A deep neural network predictor to predict the sensitivity of neoadjuvant chemoradiotherapy in locally advanced rectal cancer

Neoadjuvant chemoradiotherapy (NCRT) is widely used for locally advanced rectal cancer (LARC). This study aimed to conduct an effective model to predict NCRT sensitivity and provide guidance for clinical treatment. Biomarkers for NCRT sensitivity were identified by applying transcriptome profiles using logistic regression and subsequently screened out by Spearman correlation analysis and four machine learning algorithms. A deep neural network (DNN) predictor was constructed by using in-house dataset and validated in two independent datasets. Additionally, a web-based program was developed. Wnt/beta-catenin signaling and linoleic acid metabolism (LA) pathways were associated with NCRT sensitivity and prognosis in LARC, antagonistically. A DNN predictor with an 18-gene signature was conducted within in-house datasets. In two validation cohorts, area under ROC curve (AUC) achieved 0.706 and 0.897. The DNN subtypes were significantly associated with NCRT sensitivity, survival status et al. Moreover, NK and cytotoxic T cells were observed contribution to NCRT sensitivity while regulatory T, myeloid-derived suppressor cells and dysfunction of CD4 T effector memory cells could impede NCRT response. A DNN predictor could predict NCRT sensitivity in LARC and stratify LARC patients with different clinical and immunity characteristic.