Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI
Introduction: Alzheimer’s disease (AD) is the most common progressive neurodegenerative disorder in the elderly, which will eventually lead to dementia without an effective precaution and treatment. As a typical complex disease, the mechanism of AD’s occurrence and development still lacks sufficient...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IMR Press
2022-01-01
|
| Series: | Frontiers in Bioscience-Landmark |
| Subjects: | |
| Online Access: | https://www.imrpress.com/journal/FBL/27/1/10.31083/j.fbl2701037 |
| _version_ | 1818774222330134528 |
|---|---|
| author | Juan Zhou Yangping Qiu Xiangyu Liu Ziruo Xie Shanguo Lv Yuanyuan Peng Xiong Li |
| author_facet | Juan Zhou Yangping Qiu Xiangyu Liu Ziruo Xie Shanguo Lv Yuanyuan Peng Xiong Li |
| author_sort | Juan Zhou |
| collection | DOAJ |
| description | Introduction: Alzheimer’s disease (AD) is the most common progressive neurodegenerative disorder in the elderly, which will eventually lead to dementia without an effective precaution and treatment. As a typical complex disease, the mechanism of AD’s occurrence and development still lacks sufficient understanding. Research design and methods: In this study, we aim to directly analyze the relationship between DNA variants and phenotypes based on the whole genome sequencing data. Firstly, to enhance the biological meanings of our study, we annotate the deleterious variants and mapped them to nearest protein coding genes. Then, to eliminate the redundant features and reduce the burden of downstream analysis, a multi-objective evaluation strategy based on entropy theory is applied for ranking all candidate genes. Finally, we use multi-classifier XGBoost for classifying unbalanced data composed with 46 AD samples, 483 mild cognitive impairment (MCI) samples and 279 cognitive normal (CN) samples. Results: The experimental results on real whole genome sequencing data from Alzheimer’s Disease Neuroimaging Initiative (ADNI) show that our method not only has satisfactory classification performance but also finds significance correlation between AD and RIN3, a known susceptibility gene of AD. In addition, pathway enrichment analysis was carried out using the top 20 feature genes, and three pathways were confirmed to be significantly related to the formation of AD. Conclusions: From the experimental results, we demonstrated that the efficacy of our proposed method has practical significance. |
| first_indexed | 2024-12-18T10:37:43Z |
| format | Article |
| id | doaj.art-60d27c4d8bb54d349c5bc4414ed611b1 |
| institution | Directory Open Access Journal |
| issn | 2768-6701 |
| language | English |
| last_indexed | 2024-12-18T10:37:43Z |
| publishDate | 2022-01-01 |
| publisher | IMR Press |
| record_format | Article |
| series | Frontiers in Bioscience-Landmark |
| spelling | doaj.art-60d27c4d8bb54d349c5bc4414ed611b12022-12-21T21:10:42ZengIMR PressFrontiers in Bioscience-Landmark2768-67012022-01-0127103710.31083/j.fbl2701037S2768-6701(22)00375-6Annotating whole genome variants and constructing a multi-classifier based on samples of ADNIJuan Zhou0Yangping Qiu1Xiangyu Liu2Ziruo Xie3Shanguo Lv4Yuanyuan Peng5Xiong Li6School of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaSchool of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaSchool of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaSchool of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaSchool of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaSchool of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaSchool of Software, East China Jiaotong University, 330013 Nanchang, Jiangxi, ChinaIntroduction: Alzheimer’s disease (AD) is the most common progressive neurodegenerative disorder in the elderly, which will eventually lead to dementia without an effective precaution and treatment. As a typical complex disease, the mechanism of AD’s occurrence and development still lacks sufficient understanding. Research design and methods: In this study, we aim to directly analyze the relationship between DNA variants and phenotypes based on the whole genome sequencing data. Firstly, to enhance the biological meanings of our study, we annotate the deleterious variants and mapped them to nearest protein coding genes. Then, to eliminate the redundant features and reduce the burden of downstream analysis, a multi-objective evaluation strategy based on entropy theory is applied for ranking all candidate genes. Finally, we use multi-classifier XGBoost for classifying unbalanced data composed with 46 AD samples, 483 mild cognitive impairment (MCI) samples and 279 cognitive normal (CN) samples. Results: The experimental results on real whole genome sequencing data from Alzheimer’s Disease Neuroimaging Initiative (ADNI) show that our method not only has satisfactory classification performance but also finds significance correlation between AD and RIN3, a known susceptibility gene of AD. In addition, pathway enrichment analysis was carried out using the top 20 feature genes, and three pathways were confirmed to be significantly related to the formation of AD. Conclusions: From the experimental results, we demonstrated that the efficacy of our proposed method has practical significance.https://www.imrpress.com/journal/FBL/27/1/10.31083/j.fbl2701037unbalanced datamulti-class classificationmulti-objective optimization |
| spellingShingle | Juan Zhou Yangping Qiu Xiangyu Liu Ziruo Xie Shanguo Lv Yuanyuan Peng Xiong Li Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI Frontiers in Bioscience-Landmark unbalanced data multi-class classification multi-objective optimization |
| title | Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI |
| title_full | Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI |
| title_fullStr | Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI |
| title_full_unstemmed | Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI |
| title_short | Annotating whole genome variants and constructing a multi-classifier based on samples of ADNI |
| title_sort | annotating whole genome variants and constructing a multi classifier based on samples of adni |
| topic | unbalanced data multi-class classification multi-objective optimization |
| url | https://www.imrpress.com/journal/FBL/27/1/10.31083/j.fbl2701037 |
| work_keys_str_mv | AT juanzhou annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni AT yangpingqiu annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni AT xiangyuliu annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni AT ziruoxie annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni AT shanguolv annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni AT yuanyuanpeng annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni AT xiongli annotatingwholegenomevariantsandconstructingamulticlassifierbasedonsamplesofadni |