Robust SNP-based prediction of rheumatoid arthritis through machine-learning-optimized polygenic risk score
Ashley J. W. Lim, C. Tera Tyniana, Lee Jin Lim, Justina Wei Lynn Tan, Ee Tzun Koh, TTSH Rheumatoid Arthritis Study Group, Andrea Ee Ling Ang, Grace Yin Lai Chan, Madelynn Chan, Faith Li‐Ann Chia, Hiok Hee Chng, Choon Guan Chua, Hwee Siew Howe, Li Wearn Koh, Kok Ooi Kong, Weng Giap Law, Samuel Shang Ming Lee, Tsui Yee Lian, Xin Rong Lim, Jess Mung Ee Loh, Mona Manghani, Sze‐Chin Tan, Claire Min‐Li Teo, Bernard Yu‐Hor Thong, Paula Permatasari Tjokrosaputro, Chuanhui Xu, Samuel S. Chong, Chiea Chuen Khor, Khai Pang Leong, Caroline Lee
Abstract
BACKGROUND: The popular statistics-based Genome-wide association studies (GWAS) have provided deep insights into the field of complex disorder genetics. However, its clinical applicability to predict disease/trait outcomes remains unclear as statistical models are not designed to make predictions. This study employs statistics-free machine-learning (ML)-optimized polygenic risk score (PRS) to complement existing GWAS and bring the prediction of disease/trait outcomes closer to clinical application. Rheumatoid Arthritis (RA) was selected as a model disease to demonstrate the robustness of ML in disease prediction as RA is a prevalent chronic inflammatory joint disease with high mortality rates, affecting adults at the economic prime. Early identification of at-risk individuals may facilitate measures to mitigate the effects of the disease. METHODS: This study employs a robust ML feature selection algorithm to identify single nucleotide polymorphisms (SNPs) that can predict RA from a set of training data comprising RA patients and population control samples. Thereafter, selected SNPs were evaluated for their predictive performances across 3 independent, unseen test datasets. The selected SNPs were subsequently used to generate PRS which was also evaluated for its predictive capacity as a sole feature. RESULTS: ) and predictive (AUC > 0.9) of RA in the 3 unseen datasets. A RA ML-PRS calculator of these 9 SNPs was developed ( https://xistance.shinyapps.io/prs-ra/ ) to facilitate individualized clinical applicability. The majority of the predictive SNPs are protective, reside in non-coding regions, and are either predicted to be potentially functional SNPs (pfSNPs) or in high linkage disequilibrium (r2 > 0.8) with un-interrogated pfSNPs. CONCLUSIONS: These findings highlight the promise of this ML strategy to identify useful genetic features that can robustly predict disease and amenable to translation for clinical application.