LightGBM-guided discovery of mechanistic biomarkers in thyroid cancer: GALNT7 and SKP1P1 emerge as therapeutic targets.

[UNLABELLED] Thyroid carcinoma (THCA) exhibits molecular heterogeneity, necessitating robust biomarkers for precise diagnosis and mechanistic insights. In this study, we integrated the transcriptomic data of THCA and normal thyroid tissues from The Cancer Genome Atlas and Genotype-Tissue Expression (GTEx) databases using ComBat-based batch correction, identifying 5,573 differentially expressed genes. Functional enrichment showed that these genes were associated with dysregulation in immune-microenvironment interactions and post-transcriptional regulatory pathways. After a comparison of seven machine-learning algorithms, LightGBM was selected for its high discrimination performance and interpretability. Using this algorithm, we obtained an 8-gene diagnostic panel comprising a glycosyltransferase (), pseudogenes (, ), miRNAs (,), and novel transcripts. siRNA-mediated knockdown of and significantly attenuated the proliferative and migratory abilities and clonogenicity of the THCA cell line TPC-1 in vitro. Immune correlation analysis revealed the tumor-specific suppression of stromal components by and normal tissue-specific lymphoid regulation by , suggesting the different roles of these components in microenvironment remodeling. Knockdown of , , and had no statistically significant effects on these oncogenic phenotypes. However, their high predictive value in the computational model suggests they may serve as effective biomarkers for tumor classification, independent of their functional roles in tumorigenesis. These findings highlight the importance of orthogonal experimental validation in linking computational biomarker discovery with biological causality. This study suggests that and are promising diagnostic biomarkers and therapeutic targets for THCA, with dual roles in tumor-specific signaling and immune microenvironment modulation.

[SUPPLEMENTARY INFORMATION] The online version contains supplementary material available at 10.1007/s12672-026-04598-w.