Purpose: The purpose of this study was to optimize a peptide (nABP284) that binds to programmed cell death protein 1 (PD-1) by a computer-based protocol in order to increase its affinity. Then, this study aimed to determine the inhibitory effects of this peptide on cancer immune escape by coculturing improving cytokine-induced killer (ICIK) cells with cancer cells. Materials and Methods: nABP284 that binds to PD-1 was identified by phage display technology in our previous study. AutoDock and PyMOL were used to optimize the sequence of nABP284 to design a new peptide (nABPD1). Immunofluorescence was used to demonstrate that the peptides bound to PD-1. Surface plasmon resonance was used to measure the binding affinity of the peptides. The blocking effect of the peptides on PD-1 was evaluated by a neutralization experiment with human recombinant programmed death-ligand 1 (PD-L1) protein. The inhibition of activated lymphocytes by cancer cells was simulated by coculturing of human acute T lymphocytic leukemia cells (Jurkat T cells) with human tongue squamous cell carcinoma cells (Cal27 cells). The anticancer activities were determined by coculturing ICIK cells with Cal27 cells in vitro. Results: A high-affinity peptide (nABPD1, KD=11.9 nM) for PD-1 was obtained by optimizing the nABP284 peptide (KD=11.8 μM). nABPD1 showed better efficacy than nABP284 in terms of increasing the secretion of interkeulin-2 by Jurkat T cells and enhancing the in vitro antitumor activity of ICIK cells. Conclusion nABPD1 possesses higher affinity for PD-1 than nABP284, which significantly enhances its ability to block the PD-1/PD-L1 interaction and to increase ICIK cell-mediated antitumor activity by armoring ICIK cells.

Objective:To construct a classification model for endoscopic ultrasonography (EUS) images of gastrointestinal stromal tumors (GISTs) and leiomyomas (LM) based on deep learning technology, and to verify its value for differential diagnosis.Methods:From October 2014 to October 2021, 69 patients of GISTs and 73 of LM who underwent EUS and were pathologically confirmed by surgery or endoscopic resection in the Second Affiliated Hospital of Soochow University were retrospectively studied. One clear EUS image with typical lesion was selected for each case. Using the hold-out method, the images of each disease were divided into the training set and the validation set according to the ratio of the number of images in the training set to the number of images in the validation set, which was 8∶2. Finally, 113 EUS images (55 GISTs and 58 LM) were used to form the training set, and 29 EUS images (14 GISTs and 15 LM) were used to form the validation set. The training set was used to train and optimize the deep learning model, and the validation set was used to verify the classification model. The main observation indicators included the sensitivity, the specificity, the positive predictive value, the negative predictive value and the accuracy of differential diagnosis.Results:The accuracy of the classification model established by Resnet 34 network structure in the differential diagnosis of GISTs and LM tended to be 0.89, better than the classification model established by Resnet 50 network structure (0.81). The sensitivity, the specificity, the positive predictive value, the negative predictive value and the accuracy of the classification model based on Resnet 34 network structure for differentiating EUS images in the validation set were 85.71% (12/14, 95% CI: 67.38%-100.00%), 93.33% (14/15, 95% CI: 80.71%-100.00%), 92.31% (12/13, 95% CI: 77.82%-100.00%), 87.50% (14/16, 95% CI: 71.30%-100.00%) and 89.66% (26/29, 95% CI: 78.57%-100.00%), respectively. Conclusion:It is feasible to use deep learning technology in the differential diagnosis of EUS images of GISTs and LM, which can provide auxiliary diagnostic opinions for clinicians. The deep learning model based on Resnet 34 network structure shows higher accuracy in the differential diagnosis of EUS images of GISTs and LM.