Benchmarking omics-based prediction of asthma development in children
Abstract Background Asthma is a heterogeneous disease with high morbidity. Advancement in high-throughput multi-omics approaches has enabled the collection of molecular assessments at different layers, providing a complementary perspective of complex diseases. Numerous computational methods have bee...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-02-01
|
| Series: | Respiratory Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12931-023-02368-8 |
| _version_ | 1827983066369359872 |
|---|---|
| author | Xu-Wen Wang Tong Wang Darius P. Schaub Can Chen Zheng Sun Shanlin Ke Julian Hecker Anna Maaser-Hecker Oana A. Zeleznik Roman Zeleznik Augusto A. Litonjua Dawn L. DeMeo Jessica Lasky-Su Edwin K. Silverman Yang-Yu Liu Scott T. Weiss |
| author_facet | Xu-Wen Wang Tong Wang Darius P. Schaub Can Chen Zheng Sun Shanlin Ke Julian Hecker Anna Maaser-Hecker Oana A. Zeleznik Roman Zeleznik Augusto A. Litonjua Dawn L. DeMeo Jessica Lasky-Su Edwin K. Silverman Yang-Yu Liu Scott T. Weiss |
| author_sort | Xu-Wen Wang |
| collection | DOAJ |
| description | Abstract Background Asthma is a heterogeneous disease with high morbidity. Advancement in high-throughput multi-omics approaches has enabled the collection of molecular assessments at different layers, providing a complementary perspective of complex diseases. Numerous computational methods have been developed for the omics-based patient classification or disease outcome prediction. Yet, a systematic benchmarking of those methods using various combinations of omics data for the prediction of asthma development is still lacking. Objective We aimed to investigate the computational methods in disease status prediction using multi-omics data. Method We systematically benchmarked 18 computational methods using all the 63 combinations of six omics data (GWAS, miRNA, mRNA, microbiome, metabolome, DNA methylation) collected in The Vitamin D Antenatal Asthma Reduction Trial (VDAART) cohort. We evaluated each method using standard performance metrics for each of the 63 omics combinations. Results Our results indicate that overall Logistic Regression, Multi-Layer Perceptron, and MOGONET display superior performance, and the combination of transcriptional, genomic and microbiome data achieves the best prediction. Moreover, we find that including the clinical data can further improve the prediction performance for some but not all the omics combinations. Conclusions Specific omics combinations can reach the optimal prediction of asthma development in children. And certain computational methods showed superior performance than other methods. |
| first_indexed | 2024-04-09T22:41:48Z |
| format | Article |
| id | doaj.art-992fccd1d96f4636a1f4594427e2d343 |
| institution | Directory Open Access Journal |
| issn | 1465-993X |
| language | English |
| last_indexed | 2024-04-09T22:41:48Z |
| publishDate | 2023-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Respiratory Research |
| spelling | doaj.art-992fccd1d96f4636a1f4594427e2d3432023-03-22T12:08:09ZengBMCRespiratory Research1465-993X2023-02-0124111110.1186/s12931-023-02368-8Benchmarking omics-based prediction of asthma development in childrenXu-Wen Wang0Tong Wang1Darius P. Schaub2Can Chen3Zheng Sun4Shanlin Ke5Julian Hecker6Anna Maaser-Hecker7Oana A. Zeleznik8Roman Zeleznik9Augusto A. Litonjua10Dawn L. DeMeo11Jessica Lasky-Su12Edwin K. Silverman13Yang-Yu Liu14Scott T. Weiss15Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Mathematics, University of HamburgChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolGenetics and Aging Research Unit, Department of Neurology, McCance Center for Brain Health, Mass General Institute for Neurodegenerative Disease, Massachusetts General Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Brigham and Women’s HospitalDivision of Pediatric Pulmonology, Golisano Children’s HospitalChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical SchoolAbstract Background Asthma is a heterogeneous disease with high morbidity. Advancement in high-throughput multi-omics approaches has enabled the collection of molecular assessments at different layers, providing a complementary perspective of complex diseases. Numerous computational methods have been developed for the omics-based patient classification or disease outcome prediction. Yet, a systematic benchmarking of those methods using various combinations of omics data for the prediction of asthma development is still lacking. Objective We aimed to investigate the computational methods in disease status prediction using multi-omics data. Method We systematically benchmarked 18 computational methods using all the 63 combinations of six omics data (GWAS, miRNA, mRNA, microbiome, metabolome, DNA methylation) collected in The Vitamin D Antenatal Asthma Reduction Trial (VDAART) cohort. We evaluated each method using standard performance metrics for each of the 63 omics combinations. Results Our results indicate that overall Logistic Regression, Multi-Layer Perceptron, and MOGONET display superior performance, and the combination of transcriptional, genomic and microbiome data achieves the best prediction. Moreover, we find that including the clinical data can further improve the prediction performance for some but not all the omics combinations. Conclusions Specific omics combinations can reach the optimal prediction of asthma development in children. And certain computational methods showed superior performance than other methods.https://doi.org/10.1186/s12931-023-02368-8AsthmaDisease statusPredictionMulti-omics |
| spellingShingle | Xu-Wen Wang Tong Wang Darius P. Schaub Can Chen Zheng Sun Shanlin Ke Julian Hecker Anna Maaser-Hecker Oana A. Zeleznik Roman Zeleznik Augusto A. Litonjua Dawn L. DeMeo Jessica Lasky-Su Edwin K. Silverman Yang-Yu Liu Scott T. Weiss Benchmarking omics-based prediction of asthma development in children Respiratory Research Asthma Disease status Prediction Multi-omics |
| title | Benchmarking omics-based prediction of asthma development in children |
| title_full | Benchmarking omics-based prediction of asthma development in children |
| title_fullStr | Benchmarking omics-based prediction of asthma development in children |
| title_full_unstemmed | Benchmarking omics-based prediction of asthma development in children |
| title_short | Benchmarking omics-based prediction of asthma development in children |
| title_sort | benchmarking omics based prediction of asthma development in children |
| topic | Asthma Disease status Prediction Multi-omics |
| url | https://doi.org/10.1186/s12931-023-02368-8 |
| work_keys_str_mv | AT xuwenwang benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT tongwang benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT dariuspschaub benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT canchen benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT zhengsun benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT shanlinke benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT julianhecker benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT annamaaserhecker benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT oanaazeleznik benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT romanzeleznik benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT augustoalitonjua benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT dawnldemeo benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT jessicalaskysu benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT edwinksilverman benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT yangyuliu benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren AT scotttweiss benchmarkingomicsbasedpredictionofasthmadevelopmentinchildren |