Automated machine learning for Genome Wide Association Studies.

Kleanthi Lakiotaki; Zaharias Papadovasilakis; Vincenzo Lagani; Stefanos Fafalios; Paulos Charonyktakis; Michail Tsagris; Ioannis Tsamardinos

doi:10.1093/bioinformatics/btad545

Automated machine learning for Genome Wide Association Studies.

Kleanthi Lakiotaki, Zaharias Papadovasilakis, Vincenzo Lagani, Stefanos Fafalios, Paulos Charonyktakis, Michail Tsagris, Ioannis Tsamardinos

Biological, Environmental Sciences and Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Motivation: Genome Wide Association Studies (GWAS) present several computational and statistical challenges for their data analysis, including knowledge discovery, interpretability, and translation to clinical practice. Results: We develop, apply, and comparatively evaluate an Automated Machine Learning (AutoML) approach, customized for genomic data that delivers reliable predictive and diagnostic models, the set of genetic variants that are important for predictions (called a biosignature), and an estimate of the out-of-sample predictive power. This AutoML approach discovers variants with higher predictive performance compared to standard GWAS methods, computes an individual risk prediction score, generalizes to new, unseen data, is shown to better differentiate causal variants from other highly correlated variants, and enhances knowledge discovery and interpretability by reporting multiple equivalent biosignatures.

Original language	English (US)
Journal	Bioinformatics (Oxford, England)
DOIs	https://doi.org/10.1093/bioinformatics/btad545
State	Published - Sep 6 2023

Bibliographical note

KAUST Repository Item: Exported on 2023-09-08
Acknowledgements: The research work was supported by the European Research Council (ERC) under the European Union’s Seventh Framework Programme (FP/2007–2013) (grant agreement no 617393), the METALASSO project, which is co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH– CREATE– INNOVATE (project code: T1EDK-04347) and the Hellenic Foundation for Research and Innovation (H.F.R.I.) under the “First Call for H.F.R.I. Research Projects to support Faculty members and Researchers and the procurement of high-cost research equipment grant” (Project Number: 1941). This study makes use of data generated by the Wellcome Trust Case-Control Consortium. A full list of the investigators who contributed to the generation of the data is available from: www.wtccc.org.uk. Funding for the project was provided by the Wellcome Trust under award 076113, 085475 and 090355. We sincerely thank Professor Ioanna Tzoulaki for comments on the manuscript; Professors George Dedousis and Pavlos Pavlidis for fruitful discussions, Elissavet Greasidou for her help in data acquisition and cleaning. Several members of our mensxmachina research group for useful comments and Glykeria Fragioudaki for her administrative help on data access.

ASJC Scopus subject areas

Biochemistry
Computational Theory and Mathematics
Computational Mathematics
Molecular Biology
Statistics and Probability
Computer Science Applications

Access to Document

10.1093/bioinformatics/btad545

https://repository.kaust.edu.sa/bitstream/10754/694204/1/btad545.pdf

Cite this

@article{83372a52073f4202b6e8d4965c03c1a1,

title = "Automated machine learning for Genome Wide Association Studies.",

abstract = "Motivation: Genome Wide Association Studies (GWAS) present several computational and statistical challenges for their data analysis, including knowledge discovery, interpretability, and translation to clinical practice. Results: We develop, apply, and comparatively evaluate an Automated Machine Learning (AutoML) approach, customized for genomic data that delivers reliable predictive and diagnostic models, the set of genetic variants that are important for predictions (called a biosignature), and an estimate of the out-of-sample predictive power. This AutoML approach discovers variants with higher predictive performance compared to standard GWAS methods, computes an individual risk prediction score, generalizes to new, unseen data, is shown to better differentiate causal variants from other highly correlated variants, and enhances knowledge discovery and interpretability by reporting multiple equivalent biosignatures.",

author = "Kleanthi Lakiotaki and Zaharias Papadovasilakis and Vincenzo Lagani and Stefanos Fafalios and Paulos Charonyktakis and Michail Tsagris and Ioannis Tsamardinos",

note = "KAUST Repository Item: Exported on 2023-09-08 Acknowledgements: The research work was supported by the European Research Council (ERC) under the European Union{\textquoteright}s Seventh Framework Programme (FP/2007–2013) (grant agreement no 617393), the METALASSO project, which is co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH– CREATE– INNOVATE (project code: T1EDK-04347) and the Hellenic Foundation for Research and Innovation (H.F.R.I.) under the “First Call for H.F.R.I. Research Projects to support Faculty members and Researchers and the procurement of high-cost research equipment grant” (Project Number: 1941). This study makes use of data generated by the Wellcome Trust Case-Control Consortium. A full list of the investigators who contributed to the generation of the data is available from: www.wtccc.org.uk. Funding for the project was provided by the Wellcome Trust under award 076113, 085475 and 090355. We sincerely thank Professor Ioanna Tzoulaki for comments on the manuscript; Professors George Dedousis and Pavlos Pavlidis for fruitful discussions, Elissavet Greasidou for her help in data acquisition and cleaning. Several members of our mensxmachina research group for useful comments and Glykeria Fragioudaki for her administrative help on data access.",

year = "2023",

month = sep,

day = "6",

doi = "10.1093/bioinformatics/btad545",

language = "English (US)",

journal = "Bioinformatics (Oxford, England)",

issn = "1367-4803",

publisher = "Oxford University Press",

}

TY - JOUR

T1 - Automated machine learning for Genome Wide Association Studies.

AU - Lakiotaki, Kleanthi

AU - Papadovasilakis, Zaharias

AU - Lagani, Vincenzo

AU - Fafalios, Stefanos

AU - Charonyktakis, Paulos

AU - Tsagris, Michail

AU - Tsamardinos, Ioannis

N1 - KAUST Repository Item: Exported on 2023-09-08 Acknowledgements: The research work was supported by the European Research Council (ERC) under the European Union’s Seventh Framework Programme (FP/2007–2013) (grant agreement no 617393), the METALASSO project, which is co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH– CREATE– INNOVATE (project code: T1EDK-04347) and the Hellenic Foundation for Research and Innovation (H.F.R.I.) under the “First Call for H.F.R.I. Research Projects to support Faculty members and Researchers and the procurement of high-cost research equipment grant” (Project Number: 1941). This study makes use of data generated by the Wellcome Trust Case-Control Consortium. A full list of the investigators who contributed to the generation of the data is available from: www.wtccc.org.uk. Funding for the project was provided by the Wellcome Trust under award 076113, 085475 and 090355. We sincerely thank Professor Ioanna Tzoulaki for comments on the manuscript; Professors George Dedousis and Pavlos Pavlidis for fruitful discussions, Elissavet Greasidou for her help in data acquisition and cleaning. Several members of our mensxmachina research group for useful comments and Glykeria Fragioudaki for her administrative help on data access.

PY - 2023/9/6

Y1 - 2023/9/6

N2 - Motivation: Genome Wide Association Studies (GWAS) present several computational and statistical challenges for their data analysis, including knowledge discovery, interpretability, and translation to clinical practice. Results: We develop, apply, and comparatively evaluate an Automated Machine Learning (AutoML) approach, customized for genomic data that delivers reliable predictive and diagnostic models, the set of genetic variants that are important for predictions (called a biosignature), and an estimate of the out-of-sample predictive power. This AutoML approach discovers variants with higher predictive performance compared to standard GWAS methods, computes an individual risk prediction score, generalizes to new, unseen data, is shown to better differentiate causal variants from other highly correlated variants, and enhances knowledge discovery and interpretability by reporting multiple equivalent biosignatures.

AB - Motivation: Genome Wide Association Studies (GWAS) present several computational and statistical challenges for their data analysis, including knowledge discovery, interpretability, and translation to clinical practice. Results: We develop, apply, and comparatively evaluate an Automated Machine Learning (AutoML) approach, customized for genomic data that delivers reliable predictive and diagnostic models, the set of genetic variants that are important for predictions (called a biosignature), and an estimate of the out-of-sample predictive power. This AutoML approach discovers variants with higher predictive performance compared to standard GWAS methods, computes an individual risk prediction score, generalizes to new, unseen data, is shown to better differentiate causal variants from other highly correlated variants, and enhances knowledge discovery and interpretability by reporting multiple equivalent biosignatures.

UR - http://hdl.handle.net/10754/694204

UR - https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btad545/7261476

U2 - 10.1093/bioinformatics/btad545

DO - 10.1093/bioinformatics/btad545

M3 - Article

C2 - 37672022

SN - 1367-4803

JO - Bioinformatics (Oxford, England)

JF - Bioinformatics (Oxford, England)

ER -

Automated machine learning for Genome Wide Association Studies.

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this