Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning
BackgroundDiabetic osteoporosis exhibits heterogeneity at the molecular level. Ferroptosis, a controlled form of cell death brought on by a buildup of lipid peroxidation, contributes to the onset and development of several illnesses. The aim was to explore the molecular subtypes associated with ferr...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Endocrinology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2023.1189513/full |
| _version_ | 1827865877442199552 |
|---|---|
| author | Xingkai Wang Xingkai Wang Lei Meng Juewei Zhang Zitong Zhao Linxuan Zou Zhuqiang Jia Zhuqiang Jia Xin Han Xin Han Lin Zhao Mingzhi Song Junwei Zong Shouyu Wang Xueling Qu Ming Lu |
| author_facet | Xingkai Wang Xingkai Wang Lei Meng Juewei Zhang Zitong Zhao Linxuan Zou Zhuqiang Jia Zhuqiang Jia Xin Han Xin Han Lin Zhao Mingzhi Song Junwei Zong Shouyu Wang Xueling Qu Ming Lu |
| author_sort | Xingkai Wang |
| collection | DOAJ |
| description | BackgroundDiabetic osteoporosis exhibits heterogeneity at the molecular level. Ferroptosis, a controlled form of cell death brought on by a buildup of lipid peroxidation, contributes to the onset and development of several illnesses. The aim was to explore the molecular subtypes associated with ferroptosis in diabetic osteoporosis at the molecular level and to further elucidate the potential molecular mechanisms.MethodsIntegrating the CTD, GeneCards, FerrDb databases, and the microarray data of GSE35958, we identified ferroptosis-related genes (FRGs) associated with diabetic osteoporosis. We applied unsupervised cluster analysis to divide the 42 osteoporosis samples from the GSE56814 microarray data into different subclusters based on FRGs. Subsequently, FRGs associated with two ferroptosis subclusters were obtained by combining database genes, module-related genes of WGCNA, and differentially expressed genes (DEGs). Eventually, the key genes from FRGs associated with diabetic osteoporosis were identified using the least absolute shrinkage and selection operator (LASSO), Boruta, support vector machine recursive feature elimination (SVM RFE), and extreme gradient boosting (XGBoost) machine learning algorithms. Based on ROC curves of external datasets (GSE56815), the model’s efficiency was examined.ResultsWe identified 15 differentially expressed FRGs associated with diabetic osteoporosis. In osteoporosis, two distinct molecular clusters related to ferroptosis were found. The expression results and GSVA analysis indicated that 15 FRGs exhibited significantly different biological functions and pathway activities in the two ferroptosis subclusters. Therefore, we further identified 17 FRGs associated with diabetic osteoporosis between the two subclusters. The results of the comprehensive analysis of 17 FRGs demonstrated that these genes were heterogeneous and had a specific interaction between the two subclusters. Ultimately, the prediction model had a strong foundation and excellent AUC values (0.84 for LASSO, 0.84 for SVM RFE, 0.82 for Boruta, and 0.81 for XGBoost). IDH1 is a common gene to all four algorithms thus being identified as a key gene with a high AUC value (AUC = 0.698).ConclusionsAs a ferroptosis regulator, IDH1 is able to distinguish between distinct molecular subtypes of diabetic osteoporosis, which may offer fresh perspectives on the pathogenesis of the disease’s clinical symptoms and prognostic heterogeneity. |
| first_indexed | 2024-03-12T14:54:32Z |
| format | Article |
| id | doaj.art-5538a9c3c73d475198bd4408f10eb2d2 |
| institution | Directory Open Access Journal |
| issn | 1664-2392 |
| language | English |
| last_indexed | 2024-03-12T14:54:32Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Endocrinology |
| spelling | doaj.art-5538a9c3c73d475198bd4408f10eb2d22023-08-15T00:49:19ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922023-08-011410.3389/fendo.2023.11895131189513Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learningXingkai Wang0Xingkai Wang1Lei Meng2Juewei Zhang3Zitong Zhao4Linxuan Zou5Zhuqiang Jia6Zhuqiang Jia7Xin Han8Xin Han9Lin Zhao10Mingzhi Song11Junwei Zong12Shouyu Wang13Xueling Qu14Ming Lu15Department of Trauma and Tissue Repair Surgery, Dalian Municipal Central Hospital, Dalian, ChinaDepartment of Orthopaedic Surgery, The First Affiliated Hospital of Dalian Medical University, Dalian, ChinaDepartment of Surgery, The First Affiliated Hospital of Nanhua Medical University, Hengyang, ChinaHealth Inspection and Quarantine, College of Medical Laboratory, Dalian Medical University, Dalian, ChinaInternational Department, Beijing No.80 High School, Beijing, ChinaDepartment of Orthopaedic Surgery, The First Affiliated Hospital of Dalian Medical University, Dalian, ChinaDepartment of Surgery, The First Affiliated Hospital of Dalian Medical University, Dalian, ChinaDepartment of Surgery, Naqu People's Hospital, Tibet, ChinaDepartment of Surgery, Naqu People's Hospital, Tibet, ChinaDepartment of Orthopaedic Surgery, The Second Affiliated Hospital of Dalian Medical University, Dalian, ChinaDepartment of Quality Management, Dalian Municipal Central Hospital, Dalian, ChinaDepartment of Orthopaedic Surgery, The First Affiliated Hospital of Dalian Medical University, Dalian, ChinaDepartment of Orthopaedic Surgery, The First Affiliated Hospital of Dalian Medical University, Dalian, ChinaDepartment of Orthopaedic Surgery, The First Affiliated Hospital of Dalian Medical University, Dalian, China0Changjianglu Pelvic Floor Repair Center, Dalian Women and Children’s Medical Group, Dalian, ChinaDepartment of Trauma and Tissue Repair Surgery, Dalian Municipal Central Hospital, Dalian, ChinaBackgroundDiabetic osteoporosis exhibits heterogeneity at the molecular level. Ferroptosis, a controlled form of cell death brought on by a buildup of lipid peroxidation, contributes to the onset and development of several illnesses. The aim was to explore the molecular subtypes associated with ferroptosis in diabetic osteoporosis at the molecular level and to further elucidate the potential molecular mechanisms.MethodsIntegrating the CTD, GeneCards, FerrDb databases, and the microarray data of GSE35958, we identified ferroptosis-related genes (FRGs) associated with diabetic osteoporosis. We applied unsupervised cluster analysis to divide the 42 osteoporosis samples from the GSE56814 microarray data into different subclusters based on FRGs. Subsequently, FRGs associated with two ferroptosis subclusters were obtained by combining database genes, module-related genes of WGCNA, and differentially expressed genes (DEGs). Eventually, the key genes from FRGs associated with diabetic osteoporosis were identified using the least absolute shrinkage and selection operator (LASSO), Boruta, support vector machine recursive feature elimination (SVM RFE), and extreme gradient boosting (XGBoost) machine learning algorithms. Based on ROC curves of external datasets (GSE56815), the model’s efficiency was examined.ResultsWe identified 15 differentially expressed FRGs associated with diabetic osteoporosis. In osteoporosis, two distinct molecular clusters related to ferroptosis were found. The expression results and GSVA analysis indicated that 15 FRGs exhibited significantly different biological functions and pathway activities in the two ferroptosis subclusters. Therefore, we further identified 17 FRGs associated with diabetic osteoporosis between the two subclusters. The results of the comprehensive analysis of 17 FRGs demonstrated that these genes were heterogeneous and had a specific interaction between the two subclusters. Ultimately, the prediction model had a strong foundation and excellent AUC values (0.84 for LASSO, 0.84 for SVM RFE, 0.82 for Boruta, and 0.81 for XGBoost). IDH1 is a common gene to all four algorithms thus being identified as a key gene with a high AUC value (AUC = 0.698).ConclusionsAs a ferroptosis regulator, IDH1 is able to distinguish between distinct molecular subtypes of diabetic osteoporosis, which may offer fresh perspectives on the pathogenesis of the disease’s clinical symptoms and prognostic heterogeneity.https://www.frontiersin.org/articles/10.3389/fendo.2023.1189513/fulldiabetic osteoporosisferroptosismolecular clustersmachine learningprediction model |
| spellingShingle | Xingkai Wang Xingkai Wang Lei Meng Juewei Zhang Zitong Zhao Linxuan Zou Zhuqiang Jia Zhuqiang Jia Xin Han Xin Han Lin Zhao Mingzhi Song Junwei Zong Shouyu Wang Xueling Qu Ming Lu Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning Frontiers in Endocrinology diabetic osteoporosis ferroptosis molecular clusters machine learning prediction model |
| title | Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning |
| title_full | Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning |
| title_fullStr | Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning |
| title_full_unstemmed | Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning |
| title_short | Identification of ferroptosis-related molecular clusters and genes for diabetic osteoporosis based on the machine learning |
| title_sort | identification of ferroptosis related molecular clusters and genes for diabetic osteoporosis based on the machine learning |
| topic | diabetic osteoporosis ferroptosis molecular clusters machine learning prediction model |
| url | https://www.frontiersin.org/articles/10.3389/fendo.2023.1189513/full |
| work_keys_str_mv | AT xingkaiwang identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT xingkaiwang identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT leimeng identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT jueweizhang identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT zitongzhao identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT linxuanzou identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT zhuqiangjia identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT zhuqiangjia identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT xinhan identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT xinhan identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT linzhao identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT mingzhisong identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT junweizong identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT shouyuwang identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT xuelingqu identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning AT minglu identificationofferroptosisrelatedmolecularclustersandgenesfordiabeticosteoporosisbasedonthemachinelearning |