Explore the vast range of titles available.

Molecular machine learning bears promise for efficient molecular property prediction and drug discovery. However, labelled molecule data can be expensive and time consuming to acquire. Due to the limited labelled data, it is a great challenge for supervised-learning machine learning models to generalize to the giant chemical space. Here we present MolCLR (Molecular Contrastive Learning of Representations via Graph Neural Networks), a self-supervised learning framework that leverages large unlabelled data (~10 million unique molecules). In MolCLR pre-training, we build molecule graphs and develop graph-neural-network encoders to learn differentiable representations. Three molecule graph augmentations are proposed: atom masking, bond deletion and subgraph removal. A contrastive estimator maximizes the agreement of augmentations from the same molecule while minimizing the agreement of different molecules. Experiments show that our contrastive learning framework significantly improves the performance of graph-neural-network encoders on various molecular property benchmarks including both classification and regression tasks. Benefiting from pre-training on the large unlabelled database, MolCLR even achieves state of the art on several challenging benchmarks after fine-tuning. In addition, further investigations demonstrate that MolCLR learns to embed molecules into representations that can distinguish chemically reasonable molecular similarities. Molecular representations are hard to design due to the large size of the chemical space, the amount of potentially important information in a molecular structure and the relatively low number of annotated molecules. Still, the quality of these representations is vital for computational models trying to predict molecular properties. Wang et al. present a contrastive learning approach to provide differentiable representations from unlabelled data.

The global incidence of infertility is increasing year by year, and the association between infertility and mental illness has been widely concerned. The aim of this study was to investigate the incidence of anxiety and depression in infertile women in China and explore the risk factors which might lead to anxiety and depression. From January 2020 to December 2020, female infertile patients who received assisted reproduction technology (ART) treatment at West China Second Hospital were recruited and a total of 1712 eligible female patients were finally enrolled in this study. Generalized Anxiety Disorder-7 (GAD-7) and Patient Health Questionaire-9 (PHQ-9) were used to evaluate the patients’ psychological status. The reliability of all scales was evaluated by Cronbach’s α and Spearman-Brown half coefficient, and Kaiser-Meyer-Olkin (KMO) value was calculated by factor analysis to evaluate validity. Univariate and multivariate logistic regression analysis were applied for assessing independent risk factors of anxiety and depression, respectively. The incidence of anxiety and depression in infertile women were 25.2% and 31.3%, respectively. Cronbach’s α coefficients and Spearman-Brown half-fold coefficients of GAD-7 and PHQ-9 were 0.870, 0.825, 0.852 and 0.793, respectively. Univariate and multivariate logistic regression analysis showed that education level (junior college degree or above, OR:1. 6, 95% CI: 1.2–2.1, P = 0.003), somatic symptoms (severe somatic symptoms, OR:15.2, 95%CI: 5.6–41.3, P<0.001), sleep quality (poor sleep quality, OR:9.3, 95% CI:4.7–18.4, P<0.001) were independent risk factors for anxiety. And age>35 years old, moderate and severe somatic symptoms and poor sleep quality were independent risk factors for depression. Somatic symptoms and poor sleep quality are both the risk factors of anxiety and depression symptoms of infertile woman. And high educated (junior college degree or above) patients are more likely to be complicated with anxiety symptoms, while elderly patients (age>35) are prone to be complicated with depression symptoms.

Bistable display has been a long-awaited goal due to its zero energy cost when maintaining colored or colorless state and electrochromic material has been highly considered as a potential way to achieve bistable display due to its simple structure and possible manipulation. However, it is extremely challenging with insurmountable technical barriers related to traditional electrochromic mechanisms. Herein a prototype for bistable electronic billboard and reader with high energy efficiency is demonstrated with excellent bistability (decay 7% in an hour), reversibility (10 4 cycles), coloration efficiency (430 cm 2  C −1 ) and very short voltage stimulation time (2 ms) for color switching, which greatly outperforms current products. This is achieved by stabilization of redox molecule via intermolecular ion transfer to the supramolecular bonded colorant and further stabilization of the electrochromic molecules in semi-solid media. This promising approach for ultra-energy-efficient display will promote the development of switching molecules, devices and applications in various fields of driving/navigation/industry as display to save energy. For electrochromic materials to reach their full potential for high efficiency bistable displays, technical challenges related to their underlying mechanism must be addressed. Here, the authors, through intelligent molecular design, report a solid bistable device with state-of-the-art performance.

Accurate and efficient prediction of polymer properties is of great significance in polymer design. Conventionally, expensive and time-consuming experiments or simulations are required to evaluate polymer functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance in natural language processing. However, such methods have not been investigated in polymer sciences. Herein, we report TransPolymer, a Transformer-based language model for polymer property prediction. Our proposed polymer tokenizer with chemical awareness enables learning representations from polymer sequences. Rigorous experiments on ten polymer property prediction benchmarks demonstrate the superior performance of TransPolymer. Moreover, we show that TransPolymer benefits from pretraining on large unlabeled dataset via Masked Language Modeling. Experimental results further manifest the important role of self-attention in modeling polymer sequences. We highlight this model as a promising computational tool for promoting rational polymer design and understanding structure-property relationships from a data science view.

Diabetic nephropathy (DN) often leads to end-stage renal disease. Oxidative stress demonstrates a crucial act in the onset and progression of DN, which triggers various pathological processes while promoting the activation of inflammation and forming a vicious oxidative stress-inflammation cycle that induces podocyte injury, extracellular matrix accumulation, glomerulosclerosis, epithelial-mesenchymal transition, renal tubular atrophy, and proteinuria. Conventional treatments for DN have limited efficacy. Polyphenols, as antioxidants, are widely used in DN with multiple targets and fewer adverse effects. This review reveals the oxidative stress and oxidative stress-associated inflammation in DN that led to pathological damage to renal cells, including podocytes, endothelial cells, mesangial cells, and renal tubular epithelial cells. It demonstrates the potent antioxidant and anti-inflammatory properties by targeting Nrf2, SIRT1, HMGB1, NF-κB, and NLRP3 of polyphenols, including quercetin, resveratrol, curcumin, and phenolic acid. However, there remains a long way to a comprehensive understanding of molecular mechanisms and applications for the clinical therapy of polyphenols.

Two-dimensional nanomaterials, such as graphene, have been extensively studied because of their outstanding physical properties. Structure and topology of nanopores on such materials can be important for their performances in real-world engineering applications, like water desalination. However, discovering the most efficient nanopores often involves a very large number of experiments or simulations that are expensive and time-consuming. In this work, we propose a data-driven artificial intelligence (AI) framework for discovering the most efficient graphene nanopore for water desalination. Via a combination of deep reinforcement learning (DRL) and convolutional neural network (CNN), we are able to rapidly create and screen thousands of graphene nanopores and select the most energy-efficient ones. Molecular dynamics (MD) simulations on promising AI-created graphene nanopores show that they have higher water flux while maintaining rival ion rejection rate compared to the normal circular nanopores. Irregular shape with rough edges geometry of AI-created pores is found to be the key factor for their high water desalination performance. Ultimately, this study shows that AI can be a powerful tool for nanomaterial design and screening.

Given the growing emphasis on energy efficiency, environmental sustainability, and agricultural demand, there’s a pressing need for decentralized and scalable ammonia production. Converting nitrate ions electrochemically, which are commonly found in industrial wastewater and polluted groundwater, into ammonia offers a viable approach for both wastewater treatment and ammonia production yet limited by low producibility and scalability. Here we report a versatile and scalable solution-phase synthesis of high-entropy single-atom nanocages (HESA NCs) in which Fe and other five metals-Co, Cu, Zn, Cd, and In-are isolated via cyano-bridges and coordinated with C and N, respectively. Incorporating and isolating the five metals into the matrix of Fe resulted in Fe-C 5 active sites with a minimized symmetry of lattice as well as facilitated water dissociation and thus hydrogenation process. As a result, the Fe-HESA NCs exhibited a high selectivity toward NH 3 from the electrocatalytic reduction of nitrate with a Faradaic efficiency of 93.4% while maintaining a high yield rate of 81.4 mg h −1 mg −1 . Converting nitrate from waste sources into ammonia provides an effective method for both wastewater treatment and ammonia production. Here the authors report a scalable solution-phase synthesis of high-entropy single-atom nanocage catalysts for efficient nitrate-to-ammonia conversion.

Extreme precipitation events affect the ecological environment and are also important for the sustainable development of regional socioeconomics. Although there are some local studies on extreme precipitation events in which the temporal and spatial variation characteristics of extreme precipitation events in non-monsoon regions (NMRs) are systematically assessed, detailed study on the driving mechanisms of variation are becoming increasingly important. In this study, nine extreme precipitation indices were used to analyze the characteristics of extreme precipitation event spatiotemporal variations in NMRs in China during 1961-2017. The results show that except for the consecutive dry days, which shows a significant decreasing trend (P < 0.01) of −2.33 days/decade, all other indices showed obvious increasing trends, especially the indices of wet day precipitation (PRCPTOT), highest 5 day precipitation (RX5day) and light rain days (R5 mm), with significantly increasing trends (P < 0.01) of 6.80 mm/decade, 0.73 mm/decade and 0.45 days/decade, respectively. In addition, a correlation analysis between altitude, longitude, latitude and extreme precipitation shows that stations at an altitude of more than 3500 m have significant correlations with both extreme precipitation and longitude in NMRs (P < 0.05). In addition, results also indicated that there are significant relationships between extreme precipitation events in NMRs and large-scale ocean-atmosphere circulation patterns (P < 0.05). The rapid increase in extreme precipitation indices over the past 20 years is closely related to the Atlantic Multidecadal Oscillation shift to a warm phase, while the Pacific Decadal Oscillation, El Niño-Southern Oscillation and Summer Monsoon Index show significant correlation with the extreme indices only in certain seasons (P < 0.05).

Due to the functional limitations of a single UAV, UAV clusters have become an important part of smart cities, and the relative positioning between UAVs is the core difficulty in UAV cluster applications. Existing UAVs can be equipped with satellite navigation, radio navigation, and other positioning equipment, but in complex environments, such as urban canyons, various navigation sources cannot achieve full positioning information due to occlusion, interference, and other factors, and existing positioning fusion methods cannot meet the requirements of these environments. Therefore, demand exists for the real-time positioning of UAV clusters. Aiming to solve the above problems, this paper proposes multisource fusion UAV cluster cooperative positioning using information geometry (UCP-IG), which converts various types of navigation source information into information geometric probability models and reduces the impact of accidental errors, and proposes the Kullback–Leibler divergence minimization (KLM) fusion method to achieve rapid fusion on geometric manifolds and creatively solve the problem of difficult fusion caused by different positioning information formats and parameters. The method proposed in this paper is compared with the main synergistic methods, such as LS and neural networks, in an ideal scenario, a mutation error scenario, and a random motion scenario. The simulation results show that by using UAV cluster movement, the method proposed in this paper can effectively suppress mutation errors and achieve fast positioning.

Summary The flag leaf and grain belong to the source and sink, respectively, of cereals, and both have a bearing on final yield. Premature leaf senescence significantly reduces the photosynthetic rate and severely lowers crop yield. Cytokinins play important roles in leaf senescence and determine grain number. Here, we characterized the roles of the rice (Oryza sativa L.) cytokinin oxidase/dehydrogenase OsCKX11 in delaying leaf senescence, increasing grain number, and coordinately regulating source and sink. OsCKX11 was predominantly expressed in the roots, leaves, and panicles and was strongly induced by abscisic acid and leaf senescence. Recombinant OsCKX11 protein catalysed the degradation of various types of cytokinins but showed preference for trans‐zeatin and cis‐zeatin. Cytokinin levels were significantly increased in the flag leaves of osckx11 mutant compared to those of the wild type (WT). In the osckx11 mutant, the ABA‐biosynthesizing genes were down‐regulated and the ABA‐degrading genes were up‐regulated, thereby reducing the ABA levels relative to the WT. Thus, OsCKX11 functions antagonistically between cytokinins and ABA in leaf senescence. Moreover, osckx11 presented with significantly increased branch, tiller, and grain number compared with the WT. Collectively, our findings reveal that OsCKX11 simultaneously regulates photosynthesis and grain number, which may provide new insights into leaf senescence and crop molecular breeding.