Clinical Disease Risk Assessment System Based on Multi-source Genetic Information

NING Kaida; YU Zhengyang; ZHAO Xin; LI Ziyan; DAI Ju; XIA Li

doi:10.11999/JEIT251025

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2026 >

NING Kaida, YU Zhengyang, ZHAO Xin, LI Ziyan, DAI Ju, XIA Li. Clinical Disease Risk Assessment System Based on Multi-source Genetic Information[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251025

Citation:

NING Kaida, YU Zhengyang, ZHAO Xin, LI Ziyan, DAI Ju, XIA Li. Clinical Disease Risk Assessment System Based on Multi-source Genetic Information[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251025

Citation:

PDF( 3149 KB)

Clinical Disease Risk Assessment System Based on Multi-source Genetic Information

doi: 10.11999/JEIT251025 cstr: 32379.14.JEIT251025

NING Kaida¹,
YU Zhengyang²,
ZHAO Xin^{1, 3},
LI Ziyan²,
DAI Ju¹,
XIA Li^{2
,
,}

1.
Pengcheng Laboratory, Shenzhen 518055, China
2.
South China University of Technology, Guangzhou 510640, China
3.
Beihang University School of Computer Science and Engineering, BeiJing 100191, China

Funds: The Major Key Project of Pengcheng Laboratory (PCL2025AS212-3, PCL2024A02-2), The National Natural Science Foundation of China (12571529) , Guangdong Basic and Applied Basic Research Foundation (2024A1515-010699, 2022A1515011426)

Received Date: 2025-09-28
Accepted Date: 2026-03-09
Rev Recd Date: 2026-03-09

Available Online: 2026-03-12

Abstract

Abstract

Objective Complex diseases are driven by polygenic inheritance and gene–environment interactions, resulting in highly heterogeneous pathogenic mechanisms and posing major challenges for both research and public health. Conventional single-trait polygenic risk scores (PRS) aggregate genetic variants associated with individual diseases but are limited by their neglect of cross-trait genetic correlations and nonlinear genetic interactions. Although multi-trait PRS approaches have been proposed to improve prediction accuracy, existing statistical-learning frameworks predominantly rely on linear integration of PRS features, failing to capture nonlinear interactions among single-nucleotide polymorphisms (SNPs) and to fully exploit shared genetic information across diseases. To address these limitations, we propose a nonlinear multi-source disease prediction framework, the SNP–PRS Fusion model, termed the mtSNPPRS_XGB (mtSNP-PRS XGBoost Integration Model). Methods The mtSNPPRS_XGB framework integrates raw SNP data of target traits with multi-trait PRS information to enhance genetic risk prediction for complex diseases through nonlinear modeling. SNPs significantly associated with target diseases were extracted from the GWAS Catalog (p < 5 × 10^–8) and encoded as allele dosages (0/1/2), while PRS weights covering 80 traits were obtained from the PGS Catalog and used to compute individual PRS. After standardized preprocessing, SNP and PRS features were jointly fused and modeled using XGBoost to capture complex SNP–SNP and SNP–PRS interactions. This framework introduces two key innovations:(i) collaborative modeling of multi-trait genetic information by jointly leveraging disease-specific SNPs and cross-disease PRS, and (ii) systematic learning of nonlinear genetic interactions to overcome the linear constraints of conventional PRS-based models. Results and Discussions The mtSNPPRS_XGB model was evaluated using UK Biobank data across 18 complex diseases. It achieved an average AUC of 66.70%, representing improvements of 1.04% over the elastic-net-based model and 4.39% over the conventional UniPRS model. The inclusion of SNP features substantially improved predictive performance in diseases such as coronary heart disease, psoriasis, and celiac disease, while the integration of multi-trait PRS further enhanced specificity, particularly in cardiovascular, autoimmune, and cancer-related conditions. SHAP-based interpretability analyses demonstrated that mtSNPPRS_XGB simultaneously captures global cross-disease genetic liability encoded by PRS and disease-specific localized SNP effects, as illustrated in Alzheimer’s disease, colorectal cancer, gout, and ischemic stroke. These findings support both the biological plausibility and interpretability of the proposed framework. Conclusions We present a novel statistical learning–based multi-trait genetic risk prediction model, mtSNPPRS_XGB, which introduces an SNP–PRS fusion architecture and employs XGBoost to capture nonlinear interactions among multi-source genetic features. By integrating raw SNP data with multi-trait PRS, the proposed framework significantly improves risk prediction performance for complex diseases. Validation across 18 diseases in the UK Biobank demonstrates consistent performance gains over traditional PRS-based methods. This study overcomes the linear modeling limitations of conventional PRS approaches and provides a new paradigm for nonlinear integration of SNPs and multi-trait PRS, offering a robust and interpretable tool for personalized genetic risk prediction in precision medicine.
- Complex disease risk prediction,
- Multi-trait PRS,
- SNP characteristics,
- Nonlinear modeling

FullText(HTML)

References(24)

References

[1]	CLAUSSNITZER M, CHO J H, COLLINS R, et al. A brief history of human disease genetics[J]. Nature, 2020, 577(7789): 179–189. doi: 10.1038/s41586-019-1879-7.
[2]	MA Ying and ZHOU Xiang. Genetic prediction of complex traits with polygenic scores: A statistical review[J]. Trends in Genetics, 2021, 37(11): 995–1011. doi: 10.1016/j.tig.2021.06.004.
[3]	ZHANG Sai, SHU Hantao, ZHOU Jingtian, et al. Single-cell polygenic risk scores dissect cellular and molecular heterogeneity of complex human diseases[J]. Nature Biotechnology, 2025: 1–17. doi: 10.1038/s41587-025-02725-6.
[4]	LENNON N J, KOTTYAN L C, KACHULIS C, et al. Selection, optimization and validation of ten chronic disease polygenic risk scores for clinical implementation in diverse US populations[J]. Nature Medicine, 2024, 30(2): 480–487. doi: 10.1038/s41591-024-02796-z.
[5]	LOOS R J F. 15 years of genome-wide association studies and no signs of slowing down[J]. Nature Communications, 2020, 11(1): 5900. doi: 10.1038/s41467-020-19653-5.
[6]	ZHU Wensheng and ZHANG Heping. Why do we test multiple traits in genetic association studies?[J]. Journal of the Korean Statistical Society, 2009, 38(1): 1–10. doi: 10.1016/j.jkss.2008.10.006.
[7]	HU Yiming, LU Qiongshi, LIU Wei, et al. Joint modeling of genetically correlated diseases and functional annotations increases accuracy of polygenic risk prediction[J]. PLoS Genetics, 2017, 13(6): e1006836. doi: 10.1371/journal.pgen.1006836.
[8]	GUO Ping, GONG Weiming, LI Yuanming, et al. Pinpointing novel risk loci for Lewy body dementia and the shared genetic etiology with Alzheimer’s disease and Parkinson’s disease: A large-scale multi-trait association analysis[J]. BMC Medicine, 2022, 20(1): 214. doi: 10.1186/s12916-022-02404-2.
[9]	VILHJÁLMSSON B J, YANG Jian, FINUCANE H K, et al. Modeling linkage disequilibrium increases accuracy of polygenic risk scores[J]. American Journal of Human Genetics, 2015, 97(4): 576–592. doi: 10.1016/j.ajhg.2015.09.001.
[10]	GE Tian, CHEN C Y, NI Yang, et al. Polygenic prediction via Bayesian regression and continuous shrinkage priors[J]. Nature Communications, 2019, 10(1): 1776. doi: 10.1038/s41467-019-09718-5.
[11]	KHERA A V, CHAFFIN M, ARAGAM K G, et al. Genome-wide polygenic scores for common diseases identify individuals with risk equivalent to monogenic mutations[J]. Nature Genetics, 2018, 50(9): 1219–1224. doi: 10.1038/s41588-018-0183-z.
[12]	MAVADDAT N, MICHAILIDOU K, DENNIS J, et al. Polygenic risk scores for prediction of breast cancer and breast cancer subtypes[J]. American Journal of Human Genetics, 2019, 104(1): 21–34. doi: 10.1016/j.ajhg.2018.11.002.
[13]	PRIVÉ F, ARBEL J, and VILHJÁLMSSON B J. LDpred2: Better, faster, stronger[J]. Bioinformatics, 2021, 36(22/23): 5424–5431. doi: 10.1093/bioinformatics/btaa1029.
[14]	ZHONG Peng, ZHANG Chumeng, WU Qinfeng, et al. Shared genetic loci connect cardiovascular disease with blood pressure and lipid traits in East Asian populations[J]. Frontiers in Genetics, 2025, 16: 1635378. doi: 10.3389/fgene.2025.1635378.
[15]	ALLEGRINI A G, SELZAM S, RIMFELD K, et al. Genomic prediction of cognitive traits in childhood and adolescence[J]. Molecular Psychiatry, 2019, 24(6): 819–827. doi: 10.1038/s41380-019-0394-4.
[16]	KRAPOHL E, PATEL H, NEWHOUSE S, et al. Multi-polygenic score approach to trait prediction[J]. Molecular Psychiatry, 2018, 23(5): 1368–1374. doi: 10.1038/mp.2017.163.
[17]	CHUNG W, CHEN Jun, TURMAN C, et al. Efficient cross-trait penalized regression increases prediction accuracy in large cohorts using secondary phenotypes[J]. Nature Communications, 2019, 10(1): 569. doi: 10.1038/s41467-019-08535-0.
[18]	ALBIÑANA C, ZHU Zhihong, SCHORK A J, et al. Multi-PGS enhances polygenic prediction by combining 937 polygenic scores[J]. Nature Communications, 2023, 14(1): 4702. doi: 10.1038/s41467-023-40330-w.
[19]	TRUONG B, HULL L E, RUAN Yunfeng, et al. Integrative polygenic risk score improves the prediction accuracy of complex traits and diseases[J]. Cell Genomics, 2024, 4(4): 100523. doi: 10.1016/j.xgen.2024.100523.
[20]	CHEN T H, CHATTERJEE N, LANDI M T, et al. A penalized regression framework for building polygenic risk models based on summary statistics from genome-wide association studies and incorporating external information[J]. Journal of the American Statistical Association, 2021, 116(533): 133–143. doi: 10.1080/01621459.2020.1764849.
[21]	ZHAI Song, GUO Bin, WU Baolin, et al. Integrating multiple traits for improving polygenic risk prediction in disease and pharmacogenomics GWAS[J]. Briefings in Bioinformatics, 2023, 24(4): bbad181. doi: 10.1093/bib/bbad181.
[22]	王宇翱, 黄叶琪, 李青远, 等. 融合表示学习和知识图谱推理的糖尿病及并发症预测方法[J]. 电子与信息学报. doi: 10.11999/JEIT250798. WANG Yuao, HUANG Yeqi, LI Qingyuan, et al. Integrating representation learning and knowledge graph reasoning for diabetes and complications prediction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250798.
[23]	CHEN Tianqi and GUESTRIN C. XGBoost: A scalable tree boosting system[C]. The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 2016: 785–794. doi: 10.1145/2939672.2939785.
[24]	LAMBERT S A, WINGFIELD B, GIBSON J T, et al. Enhancing the Polygenic Score Catalog with tools for score calculation and ancestry normalization[J]. Nature Genetics, 2024, 56(10): 1989–1994. doi: 10.1038/s41588-024-01937-x.