Vehicle exhaust seriously pollutes urban air and harms human health. Photocatalytic technology can effectively degrade automobile exhaust. This work prepared g-C3N4/CeO2 photocatalytic material by constructing heterojunctions. Four kinds of g-C3N4/CeO2 composite photocatalytic materials with different mass ratios were prepared. An indoor exhaust gas purification test was carried out under natural light and ultraviolet light irradiations. The optimum mass ratio of g-C3N4 material and CeO2 material was determined by evaluating the exhaust gas degradation effective. Moreover, the structure and morphology of the g-C3N4/CeO2 composite were investigated with microscopic characterization experiments (including XRD, TG-DSC, FT-IR, UV-Vis, SEM and XPS). The results obtained were that the optimum mass ratio of g-C3N4 material to CeO2 material was 0.75. The degradation efficiencies under ultraviolet irradiation in 60 min for HC, CO, CO2, NOX were 7.59%, 12.10%, 8.25% and 36.82%, respectively. Under visible light conditions, the degradation efficiency in 60 min for HC, CO, CO2 and NOX were 15.88%, 16.22%, 10.45% and 40.58%, respectively. This work is useful for purifying automobile exhaust in the future.

Different biomarkers based on genomics variants have been used to predict the response of patients treated with PD-1/programmed death receptor 1 ligand (PD-L1) blockade. We aimed to use deep-learning algorithm to estimate clinical benefit in patients with non-small-cell lung cancer (NSCLC) before immunotherapy. Peripheral blood samples or tumor tissues of 915 patients from three independent centers were profiled by whole-exome sequencing or next-generation sequencing. Based on convolutional neural network (CNN) and three conventional machine learning (cML) methods, we used multi-panels to train the models for predicting the durable clinical benefit (DCB) and combined them to develop a nomogram model for predicting prognosis. In the three cohorts, the CNN achieved the highest area under the curve of predicting DCB among cML, PD-L1 expression, and tumor mutational burden (area under the curve [AUC] = 0.965, 95% confidence interval [CI]: 0.949–0.978, P< 0.001; AUC =0.965, 95% CI: 0.940–0.989, P< 0.001; AUC = 0.959, 95% CI: 0.942–0.976, P< 0.001, respectively). Patients with CNN-high had longer progression-free survival (PFS) and overall survival (OS) than patients with CNN-low in the three cohorts. Subgroup analysis confirmed the efficient predictive ability of CNN. Combining three cML methods (CNN, SVM, and RF) yielded a robust comprehensive nomogram for predicting PFS and OS in the three cohorts (each P< 0.001). The proposed deep-learning method based on mutational genes revealed the potential value of clinical benefit prediction in patients with NSCLC and provides novel insights for combined machine learning in PD-1/PD-L1 blockade.

No abstract

No abstract