{"title":"筛查血浆细胞相关特征基因以估计骨质疏松症风险和治疗脆弱性的机器学习框架。","authors":"Shoubao Wang, Jiafu Zhu, Weinan Liu, Aihua Liu","doi":"10.1007/s10528-024-10861-y","DOIUrl":null,"url":null,"abstract":"<p><p>Osteoporosis, in which bones become fragile owing to low bone density and impaired bone mass, is a global public health concern. Bone mineral density (BMD) has been extensively evaluated for the diagnosis of low bone mass and osteoporosis. Circulating monocytes play an indispensable role in bone destruction and remodeling. This work proposed a machine learning-based framework to investigate the impact of circulating monocyte-associated genes on bone loss in osteoporosis patients. Females with discordant BMD levels were included in the GSE56815, GSE7158, GSE7429, and GSE62402 datasets. Circulating monocyte types were quantified via CIBERSORT, with subsequent selection of plasma cell-associated DEGs. Generalized linear models, random forests, extreme gradient boosting (XGB), and support vector machines were adopted for feature selection. Artificial neural networks and nomograms were subsequently constructed for osteoporosis diagnosis, and the molecular machinery underlying the identified genes was explored. SVM outperformed the other tuned models; thus, the expression of several genes (DEFA4, HLA-DPB1, LCN2, HP, and GAS7) associated with osteoporosis were determined. ANNs and nomograms were proposed to robustly distinguish low and high BMDs and estimate the risk of osteoporosis. Clozapine, aspirin, pyridoxine, etc. were identified as possible treatment agents. The expression of these genes is extensively posttranscriptionally regulated by miRNAs and m<sup>6</sup>A modifications. Additionally, they participate in modulating key signaling pathways, e.g., autophagy. The machine learning framework based on plasma cell-associated feature genes has the potential for estimating personalized risk stratification and treatment vulnerability in osteoporosis patients.</p>","PeriodicalId":482,"journal":{"name":"Biochemical Genetics","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Machine Learning Framework for Screening Plasma Cell-Associated Feature Genes to Estimate Osteoporosis Risk and Treatment Vulnerability.\",\"authors\":\"Shoubao Wang, Jiafu Zhu, Weinan Liu, Aihua Liu\",\"doi\":\"10.1007/s10528-024-10861-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Osteoporosis, in which bones become fragile owing to low bone density and impaired bone mass, is a global public health concern. Bone mineral density (BMD) has been extensively evaluated for the diagnosis of low bone mass and osteoporosis. Circulating monocytes play an indispensable role in bone destruction and remodeling. This work proposed a machine learning-based framework to investigate the impact of circulating monocyte-associated genes on bone loss in osteoporosis patients. Females with discordant BMD levels were included in the GSE56815, GSE7158, GSE7429, and GSE62402 datasets. Circulating monocyte types were quantified via CIBERSORT, with subsequent selection of plasma cell-associated DEGs. Generalized linear models, random forests, extreme gradient boosting (XGB), and support vector machines were adopted for feature selection. Artificial neural networks and nomograms were subsequently constructed for osteoporosis diagnosis, and the molecular machinery underlying the identified genes was explored. SVM outperformed the other tuned models; thus, the expression of several genes (DEFA4, HLA-DPB1, LCN2, HP, and GAS7) associated with osteoporosis were determined. ANNs and nomograms were proposed to robustly distinguish low and high BMDs and estimate the risk of osteoporosis. Clozapine, aspirin, pyridoxine, etc. were identified as possible treatment agents. The expression of these genes is extensively posttranscriptionally regulated by miRNAs and m<sup>6</sup>A modifications. Additionally, they participate in modulating key signaling pathways, e.g., autophagy. The machine learning framework based on plasma cell-associated feature genes has the potential for estimating personalized risk stratification and treatment vulnerability in osteoporosis patients.</p>\",\"PeriodicalId\":482,\"journal\":{\"name\":\"Biochemical Genetics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-06-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biochemical Genetics\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1007/s10528-024-10861-y\",\"RegionNum\":4,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biochemical Genetics","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1007/s10528-024-10861-y","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
A Machine Learning Framework for Screening Plasma Cell-Associated Feature Genes to Estimate Osteoporosis Risk and Treatment Vulnerability.
Osteoporosis, in which bones become fragile owing to low bone density and impaired bone mass, is a global public health concern. Bone mineral density (BMD) has been extensively evaluated for the diagnosis of low bone mass and osteoporosis. Circulating monocytes play an indispensable role in bone destruction and remodeling. This work proposed a machine learning-based framework to investigate the impact of circulating monocyte-associated genes on bone loss in osteoporosis patients. Females with discordant BMD levels were included in the GSE56815, GSE7158, GSE7429, and GSE62402 datasets. Circulating monocyte types were quantified via CIBERSORT, with subsequent selection of plasma cell-associated DEGs. Generalized linear models, random forests, extreme gradient boosting (XGB), and support vector machines were adopted for feature selection. Artificial neural networks and nomograms were subsequently constructed for osteoporosis diagnosis, and the molecular machinery underlying the identified genes was explored. SVM outperformed the other tuned models; thus, the expression of several genes (DEFA4, HLA-DPB1, LCN2, HP, and GAS7) associated with osteoporosis were determined. ANNs and nomograms were proposed to robustly distinguish low and high BMDs and estimate the risk of osteoporosis. Clozapine, aspirin, pyridoxine, etc. were identified as possible treatment agents. The expression of these genes is extensively posttranscriptionally regulated by miRNAs and m6A modifications. Additionally, they participate in modulating key signaling pathways, e.g., autophagy. The machine learning framework based on plasma cell-associated feature genes has the potential for estimating personalized risk stratification and treatment vulnerability in osteoporosis patients.
期刊介绍:
Biochemical Genetics welcomes original manuscripts that address and test clear scientific hypotheses, are directed to a broad scientific audience, and clearly contribute to the advancement of the field through the use of sound sampling or experimental design, reliable analytical methodologies and robust statistical analyses.
Although studies focusing on particular regions and target organisms are welcome, it is not the journal’s goal to publish essentially descriptive studies that provide results with narrow applicability, or are based on very small samples or pseudoreplication.
Rather, Biochemical Genetics welcomes review articles that go beyond summarizing previous publications and create added value through the systematic analysis and critique of the current state of knowledge or by conducting meta-analyses.
Methodological articles are also within the scope of Biological Genetics, particularly when new laboratory techniques or computational approaches are fully described and thoroughly compared with the existing benchmark methods.
Biochemical Genetics welcomes articles on the following topics: Genomics; Proteomics; Population genetics; Phylogenetics; Metagenomics; Microbial genetics; Genetics and evolution of wild and cultivated plants; Animal genetics and evolution; Human genetics and evolution; Genetic disorders; Genetic markers of diseases; Gene technology and therapy; Experimental and analytical methods; Statistical and computational methods.