PMID- 34895289
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20231102
IS  - 1756-0381 (Print)
IS  - 1756-0381 (Electronic)
IS  - 1756-0381 (Linking)
VI  - 14
IP  - 1
DP  - 2021 Dec 11
TI  - Machine learning approaches for the genomic prediction of rheumatoid arthritis 
      and systemic lupus erythematosus.
PG  - 52
LID - 10.1186/s13040-021-00284-5 [doi]
LID - 52
AB  - BACKGROUND: Rheumatoid 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. METHODS: A 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. RESULTS: Compared 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. CONCLUSIONS: We 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.
CI  - (c) 2021. The Author(s).
FAU - Chung, Chih-Wei
AU  - Chung CW
AD  - Department of Information Management, National Taiwan University, Taipei, Taiwan.
FAU - Hsiao, Tzu-Hung
AU  - Hsiao TH
AD  - Department of Medical Research, Taichung Veterans General Hospital, Taichung, 
      Taiwan.
FAU - Huang, Chih-Jen
AU  - Huang CJ
AD  - Genomics Research Center, Academia Sinica, Taipei, Taiwan.
FAU - Chen, Yen-Ju
AU  - Chen YJ
AD  - Department of Medical Research, Taichung Veterans General Hospital, Taichung, 
      Taiwan.
AD  - Division of Allergy, Immunology and Rheumatology, Taichung Veterans General 
      Hospital, Taichung, Taiwan.
FAU - Chen, Hsin-Hua
AU  - Chen HH
AD  - Department of Medical Research, Taichung Veterans General Hospital, Taichung, 
      Taiwan.
AD  - Division of Allergy, Immunology and Rheumatology, Taichung Veterans General 
      Hospital, Taichung, Taiwan.
AD  - Rong Hsing Research Center for Translational Medicine & Ph.D. Program in 
      Translational Medicine, National Chung Hsing University, Taichung, Taiwan.
AD  - School of Medicine, College of Medicine, National Yang Ming Chiao Tung 
      University, Taipei, Taiwan.
FAU - Lin, Ching-Heng
AU  - Lin CH
AD  - Department of Medical Research, Taichung Veterans General Hospital, Taichung, 
      Taiwan.
FAU - Chou, Seng-Cho
AU  - Chou SC
AD  - Department of Information Management, National Taiwan University, Taipei, Taiwan.
FAU - Chen, Tzer-Shyong
AU  - Chen TS
AD  - Department of Information Management, Tunghai University, Taichung, Taiwan.
FAU - Chung, Yu-Fang
AU  - Chung YF
AD  - Department of Electrical Engineering, Tunghai University, Taichung, Taiwan.
FAU - Yang, Hwai-I
AU  - Yang HI
AD  - Genomics Research Center, Academia Sinica, Taipei, Taiwan.
FAU - Chen, Yi-Ming
AU  - Chen YM
AD  - Department of Medical Research, Taichung Veterans General Hospital, Taichung, 
      Taiwan. ymchen1@vghtc.gov.tw.
AD  - Division of Allergy, Immunology and Rheumatology, Taichung Veterans General 
      Hospital, Taichung, Taiwan. ymchen1@vghtc.gov.tw.
AD  - Rong Hsing Research Center for Translational Medicine & Ph.D. Program in 
      Translational Medicine, National Chung Hsing University, Taichung, Taiwan. 
      ymchen1@vghtc.gov.tw.
AD  - School of Medicine, College of Medicine, National Yang Ming Chiao Tung 
      University, Taipei, Taiwan. ymchen1@vghtc.gov.tw.
AD  - College of Medicine, National Chung Hsing University, 40227, Taichung City, 
      Taiwan. ymchen1@vghtc.gov.tw.
LA  - eng
GR  - 40-05-GMM and AS-GC-110-MD02/Academia Sinica/
PT  - Journal Article
DEP - 20211211
PL  - England
TA  - BioData Min
JT  - BioData mining
JID - 101319161
PMC - PMC8666017
OTO - NOTNLM
OT  - Genome-wide association studies
OT  - Genomic prediction
OT  - Human leukocyte antigen imputation
OT  - Machine learning
OT  - Rheumatoid arthritis
OT  - Single nucleotide polymorphism
OT  - Systemic lupus erythematosus
COIS- The authors declare that they have no conflicts of interest to declare.
EDAT- 2021/12/14 06:00
MHDA- 2021/12/14 06:01
PMCR- 2021/12/11
CRDT- 2021/12/13 11:44
PHST- 2021/07/13 00:00 [received]
PHST- 2021/11/21 00:00 [accepted]
PHST- 2021/12/13 11:44 [entrez]
PHST- 2021/12/14 06:00 [pubmed]
PHST- 2021/12/14 06:01 [medline]
PHST- 2021/12/11 00:00 [pmc-release]
AID - 10.1186/s13040-021-00284-5 [pii]
AID - 284 [pii]
AID - 10.1186/s13040-021-00284-5 [doi]
PST - epublish
SO  - BioData Min. 2021 Dec 11;14(1):52. doi: 10.1186/s13040-021-00284-5.