Integrated multi-omics analysis and machine learning identify G protein-coupled receptor-related signatures for the diagnosis and clinical benefits in soft tissue sarcoma

Duo WangJihao TuJianfeng LiuYuting PiaoYiming ZhaoYing XiongJianing WangXiaotian Zheng^*Bin Liu

• First Affiliated Hospital of Jilin University, Changchun, China

Background: G protein-coupled receptors (GPRs) are associated with tumor development and prognosis. However, there were fewer reports of GPRs-related signatures in STSs, we aim to combined GPRs-related genes with cellular landscape to construct diagnostic and prognostic models in STSs.Based on AddModuleScore, ssGSEA, DEGs and WGCNA analyses, GPRs-related genes (GPRs) were screened at both the single-cell and bulk RNA-seq levels based on TCGA and GEO databases. We developed a novel machine learning framework that incorporated 12 machine learning algorithms and their 127 combinations to construct a consensus GPR-related signatures (GPRs) to screen biomarkers with diagnostic significance and clinical translation, which was assessed by the internal and external validation datasets. Moreover, the GPR-TME classifier as the prognosis model was constructed and further performed to immune infiltration, functional enrichment, somatic mutation, immunotherapy response prediction and scRNA-seq analyses.We identified 151 GPR-related genes at both the single-cell and bulk transcriptome levels, and identified Stepglm[both]+Enet[alpha=0.6] model with 7 GPR-related genes as the final diagnostic predictive model with high accuracy and translational relevance using a 127combination machine learning computational framework, and the GPRs-integrated diagnosis nomogram provided a quantitative tool in clinical practice. Moreover, we identified 7 prognosis GPRs and 5 prognosis-good immune cells constructing GPR score and TME score, respectively. The findings indicate that high expression of GPRs is associated with a poor prognosis in patients with STS, highlighting the significant role of GPRs and tumor microenvironment (TME) in STS development. Building up a GPR-TME classifier, low GPR combined with high TME exhibited the most favorable prognosis and immunotherapeutic efficacy, which was further performed immune infiltration, functional enrichment, somatic mutation, immunotherapy response prediction and scRNA-seq analyses.Our study constructed an GPR-related signature that can serve as a promising tool for diagnosis and prognosis prediction, targeted prevention, and personalized medicine in STS.