Bioinformatics Feature Dataset for Stunting Risk Genes (GH1, GHR, IGF1, LEP)

This dataset contains engineered nucleotide- and protein-level features extracted from NCBI FASTA sequences for GH1, GHR, IGF1, and LEP. Features include GC content, CpG density, 3-mer Shannon entropy, amino-acid composition, and N-terminal hydrophobicity (first 25 residues). The dataset supports alignment-free analysis and downstream Fuzzy Maximum Likelihood risk scoring for gene prioritization in stunting-related growth–metabolic pathways.本数据集包含从美国国家生物技术信息中心（National Center for Biotechnology Information，NCBI）的FASTA序列（FASTA）中提取的、针对GH1、GHR、IGF1及LEP基因的经工程化处理的核苷酸水平与蛋白质水平特征。所提取的特征包括GC含量（GC content）、CpG密度（CpG density）、3-聚体香农熵（3-mer Shannon entropy）、氨基酸组成，以及N端疏水性（前25个残基）。本数据集可支持无序列比对分析，以及面向生长迟缓相关生长代谢通路中基因优先级排序任务的下游模糊最大似然（Fuzzy Maximum Likelihood）风险评分工作。