extended implementation of MFA, where the component value decomposition is based on Independent Component Analysis. In addition, ICA-MFA incorporates a predictive step based on an Independent Component Regression. We evaluated and compared the performance of ICA-MFA with both, the MFA method and traditional univariate analyses, in a simulation study. We showed how ICA-MFA explained up to 10-fold more variance than MFA and univariate methods. We applied the proposed algorithm in a study of 4057 individuals belonging to the population-based Rotterdam Study with available genetic and neuroimaging data, as well as information about executive cognitive functioning. Specifically, we used ICA-MFA to detect relevant genetic features related to structural brain regions, which in turn were involved, in the mechanisms of executive cognitive function. The proposed strategy makes it possible to determine the degree to which the whole set of genetic and/or neuroimaging markers contribute to the variability of the symptomatology jointly, rather than individually. While univariate results and MFA combinations only explained a limited proportion of variance (less than 2%), our method increased the explained variance (10%) and allowed the identification of significant components that maximize the variance explained in the model. The potential application of the ICA-MFA algorithm constitutes an important aspect of integrating multivariate multiscale data, specifically in the field of Neurogenetics.

AB - Multivariate methods have the potential to better capture complex relationships that may exist between different biological levels. Multiple Factor Analysis (MFA) is one of the most popular methods to obtain factor scores and measures of discrepancy between data sets. However, singular value decomposition in MFA is based on PCA, which is adequate only if the data is normally distributed, linear or stationary. In addition, including strongly correlated variables can overemphasize the contribution of the estimated components. In this work, we introduced a novel method referred as Independent Multifactorial Analysis (ICA-MFA) to derive relevant features from multiscale data. This method is an extended implementation of MFA, where the component value decomposition is based on Independent Component Analysis. In addition, ICA-MFA incorporates a predictive step based on an Independent Component Regression. We evaluated and compared the performance of ICA-MFA with both, the MFA method and traditional univariate analyses, in a simulation study. We showed how ICA-MFA explained up to 10-fold more variance than MFA and univariate methods. We applied the proposed algorithm in a study of 4057 individuals belonging to the population-based Rotterdam Study with available genetic and neuroimaging data, as well as information about executive cognitive functioning. Specifically, we used ICA-MFA to detect relevant genetic features related to structural brain regions, which in turn were involved, in the mechanisms of executive cognitive function. The proposed strategy makes it possible to determine the degree to which the whole set of genetic and/or neuroimaging markers contribute to the variability of the symptomatology jointly, rather than individually. While univariate results and MFA combinations only explained a limited proportion of variance (less than 2%), our method increased the explained variance (10%) and allowed the identification of significant components that maximize the variance explained in the model. The potential application of the ICA-MFA algorithm constitutes an important aspect of integrating multivariate multiscale data, specifically in the field of Neurogenetics.

KW - Data integration

KW - ICA-MFA

KW - Imaging genetics

KW - Modelling

KW - Neurogenetics

UR - http://www.scopus.com/inward/record.url?scp=85073806136&partnerID=8YFLogxK

U2 - 10.1007/s12021-019-09416-z

DO - 10.1007/s12021-019-09416-z

M3 - Article

VL - 17

SP - 583

EP - 592

JO - NeuroInformatics

T2 - NeuroInformatics

JF - NeuroInformatics

SN - 1539-2791

IS - 4

ER -

ID: 66518227