Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences
Antioxidant proteins are involved importantly in many aspects of cellular life activities. They protect the cell and DNA from oxidative substances (such as peroxide, nitric oxide, oxygen-free radicals, etc.) which are known as reactive oxygen species (ROS). Free radical generation and antioxidant de...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/9/10/325 |
| _version_ | 1827704828289089536 |
|---|---|
| author | Luu Ho Thanh Lam Ngoc Hoang Le Le Van Tuan Ho Tran Ban Truong Nguyen Khanh Hung Ngan Thi Kim Nguyen Luong Huu Dang Nguyen Quoc Khanh Le |
| author_facet | Luu Ho Thanh Lam Ngoc Hoang Le Le Van Tuan Ho Tran Ban Truong Nguyen Khanh Hung Ngan Thi Kim Nguyen Luong Huu Dang Nguyen Quoc Khanh Le |
| author_sort | Luu Ho Thanh Lam |
| collection | DOAJ |
| description | Antioxidant proteins are involved importantly in many aspects of cellular life activities. They protect the cell and DNA from oxidative substances (such as peroxide, nitric oxide, oxygen-free radicals, etc.) which are known as reactive oxygen species (ROS). Free radical generation and antioxidant defenses are opposing factors in the human body and the balance between them is necessary to maintain a healthy body. An unhealthy routine or the degeneration of age can break the balance, leading to more ROS than antioxidants, causing damage to health. In general, the antioxidant mechanism is the combination of antioxidant molecules and ROS in a one-electron reaction. Creating computational models to promptly identify antioxidant candidates is essential in supporting antioxidant detection experiments in the laboratory. In this study, we proposed a machine learning-based model for this prediction purpose from a benchmark set of sequencing data. The experiments were conducted by using 10-fold cross-validation on the training process and validated by three different independent datasets. Different machine learning and deep learning algorithms have been evaluated on an optimal set of sequence features. Among them, Random Forest has been identified as the best model to identify antioxidant proteins with the highest performance. Our optimal model achieved high accuracy of 84.6%, as well as a balance in sensitivity (81.5%) and specificity (85.1%) for antioxidant protein identification on the training dataset. The performance results from different independent datasets also showed the significance in our model compared to previously published works on antioxidant protein identification. |
| first_indexed | 2024-03-10T15:49:42Z |
| format | Article |
| id | doaj.art-57fd0398fa874604a6adb6acc2db2061 |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-10T15:49:42Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-57fd0398fa874604a6adb6acc2db20612023-11-20T16:10:06ZengMDPI AGBiology2079-77372020-10-0191032510.3390/biology9100325Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary SequencesLuu Ho Thanh Lam0Ngoc Hoang Le1Le Van Tuan2Ho Tran Ban3Truong Nguyen Khanh Hung4Ngan Thi Kim Nguyen5Luong Huu Dang6Nguyen Quoc Khanh Le7International Master/PhD Program in Medicine, College of Medicine, Taipei Medical University, Taipei City 110, TaiwanGraduate Institute of Biomedical Materials and Tissue Engineering, College of Biomedical Engineering, Taipei Medical University, Taipei City 110, TaiwanOrthopedic and Trauma Department, Cho Ray Hospital, Ho Chi Minh City 70000, VietnamDepartment of Pediatric Surgery, University of Medicine and Pharmacy, Ho Chi Minh City 70000, VietnamInternational Master/PhD Program in Medicine, College of Medicine, Taipei Medical University, Taipei City 110, TaiwanSchool of Nutrition and Health Sciences, Taipei Medical University, Taipei City 110, TaiwanDepartment of Otolaryngology, University of Medicine and Pharmacy, Ho Chi Minh City 70000, VietnamInternational Master/PhD Program in Medicine, College of Medicine, Taipei Medical University, Taipei City 110, TaiwanAntioxidant proteins are involved importantly in many aspects of cellular life activities. They protect the cell and DNA from oxidative substances (such as peroxide, nitric oxide, oxygen-free radicals, etc.) which are known as reactive oxygen species (ROS). Free radical generation and antioxidant defenses are opposing factors in the human body and the balance between them is necessary to maintain a healthy body. An unhealthy routine or the degeneration of age can break the balance, leading to more ROS than antioxidants, causing damage to health. In general, the antioxidant mechanism is the combination of antioxidant molecules and ROS in a one-electron reaction. Creating computational models to promptly identify antioxidant candidates is essential in supporting antioxidant detection experiments in the laboratory. In this study, we proposed a machine learning-based model for this prediction purpose from a benchmark set of sequencing data. The experiments were conducted by using 10-fold cross-validation on the training process and validated by three different independent datasets. Different machine learning and deep learning algorithms have been evaluated on an optimal set of sequence features. Among them, Random Forest has been identified as the best model to identify antioxidant proteins with the highest performance. Our optimal model achieved high accuracy of 84.6%, as well as a balance in sensitivity (81.5%) and specificity (85.1%) for antioxidant protein identification on the training dataset. The performance results from different independent datasets also showed the significance in our model compared to previously published works on antioxidant protein identification.https://www.mdpi.com/2079-7737/9/10/325antioxidant proteinsmachine learningRandom Forestprotein sequencingfeature selectioncomputational modeling |
| spellingShingle | Luu Ho Thanh Lam Ngoc Hoang Le Le Van Tuan Ho Tran Ban Truong Nguyen Khanh Hung Ngan Thi Kim Nguyen Luong Huu Dang Nguyen Quoc Khanh Le Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences Biology antioxidant proteins machine learning Random Forest protein sequencing feature selection computational modeling |
| title | Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences |
| title_full | Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences |
| title_fullStr | Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences |
| title_full_unstemmed | Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences |
| title_short | Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences |
| title_sort | machine learning model for identifying antioxidant proteins using features calculated from primary sequences |
| topic | antioxidant proteins machine learning Random Forest protein sequencing feature selection computational modeling |
| url | https://www.mdpi.com/2079-7737/9/10/325 |
| work_keys_str_mv | AT luuhothanhlam machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT ngochoangle machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT levantuan machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT hotranban machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT truongnguyenkhanhhung machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT nganthikimnguyen machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT luonghuudang machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences AT nguyenquockhanhle machinelearningmodelforidentifyingantioxidantproteinsusingfeaturescalculatedfromprimarysequences |