Disease Risk Prediction from AI and Advanced Genomic Analysis

Michigan State University senior vice president Stephen Hsu, a theoretical physicist and the founder of Genomic Prediction discusses how AI and super-cheap human gene sequencing is revealing the secrets of genetics and will enable an explosion of disease cures.

Human gene sequencing prices have been falling a rate many times faster than Moore’s law rate of lowering computing costs.

* FDA approval of the first genetic treatment for monogenic conditions and the work towards developing treatments for polygenic conditions like diabetes and cancer.
* How this technology might exacerbate existing social inequalities or create new ones; is it just an issue of access, or does it go further?
* Developing best practice protocols for governance and regulation of genomic technologies.

Genomic Prediction is a startup company that provides disease risk scores based upon AI and advanced genome sequence analysis.

Biorxiv – Genomic Prediction of Complex Disease Risk

They construct risk predictors using polygenic scores (PGS) computed from common Single Nucleotide Polymorphisms (SNPs) for a number of complex disease conditions, using L1-penalized regression (also known as LASSO) on case-control data from UK Biobank. Among the disease conditions studied are Hypothyroidism, (Resistive) Hypertension, Type 1 and 2 Diabetes, Breast Cancer, Prostate Cancer, Testicular Cancer, Gallstones, Glaucoma, Gout, Atrial Fibrillation, High Cholesterol, Asthma, Basal Cell Carcinoma, Malignant Melanoma, and Heart Attack.

They obtain values for the area under the receiver operating characteristic curves (AUC) in the range ~ 0.58 – 0.71 using SNP data alone. Substantially higher predictor AUCs are obtained when incorporating additional variables such as age and sex. Some SNP predictors alone are sufficient to identify outliers (e.g., in the 99th percentile of PGS) with 3 – 8 times higher risk than typical individuals. Substantial improvements in predictive power are attainable using training sets with larger case populations. There will be rapid improvement in genomic prediction as more case-control data become available for analysis.

Genetic analysis can now identify risk outliers (e.g., with 5 or 10 times normal risk) for about 20 common disease conditions, ranging from diabetes to heart diseases to breast cancer, using inexpensive SNP genotypes.

SOURCES- Infoproc, Biorxiv, Youtube