In recent years many GWAS (genome-wide association studies) have been performed to investigate the effect of common variants on traits and diseases. However, the interpretation of those studies remains challenging. Partially due to the huge multiple testing burden and their limited association power. A recent publication investigated gene features can help interpreting such studies [1]. Here, we will take this approach one step further and show that a small embedding of transcription and other genome-wide measurements is sufficient to achieve similar performance. You will build upon a functional gene embedding we just published [2].
1: Leveraging polygenic enrichments of gene features to predict genes underlying complex traits and diseases | Nature Genetics
2: Felix Brechtmann, Thibault Bechtler, Shubhankar Londhe, Christian Mertes, and Julien Gagneur. (2023). Evaluation of input data modality choices on functional gene embeddings. NAR Genomics and Bioinformatics, 2023, PMID: 37942285