Mix-Key: graph mixup with key structures for molecular property prediction.

Molecular property prediction faces the challenge of limited labeled data as it necessitates a series of specialized experiments to annotate target molecules. Data augmentation techniques can effectively address the issue of data scarcity. In recent years, Mixup has achieved significant success in traditional domains such as image processing. However, its application in molecular property prediction is relatively limited due to the irregular, non-Euclidean nature of graphs and the fact that minor variations in molecular structures can lead to alterations in their properties. To address these challenges, we propose a novel data augmentation method called Mix-Key tailored for molecular property prediction. Mix-Key aims to capture crucial features of molecular graphs, focusing separately on the molecular scaffolds and functional groups. By generating isomers that are relatively invariant to the scaffolds or functional groups, we effectively preserve the core information of molecules. Additionally, to capture interactive information between the scaffolds and functional groups while ensuring correlation between the original and augmented graphs, we introduce molecular fingerprint similarity and node similarity. Through these steps, Mix-Key determines the mixup ratio between the original graph and two isomers, thus generating more informative augmented molecular graphs. We extensively validate our approach on molecular datasets of different scales with several Graph Neural Network architectures. The results demonstrate that Mix-Key consistently outperforms other data augmentation methods in enhancing molecular property prediction on several datasets.

Photonic time-delayed reservoir computing based on series-coupled microring resonators with high memory capacity.

On-chip microring resonators (MRRs) have been proposed to construct time-delayed reservoir computing (RC) systems, which offer promising configurations available for computation with high scalability, high-density computing, and easy fabrication. A single MRR, however, is inadequate to provide enough memory for the computation task with diverse memory requirements. Large memory requirements are satisfied by the RC system based on the MRR with optical feedback, but at the expense of its ultralong feedback waveguide. In this paper, a time-delayed RC is proposed by utilizing a silicon-based nonlinear MRR in conjunction with an array of linear MRRs. These linear MRRs possess a high quality factor, providing enough memory capacity for the RC system. We quantitatively analyze and assess the proposed RC structure's performance on three classical tasks with diverse memory requirements, i.e., the Narma 10, Mackey-Glass, and Santa Fe chaotic timeseries prediction tasks. The proposed system exhibits comparable performance to the system based on the MRR with optical feedback, when it comes to handling the Narma 10 task, which requires a significant memory capacity. Nevertheless, the dimension of the former is at least 350 times smaller than the latter. The proposed system lays a good foundation for the scalability and seamless integration of photonic RC.

Epidemic spreading under game-based self-quarantine behaviors: The different effects of local and global information.

During the outbreak of an epidemic, individuals may modify their behaviors in response to external (including local and global) infection-related information. However, the difference between local and global information in influencing the spread of diseases remains inadequately explored. Here, we study a simple epidemic model that incorporates the game-based self-quarantine behavior of individuals, taking into account the influence of local infection status, global disease prevalence, and node heterogeneity (non-identical degree distribution). Our findings reveal that local information can effectively contain an epidemic, even with only a small proportion of individuals opting for self-quarantine. On the other hand, global information can cause infection evolution curves shaking during the declining phase of an epidemic, owing to the synchronous release of nodes with the same degree from the quarantined state. In contrast, the releasing pattern under the local information appears to be more random. This shaking phenomenon can be observed in various types of networks associated with different characteristics. Moreover, it is found that under the proposed game-epidemic framework, a disease is more difficult to spread in heterogeneous networks than in homogeneous networks, which differs from conventional epidemic models.

Data augmentation using continuous conditional generative adversarial networks for regression and its application to improved spectral sensing.

Machine learning-assisted spectroscopy analysis faces a prominent constraint in the form of insufficient spectral samples, which hinders its effectiveness. Meanwhile, there is a lack of effective algorithms to simulate synthetic spectra from limited samples of real spectra for regression models in continuous scenarios. In this study, we introduced a continuous conditional generative adversarial network (CcGAN) to autonomously generate synthetic spectra. The labels employed for generating the spectral data can be arbitrarily selected from within the range of labels associated with the real spectral data. Our approach effectively produced spectra using a small spectral dataset obtained from a self-interference microring resonator (SIMRR)-based sensor. The generated synthetic spectra were subjected to evaluation using principal component analysis, revealing an inability to discern them from the real spectra. Finally, to enhance the DNN regression model, these synthetic spectra are incorporated into the original training dataset as an augmentation technique. The results demonstrate that the synthetic spectra generated by CcGAN exhibit exceptional quality and significantly enhance the predictive performance of the DNN model. In conclusion, CcGAN exhibits promising potential in generating high-quality synthetic spectra and delivers a superior data augmentation effect for regression tasks.

Clinical and patient-reported outcomes from the first 4 years of a Psoriasis Biologics Registry in Singapore.

Interim analysis of the National Skin Centre Singapore Psoriasis Biologics Registry (SINGPSOR) from August 2017 to May 2021, in which 58 patients were analysed, showing that those receiving biologic treatment had significantly more severe psoriasis based on PASI (Psoriasis Area and Severity Index), BSA (body surface area) and PGA (Physician Global Assessment) measures at baseline, demonstrated a statistically non-significant trend towards greater improvement with treatment, and had a lower percentage of adverse events compared to those receiving conventional systemic therapy. Future analyses of SINGPSOR, with larger sample size and longer follow-up, will be invaluable to further characterize these patients and their treatment outcomes.

Targeting aging with the healthy skeletal system: The endocrine role of bone.

Aging is an inevitable biological process, and longevity may be related to bone health. Maintaining strong bone health can extend one's lifespan, but the exact mechanism is unclear. Bone and extraosseous organs, including the heart and brain, have complex and precise communication mechanisms. In addition to its load bearing capacity, the skeletal system secretes cytokines, which play a role in bone regulation of extraosseous organs. FGF23, OCN, and LCN2 are three representative bone-derived cytokines involved in energy metabolism, endocrine homeostasis and systemic chronic inflammation levels. Today, advanced research methods provide new understandings of bone as a crucial endocrine organ. For example, gene editing technology enables bone-specific conditional gene knockout models, which allows the study of bone-derived cytokines to be more precise. We systematically evaluated the various effects of bone-derived cytokines on extraosseous organs and their possible antiaging mechanism. Targeting aging with the current knowledge of the healthy skeletal system is a potential therapeutic strategy. Therefore, we present a comprehensive review that summarizes the current knowledge and provides insights for futures studies.

Aliidiomarina quisquiliarum sp. nov., isolated from landfill leachate.

Bacterial strain Y-6T, isolated from a landfill site in Yiwu, PR China, was characterized using a polyphasic taxonomy approach. Cells were Gram-stain-negative, aerobic, rod-shaped, motile by means of a single polar flagellum and formed pale beige colonies. Strain Y-6T grew at 4-40 °C (optimal at 30-37 °C), pH 6.5-9.5 (optimal at pH 7.2-8.5) and in the presence of 0.5-10.0 % (w/v) NaCl (optimal at 1.0-3.0 %). Phylogenetic analysis revealed that strain Y-6T was a member of the genus Aliidiomarina and closely related to Aliidiomarina taiwanensis MCCC 1A06493T with a 16S rRNA sequence similarity of 98.2 %. The major cellular fatty acids of the isolate were iso-C15 : 0, C16 : 0, iso-C17 : 0 and summed feature 9 (iso-C17 : 1 ω9c and/or 10-methyl-C16 : 0). Q-8 was the predominant ubiquinone. The major polar lipids comprised diphosphatidylglycerol, phosphatidylglycerol, phosphatidylethanolamine, aminoglycophospholipid, aminophospholipid, phospholipid, three glycolipids and two unknown lipids. The genomic DNA G+C content was 46.6 mol%. The digital DNA-DNA hybridization value between Y-6T and A. taiwanensis MCCC 1A06493T was 18.3 %. Strain Y-6T had an average nucleotide identity value of 74.09 % with A. taiwanensis MCCC 1A06493T. Results from the polyphasic taxonomy study support the conclusion that strain Y-6T represents a novel Aliidiomarina species, for which the name Aliidiomarina quisquiliarum sp.nov. is proposed. The type strain is Y-6T (=MCCC 1K06228T=KCTC 82676T).

Recalcitrant cutaneous fungal infections-A growing problem.

The incidence and prevalence of recalcitrant cutaneous fungal infections is on the rise. Terbinafine-resistant Trichophyton has not only been widespread in India, but has also been reported in countries spread throughout the globe. Strains of yeasts such as Malassezia and Candida, which exist both as commensals and as pathogens to the human skin, have also been found to develop resistance to antifungals. Non-dermatophyte moulds which can colonize and infect damaged nails are especially difficult to treat, not only due to resistance, but also because of poor drug penetration of hard keratin. Psychosocial factors such as the indiscriminate broad-spectrum antifungal use in agriculture and in medicine, and poor adherence to hygienic measures to break the chain of infection contribute to the development of antifungal resistance. Such environments encourage fungi to develop various resistance mechanisms to withstand antifungal treatment. These include: (a) alteration of the drug target, (b) increasing efflux of drug/metabolites, (c) inactivation of drug, (d) bypass mechanisms or substitution of the pathway affected by the drug, (e) stress adaptation mechanisms and (f) biofilm formation. Understanding of such mechanisms and how they arise are crucial for development of new ways to prevent or overcome resistance. Novel antifungal treatments have recently been approved in the United States of America for treatment of vulvovaginal candidiasis. Ibrexafungerp (enfumafungin derivative) and oteseconazole (tetrazole) differ from their respective related drug classes of echinocandins and triazoles by having different structures, which lend these medicines advantage compared to traditional treatment by having a different binding site and more selectivity for fungi respectively. Other drugs designed to circumvent the known mechanisms of antifungal resistance are also at various phases of development. Concurrent measures at an institutional and individual level to address and limit inappropriate antifungal use to reduce development of antifungal resistance should be undertaken in a concerted effort to address this epidemic.

Gestational diabetes mellitus suppresses fetal testis development in mice†.

The prevalence of gestational diabetes mellitus (GDM) is increasing rapidly. In addition to the metabolic disease risks, GDM might increase the risks of cryptorchidism in children. However, its mechanism involved in abnormalities of the male reproductive system is still unclear. The purpose of this study was to study the effects of GDM on the development of mouse fetal Leydig cells (FLCs) and Sertoli cells (SCs). Pregnant mice were treated on gestational days 6.5 and 12.5 with streptozotocin (100 mg/kg) or vehicle (sodium citrate buffer). Leydig cell and SC development and functions were evaluated by investigating serum testosterone levels, cell number and distribution, genes, and protein expression. GDM decreased serum testosterone levels, the anogenital distance, and the level of desert hedgehog in SCs of testes of male offspring. FLC number was also decreased in testes of GDM offspring by delaying the commitment of stem Leydig cells into the Leydig cell lineage. RNA-seq showed that FOXL2, RSPO1/ß-catenin signaling was activated and Gsk3ß signaling was inhibited in GDM offspring testis. In conclusion, GDM disrupted reproductive tract and testis development in mouse male offspring via altering genes related to development.

CLPVG: Circular limited penetrable visibility graph as a new network model for time series.

A visibility graph transforms time series into graphs, facilitating signal processing by advanced graph data mining algorithms. In this paper, based on the classic limited penetrable visibility graph method, we propose a novel mapping method named circular limited penetrable visibility graph, which replaces the linear visibility line in limited penetrable visibility graph with nonlinear visibility arc for pursuing more flexible and reasonable mapping of time series. Tests on degree distribution and some common network features of the generated graphs from typical time series demonstrate that our circular limited penetrable visibility graph can effectively capture the important features of time series and show higher robust classification performance than the traditional limited penetrable visibility graph in the presence of noise. The experiments on real-world time-series datasets of radio and electroencephalogram signals also suggest that the structural features provided by a circular limited penetrable visibility graph, rather than a limited penetrable visibility graph, are more useful for time-series classification, leading to higher accuracy. This classification performance can be further enhanced through structural feature expansion by adopting subgraph networks. All of these results demonstrate the effectiveness of our circular limited penetrable visibility graph model.

The evaluation of bone marrow edema in sacroiliac joint in patients with ankylosing spondylitis using magnetic resonance imaging Dixon sequence.

BACKGROUND: Bone marrow edema of the sacroiliac joint is the early imaging manifestation, an indicator of inflammatory activity of ankylosing spondylitis (AS) (Yang R, et. al. Medicine (Baltimore) 98:e14620, 2019). OBJECTIVE: The aim of the study was to investigate the value of magnetic resonance imaging (MRI) Dixon sequence in the diagnosis of marrow edema of the sacroiliac joint in patients with AS. METHODS: Forty-five patients with AS admitted in our hospital between November 2016 and February 2019 were selected retrospectively as the case group. Forty-five healthy subjects recruited between November 2016 and February 2019 served as the control group. Bath ankylosing spondylitis disease activity index (BASDAI), Bath ankylosing spondylitis functional index (BASFI), C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR) were recorded after admission to the hospital. The Dixon sequence water-fat ratio of the iliac and sacral surfaces of the bilateral sacroiliac joints in the study group were compared with indicators above in order to find the correlation. RESULTS: The water-fat ratio under the bilateral sacroiliac joints on Dixon sequence images in the case group was significantly higher than that in the healthy control group (P<0.05). The Dixon sequence water-fat ratio of the iliac and sacral surfaces of the bilateral sacroiliac joints in the study group were positively correlated with spinal arthritis research (SPARCC), BASFI and BASDAI score (all P < 0.05), but did not correlate with ESR and CRP. CONCLUSION: The water-fat ratio of magnetic resonance Dixon sequence can be used as a reference index to evaluate the degree of bone marrow edema in active stage of sacroiliac arthritis.

The impact of malicious nodes on the spreading of false information.

Increasing empirical evidence in recent years has shown that bots or malicious users in a social network play a critical role in the propagation of false information, while a theoretical modeling of such a problem has been largely ignored. In this paper, applying a simple contagion model, we study the effect of malicious nodes on the spreading of false information by incorporating the smart nodes who perform better than normal nodes in discerning false information. The malicious nodes, however, will always repost (or adopt) the false message as long as they receive it. We show analytically that, for a random distribution of malicious nodes, there is a critical number of malicious nodes above which the false information could outbreak in a random network. We further study three different distribution strategies of selecting malicious nodes for false information spreading. We find that malicious nodes that have large degrees, or are tightly connected, can enhance the spread. However, when they are close to the smart nodes, the spreading of false information can either be promoted or inhibited, depending on the network structure.

Adversarial attack on BC classification for scale-free networks.

Adversarial attacks have been alerting the artificial intelligence community recently since many machine learning algorithms were found vulnerable to malicious attacks. This paper studies adversarial attacks on Broido and Clauset classification for scale-free networks to test its robustness in terms of statistical measures. In addition to the well-known random link rewiring (RLR) attack, two heuristic attacks are formulated and simulated: degree-addition-based link rewiring (DALR) and degree-interval-based link rewiring (DILR). These three strategies are applied to attack a number of strong scale-free networks of various sizes generated from the Barabási-Albert model and the uncorrelated configuration model. It is found that both DALR and DILR are more effective than RLR in the sense that rewiring a smaller number of links can succeed in the same attack. However, DILR is as concealed as RLR in the sense that they both are introducing a relatively small change on several typical structural properties, such as the average shortest path-length, the average clustering coefficient, the average diagonal distance, and the Kolmogorov-Smirnov test of the degree distribution. The results of this paper suggest that to classify a network to be scale-free, one has to be very careful from the viewpoint of adversarial attack effects.

An urban commuters' OD hybrid prediction method based on big GPS data.

With the quick development of mobile Internet and communication technology, the use of Global Position System (GPS)-enabled devices is rapidly increasing, which facilitates the collection of huge volumes of movement data in the form of trajectories. Trajectory data contain a lot of commuters' travel information, which offer convenience for researchers to study traffic problems and to mine urban commuters' travel information. In this paper, we represent an urban commuters' origin-destination (OD) hybrid prediction method based on big GPS data, which considers the temporal and spatial dependencies of OD volume data simultaneously. The regional division was performed based on a simple grid map, and the data for each grid can be obtained. Based on the grids, the OD pairs can be constructed and the network topology of OD pairs can be established. A graph convolutional network and a long short-term memory deep learning method were introduced to capture the temporal and spatial dependencies, respectively. In addition, an attention mechanism was used to learn the weights of input data. The numerical experiment was performed based on the GPS data in Chengdu, China, and some comparisons were made. The results demonstrated that the proposed hybrid OD prediction method was significant and the accuracy was reasonable.

Overexpression of cancer susceptibility candidate 2 inhibited progression of hepatocellular carcinoma cells.

OBJECTIVE: Our study was aimed to investigate the effect of cancer susceptibility candidate 2 (CASC2) on the proliferation, cell cycle, apoptosis, and metastasis of hepatocellular carcinoma (HCC) cells. METHODS: CASC2 expression in tumor tissues and HCC cells was tested by quantitative real-time polymerase chain reaction. After manipulating the expression of CASC2 in Hep3B and HepG2 cells, cells viability, including proliferation, apoptosis, cell-cycle distribution, migration, and invasion were examined by colony formation assay, flow cytometry, wound-healing assay, and transwell assay, respectively. The expression levels of proteins associated with the cell cycle and AKT/mTOR pathway were measured by the western blot. Stably transfected HepG2 cells were used to construct nude mice models, and tumorigenesis was evaluated to investigate the in vivo functions of CASC2 in HCC progression. RESULTS: In tissues and cells of HCC, decreased CASC2 expressions were confirmed. Overexpression of CASC2 made cell cycle stagnated at G0/G1 phase and induced apoptosis. Meanwhile, the overexpression of CASC2 played significant roles in inhibiting the proliferation, migration, and invasion of HCC cells. Furthermore, In vivo experiment indicated that CASC2 restrained the growth of tumors. CONCLUSION: Our study suggested that CASC2 promoted cell apoptosis and suppressed cell growth and metastasis in HCC, indicating that CASC2 might be a useful biomarker of HCC.

Road traffic state prediction based on a graph embedding recurrent neural network under the SCATS.

Road traffic state prediction is one of the essential and vital issues in intelligence transportation system, but it is difficult to get high accuracy due to the complicated spatiotemporal characteristics of traffic flow data, especially under the Sydney coordinated adaptive traffic system. In this work, we represent the traffic road network as a graph and propose a novel traffic flow prediction framework named the graph embedding recurrent neural network (GERNN). It could tackle the difficulty in the road traffic state prediction. We conduct numerical tests to compare GERNN with other existing methods using a real-world dataset.

Superhydrophobic Coating for Antifouling of Chinese Paintings.

In the past 10 years, many studies on superhydrophobic (SH) papers have been reported. However, these works are rarely carried out on Chinese paintings. Compared with pure paper, the complexity of Chinese black ink and pigment, caused by including animal glue and fixatives allowing the nanoparticles to disperse in water, negatively affects the formation of SH coatings. In this work, we report the fabrication of SH coatings using fluorine silicon sol containing an epoxy group on Chinese paintings. Briefly, SiO2 nanoparticles were mixed with KH560 and FAS-17 and formed fluorine silicon sol. Then the sol was coated on the Chinese paintings. After drying, the SH coating was created. It can protect Chinese paintings and prevent them from being fouled by various liquids. Six types of beverages and ink can be repelled by the as-prepared SH coatings. Moreover, Chinese black ink can also be washed away from the SH coatings using water, without leaving any traces of ink behind. The SH coatings did not affect the appearance and internal structure of the Chinese paintings. Furthermore, due to covalent link, the SH coatings have good mechanical properties with regard to bending tests (120 times), finger pressing tests, and friction tests. The SH coatings also show an excellent high temperature resistance. This study has important applications for antifouling of Chinese paintings or oil paintings from dirty water.

Accurate Indoor Localization Based on CSI and Visibility Graph.

Passive indoor localization techniques can have many important applications. They are nonintrusive and do not require users carrying measuring devices. Therefore, indoor localization techniques are widely used in many critical areas, such as security, logistics, healthcare, etc. However, because of the unpredictable indoor environment dynamics, the existing nonintrusive indoor localization techniques can be quite inaccurate, which greatly limits their real-world applications. To address those problems, in this work, we develop a channel state information (CSI) based indoor localization technique. Unlike the existing methods, we employ both the intra-subcarrier statistics features and the inter-subcarrier network features. Specifically, we make the following contributions: (1) we design a novel passive indoor localization algorithm which combines the statistics and network features; (2) we modify the visibility graph (VG) technique to build complex networks for the indoor localization applications; and (3) we demonstrate the effectiveness of our technique using real-world deployments. The experimental results show that our technique can achieve about 96% accuracy on average and is more than 9% better than the state-of-the-art techniques.