Subset of 1000 genome project data for autoencoder development

This dataset contains filtered SNP data from chromosome 1 of the 1000 Genomes Project, along with processed gene annotation files from Gencode v37. The data was generated using PLINK filtering, gene annotation extraction, and SNP-to-gene mapping, following a reproducible pipeline. It includes: Filtered PLINK files for chromosome 1 (MAF ≥ 0.01). SNP counts for genes on chromosome 1. Subsets of genes (10 and 50 genes) selected based on SNP count. Extracted Gencode annotations for these selected genes. Corresponding PLINK files for each subset of genes.