Discovery of the covalent SARS-CoV-2 Mpro inhibitors from antiviral herbs via integrating target-based high-throughput screening and chemoproteomic approaches.

The main proteases (Mpro ) are highly conserved cysteine-rich proteins that can be covalently modified by numerous natural and synthetic compounds. Herein, we constructed an integrative approach to efficiently discover covalent inhibitors of Mpro from complex herbal matrices. This work begins with biological screening of 60 clinically used antiviral herbal medicines, among which Lonicera japonica Flos (LJF) demonstrated the strongest anti-Mpro effect (IC50 = 37.82 µg/mL). Mass spectrometry (MS)-based chemical analysis and chemoproteomic profiling revealed that LJF extract contains at least 50 constituents, of which 22 exhibited the capability to covalently modify Mpro . We subsequently verified the anti-Mpro effects of these covalent binders. Gallic acid and quercetin were found to potently inhibit severe acute respiratory syndrome coronavirus 2 Mpro in dose- and time- dependent manners, with the IC50 values below 10 µM. The inactivation kinetics, binding affinity and binding mode of gallic acid and quercetin were further characterized by fluorescence resonance energy transfer, surface plasmon resonance, and covalent docking simulations. Overall, this study established a practical approach for efficiently discovering the covalent inhibitors of Mpro from herbal medicines by integrating target-based high-throughput screening and MS-based assays, which would greatly facilitate the discovery of key antiviral constituents from medicinal plants.

Anatomical Partition-Based Deep Learning: An Automatic Nasopharyngeal MRI Recognition Scheme.

BACKGROUND: Training deep learning (DL) models to automatically recognize diseases in nasopharyngeal MRI is a challenging task, and optimizing the performance of DL models is difficult. PURPOSE: To develop a method of training anatomical partition-based DL model which integrates knowledge of clinical anatomical regions in otorhinolaryngology to automatically recognize diseases in nasopharyngeal MRI. STUDY TYPE: Single-center retrospective study. POPULATION: A total of 2485 patients with nasopharyngeal diseases (age range 14-82 years, female, 779[31.3%]) and 600 people with normal nasopharynx (age range 18-78 years, female, 281[46.8%]) were included. SEQUENCE: 3.0 T; T2WI fast spin-echo sequence. ASSESSMENT: Full images (512 × 512) of 3085 patients constituted 100% of the dataset, 50% and 25% of which were randomly retained as two new datasets. Two new series of images (seg112 image [112 × 112] and seg224 image [224 × 224]) were automatically generated by a segmentation model. Four pretrained neural networks for nasopharyngeal diseases classification were trained under the nine datasets (full image, seg112 image, and seg224 image, each with 100% dataset, 50% dataset, and 25% dataset). STATISTICAL TESTS: The receiver operating characteristic curve was used to evaluate the performance of the models. Analysis of variance was used to compare the performance of the models built with different datasets. Statistical significance was set at P < 0.05. RESULTS: When the 100% dataset was used for training, the performances of the models trained with the seg112 images (average area under the curve [aAUC] 0.949 ± 0.052), seg224 images (aAUC 0.948 ± 0.053), and full images (aAUC 0.935 ± 0.053) were similar (P = 0.611). When the 25% dataset was used for training, the mean aAUC of the models that were trained with seg112 images (0.823 ± 0.116) and seg224 images (0.765 ± 0.155) was significantly higher than the models that were trained with full images (0.640 ± 0.154). DATA CONCLUSION: The proposed method can potentially improve the performance of the DL model for automatic recognition of diseases in nasopharyngeal MRI. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 1.

Predicting prognosis of nasopharyngeal carcinoma based on deep learning: peritumoral region should be valued.

BACKGROUND: The purpose of this study was to explore whether incorporating the peritumoral region to train deep neural networks could improve the performance of the models for predicting the prognosis of NPC. METHODS: A total of 381 NPC patients who were divided into high- and low-risk groups according to progression-free survival were retrospectively included. Deeplab v3 and U-Net were trained to build segmentation models for the automatic segmentation of the tumor and suspicious lymph nodes. Five datasets were constructed by expanding 5, 10, 20, 40, and 60 pixels outward from the edge of the automatically segmented region. Inception-Resnet-V2, ECA-ResNet50t, EfficientNet-B3, and EfficientNet-B0 were trained with the original, segmented, and the five new constructed datasets to establish the classification models. The receiver operating characteristic curve was used to evaluate the performance of each model. RESULTS: The Dice coefficients of Deeplab v3 and U-Net were 0.741(95%CI:0.722-0.760) and 0.737(95%CI:0.720-0.754), respectively. The average areas under the curve (aAUCs) of deep learning models for classification trained with the original and segmented images and with images expanded by 5, 10, 20, 40, and 60 pixels were 0.717 ± 0.043, 0.739 ± 0.016, 0.760 ± 0.010, 0.768 ± 0.018, 0.802 ± 0.013, 0.782 ± 0.039, and 0.753 ± 0.014, respectively. The models trained with the images expanded by 20 pixels obtained the best performance. CONCLUSIONS: The peritumoral region NPC contains information related to prognosis, and the incorporation of this region could improve the performance of deep learning models for prognosis prediction.

Feasibility of anterior lobe-preserving transurethral enucleation and resection of prostate on improving urinary incontinence in patients with benign prostatic hyperplasia: A retrospective cohort study.

Transurethral enucleation and resection of prostate (TUERP), as one of the conventional surgical methods for patients with benign prostatic hyperplasia (BPH), usually resulted in pseudo urinary incontinence after surgery. The present study was thereby conducted to evaluate the feasibility of anterior lobe-preserving transurethral enucleation and resection of prostate (ALP-TUERP) on reducing the incidence rate of urinary incontinence after surgery in patients with BPH. Patients diagnosed with BPH underwent surgical treatment were enrolled in the present study within the inclusion criteria. Characteristics including age, prostate volume (before surgery), PSA level, maximum free flow rate, international prostate symptom score, and quality of life were reviewed and compared between the groups of ALP-TUERP and TUERP. Incidence rate of urinary incontinence on 24 hours, 3 days, 7 days, and 14 days after catheter drawing was deemed as main outcome, which was compared between the groups. In addition, secondary outcomes including surgery time, difference value of hemoglobin before and after surgery (∆Hemoglobin), catheter retaining time, catheter flushing time, and incidence rate of recurrent bleeding were also compared between the groups. There were 81 patients included in the present study within the inclusion criteria. There was no statistical difference on the baseline characteristics including age, prostate volume (before surgery), PSA level, maximum free flow rate (before surgery), international prostate symptom score, or quality of life between the 2 groups. Statistical superiority was observed on the incidence rate of urinary incontinence on day 1 (χ2 = 9.375, P = .002), and day 3 (χ2 = 4.046, P = .044) in the group ALP-TUERP, when comparing to group TUERP. However, the difference was not observed anymore after 7 days after catheter drawing (P = .241 for day 7, P = .494 for day 14) between them. In addition, no statistical differences were observed on surgery time, difference value of hemoglobin before and after surgery (∆Hemoglobin), catheter retaining time, or catheter flushing time between the group ALP-TUERP and TUERP (all P > .05). Results of the present study demonstrated a potentially statistical superiority of ALP-TUERP on the reduction of incidence rate of urinary incontinence comparing to conventionally TUERP.

Deep learning for locally advanced nasopharyngeal carcinoma prognostication based on pre- and post-treatment MRI.

PURPOSE: We aimed to predict the prognosis of advanced nasopharyngeal carcinoma (stage Ⅲ-Ⅳa) using Pre- and Post-treatment MR images based on deep learning (DL). METHODS: A total of 206 patients with primary nasopharyngeal carcinoma who were diagnosed and treated at the Renmin Hospital of Wuhan University between June 2012 and January 2018 were retrospectively selected. A rectangular region of interest (ROI), which included the tumor area, surrounding tissues and organs, was delineated on each Pre- and Post-treatment MR image. Two Inception-Resnet-V2 based transfer learning models, named Pre-model and Post-model, were trained with the Pre-treatment images and the Post-treatment images, respectively. In addition, an ensemble learning model based on the Pre-model and Post-models was established. The three established models were evaluated by receiver operating characteristic curve (ROC), confusion matrix, and Harrell's concordance indices (C-index). High-risk-related gradient-weighted class activation mapping (Grad-CAM) images were developed according to the DL models. RESULTS: The Pre-model, Post-model, and ensemble model displayed a C-index of 0.717 (95% CI: 0.639 to 0.795), 0.811 (95% CI: 0.745-0.877), 0.830 (95% CI: 0.767-0.893), and AUC of 0.741 (95% CI: 0.584-0.900), 0.806 (95% CI: 0.670-0.942), and 0.842 (95% CI: 0.718-0.967) for the test cohort, respectively. In comparison with the models, the performance of Post-model was better than the performance of Pre-model, which indicated the importance of Post-treatment images for prognosis prediction. All three DL models performed better than the TNM staging system (0.723, 95% CI: 0.567-0.879). The captured features presented on Grad-CAM images suggested that the areas around the tumor and lymph nodes were related to the prognosis of the tumor. CONCLUSIONS: The three established DL models based on Pre- and Post-treatment MR images have a better performance than TNM staging. Post-treatment MR images are of great significance for prognosis prediction and could contribute to clinical decision-making.

[Dynamics of unprotected soil organic carbon with the restoration process of Pinus massoniana plantation in red soil erosion area].

By the method of spatiotemporal substitution and taking the bare land and secondary forest as the control, we measured light fraction and particulate organic carbon in the topsoil under the Pinus massoniana woodlands of different ages with similar management histories in a red soil erosion area, to determine their dynamics and evaluate the conversion processes from unprotected to protected organic carbon. The results showed that the content and storage of soil organic carbon increased significantly along with ages in the process of vegetation restoration (P < 0.01). The unprotected soil organic carbon content and distribution proportion to the total soil organic carbon increased significantly (P < 0.05) after 7-11 years' restoration but stabilized after 27 and 30 years of restoration. It suggested that soil organic carbon mostly accumulated in the form of unprotected soil organic carbon during the initial restoration period, and reached a stable level after long-term vegetation restoration. Positive correlations were found between restoration years and the rate constant for C transferring from the unprotected to the protected soil pool (k) in 0-10 cm and 10-20 cm soil layers, which demonstrated that the unprotected soil organic carbon gradually transferred to the protected soil organic carbon in the process of vegetation restoration.