Multi-level Regulatory Roles of Lactate Metabolism Gene Network in Oral Cancer: Machine Learning Insights
Liu, Z.; shen, X.
Show abstract
This study explores the multi-level regulatory roles of the lactate metabolism gene network in oral cancer development using machine learning models. Machine learning analysis shows that lactate-related gene expression profiles can effectively distinguish treatment groups from controls (AUC=0.933), with SLC16A1 and KIF2C being key features. Genes like PFKP, LDHA, LDHB, LDHC, and VCAN are highlighted for their biological relevance. PFKP, involved in glycolytic metabolic regulation, is significantly upregulated in oral cancer patients, suggesting its role in tumor metabolic adaptation. VCAN, ranking sixth in feature importance, is associated with increased disease risk and may become a therapeutic target. EP300 exhibits a complex relationship with oral cancer, potentially acting as a tumor suppressor. Enrichment analysis links these genes to the HIF-1 signaling pathway and metabolic reprogramming. These findings advance the understanding of lactate metabolisms role in oral cancer and identify potential therapeutic targets.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- CD8+ tissue-resident memory T cells triggered the erosion of oral lichen planus by the cytokine network 94%
- PA28γ promotes the malignant progression of tumor by elevating mitochondrial function via C1QBP 93%
- A multi-gene predictive model for the radiation sensitivity of nasopharyngeal carcinoma based on machine learning 92%
Similar papers in this journal
- Impact of Salivary and Pancreatic Amylase Gene Copy Numbers on Diabetes, Obesity, and Functional Profiles of Microbiome in Northern Japanese Population 93%
- Development of a potential salivary biomarker panel for Oral Squamous Cell Carcinoma. 93%
- Multi-omic signatures identify pan-cancer classes of tumors beyond tissue of origin. 93%
Similar papers in this journal
Similar papers in this journal
- Dissected subgroups predict the risk of recurrence of stage II colorectal cancer and select rational treatment 91%
- Significant and conflicting correlation of IL-9 with Prevotella and Bacteroides in human colorectal cancer 91%
- Proteomic and metabolomic signatures associated with the immune response in healthy individuals immunized with an inactivated SARS-CoV-2 vaccine 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.