Exploring useful prognostic markers and developing a robust prognostic model for patients with prostate cancer are crucial for clinical practice. We applied a deep learning algorithm to construct a prognostic model and proposed the deep learning-based ferroptosis score (DLF score ) for the prediction of prognosis and potential chemotherapy sensitivity in prostate cancer. Based on this prognostic model, there was a statistically significant difference in the disease-free survival probability between patients with high and low DLF score in the The Cancer Genome Atlas (TCGA) cohort ( P < 0.0001). In the validation cohort GSE116918, we also observed a consistent conclusion with the training set ( P = 0.02). Additionally, functional enrichment analysis showed that DNA repair, RNA splicing signaling, organelle assembly, and regulation of centrosome cycle pathways might regulate prostate cancer through ferroptosis. Meanwhile, the prognostic model we constructed also had application value in predicting drug sensitivity. We predicted some potential drugs for the treatment of prostate cancer through AutoDock, which could potentially be used for prostate cancer treatment.
Keyphrases
- prostate cancer
- deep learning
- radical prostatectomy
- dna repair
- cell death
- clinical practice
- machine learning
- free survival
- convolutional neural network
- artificial intelligence
- dna damage
- emergency department
- locally advanced
- squamous cell carcinoma
- wastewater treatment
- single cell
- genome wide
- risk assessment
- radiation therapy
- human health
- dna methylation
- rectal cancer
- adverse drug
- nucleic acid
- combination therapy
- data analysis
- childhood cancer