Machine learning approaches for the genomic prediction of rheumatoid arthritis and systemic lupus erythematosus

BioData Mining

Yu-Fang Chung¹  Chih-Wei Chung²  Seng-Cho Chou²  Tzer-Shyong Chen³  Tzu-Hung Hsiao⁴  Ching-Heng Lin⁴  Yen-Ju Chen⁵  Hsin-Hua Chen⁶  Yi-Ming Chen⁷  Chih-Jen Huang⁸  Hwai-I Yang⁸ 

[1] Department of Electrical Engineering, Tunghai University, Taichung, Taiwan;Department of Information Management, National Taiwan University, Taipei, Taiwan;Department of Information Management, Tunghai University, Taichung, Taiwan;Department of Medical Research, Taichung Veterans General Hospital, Taichung, Taiwan;Department of Medical Research, Taichung Veterans General Hospital, Taichung, Taiwan;Division of Allergy, Immunology and Rheumatology, Taichung Veterans General Hospital, Taichung, Taiwan;Department of Medical Research, Taichung Veterans General Hospital, Taichung, Taiwan;Division of Allergy, Immunology and Rheumatology, Taichung Veterans General Hospital, Taichung, Taiwan;Rong Hsing Research Center for Translational Medicine & Ph.D. Program in Translational Medicine, National Chung Hsing University, Taichung, Taiwan;School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan;Department of Medical Research, Taichung Veterans General Hospital, Taichung, Taiwan;Division of Allergy, Immunology and Rheumatology, Taichung Veterans General Hospital, Taichung, Taiwan;Rong Hsing Research Center for Translational Medicine & Ph.D. Program in Translational Medicine, National Chung Hsing University, Taichung, Taiwan;School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan;College of Medicine, National Chung Hsing University, 40227, Taichung City, Taiwan;Genomics Research Center, Academia Sinica, Taipei, Taiwan;

关键词: Machine learning;    Genomic prediction;    Human leukocyte antigen imputation;    Single nucleotide polymorphism;    Genome-wide association studies;    Rheumatoid arthritis;    Systemic lupus erythematosus;   

DOI  :  10.1186/s13040-021-00284-5

来源: Springer

【 摘 要 】

BackgroundRheumatoid arthritis (RA) and systemic lupus erythematous (SLE) are autoimmune rheumatic diseases that share a complex genetic background and common clinical features. This study’s purpose was to construct machine learning (ML) models for the genomic prediction of RA and SLE.MethodsA total of 2,094 patients with RA and 2,190 patients with SLE were enrolled from the Taichung Veterans General Hospital cohort of the Taiwan Precision Medicine Initiative. Genome-wide single nucleotide polymorphism (SNP) data were obtained using Taiwan Biobank version 2 array. The ML methods used were logistic regression (LR), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and extreme gradient boosting (XGB). SHapley Additive exPlanation (SHAP) values were calculated to clarify the contribution of each SNPs. Human leukocyte antigen (HLA) imputation was performed using the HLA Genotype Imputation with Attribute Bagging package.ResultsCompared with LR (area under the curve [AUC] = 0.8247), the RF approach (AUC = 0.9844), SVM (AUC = 0.9828), GTB (AUC = 0.9932), and XGB (AUC = 0.9919) exhibited significantly better prediction performance. The top 20 genes by feature importance and SHAP values included HLA class II alleles. We found that imputed HLA-DQA1*05:01, DQB1*0201 and DRB1*0301 were associated with SLE; HLA-DQA1*03:03, DQB1*0401, DRB1*0405 were more frequently observed in patients with RA.ConclusionsWe established ML methods for genomic prediction of RA and SLE. Genetic variations at HLA-DQA1, HLA-DQB1, and HLA-DRB1 were crucial for differentiating RA from SLE. Future studies are required to verify our results and explore their mechanistic explanation.

【 授权许可】

CC BY