Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method
Recent research has witnessed the fostered application of machine learning approaches in analyzing the single nucleotide polymorphisms (SNP) data, which has been proved to be implicated in complex human diseases. In the identification of SNPs responsible for complex diseases, most genome-wide associ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8615995/ |
| id |
doaj-3dd376d18418414bbc8e35a62b900bfc |
|---|---|
| record_format |
Article |
| spelling |
doaj-3dd376d18418414bbc8e35a62b900bfc2021-03-29T22:31:28ZengIEEEIEEE Access2169-35362019-01-017126471265710.1109/ACCESS.2019.28932698615995Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting MethodLongquan Jiang0https://orcid.org/0000-0002-7333-2589Bo Zhang1https://orcid.org/0000-0002-2289-2877Qin Ni2Xuan Sun3Pingping Dong4College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, ChinaSchool of Information Science and Technology, Sanda University of Shanghai, Shanghai, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, ChinaRecent research has witnessed the fostered application of machine learning approaches in analyzing the single nucleotide polymorphisms (SNP) data, which has been proved to be implicated in complex human diseases. In the identification of SNPs responsible for complex diseases, most genome-wide association studies always took single SNP into consideration at one time and ignored diverse interactions between SNPs. One of the major problems is the higher number of features and the relatively small number of individuals, which complicates the task and harms the predictive ability of DNA sequences. In this paper, a novel boosting-based ensemble approach was proposed to study these interactions. An importance scoring strategy based on Gini impurity was introduced for feature selection. We evaluated its efficacy on the SNP genotyping data collected by the Southeastern University of China and compared it with naive Bayes, support vector machine, and random forest. The experimental results have shown its validity and effectiveness on SNP interaction identification. In addition, our approach had an obvious advantage of computational time and resources.https://ieeexplore.ieee.org/document/8615995/Single nucleotide polymorphismdata miningmachine learninginteraction detection and genome-wide association studies |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Longquan Jiang Bo Zhang Qin Ni Xuan Sun Pingping Dong |
| spellingShingle |
Longquan Jiang Bo Zhang Qin Ni Xuan Sun Pingping Dong Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method IEEE Access Single nucleotide polymorphism data mining machine learning interaction detection and genome-wide association studies |
| author_facet |
Longquan Jiang Bo Zhang Qin Ni Xuan Sun Pingping Dong |
| author_sort |
Longquan Jiang |
| title |
Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method |
| title_short |
Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method |
| title_full |
Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method |
| title_fullStr |
Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method |
| title_full_unstemmed |
Prediction of SNP Sequences via Gini Impurity Based Gradient Boosting Method |
| title_sort |
prediction of snp sequences via gini impurity based gradient boosting method |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2019-01-01 |
| description |
Recent research has witnessed the fostered application of machine learning approaches in analyzing the single nucleotide polymorphisms (SNP) data, which has been proved to be implicated in complex human diseases. In the identification of SNPs responsible for complex diseases, most genome-wide association studies always took single SNP into consideration at one time and ignored diverse interactions between SNPs. One of the major problems is the higher number of features and the relatively small number of individuals, which complicates the task and harms the predictive ability of DNA sequences. In this paper, a novel boosting-based ensemble approach was proposed to study these interactions. An importance scoring strategy based on Gini impurity was introduced for feature selection. We evaluated its efficacy on the SNP genotyping data collected by the Southeastern University of China and compared it with naive Bayes, support vector machine, and random forest. The experimental results have shown its validity and effectiveness on SNP interaction identification. In addition, our approach had an obvious advantage of computational time and resources. |
| topic |
Single nucleotide polymorphism data mining machine learning interaction detection and genome-wide association studies |
| url |
https://ieeexplore.ieee.org/document/8615995/ |
| work_keys_str_mv |
AT longquanjiang predictionofsnpsequencesviaginiimpuritybasedgradientboostingmethod AT bozhang predictionofsnpsequencesviaginiimpuritybasedgradientboostingmethod AT qinni predictionofsnpsequencesviaginiimpuritybasedgradientboostingmethod AT xuansun predictionofsnpsequencesviaginiimpuritybasedgradientboostingmethod AT pingpingdong predictionofsnpsequencesviaginiimpuritybasedgradientboostingmethod |
| _version_ |
1724191363814129664 |