Search

Sea-land segmentation based on remote sensing images is one of the most important means to realize dynamic monitoring of coastal zones. However, the traditional models adopt the same design and simple stacking, resulting in equal attention to each region in scenarios mixing strong and weak boundaries, and even less attention to weak boundaries. In addition, due to the complexity of the ecological environment, there is a large intraclass gap and a small interclass gap in the weak boundary coastal zone. Based on the above problems, this article proposes a new semantic segmentation network based on remote sensing images: A2RDNet. By replacing standard convolution with cam-conv, this model integrates position information into channel attention, enhancing focus on weak boundary features. Furthermore, the resUNet-6 is proposed to recover substantial location information lost in the initial stages and provide deeper semantic information. Utilizing the DAC module inside the decoder to realize the pyramid structure of multiscale dense fusion enhances the semantic information while fusing the image detail features. A2RDNet was evaluated using a set of Landsat-8 remote sensing images, containing weak boundaries of different types and regions. The experimental results show that the MIoU, mPA, Accuracy, and F1_Score of the proposed method have reached 98.92, 99.46, 99.46, and 99.46, respectively, verifying the validity and feasibility of the proposed method. The A2RDNet model has higher segmentation accuracy compared to other methods.

The past few years have witnessed enormous progress toward applying machine learning approaches to the development of protein–ligand scoring functions. However, the robust performance and wide applicability of scoring functions remain a big challenge for increasing the success rate of docking-based virtual screening. Herein, a novel scoring function named RTMScore was developed by introducing a tailored residue-based graph representation strategy and several graph transformer layers for the learning of protein and ligand representations, followed by a mixture density network to obtain residue–atom distance likelihood potential. Our approach was resolutely validated on the CASF-2016 benchmark, and the results indicate that RTMScore can outperform almost all of the other state-of-the-art methods in terms of both the docking and screening powers. Further evaluation confirms the robustness of our approach that can not only retain its docking power on cross-docked poses but also achieve improved performance as a rescoring tool in larger-scale virtual screening.

Background and Objective: Colorectal cancer (CRC) is a common malignant tumor of the digestive system; it is associated with high morbidity and mortality. However, an early prediction of colorectal adenoma (CRA) that is a precancerous disease of most CRC patients provides an opportunity to make an appropriate strategy for prevention, early diagnosis and treatment. It has been aimed to develop a machine learning model to predict CRA that could assist physicians in classifying high-risk patients, make informed choices and prevent CRC. Methods: Patients who had undergone a colonoscopy to fill out a questionnaire at the Sixth People Hospital of Shanghai in China from July 2018 to November 2018 were instructed. A classification model with the gradient boosting decision tree (GBDT) was developed to predict CRA. This model was compared with three other models, namely, random forest (RF), support vector machine (SVM), and logistic regression (LR). The area under the receiver operating characteristic curve (AUC) was used to evaluate performance of the models. Results: Among the 245 included patients, 65 patients had CRA. The area under the receiver operating characteristic (AUCs) of GBDT, RF, SVM ,and LR with 10 fold-cross validation was 0.8131, 0.74, 0.769 and 0.763. An online prediction service, CRA Inference System, to substantialize the proposed solution for patients with CRA was also built. Conclusion: Four classification models for CRA prediction were developed and compared, and the GBDT model showed the highest performance. Implementing a GBDT model for screening can reduce the cost of time and money and help physicians identify high-risk groups for primary prevention.

A large number of protein–protein interactions (PPIs) are mediated by the interactions between proteins and peptide segments binding partners, and therefore determination of protein–peptide interactions (PpIs) is quite crucial to elucidate important biological processes and design peptides or peptidomimetic drugs that can modulate PPIs. Nowadays, as a powerful computation tool, molecular docking has been widely utilized to predict the binding structures of protein–peptide complexes. However, although a number of docking programs have been available, the systematic study on the assessment of their performance for PpIs has never been reported. In this study, a benchmark data set called PepSet consisting of 185 protein–peptide complexes with peptide length ranging from 5 to 20 residues was employed to evaluate the performance of 14 docking programs, including three protein–protein docking programs (ZDOCK, FRODOCK, and HawkDock), three small molecule docking programs (GOLD, Surflex-Dock, and AutoDock Vina), and eight protein–peptide docking programs (GalaxyPepDock, MDockPeP, HPEPDOCK, CABS-dock, pepATTRACT, DINC, AutoDock CrankPep (ADCP), and HADDOCK peptide docking). A new evaluation parameter, named IL_RMSD, was proposed to measure the docking accuracy with fnat(the fraction of native contacts). In global docking, HPEPDOCK performs the best for the entire data set and yields the success rates of 4.3%, 24.3%, and 55.7% at the top 1, 10, and 100 levels, respectively. In local docking, overall, ADCP achieves the best predictions and reaches the success rates of 11.9%, 37.3%, and 70.3% at the top 1, 10, and 100 levels, respectively. It is expected that our work can provide some helpful insights into the selection and development of improved docking programs for PpIs. The benchmark data set is freely available at http://cadd.zju.edu.cn/pepset/.

Two new 9,10-seco and etherified abietane-type diterpenoids were isolated from Callicarpa bodinieri, and their structure were elucidated by detailed spectrometry data analysis and DP4+ NMR calculation methods.

Fungal drug resistance is a major health threat, and reports of clinical resistance worldwide are becoming increasingly common. In a research program to discover new molecules to help overcome this problem, 14 new lanostane-type triterpenoids, gibbosicolids A–G (2–8) and gibbosic acids I–O (9–15), were isolated from the fruiting bodies of Ganoderma gibbosum, along with seven known triterpenoid derivatives. These compounds featured high levels of oxidation, epimerization, and γ-lactonization. Structures were elucidated by comprehensive spectroscopic analyses and HRMS data. Absolute configurations were assigned based on quantum chemical calculations, including calculated chemical shift with DP4+ analysis, coupling constants, and electronic circular dichroism (ECD) methods. Results show that the calculated NMR with DP4+ analysis could not reliably establish the overall spatial configuration of molecules possessing independent and free-rotational stereoclusters. All these compounds significantly increased the sensitivity of fluconazole (FLC)-resistant C. albicansto FLC. Compounds 2, 5, 9, 12, 16, 17, and 21exhibited strong antifungal activity against FLC-resistant C. albicanswhen combined with FLC, with MIC50values ranging from 3.8 to 8.8 μg/mL.

The study of multi-dimensional expansion of urban space (MEUS) addresses the laws of urban spatial expansion from all directions and angles. Using Nanjing as an example, this paper constructs multi-temporal, urban three-dimensional models based on RS and GIS technology and then conducts qualitative and quantitative analysis of MEUS using plot ratio change maps and MEUS quantitative index for built-up areas. Based especially on the concept of volume growth contribution rate, this paper analyzes the characteristics of MEUS in different stages. The results show that in 2000–2004, planar expansion played the main role, the internal potential development (IPD) intensity of the urban built-up areas was relatively large, and the volume growth contribution rate was low; in 2004–2008, planar expansion accelerated, and IPD slowed down; in 2008–2012, planar expansion slowed while IPD intensity increased; the contribution rates of volume growth of urban IPD for the three periods were 22.21%, 24.51% and 73.38%, respectively. This study expands the research perspective of urban spatial expansion, and the adopted methods are instructive and meaningful for MEUS research. In addition, the results of this study will deepen the understanding of MEUS laws and help improve scientific decision-making for urban planning and urban land use management.

In this paper, the artificial neural network (ANN) model was used to evaluate the degree of intensive urban land use in Nanjing City, China. The construction and application of the ANN model took into account the comprehensive, spatial and complex nature of urban land use. Through a preliminary calculation of the degree of intensive land use of the sample area, representative sample area selection and using the back propagation neural network model to train, the intensive land use level of each evaluation unit is finally determined in the study area. Results show that the method can effectively correct the errors caused by the limitations of the model itself and the determination of the ideal value and weights when the multifactor comprehensive evaluation is used alone. The ANN model can make the evaluation results more objective and practical. The evaluation results show a tendency of decreasing land use intensity from the core urban area to the periphery and the industrial functional area has relatively low land use intensity compared with other functional areas. Based on the evaluation results, some suggestions are put forward, such as transforming the mode of urban spatial expansion, strengthening the integration and potential exploitation of the land in the urban built-up area, and strengthening the control of the construction intensity of protected areas.

Accurate estimation of the synthetic accessibility of small molecules is needed in many phases of drug discovery. Several expert-crafted scoring methods and descriptor-based quantitative structure–activity relationship (QSAR) models have been developed for synthetic accessibility assessment, but their practical applications in drug discovery are still quite limited because of relatively low prediction accuracy and poor model interpretability. In this study, we proposed a data-driven interpretable prediction framework called GASA (Graph Attention-based assessment of Synthetic Accessibility) to evaluate the synthetic accessibility of small molecules by distinguishing compounds to be easy- (ES) or hard-to-synthesize (HS). GASA is a graph neural network (GNN) architecture that makes self-feature deduction by applying an attention mechanism to automatically capture the most important structural features related to synthetic accessibility. The sampling around the hypothetical classification boundary was used to improve the ability of GASA to distinguish structurally similar molecules. GASA was extensively evaluated and compared with two descriptor-based machine learning methods (random forest, RF; eXtreme gradient boosting, XGBoost) and four existing scores (SYBA: SYnthetic Bayesian Accessibility; SCScore: Synthetic Complexity score; RAscore: Retrosynthetic Accessibility score; SAscore: Synthetic Accessibility score). Our analysis demonstrates that GASA achieved remarkable performance in distinguishing similar molecules compared with other methods and had a broader applicability domain. In addition, we show how GASA learns the important features that affect molecular synthetic accessibility by assigning attention weights to different atoms. An online prediction service for GASA was offered at http://cadd.zju.edu.cn/gasa/.

A new convenient method is reported for the synthesis of the phenyl‐capped pentamer and hexamer of aniline. The method was accomplished by the reaction of the parent aniline tetramer in the pernigraniline oxidation state with diphenylamine and N‐phenyl‐1,4‐phenylenediamine in the leucoemeraldine oxidation state, respectively. The mechanism probably involves the formation of cation radicals and their coupling.

Monodispersed phenyl‐capped trianiline and tetraaniline were successfully synthesized by the reactions of diphenylamine with acetaldehyde‐based Schiff's bases of N‐phenyl‐1,4‐phenylenediamine and 1,4‐phenylenediamine, respectively, in the presence of ammonium persulfate and hydrochloric acid, subsequent deprotonation and reduction with phenylhydrazine. The reaction mechanism probably involves the slow hydrolysis of the Schiff's bases and subsequent oxidative coupling reactions of the formed ammonium salts with diphenylamine at pseudo‐high dilution condition of the salts.

Four new compounds, a dibenzylbutane lignin, plasiaticine F (1), an acetylenic glycoside, plasiaticine G (2), an indole alkaloid, plasiaticine H (3), and an ionone derivative, plasiaticine I (4), were isolated from the seeds of Plantago asiatica. The structures of the new compounds were elucidated on the basis of comprehensive analysis of spectroscopic data. Compounds 1–3were tested for their cytotoxicity, but lacked significant activity.