Structural insights into the molecular effects of the anthelmintics monepantel and betaine on the Caenorhabditis elegans acetylcholine receptor ACR-23.

Anthelmintics are drugs used for controlling pathogenic helminths in animals and plants. The natural compound betaine and the recently developed synthetic compound monepantel are both anthelmintics that target the acetylcholine receptor ACR-23 and its homologs in nematodes. Here, we present cryo-electron microscopy structures of ACR-23 in apo, betaine-bound, and betaine- and monepantel-bound states. We show that ACR-23 forms a homo-pentameric channel, similar to some other pentameric ligand-gated ion channels (pLGICs). While betaine molecules are bound to the classical neurotransmitter sites in the inter-subunit interfaces in the extracellular domain, monepantel molecules are bound to allosteric sites formed in the inter-subunit interfaces in the transmembrane domain of the receptor. Although the pore remains closed in betaine-bound state, monepantel binding results in an open channel by wedging into the cleft between the transmembrane domains of two neighboring subunits, which causes dilation of the ion conduction pore. By combining structural analyses with site-directed mutagenesis, electrophysiology and in vivo locomotion assays, we provide insights into the mechanism of action of the anthelmintics monepantel and betaine.

Structural basis of ketamine action on human NMDA receptors.

Ketamine is a non-competitive channel blocker of N-methyl-D-aspartate (NMDA) receptors1. A single sub-anaesthetic dose of ketamine produces rapid (within hours) and long-lasting antidepressant effects in patients who are resistant to other antidepressants2,3. Ketamine is a racemic mixture of S- and R-ketamine enantiomers, with S-ketamine isomer being the more active antidepressant4. Here we describe the cryo-electron microscope structures of human GluN1-GluN2A and GluN1-GluN2B NMDA receptors in complex with S-ketamine, glycine and glutamate. Both electron density maps uncovered the binding pocket for S-ketamine in the central vestibule between the channel gate and selectivity filter. Molecular dynamics simulation showed that S-ketamine moves between two distinct locations within the binding pocket. Two amino acids-leucine 642 on GluN2A (homologous to leucine 643 on GluN2B) and asparagine 616 on GluN1-were identified as key residues that form hydrophobic and hydrogen-bond interactions with ketamine, and mutations at these residues reduced the potency of ketamine in blocking NMDA receptor channel activity. These findings show structurally how ketamine binds to and acts on human NMDA receptors, and pave the way for the future development of ketamine-based antidepressants.

The high-quality genome of Cryptotaenia japonica and comparative genomics analysis reveals anthocyanin biosynthesis in Apiaceae.

Cryptotaenia japonica, a traditional medicinal and edible vegetable crops, is well-known for its attractive flavors and health care functions. As a member of the Apiaceae family, the evolutionary trajectory and biological properties of C. japonica are not clearly understood. Here, we first reported a high-quality genome of C. japonica with a total length of 427 Mb and N50 length 50.76 Mb, was anchored into 10 chromosomes, which confirmed by chromosome (cytogenetic) analysis. Comparative genomic analysis revealed C. japonica exhibited low genetic redundancy, contained a higher percentage of single-cope gene families. The homoeologous blocks, Ks, and collinearity were analyzed among Apiaceae species contributed to the evidence that C. japonica lacked recent species-specific WGD. Through comparative genomic and transcriptomic analyses of Apiaceae species, we revealed the genetic basis of the production of anthocyanins. Several structural genes encoding enzymes and transcription factor genes of the anthocyanin biosynthesis pathway in different species were also identified. The CjANSa, CjDFRb, and CjF3H gene might be the target of Cjaponica_2.2062 (bHLH) and Cjaponica_1.3743 (MYB). Our findings provided a high-quality reference genome of C. japonica and offered new insights into Apiaceae evolution and biology.

Improved structure-related prediction for insufficient homologous proteins using MSA enhancement and pre-trained language model.

In recent years, protein structure problems have become a hotspot for understanding protein folding and function mechanisms. It has been observed that most of the protein structure works rely on and benefit from co-evolutionary information obtained by multiple sequence alignment (MSA). As an example, AlphaFold2 (AF2) is a typical MSA-based protein structure tool which is famous for its high accuracy. As a consequence, these MSA-based methods are limited by the quality of the MSAs. Especially for orphan proteins that have no homologous sequence, AlphaFold2 performs unsatisfactorily as MSA depth decreases, which may pose a barrier to its widespread application in protein mutation and design problems in which there are no rich homologous sequences and rapid prediction is needed. In this paper, we constructed two standard datasets for orphan and de novo proteins which have insufficient/none homology information, called Orphan62 and Design204, respectively, to fairly evaluate the performance of the various methods in this case. Then, depending on whether or not utilizing scarce MSA information, we summarized two approaches, MSA-enhanced and MSA-free methods, to effectively solve the issue without sufficient MSAs. MSA-enhanced model aims to improve poor MSA quality from the data source by knowledge distillation and generation models. MSA-free model directly learns the relationship between residues on enormous protein sequences from pre-trained models, bypassing the step of extracting the residue pair representation from MSA. Next, we evaluated the performance of four MSA-free methods (trRosettaX-Single, TRFold, ESMFold and ProtT5) and MSA-enhanced (Bagging MSA) method compared with a traditional MSA-based method AlphaFold2, in two protein structure-related prediction tasks, respectively. Comparison analyses show that trRosettaX-Single and ESMFold which belong to MSA-free method can achieve fast prediction ($\sim\! 40$s) and comparable performance compared with AF2 in tertiary structure prediction, especially for short peptides, $\alpha $-helical segments and targets with few homologous sequences. Bagging MSA utilizing MSA enhancement improves the accuracy of our trained base model which is an MSA-based method when poor homology information exists in secondary structure prediction. Our study provides biologists an insight of how to select rapid and appropriate prediction tools for enzyme engineering and peptide drug development. CONTACT: guofei@csu.edu.cn, jj.tang@siat.ac.cn.

GraphLncLoc: long non-coding RNA subcellular localization prediction using graph convolutional networks based on sequence to graph transformation.

The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding lncRNA functions. Most of existing lncRNA subcellular localization prediction methods use k-mer frequency features to encode lncRNA sequences. However, k-mer frequency features lose sequence order information and fail to capture sequence patterns and motifs of different lengths. In this paper, we proposed GraphLncLoc, a graph convolutional network-based deep learning model, for predicting lncRNA subcellular localization. Unlike previous studies encoding lncRNA sequences by using k-mer frequency features, GraphLncLoc transforms lncRNA sequences into de Bruijn graphs, which transforms the sequence classification problem into a graph classification problem. To extract the high-level features from the de Bruijn graph, GraphLncLoc employs graph convolutional networks to learn latent representations. Then, the high-level feature vectors derived from de Bruijn graph are fed into a fully connected layer to perform the prediction task. Extensive experiments show that GraphLncLoc achieves better performance than traditional machine learning models and existing predictors. In addition, our analyses show that transforming sequences into graphs has more distinguishable features and is more robust than k-mer frequency features. The case study shows that GraphLncLoc can uncover important motifs for nucleus subcellular localization. GraphLncLoc web server is available at http://csuligroup.com:8000/GraphLncLoc/.

IK-DDI: a novel framework based on instance position embedding and key external text for DDI extraction.

Determining drug-drug interactions (DDIs) is an important part of pharmacovigilance and has a vital impact on public health. Compared with drug trials, obtaining DDI information from scientific articles is a faster and lower cost but still a highly credible approach. However, current DDI text extraction methods consider the instances generated from articles to be independent and ignore the potential connections between different instances in the same article or sentence. Effective use of external text data could improve prediction accuracy, but existing methods cannot extract key information from external data accurately and reasonably, resulting in low utilization of external data. In this study, we propose a DDI extraction framework, instance position embedding and key external text for DDI (IK-DDI), which adopts instance position embedding and key external text to extract DDI information. The proposed framework integrates the article-level and sentence-level position information of the instances into the model to strengthen the connections between instances generated from the same article or sentence. Moreover, we introduce a comprehensive similarity-matching method that uses string and word sense similarity to improve the matching accuracy between the target drug and external text. Furthermore, the key sentence search method is used to obtain key information from external data. Therefore, IK-DDI can make full use of the connection between instances and the information contained in external text data to improve the efficiency of DDI extraction. Experimental results show that IK-DDI outperforms existing methods on both macro-averaged and micro-averaged metrics, which suggests our method provides complete framework that can be used to extract relationships between biomedical entities and process external text data.

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.

MOV10 recruits DCP2 to decap human LINE-1 RNA by forming large cytoplasmic granules with phase separation properties.

Long interspersed element 1 (LINE-1) is the only active autonomous mobile element in the human genome. Its transposition can exert deleterious effects on the structure and function of the host genome and cause sporadic genetic diseases. Tight control of LINE-1 mobilization by the host is crucial for genetic stability. In this study, we report that MOV10 recruits the main decapping enzyme DCP2 to LINE-1 RNA and forms a complex of MOV10, DCP2, and LINE-1 RNP, exhibiting liquid-liquid phase separation (LLPS) properties. DCP2 cooperates with MOV10 to decap LINE-1 RNA, which causes degradation of LINE-1 RNA and thus reduces LINE-1 retrotransposition. We here identify DCP2 as one of the key effector proteins determining LINE-1 replication, and elucidate an LLPS mechanism that facilitates the anti-LINE-1 action of MOV10 and DCP2.

MxB inhibits long interspersed element type 1 retrotransposition.

Long interspersed element type 1 (LINE-1, also L1 for short) is the only autonomously transposable element in the human genome. Its insertion into a new genomic site may disrupt the function of genes, potentially causing genetic diseases. Cells have thus evolved a battery of mechanisms to tightly control LINE-1 activity. Here, we report that a cellular antiviral protein, myxovirus resistance protein B (MxB), restricts the mobilization of LINE-1. This function of MxB requires the nuclear localization signal located at its N-terminus, its GTPase activity and its ability to form oligomers. We further found that MxB associates with LINE-1 protein ORF1p and promotes sequestration of ORF1p to G3BP1-containing cytoplasmic granules. Since knockdown of stress granule marker proteins G3BP1 or TIA1 abolishes MxB inhibition of LINE-1, we conclude that MxB engages stress granule components to effectively sequester LINE-1 proteins within the cytoplasmic granules, thus hindering LINE-1 from accessing the nucleus to complete retrotransposition. Thus, MxB protein provides one mechanism for cells to control the mobility of retroelements.

Polycystic Ovary Syndrome Fuels Cardiovascular Inflammation and Aggravates Ischemic Cardiac Injury.

BACKGROUND: Reducing cardiovascular disease burden among women remains challenging. Epidemiologic studies have indicated that polycystic ovary syndrome (PCOS), the most common endocrine disease in women of reproductive age, is associated with an increased prevalence and extent of coronary artery disease. However, the mechanism through which PCOS affects cardiac health in women remains unclear. METHODS: Prenatal anti-Müllerian hormone treatment or peripubertal letrozole infusion was used to establish mouse models of PCOS. RNA sequencing was performed to determine global transcriptomic changes in the hearts of PCOS mice. Flow cytometry and immunofluorescence staining were performed to detect myocardial macrophage accumulation in multiple PCOS models. Parabiosis models, cell-tracking experiments, and in vivo gene silencing approaches were used to explore the mechanisms underlying increased macrophage infiltration in PCOS mouse hearts. Permanent coronary ligation was performed to establish myocardial infarction (MI). Histologic analysis and small-animal imaging modalities (eg, magnetic resonance imaging and echocardiography) were performed to evaluate the effects of PCOS on injury after MI. Women with PCOS and control participants (n=200) were recruited to confirm findings observed in animal models. RESULTS: Transcriptomic profiling and immunostaining revealed that hearts from PCOS mice were characterized by increased macrophage accumulation. Parabiosis studies revealed that monocyte-derived macrophages were significantly increased in the hearts of PCOS mice because of enhanced circulating Ly6C+ monocyte supply. Compared with control mice, PCOS mice showed a significant increase in splenic Ly6C+ monocyte output, associated with elevated hematopoietic progenitors in the spleen and sympathetic tone. Plasma norepinephrine (a sympathetic neurotransmitter) levels and spleen size were consistently increased in women with PCOS when compared with those in control participants, and norepinephrine levels were significantly correlated with circulating CD14++CD16- monocyte counts. Compared with animals without PCOS, PCOS animals showed significantly exacerbated atherosclerotic plaque development and post-MI cardiac remodeling. Conditional Vcam1 silencing in PCOS mice significantly suppressed cardiac inflammation and improved cardiac injury after MI. CONCLUSIONS: Our data documented previously unrecognized mechanisms through which PCOS could affect cardiovascular health in women. PCOS may promote myocardial macrophage accumulation and post-MI cardiac remodeling because of augmented splenic myelopoiesis.

Residual Immunity from Smallpox Vaccination and Possible Protection from Mpox, China.

Among persons born in China before 1980 and tested for vaccinia virus Tiantan strain (VVT), 28.7% (137/478) had neutralizing antibodies, 71.4% (25/35) had memory B-cell responses, and 65.7% (23/35) had memory T-cell responses to VVT. Because of cross-immunity between the viruses, these findings can help guide mpox vaccination strategies in China.

Directed Dual Charge Pumping Tunes the d-Orbital Configuration of Pt Cluster Boosting Hydrogen Evolution Kinetic.

Achieving high catalytic activity with a minimum amount of platinum (Pt) is crucial for accelerating the cathodic hydrogen evolution reaction (HER) in proton exchange membrane (PEM) water electrolysis, yet it remains a significant challenge. Herein, a directed dual-charge pumping strategy to tune the d-orbital electronic distribution of Pt nanoclusters for efficient HER catalysis is proposed. Theoretical analysis reveals that the ligand effect and electronic metal-support interactions (EMSI) create an effective directional electron transfer channel for the d-orbital electrons of Pt, which in turn optimizes the binding strength to H*, thereby significantly enhancing HER efficiency of the Pt site. Experimentally, this directed dual-charge pumping strategy is validated by elaborating Sb-doped SnO2 (ATO) supported Fe-doped PtSn heterostructure catalysts (Fe-PtSn/ATO). The synthesized 3%Fe-PtSn/ATO catalysts exhibit lower overpotential (requiring only 10.5 mV to reach a current density of 10 mA cm- 2), higher mass activity (28.6 times higher than commercial 20 wt.% Pt/C), and stability in the HER process in acidic media. This innovative strategy presents a promising pathway for the development of highly efficient HER catalysts with low Pt loading.

Strain Effects in Ru-Au Bimetallic Aerogels Boost Electrocatalytic Hydrogen Evolution.

To improve the sluggish kinetics of the hydrogen evolution reaction (HER), a key component in water-splitting applications, there is an urgent desire to develop efficient, cost-effective, and stable electrocatalysts. Strain engineering is proving an efficient strategy for increasing the catalytic activity of electrocatalysts. This work presents the development of Ru-Au bimetallic aerogels by a simple one-step in situ reduction-gelation approach, which exhibits strain effects and electron transfer to create a remarkable HER activity and stability in an alkaline environment. The surface strain induced by the bimetallic segregated structure shifts the d-band center downward, enhancing catalysis by balancing the processes of water dissociation, OH* adsorption, and H* adsorption. Specifically, the optimized catalyst shows low overpotentials of only 24.1 mV at a current density of 10 mA cm-2 in alkaline electrolytes, surpassing commercial Pt/C. This study can contribute to the understanding of strain engineering in bimetallic electrocatalysts for HER at the atomic scale.

HDIContact: a novel predictor of residue-residue contacts on hetero-dimer interfaces via sequential information and transfer learning strategy.

Proteins maintain the functional order of cell in life by interacting with other proteins. Determination of protein complex structural information gives biological insights for the research of diseases and drugs. Recently, a breakthrough has been made in protein monomer structure prediction. However, due to the limited number of the known protein structure and homologous sequences of complexes, the prediction of residue-residue contacts on hetero-dimer interfaces is still a challenge. In this study, we have developed a deep learning framework for inferring inter-protein residue contacts from sequential information, called HDIContact. We utilized transfer learning strategy to produce Multiple Sequence Alignment (MSA) two-dimensional (2D) embedding based on patterns of concatenated MSA, which could reduce the influence of noise on MSA caused by mismatched sequences or less homology. For MSA 2D embedding, HDIContact took advantage of Bi-directional Long Short-Term Memory (BiLSTM) with two-channel to capture 2D context of residue pairs. Our comprehensive assessment on the Escherichia coli (E. coli) test dataset showed that HDIContact outperformed other state-of-the-art methods, with top precision of 65.96%, the Area Under the Receiver Operating Characteristic curve (AUROC) of 83.08% and the Area Under the Precision Recall curve (AUPR) of 25.02%. In addition, we analyzed the potential of HDIContact for human-virus protein-protein complexes, by achieving top five precision of 80% on O75475-P04584 related to Human Immunodeficiency Virus. All experiments indicated that our method was a valuable technical tool for predicting inter-protein residue contacts, which would be helpful for understanding protein-protein interaction mechanisms.

Identification of drug-target interactions via multiple kernel-based triple collaborative matrix factorization.

Targeted drugs have been applied to the treatment of cancer on a large scale, and some patients have certain therapeutic effects. It is a time-consuming task to detect drug-target interactions (DTIs) through biochemical experiments. At present, machine learning (ML) has been widely applied in large-scale drug screening. However, there are few methods for multiple information fusion. We propose a multiple kernel-based triple collaborative matrix factorization (MK-TCMF) method to predict DTIs. The multiple kernel matrices (contain chemical, biological and clinical information) are integrated via multi-kernel learning (MKL) algorithm. And the original adjacency matrix of DTIs could be decomposed into three matrices, including the latent feature matrix of the drug space, latent feature matrix of the target space and the bi-projection matrix (used to join the two feature spaces). To obtain better prediction performance, MKL algorithm can regulate the weight of each kernel matrix according to the prediction error. The weights of drug side-effects and target sequence are the highest. Compared with other computational methods, our model has better performance on four test data sets.

Identification of drug-side effect association via restricted Boltzmann machines with penalized term.

In the entire life cycle of drug development, the side effect is one of the major failure factors. Severe side effects of drugs that go undetected until the post-marketing stage leads to around two million patient morbidities every year in the United States. Therefore, there is an urgent need for a method to predict side effects of approved drugs and new drugs. Following this need, we present a new predictor for finding side effects of drugs. Firstly, multiple similarity matrices are constructed based on the association profile feature and drug chemical structure information. Secondly, these similarity matrices are integrated by Centered Kernel Alignment-based Multiple Kernel Learning algorithm. Then, Weighted K nearest known neighbors is utilized to complement the adjacency matrix. Next, we construct Restricted Boltzmann machines (RBM) in drug space and side effect space, respectively, and apply a penalized maximum likelihood approach to train model. At last, the average decision rule was adopted to integrate predictions from RBMs. Comparison results and case studies demonstrate, with four benchmark datasets, that our method can give a more accurate and reliable prediction result.

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.

Two-stage-vote ensemble framework based on integration of mutation data and gene interaction network for uncovering driver genes.

Identifying driver genes, exactly from massive genes with mutations, promotes accurate diagnosis and treatment of cancer. In recent years, a lot of works about uncovering driver genes based on integration of mutation data and gene interaction networks is gaining more attention. However, it is in suspense if it is more effective for prioritizing driver genes when integrating various types of mutation information (frequency and functional impact) and gene networks. Hence, we build a two-stage-vote ensemble framework based on somatic mutations and mutual interactions. Specifically, we first represent and combine various kinds of mutation information, which are propagated through networks by an improved iterative framework. The first vote is conducted on iteration results by voting methods, and the second vote is performed to get ensemble results of the first poll for the final driver gene list. Compared with four excellent previous approaches, our method has better performance in identifying driver genes on $33$ types of cancer from The Cancer Genome Atlas. Meanwhile, we also conduct a comparative analysis about two kinds of mutation information, five gene interaction networks and four voting strategies. Our framework offers a new view for data integration and promotes more latent cancer genes to be admitted.

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.