Back

RAGE protein: COPD biomarker and case study for variant pathogenicity prediction

Dawson, J. E.; Bowler, R. P.

2025-08-04 molecular biology
10.1101/2025.08.04.668362 bioRxiv
Show abstract

The structural biology of a protein is key to understanding its mechanism and plays a significant role in predicting the effects of clinical variants. New advances in pathogenicity predictors have improved their quality but interpreting the results in light of a proteins structure and functional can still be challenging. We use the Receptor for Advanced Glycosylation End-products (RAGE), which is involved in triggering inflammatory pathways during Chronic Obstructive Pulmonary Disease (COPD), as a case study to demonstrate how to utilize publicly available structure and missense variant databases, such as ClinVar and the Genomic Aggregation database (gnomAD), as well as the pathogenicity predictor AlphaMissense. Common missense RAGE variant G82S (rs2070600) has an observed allele frequency of 0.056 in gnomAD and is predicted to be benign, but is known to have clinical consequences in COPD, AD, and CV, which illustrates the need to careful interpretation of results. Additionally, missense variants for a set of COPD-related proteins were utilized to evaluate the performance of pathogenicity predictors SIFT, FATHMM, Poly-Pred2, MutPred2, and AlphaMissense.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.