MSI-XGNN: an explainable GNN computational framework integrating transcription- and methylation-level biomarkers for microsatellite instability detection.

Microsatellite instability (MSI) is a hypermutator phenotype caused by DNA mismatch repair deficiency. MSI has been reported in various human cancers, particularly colorectal, gastric and endometrial cancers. MSI is a promising biomarker for cancer prognosis and immune checkpoint blockade immunotherapy. Several computational methods have been developed for MSI detection using DNA- or RNA-based approaches based on next-generation sequencing. Epigenetic mechanisms, such as DNA methylation, regulate gene expression and play critical roles in the development and progression of cancer. We here developed MSI-XGNN, a new computational framework for predicting MSI status using bulk RNA-sequencing and DNA methylation data. MSI-XGNN is an explainable deep learning model that combines a graph neural network (GNN) model to extract features from the gene-methylation probe network with a CatBoost model to classify MSI status. MSI-XGNN, which requires tumor-only samples, exhibited comparable performance with two well-known methods that require tumor-normal paired sequencing data, MSIsensor and MANTIS and better performance than several other tools. MSI-XGNN also showed good generalizability on independent validation datasets. MSI-XGNN identified six MSI markers consisting of four methylation probes (EPM2AIP1|MLH1:cg14598950, EPM2AIP1|MLH1:cg27331401, LNP1:cg05428436 and TSC22D2:cg15048832) and two genes (RPL22L1 and MSH4) constituting the optimal feature subset. All six markers were significantly associated with beneficial tumor microenvironment characteristics for immunotherapy, such as tumor mutation burden, neoantigens and immune checkpoint molecules such as programmed cell death-1 and cytotoxic T-lymphocyte antigen-4. Overall, our study provides a powerful and explainable deep learning model for predicting MSI status and identifying MSI markers that can potentially be used for clinical MSI evaluation.

P4HA3 promotes head and neck squamous cell carcinoma progression via the WNT/ß-catenin signaling pathway.

Here, we explored the role of Prolyl 4-Hydroxylase Subunit Alpha 3 (P4HA3), the most recently identified member of the prolyl-4-hydroxylase (P4H) family, in head and neck squamous cell carcinoma (HNSCC) progression. P4HA3 is upregulated during cancer progression; however, its specific role in HNSCC progression remains elusive. Thus, this study aimed to elucidate the regulatory function of P4HA3 in HNSCC development and progression and to describe the underlying mechanisms. Initially, we analyzed the correlation between the expression of P4HA3 and the WNT pathway genes and clinicopathologic features in HNSCC based on microarray data from The Cancer Genome Atlas (TCGA). Next, we used Gene Oncology (GO) functional data to describe several potentially associated pathways in HNSCC. Then, we knocked down P4HA3 in SCC15 and SCC25 cells, two classic HNSCC cell lines, and assessed the resulting changes using RT-qPCR. Furthermore, we used Western blot to evaluate the regulatory role of P4HA3 in the epithelial-to-mesenchymal transition (EMT) and the WNT/ß-catenin signaling pathway. To explore the effect of P4HA3 knockdown on tumor progression, in vivo experiments were conducted using a murine model. Immunohistochemistry assays were then employed to identify proteins associated with EMT and the WNT/ß-catenin signaling pathway in tumor tissues. Upregulated P4HA3 in HNSCC patient tumor tissues was positively correlated with poor prognosis. Notably, P4HA3 knockdown significantly inhibited the proliferative and invasive abilities of HNSCC. The levels of genes and proteins associated with EMT and the WNT/ß-catenin signaling pathway were also markedly reduced by P4HA3 knockdown. Importantly, the in vivo experiments demonstrated that P4HA3 can promote subcutaneous tumorigenesis in nude mice and knockdown of P4HA3 induce a significant ihibitation of EMT and WNT/ß-catenin pathway detected by immunohistochemistry assay in tumor tissues. In summary, we demonstrated that P4HA3 is a promising diagnostic and therapeutic biomarker for HNSCC. As an oncogene, P4HA3 increases HNSCC proliferation by inducing the EMT and activating the WNT/ß-catenin signaling pathway.