Actively Protective Combinatorial Analysis: A Scalable Novel Method for Detecting Variants that Contribute to Reduced Disease Prevalence in High-risk Individuals
Artificial Intelligence in the Life Sciences
Authors: Jason Sardell, Sayoni Das, Krystyna Taylor, Colin Stubberfield, Andy Malinowski, Mark Strivens, Steve Gardner
The paper presents Actively Protective Combinatorial Analysis, a novel method for routinely identifying disease resilience associations that offers powerful insights for the discovery of a new class of disease protective targets to prevent disease in high-risk patients.
Highlights include:
- Actively Protective Signatures: By identifying individuals who remain healthy despite possessing high-risk genetic profiles, the paper uncovers "actively protective" genetic variants that mitigate disease risk.
- Combinatorial Approach: The method combines genomic features (e.g., SNP genotypes) and higher-order gene interactions to identify genetic resilience in patients, which traditional genetic association studies (such as GWAS) often overlook.
- Case Studies in ME/CFS and ALS: The method successfully identified protective genetic signatures in ME/CFS and ALS populations, highlighting potential therapeutic targets for these complex, chronic diseases.
- Enhanced Power over Traditional Methods: The actively protective approach provides increased sensitivity and power for detecting gene-disease associations, especially for diseases with complex and polygenic origins.
Actively protective combinatorial analysis identifies combinations of features that contribute to reducing risk of disease in individuals who remain healthy even though their genomic profile suggests that they have high risk of developing disease.
In the paper, we show how this can be used to identify mechanisms in the background of normal cellular biology that work to slow or stop progression of complex, chronic diseases.
These protective signatures can potentially be used to identify novel drug targets, pharmacogenomic and/or therapeutic mRNA opportunities and to better stratify patients by overall disease risk and mechanistic subtype.
Cite this article
J Sardell, S Das, K Taylor, C Stubberfield, A Malinowski, M Strivens, S Gardner, Actively Protective Combinatorial Analysis: a Scalable Novel Method for Detecting Variants that Contribute to Reduced Disease Prevalence in High-Risk Individuals, Artificial Intelligence in the Life Sciences, 2025, 100125, ISSN 2667-3185, https://doi.org/10.1016/j.ailsci.2025.100125.