MVML-MPI: Multi-View Multi-Label Learning for Metabolic Pathway Inference.

Development of robust and effective strategies for synthesizing new compounds, drug targeting and constructing GEnome-scale Metabolic models (GEMs) requires a deep understanding of the underlying biological processes. A critical step in achieving this goal is accurately identifying the categories of pathways in which a compound participated. However, current machine learning-based methods often overlook the multifaceted nature of compounds, resulting in inaccurate pathway predictions. Therefore, we present a novel framework on Multi-View Multi-Label Learning for Metabolic Pathway Inference, hereby named MVML-MPI. First, MVML-MPI learns the distinct compound representations in parallel with corresponding compound encoders to fully extract features. Subsequently, we propose an attention-based mechanism that offers a fusion module to complement these multi-view representations. As a result, MVML-MPI accurately represents and effectively captures the complex relationship between compounds and metabolic pathways and distinguishes itself from current machine learning-based methods. In experiments conducted on the Kyoto Encyclopedia of Genes and Genomes pathways dataset, MVML-MPI outperformed state-of-the-art methods, demonstrating the superiority of MVML-MPI and its potential to utilize the field of metabolic pathway design, which can aid in optimizing drug-like compounds and facilitating the development of GEMs. The code and data underlying this article are freely available at https://github.com/guofei-tju/MVML-MPI. Contact:  jtang@cse.sc.edu, guofei@csu.edu.com or wuxi_dyj@csj.uestc.edu.cn.

MTMol-GPT: De novo multi-target molecular generation with transformer-based generative adversarial imitation learning.

De novo drug design is crucial in advancing drug discovery, which aims to generate new drugs with specific pharmacological properties. Recently, deep generative models have achieved inspiring progress in generating drug-like compounds. However, the models prioritize a single target drug generation for pharmacological intervention, neglecting the complicated inherent mechanisms of diseases, and influenced by multiple factors. Consequently, developing novel multi-target drugs that simultaneously target specific targets can enhance anti-tumor efficacy and address issues related to resistance mechanisms. To address this issue and inspired by Generative Pre-trained Transformers (GPT) models, we propose an upgraded GPT model with generative adversarial imitation learning for multi-target molecular generation called MTMol-GPT. The multi-target molecular generator employs a dual discriminator model using the Inverse Reinforcement Learning (IRL) method for a concurrently multi-target molecular generation. Extensive results show that MTMol-GPT generates various valid, novel, and effective multi-target molecules for various complex diseases, demonstrating robustness and generalization capability. In addition, molecular docking and pharmacophore mapping experiments demonstrate the drug-likeness properties and effectiveness of generated molecules potentially improve neuropsychiatric interventions. Furthermore, our model's generalizability is exemplified by a case study focusing on the multi-targeted drug design for breast cancer. As a broadly applicable solution for multiple targets, MTMol-GPT provides new insight into future directions to enhance potential complex disease therapeutics by generating high-quality multi-target molecules in drug discovery.

Microbe-bridged disease-metabolite associations identification by heterogeneous graph fusion.

MOTIVATION: Metabolomics has developed rapidly in recent years, and metabolism-related databases are also gradually constructed. Nowadays, more and more studies are being carried out on diverse microbes, metabolites and diseases. However, the logics of various associations among microbes, metabolites and diseases are limited understanding in the biomedicine of gut microbial system. The collection and analysis of relevant microbial bioinformation play an important role in the revelation of microbe-metabolite-disease associations. Therefore, the dataset that integrates multiple relationships and the method based on complex heterogeneous graphs need to be developed. RESULTS: In this study, we integrated some databases and extracted a variety of associations data among microbes, metabolites and diseases. After obtaining the three interconnected bilateral association data (microbe-metabolite, metabolite-disease and disease-microbe), we considered building a heterogeneous graph to describe the association data. In our model, microbes were used as a bridge between diseases and metabolites. In order to fuse the information of disease-microbe-metabolite graph, we used the bipartite graph attention network on the disease-microbe and metabolite-microbe bipartite graph. The experimental results show that our model has good performance in the prediction of various disease-metabolite associations. Through the case study of type 2 diabetes mellitus, Parkinson's disease, inflammatory bowel disease and liver cirrhosis, it is noted that our proposed methodology are valuable for the mining of other associations and the prediction of biomarkers for different human diseases.Availability and implementation: https://github.com/Selenefreeze/DiMiMe.git.

Halomonas binhaiensis sp. nov., isolated from saline-alkali soil.

A Gram-stain-negative, aerobic and rod-shaped bacterium, strain Y2R2T, was isolated from a saline-alkali soil sample collected from Binhai New Area, Tianjin, PR China. Growth of strain Y2R2T was observed at 10-45 °C (optimum, 30 °C), at pH 6.0-11.0 (optimum, pH 9.0) and in the presence of 0-15 % (w/v) NaCl (optimum, 9.0 %). Phylogenetic analysis based on 16S rRNA gene sequences showed that strain Y2R2T was affiliated with the genus Halomonas and showed the highest similarity to Halomonas huangheensis BJGMM-B45T (99.0%) and Halomonas cupida DSM 4740T (98.4%). The digital DNA-DNA hybridization and average nucleotide identity values of 21.0-22.8 % and 73.3-75.7 % with the closely related species H. huangheensis BJGMM-B45T, H. cupida DSM 4740T, H. ventosae AL12T, H. stenophila N12T and H. litopenaei SYSU ZJ2214T were lower than the threshold recommended for species discrimination.The major respiratory quinone of strain Y2R2T was Q-9 and the major cellular fatty acids consisted of C16 : 0, C19 : 0 cyclo ω8c and summed feature 8 (C18 : 1 ω7c and/or C18 : 1 ω6c). The DNA G+C content of strain Y2R2T was 57.0 mol%. On the basis of this polyphasic taxonomic study, strain Y2R2T is considered to represent a novel species of the genus Halomonas, for which the name Halomonas binhaiensis sp. nov. is proposed. The type strain is Y2R2T (=CGMCC 1.16974T=KCTC 72578T).

DeepBLI: A Transferable Multichannel Model for Detecting ß-Lactamase-Inhibitor Interaction.

Pathogens producing ß-lactamase pose a great challenge to antibiotic-resistant infection treatment; thus, it is urgent to discover novel ß-lactamase inhibitors for drug development. Conventional high-throughput screening is very costly, and structure-based virtual screening is limited with mechanisms. In this study, we construct a novel multichannel deep neural network (DeepBLI) for ß-lactamase inhibitor screening, pretrained with a label reversal KIBA data set and fine-tuned on ß-lactamase-inhibitor pairs from BindingDB. First, the pairs of encoders (Conv and Att) fuse the information spatially and sequentially for both enzymes and inhibitors. Then, a co-attention module creates the connection between the inhibitor and enzyme embeddings. Finally, multichannel outputs fuse with an element-wise product and then are fed into 3-layer fully connected networks to predict interactions. Comparing the state-of-the-art methods, DeepBLI yields an AUROC of 0.9240 and an AUPRC of 0.9715, which indicates that it can identify new ß-lactamase-inhibitor interactions. To demonstrate its prediction ability, an application of DeepBLI is described to screen potential inhibitor compounds for metallo-ß-lactamase AIM-1 and repurpose rottlerin for four classes of ß-lactamase targets, showing the possibility of being a broad-spectrum inhibitor. DeepBLI provides an effective way for antibacterial drug development, contributing to antibiotic-resistant therapeutics.

Synthesis of Cyclic Peptides in SPPS with Npb-OH Photolabile Protecting Group.

Significant efforts have been made in recent years to identify more environmentally benign and safe alternatives to side-chain protection and deprotection in solid-phase peptide synthesis (SPPS). Several protecting groups have been endorsed as suitable candidates, but finding a greener protecting group in SPPS has been challenging. Here, based on the 2-(o-nitrophenyl) propan-1-ol (Npp-OH) photolabile protecting group, a structural modification was carried out to synthesize a series of derivatives. Through experimental verification, we found that 3-(o-Nitrophenyl) butan-2-ol (Npb-OH) had a high photo-release rate, high tolerance to the key conditions of Fmoc-SPPS (20% piperidine DMF alkaline solution, and pure TFA acidic solution), and applicability as a carboxyl-protective group in aliphatic and aromatic carboxyl groups. Finally, Npb-OH was successfully applied to the synthesis of head-tail cyclic peptides and side-chain-tail cyclic peptides. Moreover, we found that Npb-OH could effectively resist diketopiperazines (DKP). The α-H of Npb-OH was found to be necessary for its photosensitivity in comparison to 3-(o-Nitrophenyl)but-3-en-2-ol (Npbe-OH) during photolysis-rate verification.

Identifying potential association on gene-disease network via dual hypergraph regularized least squares.

BACKGROUND: Identifying potential associations between genes and diseases via biomedical experiments must be the time-consuming and expensive research works. The computational technologies based on machine learning models have been widely utilized to explore genetic information related to complex diseases. Importantly, the gene-disease association detection can be defined as the link prediction problem in bipartite network. However, many existing methods do not utilize multiple sources of biological information; Additionally, they do not extract higher-order relationships among genes and diseases. RESULTS: In this study, we propose a novel method called Dual Hypergraph Regularized Least Squares (DHRLS) with Centered Kernel Alignment-based Multiple Kernel Learning (CKA-MKL), in order to detect all potential gene-disease associations. First, we construct multiple kernels based on various biological data sources in gene and disease spaces respectively. After that, we use CAK-MKL to obtain the optimal kernels in the two spaces respectively. To specific, hypergraph can be employed to establish higher-order relationships. Finally, our DHRLS model is solved by the Alternating Least squares algorithm (ALSA), for predicting gene-disease associations. CONCLUSION: Comparing with many outstanding prediction tools, DHRLS achieves best performance on gene-disease associations network under two types of cross validation. To verify robustness, our proposed approach has excellent prediction performance on six real-world networks. Our research work can effectively discover potential disease-associated genes and provide guidance for the follow-up verification methods of complex diseases.

Changes of hippocampus proteomic profiles after blueberry extracts supplementation in APP/PS1 transgenic mice.

Objective: To examine protein changes in the hippocampus of APP/PS1 transgenic mice after blueberry extracts (BB) intervention.Methods: Eight APP/PS1 transgenic mice were randomly assigned to Alzheimer's disease (AD)+BB group (n=4) and AD+control group (n=4). After a 16-week treatment, 2-DE and MALDI-TOF-MS were used to compare the proteomic profiles of the hippocampus in the two groups and Western blot was used to confirm the important differentially expressed proteins.Results: Twelve proteins were differentially expressed between the two groups. Nine of them were identified. Cytochrome b-c1 complex subunit 6, beta-actin, dynamin 1, and heat shock cognate 71 were up-regulated in AD+BB group, while a-enolase, stress-induced-phosphoprotein 1, malate dehydrogenase (MDH), MDH 1, and T-complex protein 1 subunit beta were down-regulated, respectively. Importantly, some of the identified proteins (e.g. dynamin 1) are known to be involved in cognitive impairment. Western blot analysis of hippocampus dynamin 1 expression confirmed the proteomic findings.Conclusions: The consumption of BB modulates the expression of proteins that are linked to the improvements of cognitive dysfunction in hippocampus of APP/PS1 transgenic mice.

Vitexin alleviates interleukin-1ß-induced inflammatory responses in chondrocytes from osteoarthritis patients: Involvement of HIF-1α pathway.

It has been reported that vitexin has anti-inflammatory effects in osteoarthritis (OA) rats. However, the effects of vitexin on interleukins-1ß (IL-1ß)-stimulated OA patient-derived chondrocytes have not been reported. The purpose of this study was to investigate the anti-inflammatory effects of vitexin on IL-1ß-stimulated human osteoarthritis chondrocytes and to reveal the involvement of hypoxia-inducible factor 1α (HIF-1α) pathway. Enzyme-linked immunosorbent assay, quantitative real-time PCR and Western blotting assays were employed. ELISA results demonstrated that the proinflammatory cytokine levels of interleukins-6 (IL-6) and tumour necrosis factor α (TNF-α) in the serum and synovial fluid and HIF-1α level in the synovial fluid were significantly elevated in OA patients compared to normal healthy subjects. Moreover, the Western blotting results indicated that the protein expression of HIF-1α was significantly higher in the cartilage tissues of OA patients. OA patient-derived chondrocytes were stimulated by IL-1ß and treated with different concentration of vitexin for 24 hours. Vitexin showed no cytotoxicity and increased the survival of chondrocytes under IL-1ß stimulation. Vitexin suppressed IL-1ß-induced production of NO and prostaglandin E2 (PGE2 ) in chondrocytes culture. The treatment of vitexin significantly inhibited IL-1ß-induced expressions of proinflammatory cytokine levels of IL-6, TNF-α, matrix metalloproteinase (MMP)-1, MMP-3 and MMP-13. Furthermore, Western blotting results demonstrated that HIF-1α is involved in vitexin's protective effects on IL-1ß-stimulated injuries in OA patient-derived chondrocytes. Our study demonstrates that vitexin alleviates IL-1ß-induced inflammatory responses in chondrocytes from osteoarthritis patients, which may be attributed partly to the inhibition of HIF-1α pathway.

B vitamin supplementation improves cognitive function in the middle aged and elderly with hyperhomocysteinemia.

OBJECTIVE: An intervention study was performed to determine if supplement containing folic acid, vitamin B6, and vitamin B12 could improve cognitive function and lower homocysteine in middle-aged and elderly patients with hyperhomocysteinemia. METHODS: One hundred and four participants with hyperhomocysteinemia were recruited in Tianjin, China, aged 55-94 years old. Fifty-seven individuals with hyperhomocysteinemia were included in the intervention group (vitamin B group, which received 800 µg/day of folate, with 10 mg of vitamin B6 and 25 µg of vitamin B12) and 47 patients in the placebo group. The endpoint was the improvement in cognitive function as evaluated by Basic Cognitive Aptitude Tests (BCATs). All parameters were measured before and after the treatment period of 14 weeks. RESULTS: The BCAT total score and four sub-tests scores (digit copy, Chinese character rotation, digital working memory, and recognition of meaningless figure) of BCAT at 14 weeks significantly increased only for the vitamin B group. Serum total homocysteine (tHcy) levels significantly decreased in the intervention group, while serum concentrations of folate, vitamin B6, and vitamin B12 significantly increased in the intervention group. CONCLUSION: The results demonstrated that supplement containing folate, vitamin B6, and vitamin B12 in middle-aged and elderly patients with hyperhomocysteinemia could improve their cognitive function partly and reduce serum tHcy levels.

NormAUG: Normalization-Guided Augmentation for Domain Generalization.

Deep learning has made significant advancements in supervised learning. However, models trained in this setting often face challenges due to domain shift between training and test sets, resulting in a significant drop in performance during testing. To address this issue, several domain generalization methods have been developed to learn robust and domain-invariant features from multiple training domains that can generalize well to unseen test domains. Data augmentation plays a crucial role in achieving this goal by enhancing the diversity of the training data. In this paper, inspired by the observation that normalizing an image with different statistics generated by different batches with various domains can perturb its feature, we propose a simple yet effective method called NormAUG (Normalization-guided Augmentation). Our method includes two paths: the main path and the auxiliary (augmented) path. During training, the auxiliary path includes multiple sub-paths, each corresponding to batch normalization for a single domain or a random combination of multiple domains. This introduces diverse information at the feature level and improves the generalization of the main path. Moreover, our NormAUG method effectively reduces the existing upper boundary for generalization based on theoretical perspectives. During the test stage, we leverage an ensemble strategy to combine the predictions from the auxiliary path of our model, further boosting performance. Extensive experiments are conducted on multiple benchmark datasets to validate the effectiveness of our proposed method.

Jerks are Useful: Extracting pulse rate from wrist-placed accelerometry jerk during sleep in children.

STUDY OBJECTIVES: Evaluate wrist-placed accelerometry predicted heartrate compared to electrocardiogram (ECG) heartrate in children during sleep. METHODS: Children (n=82, 61% male, 43.9% Black) wore a wrist-placed Apple Watch Series 7 (AWS7) and ActiGraph GT9X during a polysomnogram. 3-Axis accelerometry data was extracted from AWS7 and the GT9X. Accelerometry heartrate estimates were derived from jerk (the rate of acceleration change), computed using the peak magnitude frequency in short time Fourier Transforms of Hilbert transformed jerk computed from acceleration magnitude. Heartrates from ECG traces were estimated from R-R intervals using R-pulse detection. Lin's Concordance Correlation Coefficient (CCC), mean absolute error (MAE) and mean absolute percent error (MAPE) assessed agreement with ECG estimated heartrate. Secondary analyses explored agreement by polysomnography sleep stage and a signal quality metric. RESULTS: The developed scripts are available on Github. For the GT9X, CCC was poor at -0.11 and MAE and MAPE were high at 16.8 (SD=14.2) beats/minute and 20.4% (SD=18.5%). For AWS7, CCC was moderate at 0.61 while MAE and MAPE were lower at 6.4 (SD=9.9) beats/minute and 7.3% (SD=10.3%). Accelerometry estimated heartrate for AWS7 was more closely related to ECG heartrate during N2, N3 and REM sleep than lights on, wake, and N1 and when signal quality was high. These patterns were not evident for the GT9X. CONCLUSIONS: Raw accelerometry data extracted from AWS7, but not the GT9X, can be used to estimate heartrate in children while they sleep. Future work is needed to explore the sources (i.e., hardware, software, etc.) of the GT9X's poor performance.

Low Rank Matrix Factorization Algorithm Based on Multi-Graph Regularization for Detecting Drug-Disease Association.

Detecting potential associations between drugs and diseases plays an indispensable role in drug development, which has also become a research hotspot in recent years. Compared with traditional methods, some computational approaches have the advantages of fast speed and low cost, which greatly accelerate the progress of predicting the drug-disease association. In this study, we propose a novel similarity-based method of low-rank matrix decomposition based on multi-graph regularization. On the basis of low-rank matrix factorization with L2 regularization, the multi-graph regularization constraint is constructed by combining a variety of similarity matrices from drugs and diseases respectively. In the experiments, we analyze the difference in the combination of different similarities, resulting that combining all the similarity information on drug space is unnecessary, and only a part of the similarity information can achieve the desired performance. Then our method is compared with other existing models on three data sets (Fdataset, Cdataset and LRSSLdataset) and have a good advantage in the evaluation measurement of AUPR. Besides, a case study experiment is conducted and showing that the superior ability for predicting the potential disease-related drugs of our model. Finally, we compare our model with some methods on six real world datasets, and our model has a good performance in detecting real world data.

The pH-responsiveness carrier of sanxan gel beads crosslinked with CaCl2 to control drug release.

Natural polysaccharide-based gel carriers have been widely studied for their potential to provide slow and controlled release. Sanxan is an edible polysaccharide produced by Sphingomonas sanxanigenens. In this study, gel beads were prepared using the extrusion dripping method with sanxan as the carrier material and HCl and CaCl2 as the fixing solution. The molecular structure, texture profile, and microstructure of the bead were analyzed. And the swelling characterization and in vitro release of beads were evaluated. The results of Fourier-transform infrared analysis indicate that Ca2+ was used to create an ionically crosslinked structure of sanxan. Texture analyzer and scanning electron microscope studies showed that the acid­calcium gel exhibited physical resistance and resilience, as well as a distinct gel pore structure. The swelling, dissolution, and drug release of the beads decreased as the amount of CaCl2 increased. Compared to the control (without CaCl2), the release of sanxan beads when 0.5 CaCl2 was added (sanxan carboxyl/Ca2+, by the number of moles M/M) in the stomach and small intestine release decreased by 40.9 % and 49.5 %, respectively. This study indicates that the fabrication of sanxan-Ca2+ crosslinked gel had sustained release characteristics, indicating that sanxan carriers have great potential for gradual and regulated medication delivery.

Preparation and properties of Sanxan gel based fertilizer for water retention and slow-release.

The advent of gel fertilizers has benefited agriculture and the environment. This study utilized sanxan, a novel polysaccharide, as a carrier and loaded it with urea to create sanxan gel fertilizer (SGF), thus creating a new, effective gel fertilizer. Water retention and sustained release ability of SGF were evaluated, and crop experiments were carried out. The results showed that, SGF that content 2.0 % solution of sanxan and loaded 20 g g-1 of urea were prepared by heating-cooling method. The water-retention ratio of SGF was attained at 56.4 g g-1 for 10 h. The urea releases of SGF in water have a more significant persistence than pure urea. In addition, wheat growth was promoted by SGF, compared with pure urea, the biomass of wheat shoot and root increased 27.4 % and 62.2 % during 20 days, respectively. Consequently, SGF has the ability to retain water and slowly release nutrition, which was an ideal carrier for managing water and urea. The SGF developed in this study provides data support and theoretical basis for the application of sanxan gel in agriculture and the environment.

Depletion of intracellular zinc induced apoptosis in cultured hippocampal neurons through Raf/MEK/ERK pathways.

An experiment was performed to observe the changes in Raf-1 kinase/mitogen-activated protein kinase ERK (MEK)/extracellular signal-regulated kinase (ERK) signaling pathways in cultured hippocampal neurons and its correlation with neurons apoptosis induced by intracellular zinc depletion. Cultured hippocampal neurons were exposed to a cell membrane-permeant zinc chelator TPEN (2 µM), and to TPEN plus zinc sulfate (5 µM) for 24 h. Cultures were then processed to detect neuronal viability by the methyl thiazolyl tetrazolium assay, while apoptosis rate was simultaneously observed by the flow cytometric analysis. Caspase-3, Raf-1, pMEK, pERK1/2, and pCREB protein levels were examined by Western blot assays. The viability in TPEN-incubated neurons was notably decreased, apoptosis rate and expression of caspase-3 significantly increased compared to untreated controls. The significant down-regulation of Raf/MEK/ERK signaling pathway and expression of pCREB were decreased in TPEN-treated neurons. Co-addition of zinc almost completely reversed TPEN-induced alterations described. The results demonstrated zinc-modulated apoptosis and the expression of Raf/MEK/ERK at the protein level in hippocampal neurons. It is possible that zinc depletion-induced apoptosis in cultured hippocampal neurons may be relevant to the changes of Raf/MEK/ERK signaling pathway.

[Primary study on protective effect of mulberry extracts on Abeta25-35-induced PC12 cells injury].

OBJECTIVE: To investigate the neuroprotective effect of mulberry extracts (ME) against Abeta25-35-induced injury in cultured PC12 cells and explore the possible mechanisms involved. METHODS: PC12 cells at logarithmic growth phase were divided into the normal control group, Abeta25-35 group (20 micromol/L for 24h) and ME pretreating groups at the concentrations of 25, 50, 100, 200, 400, 800 microg/ml. Cell viability was determined by MTT assay. On that basis, PC12 cells were divided into the normal control group, ME group (200 microg/ml ME incubation alone for 24h), Abeta25-35 group (20 micromol/L for 24h) and ME plus Abeta25-35 group (after pretreatment with 200 microg/ml ME for 24h, cells were exposed to 201 micromol/L Abeta25-35 for another 24h). Intracellular reactive oxidative species (ROS) was measured by using the fluorescent DCFH-DA and the apoptotic cells were observed by Hoechst33342 staining method. RESULTS: (1) The results showed that exposure of PC12 cells to Abeta22-35 (20 micromol/L) for 24h induced notably neuronal injury (P < 0.05) as compared with the control group, while pretreatment with 100 or 200 microg/ml ME almost completely reversed Abeta25-35 induced neuronal injury (P < 0.05). (2) There were no remarkable changes in ROS levels and apoptosis rate of ME group as compared with the control group (P > 0.05). Compared with the control group, exposure to 20 micromol/L Abeta25-35 for 24h resulted in a significant decrease in cell viability (P < 0.05) while increase in ROS levels and cell apoptosis rate (P < 0.05). But pretreatment of PC12 cells with 200 microg/ml ME could counteract ROS formation and inhibit apoptosis (P < 0.05). CONCLUSION: These results suggest that mulberry extracts rich in phenolics and anthocyanins could alleviate Abeta25-35-induced injury in PC12 cells, which might be associated with the antioxidative and antiapoptosis effects.

Predicting RBP Binding Sites of RNA With High-Order Encoding Features and CNN-BLSTM Hybrid Model.

RNA binding protein (RBP) is extensively involved in various cellular regulatory processes through the interaction with RNAs. Capturing the RBP binding preferences is fundamental for revealing the pathogenesis of complex diseases. Many experimental detection techniques are still time-consuming and labor-intensive, therefore, it is indispensable to develop a computational method with convincing accuracy. In this study, we proposed a CNN-BLSTM hybrid deep learning framework, named DeepDW, for predicting the RBP binding sites on RNAs with high-order encoding features of RNA sequence and secondary structure. The high-order encoding strategy was used to characterize the dependencies among adjacency nucleotides. For CNN-BLSTM hybrid model, DeepDW first employed two 1-D convolutional neural networks (CNNs) for learning the local features from high-order encoded matrices of RNA sequence and structure separately, and then applied two bidirectional long short-term memory networks (BLSTMs) to capture the global information in a higher level. Moreover, a series of experiments were carried out on 31 public datasets to evaluate our proposed framework, and DeepDW achieved superior performance than the state-of-the-art methods. The results indicated that the combination of high-order encoding method and CNN-BLSTM hybrid model had advantages in identifying RBP-RNA binding sites.

Study on the effects of environmental factors on enzyme activities during growth of Hypsizygus marmoreus.

The sensitivity of Hypsizygus marmoreus to environmental factors such as temperature, humidity, illumination and CO2 concentration varies greatly in different growth stages. In this paper, the effects of various environmental factors on the growth and development of H. marmoreus were investigated by measuring the enzyme activities of H. marmoreus at different growth stages under different microenvironment conditions in the mushroom room, so as to confirm the influence mechanism of environmental factors on the growth of H. marmoreus. The results showed that at budding stage xylanase and laccase were found significantly positively correlated with CO2 concentration and light intensity, and dramatically negatively correlated with humidity while carboxymethyl cellulose and manganese peroxidase were markedly positively correlated with humidity, and significantly negatively correlated with CO2 concentration and light intensity. On the other hand, in mature fruit bodies xylanase activity was found significantly positively correlated with CO2 concentration and light intensity, and dramatically negatively correlated with humidity while manganese peroxidase activities were found significantly positively correlated with humidity, and dramatically negatively correlated with light intensity. The activity of ß-glucosidase in budding and mature fruiting bodies was markedly negatively correlated with CO2 concentration and significantly positively correlated with humidity.

Synthesis and antitumor effects of novel benzyl naphthyl sulfoxide/sulfone derivatives derived from Rigosertib.

In this work, a series of novel benzyl naphthyl sulfoxides/sulfones derived from Rigosertib were designed and synthesized as potential antitumor agents. The in vitro cytotoxicity against four human cancer cell lines (HeLa, MCF-7, HepG2 and SCC-15) and two normal human cell lines (HUVEC and 293T) indicated that some of the sulfones and sulfoxides possessed potent antineoplastic activity that reached nanomolar levels and relatively low toxicity to normal cells. Among them, (2-methoxy-5-((naphthalen-2-ylsulfonyl)methyl)phenyl)glycine (15b) was found to be a promising antitumor drug candidate that could significantly inhibit tumor cell migration and induce tumor cell apoptosis via the p53-Bcl-2-Bax signaling pathway at nanomolar concentrations.