Mendelian Randomization Analysis reveals Inverse Genetic Risks between Skin Cancers and Vitiligo.

Several observational studies have demonstrated a consistent pattern of decreased melanoma risk among patients with vitiligo. More recently, this finding has been supported by a suggested genetic relationship between the two entities, with certain variants significantly associated with an increased risk of melanoma, basal cell carcinoma, and squamous cell carcinoma but a decreased risk of vitiligo. We compared 48 associated variants from a recently published GWAS and identified three variants-located in the TYR, MC1R-DEF8, and RALY-EIF2S2-ASIP-AHCY-ITCH loci- that correlated with an increased risk for melanoma, basal cell carcinoma, and squamous cell carcinoma and a decreased risk for vitiligo. We then used results of skin cancers and vitiligo GWAS to compare the shared genetic properties between these two traits through an unbiased Mendelian randomization analysis. Our results suggest that the inverse genetic relationship between common skin cancers and vitiligo is broader than previously reported owing to the influence of shared genome-wide significant associations.

Detecting biased validation of predictive models in the positive-unlabeled setting: disease gene prioritization case study.

Motivation: Positive-unlabeled data consists of points with either positive or unknown labels. It is widespread in medical, genetic, and biological settings, creating a high demand for predictive positive-unlabeled models. The performance of such models is usually estimated using validation sets, assumed to be selected completely at random (SCAR) from known positive examples. For certain metrics, this assumption enables unbiased performance estimation when treating positive-unlabeled data as positive/negative. However, the SCAR assumption is often adopted without proper justifications, simply for the sake of convenience. Results: We provide an algorithm that under the weak assumptions of a lower bound on the number of positive examples can test for the violation of the SCAR assumption. Applying it to the problem of gene prioritization for complex genetic traits, we illustrate that the SCAR assumption is often violated there, causing the inflation of performance estimates, which we refer to as validation bias. We estimate the potential impact of validation bias on performance estimation. Our analysis reveals that validation bias is widespread in gene prioritization data and can significantly overestimate the performance of models. This finding elucidates the discrepancy between the reported good performance of models and their limited practical applications. Availability and implementation: Python code with examples of application of the validation bias detection algorithm is available at github.com/ArtomovLab/ValidationBias.