Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers
Abstract
The Environmental Determinants of the Diabetes in the Young (TEDDY) study has prospectively followed, from birth, children at increased genetic risk of type 1 diabetes. We evaluated the potential of machine learning to identify new biomarkers that predict imminent (within 6 months) development of persistent islet autoantibodies to insulin, GAD or IA-2 in TEDDY participants through integration of time-invariant risk factors with time-varying metabolomics. The predictive modeling was initiated with over 220 potential biomarkers; through ensemble-based feature evaluation, the optimal model included 42 biomarkers, returning a cross-validated receiver operating characteristic area under the curve of 0.74. The model identified a principal set of 20 time-invariant markers, including 16 single nucleotide polymorphisms and two HLA-DR genotypes, gestational age, and exposure to a prebiotic formula. Integration of the metabolome identified 22 high-priority metabolites and lipids, including adipic acid and ceramide d42:0, that predicted development of islet autoantibodies, dependent upon the time horizon. The majority (86%) of metabolites that predicted development of islet autoantibodies belonged to 3 pathways: lipid oxidation, phospholipase A2 signaling, and pentose phosphate pathway. TEDDY data suggest that these metabolic processes may play a role in triggering islet autoimmunity.
- Authors:
-
[1];
[2];
[2];
[2];
[2];
[3];
[3];
[3];
[4];
[3]
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States); Univ. of Colorado, Aurora, CO (United States). Anschutz Medical Campus
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Univ. of Colorado, Aurora, CO (United States). Anschutz Medical Campus
- Univ. of Virginia, Charlottesville, VA (United States)
- Publication Date:
- Research Org.:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE; National Institutes of Health (NIH)
- OSTI Identifier:
- 1756070
- Report Number(s):
- PNNL-SA-146734
Journal ID: ISSN 1753-0407
- Grant/Contract Number:
- AC05-76RL01830; U01 DK63829; U01 DK63861; U01 DK63821; U01 DK63865; U01 DK63863; U01 DK63836; U01 DK63790; UC4 DK63829; UC4 DK63861; UC4 DK63821; UC4 DK63865; UC4 DK63863; UC4 DK63836; UC4 DK95300; UC4 DK100238; HHSN267200700014C; UL1 TR000064; UL1 TR001082
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Diabetes (Online)
- Additional Journal Information:
- Journal Name: Journal of Diabetes (Online); Journal Volume: 13; Journal Issue: 2; Journal ID: ISSN 1753-0407
- Publisher:
- Wiley and Ruijin Hospital, Shanghai Jiaotong University School of Medicine
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 59 BASIC BIOLOGICAL SCIENCES; autoimmunity; genetics; machine learning; metabolomics
Citation Formats
Webb‐Robertson, Bobbie‐Jo M., Bramer, Lisa M., Stanfill, Bryan A., Reehl, Sarah M., Nakayasu, Ernesto S., Metz, Thomas O., Frohnert, Brigitte I., Norris, Jill M., Johnson, Randi K., Rich, Stephen S., and Rewers, Marian J. Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers. United States: N. p., 2020.
Web. doi:10.1111/1753-0407.13093.
Webb‐Robertson, Bobbie‐Jo M., Bramer, Lisa M., Stanfill, Bryan A., Reehl, Sarah M., Nakayasu, Ernesto S., Metz, Thomas O., Frohnert, Brigitte I., Norris, Jill M., Johnson, Randi K., Rich, Stephen S., & Rewers, Marian J. Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers. United States. https://doi.org/10.1111/1753-0407.13093
Webb‐Robertson, Bobbie‐Jo M., Bramer, Lisa M., Stanfill, Bryan A., Reehl, Sarah M., Nakayasu, Ernesto S., Metz, Thomas O., Frohnert, Brigitte I., Norris, Jill M., Johnson, Randi K., Rich, Stephen S., and Rewers, Marian J. Wed .
"Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers". United States. https://doi.org/10.1111/1753-0407.13093. https://www.osti.gov/servlets/purl/1756070.
@article{osti_1756070,
title = {Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers},
author = {Webb‐Robertson, Bobbie‐Jo M. and Bramer, Lisa M. and Stanfill, Bryan A. and Reehl, Sarah M. and Nakayasu, Ernesto S. and Metz, Thomas O. and Frohnert, Brigitte I. and Norris, Jill M. and Johnson, Randi K. and Rich, Stephen S. and Rewers, Marian J.},
abstractNote = {The Environmental Determinants of the Diabetes in the Young (TEDDY) study has prospectively followed, from birth, children at increased genetic risk of type 1 diabetes. We evaluated the potential of machine learning to identify new biomarkers that predict imminent (within 6 months) development of persistent islet autoantibodies to insulin, GAD or IA-2 in TEDDY participants through integration of time-invariant risk factors with time-varying metabolomics. The predictive modeling was initiated with over 220 potential biomarkers; through ensemble-based feature evaluation, the optimal model included 42 biomarkers, returning a cross-validated receiver operating characteristic area under the curve of 0.74. The model identified a principal set of 20 time-invariant markers, including 16 single nucleotide polymorphisms and two HLA-DR genotypes, gestational age, and exposure to a prebiotic formula. Integration of the metabolome identified 22 high-priority metabolites and lipids, including adipic acid and ceramide d42:0, that predicted development of islet autoantibodies, dependent upon the time horizon. The majority (86%) of metabolites that predicted development of islet autoantibodies belonged to 3 pathways: lipid oxidation, phospholipase A2 signaling, and pentose phosphate pathway. TEDDY data suggest that these metabolic processes may play a role in triggering islet autoimmunity.},
doi = {10.1111/1753-0407.13093},
journal = {Journal of Diabetes (Online)},
number = 2,
volume = 13,
place = {United States},
year = {Wed Jul 22 00:00:00 EDT 2020},
month = {Wed Jul 22 00:00:00 EDT 2020}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Early Infant Diet and Islet Autoimmunity in the TEDDY Study
journal, January 2018
- Uusitalo, Ulla; Lee, Hye-Seung; Andrén Aronsson, Carin
- Diabetes Care, Vol. 41, Issue 3
2-Aminoadipic acid is a biomarker for diabetes risk
journal, September 2013
- Wang, Thomas J.; Ngo, Debby; Psychogios, Nikolaos
- Journal of Clinical Investigation, Vol. 123, Issue 10
Infant Exposures and Development of Type 1 Diabetes Mellitus: The Diabetes Autoimmunity Study in the Young (DAISY)
journal, September 2013
- Frederiksen, Brittni; Kroehl, Miranda; Lamb, Molly M.
- JAMA Pediatrics, Vol. 167, Issue 9
The human gut microbiome in early-onset type 1 diabetes from the TEDDY study
journal, October 2018
- Vatanen, Tommi; Franzosa, Eric A.; Schwager, Randall
- Nature, Vol. 562, Issue 7728
Emerging applications of metabolomics in drug discovery and precision medicine
journal, March 2016
- Wishart, David S.
- Nature Reviews Drug Discovery, Vol. 15, Issue 7
Genetic and Environmental Interactions Modify the Risk of Diabetes-Related Autoimmunity by 6 Years of Age: The TEDDY Study
journal, June 2017
- Krischer, Jeffrey P.; Lynch, Kristian F.; Lernmark, Åke
- Diabetes Care, Vol. 40, Issue 9
The DAVID Gene Functional Classification Tool: a novel biological module-centric algorithm to functionally analyze large gene lists
journal, January 2007
- Huang, Da; Sherman, Brad T.; Tan, Qina
- Genome Biology, Vol. 8, Issue 9
VIBE 2.0: Visual Integration for Bayesian Evaluation
journal, November 2009
- Beagley, Nathaniel; Stratton, Kelly G.; Webb-Robertson, Bobbie-Jo M.
- Bioinformatics, Vol. 26, Issue 2
Precision Diabetes Is Slowly Becoming a Reality
journal, January 2019
- Mohan, Viswanathan; Radha, Venkatesan
- Medical Principles and Practice, Vol. 28, Issue 1
SNPedia: a wiki supporting personal genome annotation, interpretation and analysis
journal, December 2011
- Cariaso, Michael; Lennon, Greg
- Nucleic Acids Research, Vol. 40, Issue D1
Precision diabetes: a realistic outlook on a promising approach
journal, March 2017
- Marshall, Sally M.
- Diabetologia, Vol. 60, Issue 5
Interferon γ Attenuates Insulin Signaling, Lipid Storage, and Differentiation in Human Adipocytes via Activation of the JAK/STAT Pathway
journal, September 2009
- McGillicuddy, Fiona C.; Chiquoine, Elise H.; Hinkle, Christine C.
- Journal of Biological Chemistry, Vol. 284, Issue 46
Nested case‐control data analysis using weighted conditional logistic regression in The Environmental Determinants of Diabetes in the Young (TEDDY) study: A novel approach
journal, July 2019
- Lee, Hye‐Seung; Lynch, Kristian F.; Krischer, Jeffrey P.
- Diabetes/Metabolism Research and Reviews, Vol. 36, Issue 1
Gestational Age and Birth Weight and the Risk of Childhood Type 1 Diabetes: A Population-Based Cohort and Sibling Design Study
journal, October 2015
- Khashan, Ali S.; Kenny, Louise C.; Lundholm, Cecilia
- Diabetes Care, Vol. 38, Issue 12
Clinical and Novel Biomarkers in the Management of Prostate Cancer
journal, February 2018
- Sanhueza, Cristóbal; Kohli, Manish
- Current Treatment Options in Oncology, Vol. 19, Issue 2
Extending Classification Algorithms to Case-Control Studies
journal, January 2019
- Stanfill, Bryan; Reehl, Sarah; Bramer, Lisa
- Biomedical Engineering and Computational Biology, Vol. 10
Artificial intelligence and the analysis of multi-platform metabolomics data for the detection of intrauterine growth restriction
journal, April 2019
- Bahado-Singh, Ray Oliver; Yilmaz, Ali; Bisgin, Halil
- PLOS ONE, Vol. 14, Issue 4
Late-onset islet autoimmunity in childhood: the Diabetes Autoimmunity Study in the Young (DAISY)
journal, March 2017
- Frohnert, Brigitte I.; Ide, Lisa; Dong, Fran
- Diabetologia, Vol. 60, Issue 6
Metabolic gatekeepers to safeguard against autoimmunity and oncogenic B cell transformation
journal, March 2019
- Müschen, Markus
- Nature Reviews Immunology, Vol. 19, Issue 5
Procedures for large-scale metabolic profiling of serum and plasma using gas chromatography and liquid chromatography coupled to mass spectrometry
journal, June 2011
- Dunn, Warwick B.; Broadhurst, David; Begley, Paul
- Nature Protocols, Vol. 6, Issue 7
Biomarker discovery study design for type 1 diabetes in The Environmental Determinants of Diabetes in the Young (TEDDY) study: Biomarker Discovery Study Design
journal, July 2014
- Lee, Hye-Seung; Burkhardt, Brant R.; McLeod, Wendy
- Diabetes/Metabolism Research and Reviews, Vol. 30, Issue 5
LipidBlast in silico tandem mass spectrometry database for lipid identification
journal, June 2013
- Kind, Tobias; Liu, Kwang-Hyeon; Lee, Do Yup
- Nature Methods, Vol. 10, Issue 8
FiehnLib: Mass Spectral and Retention Index Libraries for Metabolomics Based on Quadrupole and Time-of-Flight Gas Chromatography/Mass Spectrometry
journal, December 2009
- Kind, Tobias; Wohlgemuth, Gert; Lee, Do Yup
- Analytical Chemistry, Vol. 81, Issue 24
iLearn: an integrated platform and meta-learner for feature engineering, machine-learning analysis and modeling of DNA, RNA and protein sequence data
journal, April 2019
- Chen, Zhen; Zhao, Pei; Li, Fuyi
- Briefings in Bioinformatics, Vol. 21, Issue 3
The Influence of Type 1 Diabetes Genetic Susceptibility Regions, Age, Sex, and Family History on the Progression From Multiple Autoantibodies to Type 1 Diabetes: A TEDDY Study Report
journal, September 2017
- Krischer, Jeffrey P.; Liu, Xiang; Lernmark, Åke
- Diabetes, Vol. 66, Issue 12
Systematic Error Removal Using Random Forest for Normalizing Large-Scale Untargeted Lipidomics Data
journal, February 2019
- Fan, Sili; Kind, Tobias; Cajka, Tomas
- Analytical Chemistry, Vol. 91, Issue 5
Role of Type 1 Diabetes–Associated SNPs on Autoantibody Positivity in the Type 1 Diabetes Genetics Consortium: Overview
journal, September 2015
- Rich, Stephen S.; Concannon, Patrick
- Diabetes Care, Vol. 38, Issue Supplement 2
A data-driven, knowledge-based approach to biomarker discovery: application to circulating microRNA markers of colorectal cancer prognosis
journal, June 2018
- Vafaee, Fatemeh; Diakos, Connie; Kirschner, Michaela B.
- npj Systems Biology and Applications, Vol. 4, Issue 1
Role of Type 1 Diabetes–Associated SNPs on Risk of Autoantibody Positivity in the TEDDY Study
journal, November 2014
- Törn, Carina; Hadley, David; Lee, Hye-Seung
- Diabetes, Vol. 64, Issue 5
The Environmental Determinants of Diabetes in the Young (TEDDY) Study: 2018 Update
journal, October 2018
- Rewers, Marian; Hyöty, Heikki; Lernmark, Åke
- Current Diabetes Reports, Vol. 18, Issue 12
ROFI - The Use of Repeated Optimization for Feature Interpretation
conference, December 2016
- Webb-Robertson, Bobbie-Jo M.; Bramer, Lisa M.; Reehl, Sarah M.
- 2016 International Conference on Computational Science and Computational Intelligence (CSCI)
Predictive Modeling of Type 1 Diabetes Stages Using Disparate Data Sources
journal, November 2019
- Frohnert, Brigitte I.; Webb-Robertson, Bobbie-Jo; Bramer, Lisa M.
- Diabetes, Vol. 69, Issue 2
Common patterns of gene regulation associated with Cesarean section and the development of islet autoimmunity – indications of immune cell activation
journal, April 2019
- Laimighofer, M.; Lickert, R.; Fuerst, R.
- Scientific Reports, Vol. 9, Issue 1
Metabolomics by Gas Chromatography–Mass Spectrometry: Combined Targeted and Untargeted Profiling
journal, April 2016
- Fiehn, Oliver
- Current Protocols in Molecular Biology, Vol. 114, Issue 1
MissForest--non-parametric missing value imputation for mixed-type data
journal, October 2011
- Stekhoven, D. J.; Buhlmann, P.
- Bioinformatics, Vol. 28, Issue 1
Evidence of Contribution of iPLA2β-Mediated Events During Islet β-Cell Apoptosis Due to Proinflammatory Cytokines Suggests a Role for iPLA2β in T1D Development
journal, September 2014
- Lei, Xiaoyong; Bone, Robert N.; Ali, Tomader
- Endocrinology, Vol. 155, Issue 9
Genetic scores to stratify risk of developing multiple islet autoantibodies and type 1 diabetes: A prospective study in children
journal, April 2018
- Bonifacio, Ezio; Beyerlein, Andreas; Hippich, Markus
- PLOS Medicine, Vol. 15, Issue 4
Temporal development of the gut microbiome in early childhood from the TEDDY study
journal, October 2018
- Stewart, Christopher J.; Ajami, Nadim J.; O’Brien, Jacqueline L.
- Nature, Vol. 562, Issue 7728
Comparison of insulin autoantibody: polyethylene glycol and micro-IAA 1-day and 7-day assays
journal, October 2009
- Babaya, Naru; Yu, Liping; Miao, Dongmei
- Diabetes/Metabolism Research and Reviews, Vol. 25, Issue 7
Computer-aided biomarker discovery for precision medicine: data resources, models and applications
journal, November 2017
- Lin, Yuxin; Qian, Fuliang; Shen, Li
- Briefings in Bioinformatics, Vol. 20, Issue 3
Validating Quantitative Untargeted Lipidomics Across Nine Liquid Chromatography–High-Resolution Mass Spectrometry Platforms
journal, November 2017
- Cajka, Tomas; Smilowitz, Jennifer T.; Fiehn, Oliver
- Analytical Chemistry, Vol. 89, Issue 22
Newborn screening for HLA markers associated with IDDM: Diabetes Autoimmunity Study in the Young (DAISY)
journal, July 1996
- Rewers, M.; Bugawan, T. L.; Norris, J. M.
- Diabetologia, Vol. 39, Issue 7
Probiotics and Prebiotics for the Amelioration of Type 1 Diabetes: Present and Future Perspectives
journal, March 2019
- Mishra, Sidharth; Wang, Shaohua; Nagpal, Ravinder
- Microorganisms, Vol. 7, Issue 3
Early prediction of autoimmune (type 1) diabetes
journal, May 2017
- Regnell, Simon E.; Lernmark, Åke
- Diabetologia, Vol. 60, Issue 8
Association Between Vitamin D Metabolism Gene Polymorphisms and Risk of Islet Autoimmunity and Progression to Type 1 Diabetes: The Diabetes Autoimmunity Study in the Young (DAISY)
journal, November 2013
- Frederiksen, Brittni N.; Kroehl, Miranda; Fingerlin, Tasha E.
- The Journal of Clinical Endocrinology & Metabolism, Vol. 98, Issue 11
Role of calcium-independent phospholipase A 2 β in human pancreatic islet β-cell apoptosis
journal, December 2012
- Lei, Xiaoyong; Zhang, Sheng; Bohrer, Alan
- American Journal of Physiology-Endocrinology and Metabolism, Vol. 303, Issue 11
Predicting progression to type 1 diabetes from ages 3 to 6 in islet autoantibody positive TEDDY children
journal, January 2019
- Jacobsen, Laura M.; Larsson, Helena E.; Tamura, Roy N.
- Pediatric Diabetes, Vol. 20, Issue 3