GCNCPR-ACPs: a novel graph convolution network method for ACPs prediction.

BACKGROUND: Anticancer peptide (ACP) inhibits and kills tumor cells. Research on ACP is of great significance for the development of new drugs, and the prediction of ACPs and non-ACPs is the new hotspot. RESULTS: We propose a new machine learning-based method named GCNCPR-ACPs (a Graph Convolutional Neural Network Method based on collapse pooling and residual network to predict the ACPs), which automatically and accurately predicts ACPs using residual graph convolution networks, differentiable graph pooling, and features extracted using peptide sequence information extraction. The GCNCPR-ACPs method can effectively capture different levels of node attributes for amino acid node representation learning, GCNCPR-ACPs uses node2vec and one-hot embedding methods to extract initial amino acid features for ACP prediction. CONCLUSIONS: Experimental results of ten-fold cross-validation and independent validation based on different metrics showed that GCNCPR-ACPs significantly outperformed state-of-the-art methods. Specifically, the evaluation indicators of Matthews Correlation Coefficient (MCC) and AUC of our predicator were 69.5% and 90%, respectively, which were 4.3% and 2% higher than those of the other predictors, respectively, in ten-fold cross-validation. And in the independent test, the scores of MCC and SP were 69.6% and 93.9%, respectively, which were 37.6% and 5.5% higher than those of the other predictors, respectively. The overall results showed that the GCNCPR-ACPs method proposed in the current paper can effectively predict ACPs.

NeuRank: learning to rank with neural networks for drug-target interaction prediction.

BACKGROUND: Experimental verification of a drug discovery process is expensive and time-consuming. Therefore, recently, the demand to more efficiently and effectively identify drug-target interactions (DTIs) has intensified. RESULTS: We treat the prediction of DTIs as a ranking problem and propose a neural network architecture, NeuRank, to address it. Also, we assume that similar drug compounds are likely to interact with similar target proteins. Thus, in our model, we add drug and target similarities, which are very effective at improving the prediction of DTIs. Then, we develop NeuRank from a point-wise to a pair-wise, and further to list-wise model. CONCLUSION: Finally, results from extensive experiments on five public data sets (DrugBank, Enzymes, Ion Channels, G-Protein-Coupled Receptors, and Nuclear Receptors) show that, in identifying DTIs, our models achieve better performance than other state-of-the-art methods.

Bioinspired Fast Room-Temperature Self-Healing, Robust, Adhesive, and AIE Fluorescent Waterborne Polyurethane via Hierarchical Hydrogen Bonds and Use as a Strain Sensor.

Developing a new generation of ecofriendly water-based polymeric materials that integrate mechanical robustness, fast room-temperature self-healing, adhesive, and fluorescence remains a formidable challenge. Herein, inspired by titin protein, a series of novel waterborne polyurethanes (WPU-CHZ-NAGA) containing irregular 6-fold and diamide hydrogen bonds are synthesized by introducing carbohydrazide (CHZ) and N,N-bis(2-hydroxyethyl)-3-amino propionyl glycinamide (HO-NAGA-OH) groups. The representative WPU-CHZ2-NAGA3 exhibits outstanding mechanical properties (tensile strength of 36.58 MPa, tearing energy of 81.2 kJ m-2, and toughness of 125.82 MJ m-3) and fast room-temperature self-healing ability with the aid of ethanol (≥90% within 8 h) originated from hierarchical hydrogen bonds. These properties are superior to those of most of the reported room-temperature self-healing polymer materials. Benefiting from plentiful hydrogen bonds, the WPU matrix achieves excellent adhesive properties without heating or adding curing agents. Interestingly, WPU-CHZ2-NAGA3 film emits inherent blue fluorescence due to the aggregation-induced emission effect of tertiary amine groups, and its potential applications in information encryption and anticounterfeiting are further demonstrated. Specially, a eutectic gel strain sensor is also fabricated with WPU-CHZ2-NAGA3 and deep eutectic solvent by a simple physical blending method, which can be used to monitor the movement of human fingers and wrists as well as the change in body temperature. In summary, this work provides new insight into the design and synthesis of multifunctional WPU with fast room-temperature self-healing and high mechanical properties.

Flame-Retardant and Self-Healing Waterborne Polyurethane Based on Organic Selenium.

Waterborne polyurethane has drawn extensive attention due to its environmental friendliness and is widely used in many areas. However, it is still a great challenge to synthesize waterborne polyurethanes with flame retardancy and fast room-temperature self-healing ability, along with excellent mechanical performance and emulsion stability due to the mutually contradictory nature of these properties. Herein, waterborne polyurethanes containing organic selenium (SWPU-x) from 0.67 to 3.28 wt % were synthesized, which could simultaneously realize flame retardancy and self-healing ability based on the ability to scavenge active free radicals at high temperature and the dynamic switch of diselenide. All these SWPU-x films self-extinguished within 1 s after the ignition in the vertical combustion tests. The limiting oxygen index of SWPU-4 was improved to 28.5% with excellent UL-94 level (V-0) and self-healing efficiency (91.25%, after being healed in the photoreactor for 30 min at room temperature), together with high mechanical properties (tensile strength was 18.5 MPa and elongation at break was 869.63%), and the total heat release (THR) for SWPU-4 (49.28 MJ/m2) could decrease to 23.80% of the THR for the original waterborne polyurethane WPU (64.67 MJ/m2). This work discovered a new flame-retardant element (organic selenium) and studied its flame-retardant behaviors and self-healing function simultaneously, which would extremely extend the application of waterborne polyurethanes.

A Survey on Reinforcement Learning for Recommender Systems.

Recommender systems have been widely applied in different real-life scenarios to help us find useful information. In particular, reinforcement learning (RL)-based recommender systems have become an emerging research topic in recent years, owing to the interactive nature and autonomous learning ability. Empirical results show that RL-based recommendation methods often surpass supervised learning methods. Nevertheless, there are various challenges in applying RL in recommender systems. To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems. To this end, we first provide a thorough overview, comparisons, and summarization of RL approaches applied in four typical recommendation scenarios, including interactive recommendation, conversational recommendation, sequential recommendation, and explainable recommendation. Furthermore, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommender systems, we highlight some potential research directions in this field.

The Clinical Value of Prenatal Ultrasonography in the Differential Diagnosis of Fetal Suprarenal Space-Occupying Lesions.

Objective: This study aimed to investigate the value of prenatal ultrasonography in the differential diagnosis of fetal space-occupying lesions in the adrenal gland. Methods: Thirty-six fetuses with adrenal gland space-occupying lesions diagnosed by prenatal ultrasonography between January 2019 and July 2021 were included in this retrospective study. The clinical data, ultrasonographic features, treatments, and prognoses of the fetuses were analyzed. Postnatal diagnoses were made using computed tomography (CT), magnetic resonance imaging, and surgical resection. Results: Of the 36 fetuses, 10 were diagnosed with adrenal hematomas, eight with adrenal neuroblastomas, seven with adrenal cysts, seven with subphrenic pulmonary sequestration, and four with adrenal teratomas. The accuracy of prenatal diagnosis was highest in those with adrenal cysts and subphrenic pulmonary sequestration, with the accuracy being 85.7% for both conditions. The mean gestational age at first detection of subphrenic pulmonary sequestration was 22.5 ± 3.1 weeks, which was significantly lower than that of other diagnoses (P < 0.05), and the mean diameter of adrenal cysts was 15.1 ± 4.2 mm, which was significantly smaller than that of other lesions (P < 0.05). All newborns with adrenal teratomas and neuroblastomas were treated surgically. Five of the seven patients with subphrenic pulmonary sequestration and three of the seven patients with cysts were also treated surgically. Follow-ups of the remaining cases were carried out by enhanced CT examination, and the prognoses were good. Conclusion: Prenatal ultrasonography can help differentiate between different types of fetal adrenal space-occupying lesions, and there is a high coincidence rate between the diagnosis of adrenal cysts and subphrenic pulmonary sequestration.

Anticancer Peptide Prediction via Multi-Kernel CNN and Attention Model.

Background: Modern lifestyles mean that people are more likely to suffer from some form of cancer. As anticancer peptides can effectively kill cancer cells and play an important role in fighting cancer, they have been a subject of increasing research interest. Methods: This study presents a useful tool to identify the anticancer peptides based on a multi-kernel CNN and attention model, called ACP-MCAM. This model can automatically learn adaptive embedding and the context sequence features of ACP. In addition, to obtain better interpretability and integrity, we visualized the model. Results: Benchmarking comparison shows that ACP-MCAM significantly outperforms several state-of-the-art models. Different encoding schemes have different impacts on the performance of the model. We also studied tmethod parameter optimization. Conclusion: The ACP-MCAM can integrate multi-kernel CNN and self-attention mechanism, which outperforms the previous model in identifying anticancer peptides. It is expected that the work will provide new research ideas for anticancer peptide prediction in the future. In addition, this work will promote the development of the interdisciplinary field of artificial intelligence and biomedicine.

Liquid-Free Ion-Conducting Elastomer with Environmental Stability for Soft Sensing and Thermoelectric Generating.

Ionic conductors are promising candidates for fabricating soft electronics, but currently applied ionic hydrogels and organogels suffer from liquid leakage and evaporation issues. Herein, we fabricated a free-liquid ionic conducting elastomer (LFICE) with dry lithium bis(trifluoromethane sulfonimide) and elastomeric waterborne polyurethane. The resultant versatile LFICE exhibits superior tensile strength (∼4.5 MPa), satisfactory stretchability (>900%), excellent ionic conductivity (8.32 × 10-4 S m-1 at 25 °C), and sensitive strain (3.21) and temperature (2.22% °C-1) response. The LFICE also presents durable environmental stability due to the all-solid-state feature. In the exploration of application prospects, the as-assembled LFICE sensor can precisely and repeatedly detect human motion and temperature changes, demonstrating its potentials in digital medical diagnosis and monitoring; the as-assembled LFICE thermoelectric generator (TEG) shows a high ionic thermovoltage of 4.41 mV K-1, paving a bright path for the advent of self-powered soft electronics. It is believed that this research boosts the facile fabrication of environmental stable stretchable ionic conductors holding great promise in next-generation soft electronics integrated with dual thermo- and strain-response and energy harvesting.

A Polar-Metric-Based Evolutionary Algorithm.

Over the past two decades, numerous multi- and many-objective evolutionary algorithms (MOEAs and MaOEAs) have been proposed to solve the multi- and many-objective optimization problems (MOPs and MaOPs), respectively. It is known that the difficulty of maintaining the convergence and diversity performances rapidly grows as the number of objectives increases. This phenomenon is especially evident for the Pareto-dominance-based EAs, because the nondominated sorting often fails to provide enough convergent pressure toward the Pareto front (PF). Therefore, many researchers came up with some non-Pareto-dominance-based EAs, which are based on indicator, decomposition, and so on. In this article, we propose a polar-metric ( p -metric)-based EA (PMEA) for tackling both MOPs and MaOPs. p -metric is a recently proposed performance indicator which adopts a set of uniformly distributed direction vectors. In PMEA, we use a two-phase selection which combines both nondominated sorting and p -metric. Moreover, a modification is proposed to adjust the direction vectors of p -metric dynamically. In the experiments, PMEA is compared with six state-of-the-art EAs in total and is measured by three performance metrics, including p -metric. According to the empirical results, PMEA shows promising performances on most of the test problems, involving both MOPs and MaOPs.

An Evolutionary Algorithm Based on Minkowski Distance for Many-Objective Optimization.

The existing multiobjective evolutionary algorithms (EAs) based on nondominated sorting may encounter serious difficulties in tackling many-objective optimization problems (MaOPs), because the number of nondominated solutions increases exponentially with the number of objectives, leading to a severe loss of selection pressure. To address this problem, some existing many-objective EAs (MaOEAs) adopt Euclidean or Manhattan distance to estimate the convergence of each solution during the environmental selection process. Nevertheless, either Euclidean or Manhattan distance is a special case of Minkowski distance with the order P=2 or P=1 , respectively. Thus, it is natural to adopt Minkowski distance for convergence estimation, in order to cover various types of Pareto fronts (PFs) with different concavity-convexity degrees. In this paper, a Minkowski distance-based EA is proposed to solve MaOPs. In the proposed algorithm, first, the concavity-convexity degree of the approximate PF, denoted by the value of P , is dynamically estimated. Subsequently, the Minkowski distance of order P is used to estimate the convergence of each solution. Finally, the optimal solutions are selected by a comprehensive method, based on both convergence and diversity. In the experiments, the proposed algorithm is compared with five state-of-the-art MaOEAs on some widely used benchmark problems. Moreover, the modified versions for two compared algorithms, integrated with the proposed P -estimation method and the Minkowski distance, are also designed and analyzed. Empirical results show that the proposed algorithm is very competitive against other MaOEAs for solving MaOPs, and two modified compared algorithms are generally more effective than their predecessors.

MOEA/HD: A Multiobjective Evolutionary Algorithm Based on Hierarchical Decomposition.

Recently, numerous multiobjective evolutionary algorithms (MOEAs) have been proposed to solve the multiobjective optimization problems (MOPs). One of the most widely studied MOEAs is that based on decomposition (MOEA/D), which decomposes an MOP into a series of scalar optimization subproblems, via a set of uniformly distributed weight vectors. MOEA/D shows excellent performance on most mild MOPs, but may face difficulties on ill MOPs, with complex Pareto fronts, which are pointed, long tailed, disconnected, or degenerate. That is because the weight vectors used in decomposition are all preset and invariant. To overcome it, a new MOEA based on hierarchical decomposition (MOEA/HD) is proposed in this paper. In MOEA/HD, subproblems are layered into different hierarchies, and the search directions of lower-hierarchy subproblems are adaptively adjusted, according to the higher-hierarchy search results. In the experiments, MOEA/HD is compared with four state-of-the-art MOEAs, in terms of two widely used performance metrics. According to the empirical results, MOEA/HD shows promising performance on all the test problems.

Clinical value of prenatal echocardiographic examination in the diagnosis of fetal cardiac tumors.

The aim of the present study was to explore the clinical value of prenatal echocardiographic examination in the diagnosis of fetal cardiac tumors. In total, the cases of 8 fetuses with fetal cardiac tumors, which were identified by prenatal ultrasound examination in The First Affiliated Hospital of Nanchang University between January 2012 and January 2014, were retrospectively analyzed. The size, shape, location, activity and hemodynamic changes of the lesions were described in detail, and the patients were followed up. Out of the 8 identified cases of fetal cardiac tumors, 2 fetuses contained tumors only in the left ventricular cavity and 6 fetuses contained tumors of the left and right ventricular cavities, interventricular septum and apex of the heart. Overall, 5 of the 8 female patients requested termination of the pregnancy and labor was induced. The fetuses were pathologically confirmed to possess rhabdomyoma. In addition, 1 patient was followed-up for 5 weeks, and the tumor in the fetal heart cavity was found to have enlarged and developed in multiple regions when follow-up was performed. The patient then requested termination of the pregnancy and labor was induced. The fetus was pathologically confirmed to possess rhabdomyoma. The remaining 2 patients insisted on continuation of the pregnancy and the fetuses were followed up during gestation and subsequent to birth by echocardiographic examination. Prenatal echocardiography may precisely position and diagnose occupying lesions of the fetal heart, which is of considerable value in clinical decision making and instruction for treatment.

Load balancing prediction method of cloud storage based on analytic hierarchy process and hybrid hierarchical genetic algorithm.

With the continuous expansion of the cloud computing platform scale and rapid growth of users and applications, how to efficiently use system resources to improve the overall performance of cloud computing has become a crucial issue. To address this issue, this paper proposes a method that uses an analytic hierarchy process group decision (AHPGD) to evaluate the load state of server nodes. Training was carried out by using a hybrid hierarchical genetic algorithm (HHGA) for optimizing a radial basis function neural network (RBFNN). The AHPGD makes the aggregative indicator of virtual machines in cloud, and become input parameters of predicted RBFNN. Also, this paper proposes a new dynamic load balancing scheduling algorithm combined with a weighted round-robin algorithm, which uses the predictive periodical load value of nodes based on AHPPGD and RBFNN optimized by HHGA, then calculates the corresponding weight values of nodes and makes constant updates. Meanwhile, it keeps the advantages and avoids the shortcomings of static weighted round-robin algorithm.

Finite element analysis for edge-to-edge technique to treat post-mitral valve repair systolic anterior motion.

Systolic anterior motion of the mitral valve is an uncommon complication of mitral valve repair, which requires immediate supplementary surgical action. Edge-to-edge suture is considered as an effective technique to treat post-mitral valve repair systolic anterior motion by clinical researchers. However, the fundamentals and quantitative analysis are vacant to validate the effectiveness of the additional edge-to-edge surgery to repair systolic anterior motion. In the present work, finite element models were developed to simulate a specific clinical surgery for patients with posterior leaflet prolapse, so as to analyze the edge-to-edge technique quantificationally. The simulated surgery procedure concluded several actions such as quadrangular resection, mitral annuloplasty and edge-to-edge suture. And the simulated results were compared with echocardiography and measurement data of the patients under the mitral valve surgery, which shows good agreement. The leaflets model with additional edge-to-edge suture has a shorter mismatch length than that of the model merely under quadrangular resection and mitral annuloplasty actions at systole, which assures a better coaptation status. The stress on the leaflets after edge-to-edge suture is lessened as well.