Please use this identifier to cite or link to this item: https://doi.org/10.1093/rheumatology/keac032
DC FieldValue
dc.titleMachine learning using genetic and clinical data identifies a signature that robustly predicts methotrexate response in rheumatoid arthritis
dc.contributor.authorLim, Lee Jin
dc.contributor.authorLim, Ashley JW
dc.contributor.authorBRANDON OOI NICK SERN
dc.contributor.authorTan, Justina Wei Lynn
dc.contributor.authorKoh, Ee Tzun
dc.contributor.authorGroup, Ttsh Rheumatoid Arthritis Study
dc.contributor.authorChong, Samuel S
dc.contributor.authorKhor, Chiea Chuen
dc.contributor.authorTucker-Kellogg, Lisa
dc.contributor.authorLee, Caroline G
dc.contributor.authorLeong, Khai Pang
dc.date.accessioned2022-06-09T06:54:54Z
dc.date.available2022-06-09T06:54:54Z
dc.date.issued2022-01-30
dc.identifier.citationLim, Lee Jin, Lim, Ashley JW, BRANDON OOI NICK SERN, Tan, Justina Wei Lynn, Koh, Ee Tzun, Group, Ttsh Rheumatoid Arthritis Study, Chong, Samuel S, Khor, Chiea Chuen, Tucker-Kellogg, Lisa, Lee, Caroline G, Leong, Khai Pang (2022-01-30). Machine learning using genetic and clinical data identifies a signature that robustly predicts methotrexate response in rheumatoid arthritis. RHEUMATOLOGY. ScholarBank@NUS Repository. https://doi.org/10.1093/rheumatology/keac032
dc.identifier.issn14620324
dc.identifier.issn14620332
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/226870
dc.description.abstractOBJECTIVE: To develop a hypothesis-free model that best predicts response to methotrexate (MTX) drug in rheumatoid arthritis (RA) patients utilizing biologically meaningful genetic feature selection of potentially functional single nucleotide polymorphisms (pfSNPs) through robust machine learning (ML) feature selection methods. METHODS: MTX-treated RA patients with known response were divided in a 4:1 ratio into training and test sets. From the patients' exomes, potential features for classifier prediction were identified from pfSNPs and non-genetic factors through ML using recursive feature elimination with cross-validation incorporating Random Forest Classifier. Feature selection was repeated on random subsets of the training cohort, and consensus features were assembled into the final feature set. This feature set was evaluated for predictive potential using six ML classifiers, first by cross-validation within the training set, and finally by analyzing its performance with the unseen test set. RESULTS: The final feature set contains 56 pfSNPs and five non-genetic factors. The majority of these pfSNPs are located in pathways related to RA pathogenesis or methotrexate action and are predicted to modulate gene expression. When used for training in six ML classifiers, performance was good in both the training set (AUC : 0·855-0·916, sensitivity : 0·715-0·892 and specificity : 0·733-0·862) in the unseen test set (AUC : 0·751-0·826, sensitivity: 0·581-0·839 and specificity: 0·641-0·923). CONCLUSION: Sensitive and specific predictors of MTX response in RA patients were identified in this study through a novel strategy combining biologically meaningful and machine learning feature selection and training. These predictors may facilitate better treatment decision-making in RA management.
dc.language.isoen
dc.publisherOXFORD UNIV PRESS
dc.sourceElements
dc.subjectScience & Technology
dc.subjectLife Sciences & Biomedicine
dc.subjectRheumatology
dc.subjectrheumatoid arthritis
dc.subjectmethotrexate
dc.subjectgenetic polymorphism
dc.subjectmachine learning
dc.subjectfeature selection
dc.subjectFUNCTIONAL ANNOTATION
dc.subjectRHEUMATOLOGY/EUROPEAN LEAGUE
dc.subjectAMERICAN-COLLEGE
dc.subjectDISEASE-ACTIVITY
dc.subjectSCORES
dc.subjectPHARMACOGENETICS
dc.subjectCLASSIFICATION
dc.subjectCOMBINATION
dc.subjectSNPNEXUS
dc.subjectCRITERIA
dc.typeArticle
dc.date.updated2022-06-07T07:19:11Z
dc.contributor.departmentBIOCHEMISTRY
dc.contributor.departmentNUS GRADUATE SCHOOL
dc.description.doi10.1093/rheumatology/keac032
dc.description.sourcetitleRHEUMATOLOGY
dc.published.statePublished
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Rheumatology_keac032.pdfPublished version1.12 MBAdobe PDF

CLOSED

Published

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.