A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks.

The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces Drug-Substructures relationship into Molecular interaction Networks to construct the micro-to-macro drug centric heterogeneous network (DSMN), and develop a multi-branches HyperGraph learning model, called HGDrug, for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks.

Chemical structure-aware molecular image representation learning.

Current methods of molecular image-based drug discovery face two major challenges: (1) work effectively in absence of labels, and (2) capture chemical structure from implicitly encoded images. Given that chemical structures are explicitly encoded by molecular graphs (such as nitrogen, benzene rings and double bonds), we leverage self-supervised contrastive learning to transfer chemical knowledge from graphs to images. Specifically, we propose a novel Contrastive Graph-Image Pre-training (CGIP) framework for molecular representation learning, which learns explicit information in graphs and implicit information in images from large-scale unlabeled molecules via carefully designed intra- and inter-modal contrastive learning. We evaluate the performance of CGIP on multiple experimental settings (molecular property prediction, cross-modal retrieval and distribution similarity), and the results show that CGIP can achieve state-of-the-art performance on all 12 benchmark datasets and demonstrate that CGIP transfers chemical knowledge in graphs to molecular images, enabling image encoder to perceive chemical structures in images. We hope this simple and effective framework will inspire people to think about the value of image for molecular representation learning.

Improving molecular representation learning with metric learning-enhanced optimal transport.

Training data are usually limited or heterogeneous in many chemical and biological applications. Existing machine learning models for chemistry and materials science fail to consider generalizing beyond training domains. In this article, we develop a novel optimal transport-based algorithm termed MROT to enhance their generalization capability for molecular regression problems. MROT learns a continuous label of the data by measuring a new metric of domain distances and a posterior variance regularization over the transport plan to bridge the chemical domain gap. Among downstream tasks, we consider basic chemical regression tasks in unsupervised and semi-supervised settings, including chemical property prediction and materials adsorption selection. Extensive experiments show that MROT significantly outperforms state-of-the-art models, showing promising potential in accelerating the discovery of new substances with desired properties.

Pharmacophoric-constrained heterogeneous graph transformer model for molecular property prediction.

Informative representation of molecules is a crucial prerequisite in AI-driven drug design and discovery. Pharmacophore information including functional groups and chemical reactions can indicate molecular properties, which have not been fully exploited by prior atom-based molecular graph representation. To obtain a more informative representation of molecules for better molecule property prediction, we propose the Pharmacophoric-constrained Heterogeneous Graph Transformer (PharmHGT). We design a pharmacophoric-constrained multi-views molecular representation graph, enabling PharmHGT to extract vital chemical information from functional substructures and chemical reactions. With a carefully designed pharmacophoric-constrained multi-view molecular representation graph, PharmHGT can learn more chemical information from molecular functional substructures and chemical reaction information. Extensive downstream experiments prove that PharmHGT achieves remarkably superior performance over the state-of-the-art models the performance of our model is up to 1.55% in ROC-AUC and 0.272 in RMSE higher than the best baseline model) on molecular properties prediction. The ablation study and case study show that our proposed molecular graph representation method and heterogeneous graph transformer model can better capture the pharmacophoric structure and chemical information features. Further visualization studies also indicated a better representation capacity achieved by our model.

KGNMDA: A Knowledge Graph Neural Network Method for Predicting Microbe-Disease Associations.

Accumulated studies discovered that various microbes in human bodies were closely related to complex human diseases and could provide new insight into drug development. Multiple computational methods were constructed to predict microbes that were potentially associated with diseases. However, most previous methods were based on single characteristics of microbes or diseases, that lacked important biological information related to microorganisms or diseases. Therefore, we constructed a knowledge graph centered on microorganisms and diseases from several existed databases to provide knowledgeable information for microbes and diseases. Then, we adopted a graph neural network method to learn representations of microbes and diseases from the constructed knowledge graph. After that, we introduced the Gaussian kernel similarity features of microbes and diseases to generate final representations of microbes and diseases. At last, we proposed a score function on final representations of microbes and diseases to predict scores of microbe-disease associations. Comprehensive experiments on the Human Microbe-Disease Association Database (HMDAD) dataset had demonstrated that our approach outperformed baseline methods. Furthermore, we implemented case studies on two important diseases (asthma and inflammatory bowel disease), the result demonstrated that our proposed model was effective in revealing the relationship between diseases and microbes. The source code of our model and the data were available on https://github.com/ChangzhiJiang/KGNMDA_master.

Pre-Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding.

The latest biological findings observe that the motionless "lock-and-key" theory is not generally applicable and that changes in atomic sites and binding pose can provide important information for understanding drug binding. However, the computational expenditure limits the growth of protein trajectory-related studies, thus hindering the possibility of supervised learning. A spatial-temporal pre-training method based on the modified equivariant graph matching networks, dubbed ProtMD which has two specially designed self-supervised learning tasks: atom-level prompt-based denoising generative task and conformation-level snapshot ordering task to seize the flexibility information inside molecular dynamics (MD) trajectories with very fine temporal resolutions is presented. The ProtMD can grant the encoder network the capacity to capture the time-dependent geometric mobility of conformations along MD trajectories. Two downstream tasks are chosen to verify the effectiveness of ProtMD through linear detection and task-specific fine-tuning. A huge improvement from current state-of-the-art methods, with a decrease of 4.3% in root mean square error for the binding affinity problem and an average increase of 13.8% in the area under receiver operating characteristic curve and the area under the precision-recall curve for the ligand efficacy problem is observed. The results demonstrate a strong correlation between the magnitude of conformation's motion in the 3D space and the strength with which the ligand binds with its receptor.

LaGAT: link-aware graph attention network for drug-drug interaction prediction.

MOTIVATION: Drug-drug interaction (DDI) prediction is a challenging problem in pharmacology and clinical applications. With the increasing availability of large biomedical databases, large-scale biological knowledge graphs containing drug information have been widely used for DDI prediction. However, large knowledge graphs inevitably suffer from data noise problems, which limit the performance and interpretability of models based on the knowledge graph. Recent studies attempt to improve models by introducing inductive bias through an attention mechanism. However, they all only depend on the topology of entity nodes independently to generate fixed attention pathways, without considering the semantic diversity of entity nodes in different drug pair links. This makes it difficult for models to select more meaningful nodes to overcome data quality limitations and make more interpretable predictions. RESULTS: To address this issue, we propose a Link-aware Graph Attention method for DDI prediction, called LaGAT, which is able to generate different attention pathways for drug entities based on different drug pair links. For a drug pair link, the LaGAT uses the embedding representation of one of the drugs as a query vector to calculate the attention weights, thereby selecting the appropriate topological neighbor nodes to obtain the semantic information of the other drug. We separately conduct experiments on binary and multi-class classification and visualize the attention pathways generated by the model. The results prove that LaGAT can better capture semantic relationships and achieves remarkably superior performance over both the classical and state-of-the-art models on DDI prediction. AVAILABILITYAND IMPLEMENTATION: The source code and data are available at https://github.com/Azra3lzz/LaGAT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Hierarchical CoMoS3.13/MoS2 hollow nanosheet arrays as bifunctional electrocatalysts for overall water splitting.

Hollow hetero-nanosheet arrays have attracted great attention due to their efficient catalytic abilities for water splitting. We successfully fabricated ZIF-67-derived hollow CoMoS3.13/MoS2 nanosheet arrays on carbon cloth in situ through a two-step heating-up hydrothermal method, in which the MoS2 nanosheets were suitably distributed on the surface of the hollow CoMoS3.13 nanosheet arrays. There was a distinct synergistic effect between CoMoS3.13 and MoS2, and a large number of defective and disordered interfaces were formed, which improved the charge transfer rate and provided abundant electrochemical active sites. CMM 0.5, with the optimal Mo doping concentration of 0.5 mmol, exhibited the best catalytic properties. The overpotential values of CMM 0.5 at 10 mA cm-2 were only 107 and 169 mV for the HER and OER, respectively, and it had nearly 100% faradaic efficiency. A dual-electrode electrolytic cell assembled with CMM 0.5 required a voltage of only 1.507 V at 10 mA cm-2 for overall water splitting, and it displayed remarkable long-term durable bifunctional stability.

DeepTTA: a transformer-based model for predicting cancer drug response.

Identifying new lead molecules to treat cancer requires more than a decade of dedicated effort. Before selected drug candidates are used in the clinic, their anti-cancer activity is generally validated by in vitro cellular experiments. Therefore, accurate prediction of cancer drug response is a critical and challenging task for anti-cancer drugs design and precision medicine. With the development of pharmacogenomics, the combination of efficient drug feature extraction methods and omics data has made it possible to use computational models to assist in drug response prediction. In this study, we propose DeepTTA, a novel end-to-end deep learning model that utilizes transformer for drug representation learning and a multilayer neural network for transcriptomic data prediction of the anti-cancer drug responses. Specifically, DeepTTA uses transcriptomic gene expression data and chemical substructures of drugs for drug response prediction. Compared to existing methods, DeepTTA achieved higher performance in terms of root mean square error, Pearson correlation coefficient and Spearman's rank correlation coefficient on multiple test sets. Moreover, we discovered that anti-cancer drugs bortezomib and dactinomycin provide a potential therapeutic option with multiple clinical indications. With its excellent performance, DeepTTA is expected to be an effective method in cancer drug design.

Drug-target interactions prediction via deep collaborative filtering with multiembeddings.

Drug-target interactions (DTIs) prediction research presents important significance for promoting the development of modern medicine and pharmacology. Traditional biochemical experiments for DTIs prediction confront the challenges including long time period, high cost and high failure rate, and finally leading to a low-drug productivity. Chemogenomic-based computational methods can realize high-throughput prediction. In this study, we develop a deep collaborative filtering prediction model with multiembeddings, named DCFME (deep collaborative filtering prediction model with multiembeddings), which can jointly utilize multiple feature information from multiembeddings. Two different representation learning algorithms are first employed to extract heterogeneous network features. DCFME uses the generated low-dimensional dense vectors as input, and then simulates the drug-target relationship from the perspective of both couplings and heterogeneity. In addition, the model employs focal loss that concentrates the loss on sparse and hard samples in the training process. Comparative experiments with five baseline methods show that DCFME achieves more significant performance improvement on sparse datasets. Moreover, the model has better robustness and generalization capacity under several harder prediction scenarios.

preMLI: a pre-trained method to uncover microRNA-lncRNA potential interactions.

The interaction between microribonucleic acid and long non-coding ribonucleic acid plays a very important role in biological processes, and the prediction of the one is of great significance to the study of its mechanism of action. Due to the limitations of traditional biological experiment methods, more and more computational methods are applied to this field. However, the existing methods often have problems, such as inadequate acquisition of potential features of the sequence due to simple coding and the need to manually extract features as input. We propose a deep learning model, preMLI, based on rna2vec pre-training and deep feature mining mechanism. We use rna2vec to train the ribonucleic acid (RNA) dataset and to obtain the RNA word vector representation and then mine the RNA sequence features separately and finally concatenate the two feature vectors as the input of the prediction task. The preMLI performs better than existing methods on benchmark datasets and has cross-species prediction capabilities. Experiments show that both pre-training and deep feature mining mechanisms have a positive impact on the prediction performance of the model. To be more specific, pre-training can provide more accurate word vector representations. The deep feature mining mechanism also improves the prediction performance of the model. Meanwhile, The preMLI only needs RNA sequence as the input of the model and has better cross-species prediction performance than the most advanced prediction models, which have reference value for related research.

Prediction of Protein-Protein Interaction Sites Based on Stratified Attentional Mechanisms.

Proteins are the basic substances that undertake human life activities, and they often perform their biological functions through interactions with other biological macromolecules, such as cell transmission and signal transduction. Predicting the interaction sites between proteins can deepen the understanding of the principle of protein interactions, but traditional experimental methods are time-consuming and labor-intensive. In this study, a new hierarchical attention network structure, named HANPPIS, by adding six effective features of protein sequence, position-specific scoring matrix (PSSM), secondary structure, pre-training vector, hydrophilic, and amino acid position, is proposed to predict protein-protein interaction (PPI) sites. The experiment proved that our model has obtained very effective results, which was better than the existing advanced calculation methods. More importantly, we used the double-layer attention mechanism to improve the interpretability of the model and to a certain extent solved the problem of the "black box" of deep neural networks, which can be used as a reference for location positioning on the biological level.

HeTDR: Drug repositioning based on heterogeneous networks and text mining.

Using existing knowledge to carry out drug-disease associations prediction is a vital method for drug repositioning. However, effectively fusing the biomedical text and biological network information is one of the great challenges for most current drug repositioning methods. In this study, we propose a drug repositioning method based on heterogeneous networks and text mining (HeTDR). This model can combine drug features from multiple drug-related networks, disease features from biomedical corpora with the known drug-disease associations network to predict the correlation scores between drug and disease. Experiments demonstrate that HeTDR has excellent performance that is superior to that of state-of-the-art models. We present the top 10 novel HeTDR-predicted approved drugs for five diseases and prove our model is capable of discovering potential candidate drugs for disease indications.

Application of deep learning methods in biological networks.

The increase in biological data and the formation of various biomolecule interaction databases enable us to obtain diverse biological networks. These biological networks provide a wealth of raw materials for further understanding of biological systems, the discovery of complex diseases and the search for therapeutic drugs. However, the increase in data also increases the difficulty of biological networks analysis. Therefore, algorithms that can handle large, heterogeneous and complex data are needed to better analyze the data of these network structures and mine their useful information. Deep learning is a branch of machine learning that extracts more abstract features from a larger set of training data. Through the establishment of an artificial neural network with a network hierarchy structure, deep learning can extract and screen the input information layer by layer and has representation learning ability. The improved deep learning algorithm can be used to process complex and heterogeneous graph data structures and is increasingly being applied to the mining of network data information. In this paper, we first introduce the used network data deep learning models. After words, we summarize the application of deep learning on biological networks. Finally, we discuss the future development prospects of this field.

Bibliometric Analysis of Chronic Traumatic Encephalopathy Research from 1999 to 2019.

Research on chronic traumatic encephalopathy (CTE) has increased over the past two decades. However, few studies have statistically analyzed these publications. In this work, we conducted a bibliometric analysis of studies on CTE to track research trends and highlight current research hotspots. Relevant original articles were obtained from the Web of Science Core Collection database between 1999 and 2019. CiteSpace and VOSviewer software were used to perform analysis and visualization of scientific productivity and emerging trends. Our results show that the publications related to CTE dramatically increased from four publications in 1999 to 160 publications in 2019. The United States dominated this field with 732 publications (75.934%), followed by Canada with 88 publications (9.129%). Most of related publications were published in the journals with a focus on molecular biology, immunology, neurology, sports and ophthalmology, as represented by the dual-map overlay. A total of 11 major clusters were explored based on the reference co-citation analysis. In addition, three predominant research topics were summarized by clustering high-frequency keywords: epidemiological, clinical and pathological studies. The research frontiers were the diagnosis of diseases using new neuroimaging techniques, and the investigation of the molecular mechanism of tau aggregation. This study provides researchers with valuable guidance in the selection of research topics.

A network-based approach to uncover microRNA-mediated disease comorbidities and potential pathobiological implications.

Disease-disease relationships (e.g., disease comorbidities) play crucial roles in pathobiological manifestations of diseases and personalized approaches to managing those conditions. In this study, we develop a network-based methodology, termed meta-path-based Disease Network (mpDisNet) capturing algorithm, to infer disease-disease relationships by assembling four biological networks: disease-miRNA, miRNA-gene, disease-gene, and the human protein-protein interactome. mpDisNet is a meta-path-based random walk to reconstruct the heterogeneous neighbors of a given node. mpDisNet uses a heterogeneous skip-gram model to solve the network representation of the nodes. We find that mpDisNet reveals high performance in inferring clinically reported disease-disease relationships, outperforming that of traditional gene/miRNA-overlap approaches. In addition, mpDisNet identifies network-based comorbidities for pulmonary diseases driven by underlying miRNA-mediated pathobiological pathways (i.e., hsa-let-7a- or hsa-let-7b-mediated airway epithelial apoptosis and pro-inflammatory cytokine pathways) as derived from the human interactome network analysis. The mpDisNet offers a powerful tool for network-based identification of disease-disease relationships with miRNA-mediated pathobiological pathways.

Machine Learning for Drug-Target Interaction Prediction.

Identifying drug-target interactions will greatly narrow down the scope of search of candidate medications, and thus can serve as the vital first step in drug discovery. Considering that in vitro experiments are extremely costly and time-consuming, high efficiency computational prediction methods could serve as promising strategies for drug-target interaction (DTI) prediction. In this review, our goal is to focus on machine learning approaches and provide a comprehensive overview. First, we summarize a brief list of databases frequently used in drug discovery. Next, we adopt a hierarchical classification scheme and introduce several representative methods of each category, especially the recent state-of-the-art methods. In addition, we compare the advantages and limitations of methods in each category. Lastly, we discuss the remaining challenges and future outlook of machine learning in DTI prediction. This article may provide a reference and tutorial insights on machine learning-based DTI prediction for future researchers.

Chronic Helminth Infection Perturbs the Gut-Brain Axis, Promotes Neuropathology, and Alters Behavior.

Helminth infections in children are associated with impaired cognitive development; however, the biological mechanisms for this remain unclear. Using a murine model of gastrointestinal helminth infection, we demonstrate that early-life exposure to helminths promotes local and systemic inflammatory responses and transient changes in the gastrointestinal microbiome. Behavioral and cognitive analyses performed 9-months postinfection revealed deficits in spatial recognition memory and an anxiety-like behavioral phenotype in worm-infected mice, which was associated with neuropathology and increased microglial activation within the brain. This study demonstrates a previously unrecognized mechanism through which helminth infections may influence cognitive function, via perturbations in the gut-immune-brain axis.

Predict the Relationship between Gene and Large Yellow Croaker's Economic Traits.

The importance of a gene's impact on traits is well appreciated. Gene expression will affect the growth, immunity, reproduction and environmental resistance of some fish, and then affect the economic performance of fish-related business. Studying the connection between gene and character can help elucidate the growth of fishes. Thus far, a collected database containing large yellow croaker (Larimichthys crocea) genes does not exist. The gene having to do with the growth efficiency of fish will have a huge impact on research. For example, the protein encoded by the IFIH1 gene is associated with the function of viral infection in the immune system, which affects the survival rate of large yellow croakers. Thus, we collected data through the published literature and combined them with a biological genetic database related to the large yellow croaker. Based on the data, we can predict new gene-trait associations which have not yet been discovered. This work will contribute to research on the growth of large yellow croakers.

COMT genotype predicts longitudinal cognitive decline and psychosis in 22q11.2 deletion syndrome.

Although schizophrenia is strongly hereditary, there are limited data regarding biological risk factors and pathophysiological processes. In this longitudinal study of adolescents with 22q11.2 deletion syndrome, we identified the catechol-O-methyltransferase low-activity allele (COMT(L)) as a risk factor for decline in prefrontal cortical volume and cognition, as well as for the consequent development of psychotic symptoms during adolescence. The 22q11.2 deletion syndrome is a promising model for identifying biomarkers related to the development of schizophrenia.