RESUMO
The function of the Trihelix transcription factor is that it plays an important role in many abiotic stresses, especially in the signaling pathway of low temperature, drought, flood, saline, abscisic acid, methyl jasmonate, and other abiotic stresses. However, there are few studies on the Trihelix gene family of ginseng. In this study, 41 Trihelix gene family members were identified and screened from the ginseng genome database, and their physicochemical properties, cis-acting elements, subcellular localization, chromosomal assignment, and abiotic stress-induced expression patterns were analyzed by bioinformatics methods. The results showed that 85% of Trihelix family members of ginseng were located in the nucleus, and the main secondary structure of Trihelix protein was random coil and α helix. In the promoter region of Trihelix, cis-acting regulatory elements related to various abiotic stresses such as low temperature, hormone response, and growth and development were identified. Through the collinearity analysis of interspecific Trihelix transcription factors of model plants Arabidopsis thaliana and ginseng, 19 collinear gene pairs were found between A. thaliana and ginseng, and no collinear gene pairs existed on chromosomes 3, 6, and 12 only. qRT-PCR analysis showed that the expression of GWHGBEIJ010320.1 was significantly up-regulated under low temperature stress, a significant response to low temperature stress. This study lays a foundation for further research on the role of the Trihelix transcription factor of ginseng in abiotic stress, as well as the growth and development of ginseng.
Assuntos
Regulação da Expressão Gênica de Plantas , Família Multigênica , Panax , Filogenia , Proteínas de Plantas , Estresse Fisiológico , Fatores de Transcrição , Panax/genética , Panax/química , Proteínas de Plantas/genética , Proteínas de Plantas/metabolismo , Regulação da Expressão Gênica de Plantas/efeitos dos fármacos , Fatores de Transcrição/genética , Fatores de Transcrição/metabolismo , Estresse Fisiológico/genética , Regiões Promotoras Genéticas , Perfilação da Expressão GênicaRESUMO
Postharvest fibrosis and greening of Toona sinensis buds significantly affect their quality during storage. This study aimed to clarify the effects of low-temperature storage on postharvest red TSB quality harvested in different seasons. Red TSB samples were collected from Guizhou province, China, 21 days after the beginning of spring (Lichun), summer (Lixia), and autumn (Liqiu), and stored at 4 °C in dark conditions. We compared and analyzed the appearance, microstructure, chlorophyll and cellulose content, and expression levels of related genes across different seasons. The results indicated that TSB harvested in spring had a bright, purple-red color, whereas those harvested in summer and autumn were green. All samples lost water and darkened after 1 day of storage. Severe greening occurred in spring-harvested TSB within 3 days, a phenomenon not observed in summer and autumn samples. Microstructural analysis revealed that the cells in the palisade and spongy tissues of spring and autumn TSB settled closely during storage, while summer TSB cells remained loosely aligned. Xylem cells were smallest in spring-harvested TSB and largest in autumn. Prolonged storage led to thickening of the secondary cell walls and pith cell autolysis in the petioles, enlarging the cavity area. Chlorophyll content was higher in leaves than in petioles, while cellulose content was lower in petioles across all seasons. Both chlorophyll and cellulose content increased with storage time. Gene expression analysis showed season-dependent variations and significant increases in the expression of over half of the chlorophyll-related and cellulose-related genes during refrigeration, correlating with the observed changes in chlorophyll and cellulose content. This research provides valuable insights for improving postharvest storage and freshness preservation strategies for red TSB across different seasons.
Assuntos
Celulose , Clorofila , Temperatura Baixa , Estações do Ano , Clorofila/metabolismo , Celulose/metabolismo , Regulação da Expressão Gênica de Plantas , ChinaRESUMO
Cannabis sativa L. is a multipurpose crop with high value for food, textiles, and other industries. Its secondary metabolites, including cannabidiol (CBD), have potential for broad application in medicine. With the CBD market expanding, traditional production may not be sufficient. Here we review the potential for the production of CBD using biotechnology. We describe the chemical and biological synthesis of cannabinoids, the associated enzymes, and the application of metabolic engineering, synthetic biology, and heterologous expression to increasing production of CBD.
Assuntos
Canabidiol , Cannabis , Engenharia Metabólica , Canabidiol/metabolismo , Cannabis/metabolismo , Engenharia Metabólica/métodos , Biologia Sintética/métodos , Biotecnologia/métodosRESUMO
Studying drug-target interactions (DTIs) is the foundational and crucial phase in drug discovery. Biochemical experiments, while being the most reliable method for determining drug-target affinity (DTA), are time-consuming and costly, making it challenging to meet the current demands for swift and efficient drug development. Consequently, computational DTA prediction methods have emerged as indispensable tools for this research. In this article, we propose a novel deep learning algorithm named GRA-DTA, for DTA prediction. Specifically, we introduce Bidirectional Gated Recurrent Unit (BiGRU) combined with a soft attention mechanism to learn target representations. We employ Graph Sample and Aggregate (GraphSAGE) to learn drug representation, especially to distinguish the different features of drug and target representations and their dimensional contributions. We merge drug and target representations by an attention neural network (ANN) to learn drug-target pair representations, which are fed into fully connected layers to yield predictive DTA. The experimental results showed that GRA-DTA achieved mean squared error of 0.142 and 0.225 and concordance index reached 0.897 and 0.890 on the benchmark datasets KIBA and Davis, respectively, surpassing the most state-of-the-art DTA prediction algorithms.
Assuntos
Algoritmos , Aprendizado Profundo , Redes Neurais de Computação , Descoberta de Drogas/métodos , Humanos , Preparações Farmacêuticas/químicaRESUMO
Ginseng frequently encounters environmental stress during its growth and development. Late Embryogenesis Abundant (LEA) proteins play a crucial role in combating adversity stress, particularly against abiotic challenges In this study, 107 LEA genes from ginseng, spanning eight subfamilies, were identified, demonstrating significant evolutionary conservation, with the LEA2 subfamily being most prominent. Gene duplication events, primarily segmental duplications, have played a major role in the expansion of the LEA gene family, which has undergone strong purifying selection. PgLEAs were unevenly distributed across 22 chromosomes, with each subfamily featuring unique structural domains and conserved motifs. PgLEAs were expressed in various tissues, exhibiting distinct variations in abundance and tissue specificity. Numerous regulatory cis-elements, related to abiotic stress and hormones, were identified in the promoter region. Additionally, PgLEAs were regulated by a diverse array of abiotic stress-related transcription factors. A total of 35 PgLEAs were differentially expressed following treatments with ABA, GA, and IAA. Twenty-three PgLEAs showed significant but varied responses to drought, extreme temperatures, and salinity stress. The transformation of tobacco with the key gene PgLEA2-50 enhanced osmoregulation and antioxidant levels in transgenic lines, improving their resistance to abiotic stress. This study offers insights into functional gene analysis, focusing on LEA proteins, and establishes a foundational framework for research on ginseng's resilience to abiotic stress.
Assuntos
Regulação da Expressão Gênica de Plantas , Família Multigênica , Panax , Proteínas de Plantas , Estresse Fisiológico , Panax/genética , Panax/metabolismo , Proteínas de Plantas/genética , Proteínas de Plantas/metabolismo , Estresse Fisiológico/genética , Genoma de Planta/genética , Filogenia , Plantas Geneticamente Modificadas , Nicotiana/genética , Nicotiana/metabolismoRESUMO
Circular RNA (circRNA) is a common non-coding RNA and plays an important role in the diagnosis and therapy of human diseases, circRNA-disease associations prediction based on computational methods can provide a new way for better clinical diagnosis. In this article, we proposed a novel method for circRNA-disease associations prediction based on ensemble learning, named ELCDA. First, the association heterogeneous network was constructed via collecting multiple information of circRNAs and diseases, and multiple similarity measures are adopted here, then, we use metapath, matrix factorization and GraphSAGE-based models to extract features of nodes from different views, the final comprehensive features of circRNAs and diseases via ensemble learning, finally, a soft voting ensemble strategy is used to integrate the predicted results of all classifier. The performance of ELCDA is evaluated by fivefold cross-validation and compare with other state-of-the-art methods, the experimental results show that ELCDA is outperformance than others. Furthermore, three common diseases are used as case studies, which also demonstrate that ELCDA is an effective method for predicting circRNA-disease associations.
Assuntos
Aprendizado de Máquina , RNA Circular , Humanos , RNA Circular/genética , Biologia Computacional/métodosRESUMO
Cervical cytology image classification is of great significance to the cervical cancer diagnosis and prognosis. Recently, convolutional neural network (CNN) and visual transformer have been adopted as two branches to learn the features for image classification by simply adding local and global features. However, such the simple addition may not be effective to integrate these features. In this study, we explore the synergy of local and global features for cytology images for classification tasks. Specifically, we design a Deep Integrated Feature Fusion (DIFF) block to synergize local and global features of cytology images from a CNN branch and a transformer branch. Our proposed method is evaluated on three cervical cell image datasets (SIPaKMeD, CRIC, Herlev) and another large blood cell dataset BCCD for several multi-class and binary classification tasks. Experimental results demonstrate the effectiveness of the proposed method in cervical cell classification, which could assist medical specialists to better diagnose cervical cancer.
Assuntos
Neoplasias do Colo do Útero , Feminino , Humanos , Aprendizagem , Redes Neurais de Computação , Processamento de Imagem Assistida por ComputadorRESUMO
CircRNA and miRNA are crucial non-coding RNAs, which are associated with biological diseases. Exploring the associations between RNAs and diseases often requires a significant time and financial investments, which has been greatly alleviated and improved with the application of deep learning methods in bioinformatics. However, existing methods often fail to achieve higher accuracy and cannot be universal between multiple RNAs. Moreover, complex RNA-disease associations hide important higher-order topology information. To address these issues, we learn higher-order structure information for predicting RNA-disease associations (HoRDA). Firstly, the correlations between RNAs and the correlations between diseases are fully explored by combining similarity and higher-order graph attention network. Then, a higher-order graph convolutional network is constructed to aggregate neighbor information, and further obtain the representations of RNAs and diseases. Meanwhile, due to the large number of complex and variable higher-order structures in biological networks, we design a higher-order negative sampling strategy to gain more desirable negative samples. Finally, the obtained embeddings of RNAs and diseases are feed into logistic regression model to acquire the probabilities of RNA-disease associations. Diverse simulation results demonstrate the superiority of the proposed method. In the end, the case study is conducted on breast neoplasms, colorectal neoplasms, and gastric neoplasms. We validate the proposed higher-order strategies through ablative and exploratory analyses and further demonstrate the practical applicability of HoRDA. HoRDA has a certain contribution in RNA-disease association prediction.
Assuntos
Neoplasias Colorretais , MicroRNAs , Humanos , Algoritmos , MicroRNAs/genética , Biologia Computacional/métodosRESUMO
Drug repositioning is critical to drug development. Previous drug repositioning methods mainly constructed drug-disease heterogeneous networks to extract drug-disease features. However, these methods faced difficulty when we are using structurally simple models to deal with complex heterogeneous networks. Therefore, in this study, the researchers introduced a drug repositioning method named DRDSA. The method utilizes a deep sparse autoencoder and integrates drug-disease similarities. First, the researchers constructed a drug-disease feature network by incorporating information from drug chemical structure, disease semantic data, and existing known drug-disease associations. Then, we learned the low-dimensional representation of the feature network using a deep sparse autoencoder. Finally, we utilized a deep neural network to make predictions on new drug-disease associations based on the feature representation. The experimental results show that our proposed method has achieved optimal results on all four benchmark datasets, especially on the CTD dataset where AUC and AUPR reached 0.9619 and 0.9676, respectively, outperforming other baseline methods. In the case study, the researchers predicted the top ten antiviral drugs for COVID-19. Remarkably, six out of these predictions were subsequently validated by other literature sources.
Assuntos
Reposicionamento de Medicamentos , Redes Neurais de Computação , Reposicionamento de Medicamentos/métodos , Semântica , Algoritmos , Biologia Computacional/métodosRESUMO
Extracting expressive molecular features is essential for molecular property prediction. Sequence-based representation is a common representation of molecules, which ignores the structure information of molecules. While molecular graph representation has a weak ability in expressing the 3D structure. In this article, we try to make use of the advantages of different type representations simultaneously for molecular property prediction. Thus, we propose a fusion model named DLF-MFF, which integrates the multi-type molecular features. Specifically, we first extract four different types of features from molecular fingerprints, 2D molecular graph, 3D molecular graph and molecular image. Then, in order to learn molecular features individually, we use four essential deep learning frameworks, which correspond to four distinct molecular representations. The final molecular representation is created by integrating the four feature vectors and feeding them into prediction layer to predict molecular property. We compare DLF-MFF with 7 state-of-the-art methods on 6 benchmark datasets consisting of multiple molecular properties, the experimental results show that DLF-MFF achieves state-of-the-art performance on 6 benchmark datasets. Moreover, DLF-MFF is applied to identify potential anti-SARS-CoV-2 inhibitor from 2500 drugs. We predict probability of each drug being inferred as a 3CL protease inhibitor and also calculate the binding affinity scores between each drug and 3CL protease. The results show that DLF-MFF product better performance in the identification of anti-SARS-CoV-2 inhibitor. This work is expected to offer novel research perspectives for accurate prediction of molecular properties and provide valuable insights into drug repurposing for COVID-19.
Assuntos
COVID-19 , Aprendizado Profundo , Humanos , Antivirais , Benchmarking , Reposicionamento de Medicamentos , SARS-CoV-2RESUMO
RNA modification is a post transcriptional modification that occurs in all organisms and plays a crucial role in the stages of RNA life, closely related to many life processes. As one of the newly discovered modifications, N1-methyladenosine (m1A) plays an important role in gene expression regulation, closely related to the occurrence and development of diseases. However, due to the low abundance of m1A, verifying the associations between m1As and diseases through wet experiments requires a great quantity of manpower and resources. In this study, we proposed a computational method for predicting the associations of RNA methylation and disease based on graph convolutional network (RMDGCN) with attention mechanism. We build an adjacency matrix through the collected m1As and diseases associations, and use positive-unlabeled learning to increase the number of positive samples. By extracting the features of m1As and diseases, a heterogeneous network is constructed, and a GCN with attention mechanism is adopted to predict the associations between m1As and diseases. The experimental results indicate that under a 5-fold cross validation, RMDGCN is superior to other methods (AUC = 0.9892 and AUPR = 0.8682). In addition, case studies indicate that RMDGCN can predict the relationships between unknown m1As and diseases. In summary, RMDGCN is an effective method for predicting the associations between m1As and diseases.
Assuntos
Aprendizagem , Metilação de RNA , RNA/genética , Projetos de Pesquisa , Biologia Computacional , AlgoritmosRESUMO
The purpose of drug discovery is to identify new drugs, and the solubility of drug molecules is an important physicochemical property in medicinal chemistry, that plays a crucial role in drug discovery. In solubility prediction, high-precision computational methods can significantly reduce the experimental costs and time associated with drug development. Therefore, artificial intelligence technologies have been widely used for solubility prediction. This study utilized the attention layer in mechanism in the deep learning model to consider the atomic-level features of the molecules, and used gated recurrent neural networks to aggregate vectors between layers. It also utilized molecular fragment technology to divide the complete molecule into pairs of fragments, extracted characteristics from each fragment pair, and finally fused the characteristics to predict the solubility of drug molecules. We compared and evaluated our method with five existing models using two performance evaluation indicators, demonstrating that our method has better performance and greater robustness.
RESUMO
BACKGROUND: Panax ginseng is a perennial herb and one of the most widely used traditional medicines in China. During its long growth period, it is affected by various environmental factors. Past studies have shown that growth-regulating factors (GRFs) and GRF-interacting factors (GIFs) are involved in regulating plant growth and development, responding to environmental stress, and responding to the induction of exogenous hormones. However, GRF and GIF transcription factors in ginseng have not been reported. RESULTS: In this study, 20 GRF gene members of ginseng were systematically identified and found to be distributed on 13 chromosomes. The ginseng GIF gene family has only ten members, which are distributed on ten chromosomes. Phylogenetic analysis divided these PgGRFs into six clades and PgGIFs into two clades. In total, 18 of the 20 PgGRFs and eight of the ten PgGIFs are segmental duplications. Most PgGRF and PgGIF gene promoters contain some hormone- and stress- related cis-regulatory elements. Based on the available public RNA-Seq data, the expression patterns of PgGRF and PgGIF genes were analysed from 14 different tissues. The responses of the PgGRF gene to different hormones (6-BA, ABA, GA3, IAA) and abiotic stresses (cold, heat, drought, and salt) were studied. The expression of the PgGRF gene was significantly upregulated under GA3 induction and three weeks of heat treatment. The expression level of the PgGIF gene changed only slightly after one week of heat treatment. CONCLUSIONS: The results of this study may be helpful for further study of the function of PgGRF and PgGIF genes and lay a foundation for further study of their role in the growth and development of Panax ginseng.
Assuntos
Panax , Filogenia , Panax/genética , Panax/metabolismo , Fatores de Transcrição/metabolismo , Peptídeos e Proteínas de Sinalização Intercelular/genética , Hormônios , Regulação da Expressão Gênica de Plantas , Proteínas de Plantas/genética , Proteínas de Plantas/metabolismo , Perfilação da Expressão GênicaRESUMO
Background: Panax Ginseng is a perennial and semi-shady herb with tremendous medicinal value. Due to its unique botanical characteristics, ginseng is vulnerable to various abiotic factors during its growth and development, especially in high temperatures. Proteins encoded by 14-3-3 genes form a highly conserved protein family that widely exists in eukaryotes. The 14-3-3 family regulates the vital movement of cells and plays an essential role in the response of plants to abiotic stresses, including high temperatures. Currently, there is no relevant research on the 14-3-3 genes of ginseng. Methods: The identification of the ginseng 14-3-3 gene family was mainly based on ginseng genomic data and Hidden Markov Models (HMM). We used bioinformatics-related databases and tools to analyze the gene structure, physicochemical properties, cis-acting elements, gene ontology (GO), phylogenetic tree, interacting proteins, and transcription factor regulatory networks. We analyzed the transcriptome data of different ginseng tissues to clarify the expression pattern of the 14-3-3 gene family in ginseng. The expression level and modes of 14-3-3 genes under heat stress were analyzed by quantitative real-time PCR (qRT-PCR) technology to determine the genes in the 14-3-3 gene family responding to high-temperature stress. Results: In this study, 42 14-3-3 genes were identified from the ginseng genome and renamed PgGF14-1 to PgGF14-42. Gene structure and evolutionary relationship research divided PgGF14s into epsilon (ε) and non-epsilon (non-ε) groups, mainly located in four evolutionary branches. The gene structure and motif remained highly consistent within a subgroup. The physicochemical properties and structure of the predicted PgGF14 proteins conformed to the essential characteristics of 14-3-3 proteins. RNA-seq results indicated that the detected PgGF14s existed in different organs and tissues but differed in abundance; their expression was higher in roots, stems, leaves, and fruits but lower in seeds. The analysis of GO, cis-acting elements, interacting proteins, and regulatory networks of transcription factors indicated that PgGF14s might participate in physiological processes, such as response to stress, signal transduction, material synthesis-metabolism, and cell development. The qRT-PCR results indicated PgGF14s had multiple expression patterns under high-temperature stress with different change trends in several treatment times, and 38 of them had an apparent response to high-temperature stress. Furthermore, PgGF14-5 was significantly upregulated, and PgGF14-4 was significantly downregulated in all treatment times. This research lays a foundation for further study on the function of 14-3-3 genes and provides theoretical guidance for investigating abiotic stresses in ginseng.
Assuntos
Panax , Filogenia , Panax/genética , Proteínas de Plantas/genética , Resposta ao Choque Térmico/genética , Estresse Fisiológico/genética , Fatores de Transcrição/genéticaRESUMO
Accumulating evidence has shown that microbes play significant roles in human health and diseases. Therefore, identifying microbe-disease associations is conducive to disease prevention. In this article, a predictive method called TNRGCN is designed for microbe-disease associations based on Microbe-Drug-Disease Network and Relation Graph Convolutional Network (RGCN). First, considering that indirect links between microbes and diseases will be increased by introducing drug related associations, we construct a Microbe-Drug-Disease tripartite network through data processing from four databases including Human Microbe-Disease Association Database (HMDAD), Disbiome Database, Microbe-Drug Association Database (MDAD) and Comparative Toxicoge-nomics Database (CTD). Second, we construct similarity networks for microbes, diseases and drugs via microbe function similarity, disease semantic similarity and Gaussian interaction profile kernel similarity, respectively. Based on the similarity networks, Principal Component Analysis (PCA) is utilized to extract main features of nodes. These features will be input into the RGCN as initial features. Finally, based on the tripartite network and initial features, we design two-layer RGCN to predict microbe-disease associations. Experimental results indicate that TNRGCN achieves best performance in cross validation compared with other methods. Meanwhile, case studies for Type 2 diabetes (T2D), Bipolar disorder and Autism demonstrate the favorable effectiveness of TNRGCN in association prediction.
Assuntos
Diabetes Mellitus Tipo 2 , Humanos , Diabetes Mellitus Tipo 2/genética , Bases de Dados de Produtos Farmacêuticos , Bases de Dados Factuais , Algoritmos , Biologia Computacional/métodosRESUMO
Biomolecules, microRNAs (miRNAs) and long non-coding RNAs (lncRNAs), play critical roles in diverse fundamental and vital biological processes. They can serve as disease biomarkers as their dysregulations could cause complex human diseases. Identifying those biomarkers is helpful with the diagnosis, treatment, prognosis, and prevention of diseases. In this study, we propose a factorization machine-based deep neural network with binary pairwise encoding, DFMbpe, to identify the disease-related biomarkers. First, to comprehensively consider the interdependence of features, a binary pairwise encoding method is designed to obtain the raw feature representations for each biomarker-disease pair. Second, the raw features are mapped into their corresponding embedding vectors. Then, the factorization machine is conducted to get the wide low-order feature interdependence, while the deep neural network is applied to obtain the deep high-order feature interdependence. Finally, two kinds of features are combined to get the final prediction results. Unlike other biomarker identification models, the binary pairwise encoding considers the interdependence of features even though they never appear in the same sample, and the DFMbpe architecture emphasizes both low-order and high-order feature interactions simultaneously. The experimental results show that DFMbpe greatly outperforms the state-of-the-art identification models on both cross-validation and independent dataset evaluation. Besides, three types of case studies further demonstrate the effectiveness of this model.
Assuntos
MicroRNAs , RNA Longo não Codificante , Humanos , Redes Neurais de Computação , Biologia Computacional/métodosRESUMO
Drug-drug interaction refers to taking the two drugs may produce certain reaction which may be a threat to patients' health, or enhance the efficacy helpful for medical work. Therefore, it is necessary to study and predict it. In fact, traditional experimental methods can be used for drug-drug interaction prediction, but they are time-consuming and costly, so we prefer to use more accurate and convenient calculation methods to predict the unknown drug-drug interaction. In this paper, we proposed a deep learning framework called MSResG that considers multi-sources features of drugs and combines them with Graph Auto-Encoder to predicting. Firstly, the model obtains four feature representations of drugs from the database, namely, chemical substructure, target, pathway and enzyme, and then calculates the Jaccard similarity of the drugs. To balance different drug features, we perform similarity integration by finding the mean value. Then we will be comprehensive similarity network combined with drug interaction network, and encodes and decodes it using the graph auto-encoder based on residual graph convolution network. Encoding is to learn the potential feature vectors of drugs, which contain similar information and interaction information. Decoding is to reconstruct the network to predict unknown drug-drug interaction. The experimental results show that our model has advanced performance and is superior to other existing advanced methods. Case study also shows that MSResG has practical significance.
Assuntos
Projetos de Pesquisa , Humanos , Interações Medicamentosas , Bases de Dados FactuaisRESUMO
The prediction of molecules toxicity properties plays an crucial role in the realm of the drug discovery, since it can swiftly screen out the expected drug moleculars. The conventional method for predicting toxicity is to use some in vivo or in vitro biological experiments in the laboratory, which can easily pose a threat significant time and financial waste and even ethical issues. Therefore, using computational approaches to predict molecular toxicity has become a common strategy in modern drug discovery. In this article, we propose a novel model named MTBG, which primarily makes use of both SMILES (Simplified molecular input line entry system) strings and graph structures of molecules to extract drug molecular feature in the field of drug molecular toxicity prediction. To verify the performance of the MTBG model, we opt the Tox21 dataset and several widely used baseline models. Experimental results demonstrate that our model can perform better than these baseline models.
Assuntos
Descoberta de Drogas , Descoberta de Drogas/métodosRESUMO
Expressive molecular representation plays critical roles in researching drug design, while effective methods are beneficial to learning molecular representations and solving related problems in drug discovery, especially for drug-drug interactions (DDIs) prediction. Recently, a lot of work has been put forward using graph neural networks (GNNs) to forecast DDIs and learn molecular representations. However, under the current GNNs structure, the majority of approaches learn drug molecular representation from one-dimensional string or two-dimensional molecular graph structure, while the interaction information between chemical substructure remains rarely explored, and it is neglected to identify key substructures that contribute significantly to the DDIs prediction. Therefore, we proposed a dual graph neural network named DGNN-DDI to learn drug molecular features by using molecular structure and interactions. Specifically, we first designed a directed message passing neural network with substructure attention mechanism (SA-DMPNN) to adaptively extract substructures. Second, in order to improve the final features, we separated the drug-drug interactions into pairwise interactions between each drug's unique substructures. Then, the features are adopted to predict interaction probability of a DDI tuple. We evaluated DGNN-DDI on real-world dataset. Compared to state-of-the-art methods, the model improved DDIs prediction performance. We also conducted case study on existing drugs aiming to predict drug combinations that may be effective for the novel coronavirus disease 2019 (COVID-19). Moreover, the visual interpretation results proved that the DGNN-DDI was sensitive to the structure information of drugs and able to detect the key substructures for DDIs. These advantages demonstrated that the proposed method enhanced the performance and interpretation capability of DDI prediction modeling.
Assuntos
COVID-19 , Humanos , Estrutura Molecular , Interações Medicamentosas , Redes Neurais de Computação , ProbabilidadeRESUMO
Introduction: The BAHD (benzylalcohol O-acetyl transferase, anthocyanin O-hydroxycinnamoyl transferase, N-hydroxycinnamoyl anthranilate benzoyl transferase and deacetylvindoline 4-O-acetyltransferase), has various biological functions in plants, including catalyzing the biosynthesis of terpenes, phenolics and esters, participating in plant stress response, affecting cell stability, and regulating fruit quality. Methods: Bioinformatics methods, real-time fluorescence quantitative PCR technology, and ultra-high-performance liquid chromatography combined with an Orbitrap mass spectrometer were used to explore the relationship between the BAHD gene family and malonyl ginsenosides in Panax ginseng. Results: In this study, 103 BAHD genes were identified in P. ginseng, mainly distributed in three major clades. Most PgBAHDs contain cis-acting elements associated with abiotic stress response and plant hormone response. Among the 103 genes, 68 PgBAHDs are WGD (whole-genome duplication) genes. The significance of malonylation in biosynthesis has garnered considerable attention in the study of malonyltransferases. The phylogenetic tree results showed 34 PgBAHDs were clustered with genes that have malonyl characterization. Among them, seven PgBAHDs (PgBAHD4, 45, 65, 74, 90, 97, and 99) showed correlations > 0.9 with crucial enzyme genes involved in ginsenoside biosynthesis and > 0.8 with malonyl ginsenosides. These seven genes were considered potential candidates involved in the biosynthesis of malonyl ginsenosides. Discussion: These results help elucidate the structure, evolution, and functions of the P. ginseng BAHD gene family, and establish the foundation for further research on the mechanism of BAHD genes in ginsenoside biosynthesis.