A hybrid deep learning framework for gene regulatory network inference from single-cell transcriptomic data.

Inferring gene regulatory networks (GRNs) based on gene expression profiles is able to provide an insight into a number of cellular phenotypes from the genomic level and reveal the essential laws underlying various life phenomena. Different from the bulk expression data, single-cell transcriptomic data embody cell-to-cell variance and diverse biological information, such as tissue characteristics, transformation of cell types, etc. Inferring GRNs based on such data offers unprecedented advantages for making a profound study of cell phenotypes, revealing gene functions and exploring potential interactions. However, the high sparsity, noise and dropout events of single-cell transcriptomic data pose new challenges for regulation identification. We develop a hybrid deep learning framework for GRN inference from single-cell transcriptomic data, DGRNS, which encodes the raw data and fuses recurrent neural network and convolutional neural network (CNN) to train a model capable of distinguishing related gene pairs from unrelated gene pairs. To overcome the limitations of such datasets, it applies sliding windows to extract valuable features while preserving the direction of regulation. DGRNS is constructed as a deep learning model containing gated recurrent unit network for exploring time-dependent information and CNN for learning spatially related information. Our comprehensive and detailed comparative analysis on the dataset of mouse hematopoietic stem cells illustrates that DGRNS outperforms state-of-the-art methods. The networks inferred by DGRNS are about 16% higher than the area under the receiver operating characteristic curve of other unsupervised methods and 10% higher than the area under the precision recall curve of other supervised methods. Experiments on human datasets show the strong robustness and excellent generalization of DGRNS. By comparing the predictions with standard network, we discover a series of novel interactions which are proved to be true in some specific cell types. Importantly, DGRNS identifies a series of regulatory relationships with high confidence and functional consistency, which have not yet been experimentally confirmed and merit further research.

Theoretical study on intramolecular hydrogen bonds of flavonoid cocrystals.

This study investigates the role of intramolecular hydrogen bonds in the formation of cocrystals involving flavonoid molecules, focusing on three active pharmaceutical ingredients (APIs): chrysin (CHR), isoliquiritigenin (ISO), and kaempferol (KAE). These APIs form cocrystals with different cocrystal formers (CCFs) through intramolecular hydrogen bonding. We found that disruption of these intramolecular hydrogen bonds leads to decreased stability compared to molecules with intact bonds. The extrema of molecular electrostatic potential surfaces (MEPS) show that flavonoid molecules with disrupted intramolecular hydrogen bonds have stronger hydrogen bond donors and acceptors than those with intact bonds. Using the artificial bee colony algorithm, dimeric structures of these flavonoid molecules were explored, representing early-stage structures in cocrystal formation, including API-API, API-CCF, and CCF-CCF dimers. It was observed that the number and strength of dimeric interactions significantly increased, and the types of interactions changed when intramolecular hydrogen bonds were disrupted. These findings suggest that disrupting intramolecular hydrogen bonds generally hinders the formation of cocrystals. This theoretical study provides deeper insight into the role of intramolecular hydrogen bonds in the cocrystal formation of flavonoids.

NBCR-ac4C: A Deep Learning Framework Based on Multivariate BERT for Human mRNA N4-Acetylcytidine Sites Prediction.

N4-acetylcytidine (ac4C) plays a crucial role in regulating cellular biological processes, particularly in gene expression regulation and disease development. However, experiments to identify ac4C in a wet lab are time-consuming and costly, and the learning-based methods struggle to capture the underlying semantic knowledge and relations within sequences. To address this, we propose a deep learning approach called NBCR-ac4C based on pretrained models. Specifically, we employ Nucleotide Transformer and DNABERT2 to construct contextual embedding of nucleotide sequences, which effectively mine and express context relations between different features in the sequence. Convolutional neural network (CNN) and ResNet18 are then applied to further extract shallow and deep knowledge from context embedding. Depending on extensive experiments for the prediction of ac4C sites in nucleotide sequences, we observe that NBCR-ac4C outperforms general learning-based models. It achieves the highest accuracy (ACC) of 83.51% and an Area Under the Receiver Operating Characteristic Curve (AUROC) of 89.58% on an independent test set. Moreover, the proposed model, compared to the current state-of-the-art (SOTA) model LSA-ac4C, demonstrates higher ACC and AUROC by 0.81-3.7% and 0.05-1.58%, respectively. The data set and code are available on https://github.com/2103374200/NBCR to facilitate further discussion on NBCR-ac4C.

Glypred: Lysine Glycation Site Prediction via CCU-LightGBM-BiLSTM Framework with Multi-Head Attention Mechanism.

Glycation, a type of posttranslational modification, preferentially occurs on lysine and arginine residues, impairing protein functionality and altering characteristics. This process is linked to diseases such as Alzheimer's, diabetes, and atherosclerosis. Traditional wet lab experiments are time-consuming, whereas machine learning has significantly streamlined the prediction of protein glycation sites. Despite promising results, challenges remain, including data imbalance, feature redundancy, and suboptimal classifier performance. This research introduces Glypred, a lysine glycation site prediction model combining ClusterCentroids Undersampling (CCU), LightGBM, and bidirectional long short-term memory network (BiLSTM) methodologies, with an additional multihead attention mechanism integrated into the BiLSTM. To achieve this, the study undertakes several key steps: selecting diverse feature types to capture comprehensive protein information, employing a cluster-based undersampling strategy to balance the data set, using LightGBM for feature selection to enhance model performance, and implementing a bidirectional LSTM network for accurate classification. Together, these approaches ensure that Glypred effectively identifies glycation sites with high accuracy and robustness. For feature encoding, five distinct feature types─AAC, KMER, DR, PWAA, and EBGW─were selected to capture a broad spectrum of protein sequence and biological information. These encoded features were integrated and validated to ensure comprehensive protein information acquisition. To address the issue of highly imbalanced positive and negative samples, various undersampling algorithms, including random undersampling, NearMiss, edited nearest neighbor rule, and CCU, were evaluated. CCU was ultimately chosen to remove redundant nonglycated training data, establishing a balanced data set that enhances the model's accuracy and robustness. For feature selection, the LightGBM ensemble learning algorithm was employed to reduce feature dimensionality by identifying the most significant features. This approach accelerates model training, enhances generalization capabilities, and ensures good transferability of the model. Finally, a bidirectional long short-term memory network was used as the classifier, with a network structure designed to capture glycation modification site features from both forward and backward directions. To prevent overfitting, appropriate regularization parameters and dropout rates were introduced, achieving efficient classification. Experimental results show that Glypred achieved optimal performance. This model provides new insights for bioinformatics and encourages the application of similar strategies in other fields. A lysine glycation site prediction software tool was also developed using the PyQt5 library, offering researchers an auxiliary screening tool to reduce workload and improve efficiency. The software and data sets are available on GitHub: https://github.com/ZBYnb/Glypred.

Impacts of Evidence-based Nursing on Quality of Life and Anxiety in Patients with Liver Injury.

Background: Plasma exchange is the most commonly applied method for treating severe hepatitis. As a kind of invasive treatment, plasma exchange may have various complications during treatment. Therefore, effective nursing should be implemented during plasma exchange treatment to prevent the incidence of complications. Objective: To compare the effects of traditional nursing methods versus evidence-based nursing practices on the quality of life and anxiety of patients with liver injury. Design: This was a retrospective study. Patient data were obtained from patient records. Setting: This study was carried out in the Department of Gastroenterology, Second Hospital of Hebei Medical University. Participants: One hundred and twenty severe hepatitis patients with 89 cases of early hepatic failure and 31 cases of middle hepatic failure admitted to our department from January 2020 to December 2022 were chosen, followed by randomly separating into a control group and an observation group. Interventions: The control group adopted nursing, while the observation group received evidence-based nursing including psychological nursing, nursing during treatment and post-treatment nursing. Primary Outcome Measures: (1) liver function (2) emotional state assessed by Self-rating Anxiety Scale (SAS) along with Self-rating Depression Scale (SDS) (3) coagulation function, (4) quality of life assessed by Short-Form 36 (SF-36) scale (5) nursing satisfaction, and (6) incidence of complications. Results: In contrast to the control group, the occurrence of complications in the observation group was significantly lower (P < .05). At 1-month review, the quality of life score in the observation group was higher in contrast to the control group (P < .05). In contrast to the control group, the nursing satisfaction of patients in the observation group was better (P < .05), alanine aminotransferase and total bilirubin levels in the observation group were lower, while albumin levels were higher (P < .05), the anxiety and depression scores of the observation group were lessened (P < .05), and the required time of coagulation function indexes in the observation group was shorter (P < .05). Conclusion: The application of evidence-based nursing to artificial liver therapy in patients with liver failure can effectively promote the liver function and coagulation index of patients, help to relieve negative emotions, and promote the quality of life of patients. This study may provide clinical reference for the nursing of artificial liver therapy in patients with liver failure.

MMFGRN: a multi-source multi-model fusion method for gene regulatory network reconstruction.

Lots of biological processes are controlled by gene regulatory networks (GRNs), such as growth and differentiation of cells, occurrence and development of the diseases. Therefore, it is important to persistently concentrate on the research of GRN. The determination of the gene-gene relationships from gene expression data is a complex issue. Since it is difficult to efficiently obtain the regularity behind the gene-gene relationship by only relying on biochemical experimental methods, thus various computational methods have been used to construct GRNs, and some achievements have been made. In this paper, we propose a novel method MMFGRN (for "Multi-source Multi-model Fusion for Gene Regulatory Network reconstruction") to reconstruct the GRN. In order to make full use of the limited datasets and explore the potential regulatory relationships contained in different data types, we construct the MMFGRN model from three perspectives: single time series data model, single steady-data model and time series and steady-data joint model. And, we utilize the weighted fusion strategy to get the final global regulatory link ranking. Finally, MMFGRN model yields the best performance on the DREAM4 InSilico_Size10 data, outperforming other popular inference algorithms, with an overall area under receiver operating characteristic score of 0.909 and area under precision-recall (AUPR) curves score of 0.770 on the 10-gene network. Additionally, as the network scale increases, our method also has certain advantages with an overall AUPR score of 0.335 on the DREAM4 InSilico_Size100 data. These results demonstrate the good robustness of MMFGRN on different scales of networks. At the same time, the integration strategy proposed in this paper provides a new idea for the reconstruction of the biological network model without prior knowledge, which can help researchers to decipher the elusive mechanism of life.

A comprehensive overview and critical evaluation of gene regulatory network inference technologies.

Gene regulatory network (GRN) is the important mechanism of maintaining life process, controlling biochemical reaction and regulating compound level, which plays an important role in various organisms and systems. Reconstructing GRN can help us to understand the molecular mechanism of organisms and to reveal the essential rules of a large number of biological processes and reactions in organisms. Various outstanding network reconstruction algorithms use specific assumptions that affect prediction accuracy, in order to deal with the uncertainty of processing. In order to study why a certain method is more suitable for specific research problem or experimental data, we conduct research from model-based, information-based and machine learning-based method classifications. There are obviously different types of computational tools that can be generated to distinguish GRNs. Furthermore, we discuss several classical, representative and latest methods in each category to analyze core ideas, general steps, characteristics, etc. We compare the performance of state-of-the-art GRN reconstruction technologies on simulated networks and real networks under different scaling conditions. Through standardized performance metrics and common benchmarks, we quantitatively evaluate the stability of various methods and the sensitivity of the same algorithm applying to different scaling networks. The aim of this study is to explore the most appropriate method for a specific GRN, which helps biologists and medical scientists in discovering potential drug targets and identifying cancer biomarkers.

Reaction-based fluorescence probes for "turn on" sensing fluoride ions.

Introducing a weak covalent bond into an originally highly fluorescent molecule to create a non-fluorescent probe is able to provide a new way to detect some nucleophilic targets with enhanced sensitivity. Herein, this is the first time that a tetraphenylethene (TPE)-based probe (TPEONO2) bearing a p-nitrobenzenesulfonyl moiety for the sensing of F- ions in aqueous solution via a cleavage reaction of the sulfonyl ester bond to induce aggregation-induced emission (AIE) has been reported.

Effect of WeChat Messaging on Improving the Quality of Bowel Preparation for Outpatient Colonoscopy: A Randomized Controlled Study.

With the most active users of any social media platform in China, WeChat has become the preferred platform for public announcements and is widely used in the fields of medicine and nursing (Hong, Zhou, Fang, & Shi, 2017; Zeng, Deng, Wang, & Liu, 2016). The aim of this study was to evaluate the effect of WeChat messaging on bowel preparation for outpatient colonoscopy. A total of 150 outpatients scheduled for colonoscopy in a Grade III level A hospital were randomly assigned to the experimental group (n = 73) or the control group (n = 72). Both groups received routine guidance from the day of the scheduling appointment through the day of colonoscopy. In addition, the experimental group received colonoscopy-related information and individualized guidance daily through WeChat from the day of the appointment. After the colonoscopy, the diet and medication compliance, satisfaction, anxiety, and bowel cleanliness were compared. Post-intervention, there were significant differences in bowel cleanliness, satisfaction, diet and medication compliance, and anxiety between the two groups. WeChat messaging can help improve diet and medication compliance, patient satisfaction, and the success rate and thoroughness of colonoscopy, as well as alleviate the anxiety of patients scheduled for outpatient colonoscopy.

4mCPred: machine learning methods for DNA N4-methylcytosine sites prediction.

MOTIVATION: N4-methylcytosine (4mC), an important epigenetic modification formed by the action of specific methyltransferases, plays an essential role in DNA repair, expression and replication. The accurate identification of 4mC sites aids in-depth research to biological functions and mechanisms. Because, experimental identification of 4mC sites is time-consuming and costly, especially given the rapid accumulation of gene sequences. Supplementation with efficient computational methods is urgently needed. RESULTS: In this study, we developed a new tool, 4mCPred, for predicting 4mC sites in Caenorhabditis elegans, Drosophila melanogaster, Arabidopsis thaliana, Escherichia coli, Geoalkalibacter subterraneus and Geobacter pickeringii. 4mCPred consists of two independent models, 4mCPred_I and 4mCPred_II, for each species. The predictive results of independent and cross-species tests demonstrated that the performance of 4mCPred_I is a useful tool. To identify position-specific trinucleotide propensity (PSTNP) and electron-ion interaction potential features, we used the F-score method to construct predictive models and to compare their PSTNP features. Compared with other existing predictors, 4mCPred achieved much higher accuracies in rigorous jackknife and independent tests. We also analyzed the importance of different features in detail. AVAILABILITY AND IMPLEMENTATION: The web-server 4mCPred is accessible at http://server.malab.cn/4mCPred/index.jsp. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A new 1,2,3-triazole and its rhodamine B derivatives as a fluorescence probe for mercury ions.

A newly synthesized compound, 5-methyl-1-phenyl-1H-1,2,3-triazole-4- carboxylic acid (MPC) was analyzed for its quantum chemical parameters and theoretical spectrum by computational chemistry. The calculated spectrum was in accord with the experimental measurements in a great degree. Then MPC was successfully designed and synthesized to a novel rhodamine B derivative RMPC. The RMPC exhibited about a 4000-fold increase in fluorescence intensity in the presence of Hg2+ ions over most other competitive metal ions. The triazole appended colorless chemodosimeter RMPC turns to pink upon the complex formation only with Hg2+ ions as a 1: 2 M ratio and enables naked-eye detection. The coordination mechanism of turning on/off fluorescence for Hg2+ ions were well proposed by explaining Hg2+ inducing the ring-opened rhodamine B moiety. The fluorescence imaging experiments of Hg2+ in HeLa cell demonstrated that the probe was labeled and it could be used in biological systems.

Identification of Highest-Affinity Binding Sites of Yeast Transcription Factor Families.

Transcription factors (TFs) play a crucial role in controlling key cellular processes and responding to the environment. Yeast is a single-cell fungal organism that is a vital biological model organism for studying transcription and translation in basic biology. The transcriptional control process of yeast cells has been extensively calculated and studied using traditional methods and high-throughput technologies. However, the identities of transcription factors that regulate major functional categories of genes remain unknown. Due to the avalanche of biological data in the post-genomic era, it is an urgent need to develop automated computational methods to enable accurate identification of efficient transcription factor binding sites from the large number of candidates. In this paper, we analyzed high-resolution DNA-binding profiles and motifs for TFs, covering all possible contiguous 8-mers. First, we divided all 8-mer motifs into 16 various categories and selected all sorts of samples from each category by setting the threshold of E-score. Then, we employed five feature representation methods. Also, we adopted a total of four feature selection methods to filter out useless features. Finally, we used Extreme Gradient Boosting (XGBoost) as our base classifier and then utilized the one-vs-rest tactics to build 16 binary classifiers to solve this multiclassification problem. In the experiment, our method achieved the best performance with an overall accuracy of 79.72% and Mathew's correlation coefficient of 0.77. We found the similarity relationship among each category from different TF families and obtained sequence motif schematic diagrams via multiple sequence alignment. The complexity of DNA recognition may act as an important role in the evolution of gene regulation. Source codes are available at https://github.com/guofei-tju/tfbs.

A Combined Analysis of Genetically Correlated Traits Identifies Genes and Brain Regions for Insomnia.

AIMS: Previous studies have inferred that there is a strong genetic component in insomnia. However, the etiology of insomnia is still unclear. This study systematically analyzed multiple genome-wide association study (GWAS) data sets with core human pathways and functional networks to detect potential gene pathways and networks associated with insomnia. METHODS: We used a novel method, multitrait analysis of genome-wide association studies (MTAG), to combine 3 large GWASs of insomnia symptoms/complaints and sleep duration. The i-Gsea4GwasV2 and Reactome FI programs were used to analyze data from the result of MTAG analysis and the nominally significant pathways, respectively. RESULTS: Through analyzing data sets using the MTAG program, our sample size increased from 113,006 subjects to 163,188 subjects. A total of 17 of 1,816 Reactome pathways were identified and showed to be associated with insomnia. We further revealed 11 interconnected functional and topologically interacting clusters (Clusters 0 to 10) that were associated with insomnia. Based on the brain transcriptome data, it was found that the genes in Cluster 4 were enriched for the transcriptional coexpression profile in the prenatal dorsolateral prefrontal cortex (P = 7 × 10-5), inferolateral temporal cortex (P = 0.02), medial prefrontal cortex (P < 1 × 10-5), and amygdala (P < 1 × 10-5), and detected RPA2, ORC6, PIAS3, and PRIM2 as core nodes in these 4 brain regions. CONCLUSIONS: The findings provided new genes, pathways, and brain regions to understand the pathology of insomnia.

Systematic genetic analyses of genome-wide association study data reveal an association between the key nucleosome remodeling and deacetylase complex and bipolar disorder development.

BACKGROUND: Genome-wide association studies (GWASs) are used to identify genetic variants for association with bipolar disorder (BD) risk; however, each GWAS can only reveal a small fraction of this association. This study systematically analyzed multiple GWAS data sets to provide further insights into potential causal BD processes by integrating the results of Psychiatric Genomics Consortium Phase I (PGC-I) for BD with core human pathways and functional networks. METHODS: The i-Gsea4GwasV2 program was used to analyze data from the PGC-I GWAS for BD (the pathways came from Reactome), as well as the nominally significant pathways. We established a gene network of the significant pathways and performed a gene set analysis for each gene cluster of the Enhancing Neuroimaging Genetics through Meta-Analysis (ENIGMA) GWAS data for the volumes of the intracranial region and seven subcortical regions. RESULTS: A total of 30 of 1816 Reactome pathways were identified and showed associations with BD risk. We further revealed 22 interconnected functional and topologically interacting clusters (Clusters 0-21) that were associated with BD risk. Moreover, we obtained brain transcriptome data from BrainSpan and found significant associations between common variants of the genes in Cluster 1 with the hippocampus (HIP; P = .026; family-wise error [FWE] correction) and amygdala (AMY; P = .016; FEW correction) in Cluster 8 with HIP (P = .022; FWE correction). The genes in Cluster 1 were enriched for the transcriptional co-expression profile in the prenatal AMY, and core genes (CDH4, MTA2, RBBP4, and HDAC2) were identified to be involved in regulating early brain development. CONCLUSION: This study demonstrated that the HIP and AMY play a central role in neurodevelopment and BD risk.

Special Protein Molecules Computational Identification.

Computational identification of special protein molecules is a key issue in understanding protein function. It can guide molecular experiments and help to save costs. I assessed 18 papers published in the special issue of Int. J. Mol. Sci., and also discussed the related works. The computational methods employed in this special issue focused on machine learning, network analysis, and molecular docking. New methods and new topics were also proposed. There were in addition several wet experiments, with proven results showing promise. I hope our special issue will help in protein molecules identification researches.

The evaluation of acute toxicity, antimicrobial activity of 1-phenyl-5-p-tolyl-1H-1, 2, 3-triazole, and binding to human serum albumin.

1-Phenyl-5-p-tolyl-1H-1, 2, 3-triazole (PPTA) was a synthesized compound. The result of acute toxicities to mice of PPTA by intragastric administration indicated that PPTA did not produce any significant acute toxic effect on Kunming strain mice. It exhibited the various potent inhibitory activities against two kinds of bananas pathogenic bacteria, black sigatoka and freckle, when compared with that of control drugs and the inhibitory rates were up to 64.14% and 43.46%, respectively, with the same concentration of 7.06 mM. The interaction of PPTA with human serum albumin (HSA) was studied using fluorescence polarization, absorption spectra, 3D fluorescence, and synchronous spectra in combination with quantum chemistry and molecular modeling. Multiple modes of interaction between PPTA and HSA were suggested to stabilize the PPTA-HSA complex, based on thermodynamic data and molecular modeling. Binding of PPTA to HSA induced perturbation in the microenvironment around HSA as well as secondary structural changes in the protein.

[Exploration of common biological pathways for attention deficit hyperactivity disorder and low birth weight].

OBJECTIVE: To explore common biological pathways for attention deficit hyperactivity disorder (ADHD) and low birth weight (LBW). METHODS: Thei-Gsea4GwasV2 software was used to analyze the result of genome-wide association analysis (GWAS) for LBW (pathways were derived from Reactome), and nominally significant (P< 0.05, FDR< 0.25) pathways were tested for replication in ADHD.Significant pathways were analyzed with DAPPLE and Reatome FI software to identify genes involved in such pathways, with each cluster enriched with the gene ontology (GO). The Centiscape2.0 software was used to calculate the degree of genetic networks and the betweenness value to explore the core node (gene). Weighed gene co-expression network analysis (WGCNA) was then used to explore the co-expression of genes in these pathways.With gene expression data derived from BrainSpan, GO enrichment was carried out for each gene module. RESULTS: Eleven significant biological pathways was identified in association with LBW, among which two (Selenoamino acid metabolism and Diseases associated with glycosaminoglycan metabolism) were replicated during subsequent ADHD analysis. Network analysis of 130 genes in these pathways revealed that some of the sub-networksare related with morphology of cerebellum, development of hippocampus, and plasticity of synaptic structure. Upon co-expression network analysis, 120 genes passed the quality control and were found to express in 3 gene modules. These modules are mainly related to the regulation of synaptic structure and activity regulation. CONCLUSION: ADHD and LBW share some biological regulation processes. Anomalies of such proces sesmay predispose to ADHD.

Characterization of in vivo phosphorylation modification of differentially accumulated proteins in cotton fiber-initiation process.

Initiation of cotton fiber from ovule epidermal cells determines the ultimate number of fibers per cotton ovule, making it one of the restriction factors of cotton fiber yield. Previous comparative proteomics studies have collectively revealed 162 important differentially accumulated proteins (DAPs) in cotton fiber-initiation process, however, whether and how post-translational modifications, especially phosphorylation modification, regulate the expression and function of the DAPs are still unclear. Here we reported the successful identification of 17 phosphopeptides from 16 phosphoproteins out of the 162 DAPs using the integrated bioinformatics analyses of peptide mass fingerprinting data and targeted MS/MS identification method. In-depth analyses indicated that 15 of the 17 phosphorylation sites were novel phosphorylation sites first identified in plants, whereas 6 of the 16 phosphoproteins were found to be the phosphorylated isoforms of 6 proteins. The phosphorylation-regulated dynamic protein network derived from this study not only expanded our understanding of the cotton fiber-initiation process, but also provided a valuable resource for future functional studies of the phosphoproteins.

[Determination of Main Active Components and Metal Elements of Hainan Alpinia Katsumadai by Spectral Analysis].

Fourier transform infrared spectroscopy (FT-IR), UV spectroscopy and fluorescence spectroscopy combined with inductively coupled plasma mass spectrometry (ICP-MS) were employed to analyze Alpinia Katsumadai harvested from Hainan Baisha and Bawangling. The results from FT-IR indicated that the emergence of several characteristic absorption peaks around 1 051, 1 390，2 976 and 3 300 cm-1 belong to flavonoids. In light of second derivative spectra, two similar peaks around 2 977.72 and 2 899.94 cm-1 and evident differences peaks around 1 922.36 and 1 650.87 cm-1 were observed, which was obvious to identify and distinguish Hainan Alpinia Katsumadai from different geographical regions. The method of UV spectroscopy were used to determine the different characteristic spectra of Alpinia Katsumadai harvested from Hainan Baisha and Bawangling. An UV-quantitative analysis method for alpinetin and cardamonin in Alpinia Katsumadai was established according to the relevant absorption principle. The results from fluorescence experiments revealed that both ethanol extracts of Alpinia katsumadai Hayata harvestd from Baisha and Bawangling have the similar fluorescence emission spectra and excitation spectra. The difference of fluorescence intensity once again demonstrated the concentration of ethanol extracts of Alpinia katsumadai Hayata harvestd from Baisha was bigger than that of Bawangling. The good relative recovery was in the range of 84.28%～117.41% with the RSDs (n=3) of 0.42%～0.29%. The content of alpinetin and cardamomin in Alpinia katsumadai from various habitats are 4.23% and 3.83% for Baisha, 3.72% and 3.34% for Baiwangling, respectively. Seventeen kinds of metal elements including K, Ca, Mg, Na, Al，Fe, Mn, Cu, Zn et al were determined by using microwave digestion-ICP-MS. Therefore, FT-IR combined with second derivative spectra was an express and comprehensive to analyze and evaluate the subtle difference among different habitats. It was also indicated that the method of UV-absorption spectroscopy was simple and reliable for identifing Alpinia katsumadai from differern geographical regions and cultivation batches, and determining qualitatively and quantitatively their main active components. The determination results of metal elements according to ICP-MS experiments will provide a theoretical foundation for the further development and utilization Alpinia katsumadai and enhancing the food danger consciousness.

CarSitePred: an integrated algorithm for identifying carbonylated sites based on KNDUA-LNDOT resampling technique.

Carbonylated sites are the determining factors for functional changes or deletions in carbonylated proteins, so identifying carbonylated sites is essential for understanding the process of protein carbonylated and exploring the pathogenesis of related diseases. The current wet experimental methods for predicting carbonylated modification sites ae not only expensive and time-consuming, but also have limited protein processing capabilities and cannot meet the needs of researchers. The identification of carbonylated sites using computational methods not only improves the functional characterization of proteins, but also provides researchers with free tools for predicting carbonylated sites. Therefore, it is essential to establish a model using computational methods that can accurately predict protein carbonylated sites. In this study, a prediction model, CarSitePred, is proposed to identify carbonylation sites. In CarSitePred, specific location amino acid hydrophobic hydrophilic, one-to-one numerical conversion of amino acids, and AlexNet convolutional neural networks convert preprocessed carbonylated sequences into valid numerical features. The K-means Normal Distribution-based Undersampling Algorithm (KNDUA) and Localized Normal Distribution Oversampling Technology (LNDOT) were firstly proposed and employed to balance the K, P, R and T carbonylation training dataset. And for the first time, carbonylation modification sites were transformed into the form of images and directly inputted into AlexNet convolutional neural network to extract features for fitting SVM classifiers. The 10-fold cross-validation and independent testing results show that CarSitePred achieves better prediction performance than the best currently available prediction models. Availability: https://github.com/zuoyun123/CarSitePred.Communicated by Ramaswamy H. Sarma.