Dual-channel hypergraph convolutional network for predicting herb-disease associations.

Herbs applicability in disease treatment has been verified through experiences over thousands of years. The understanding of herb-disease associations (HDAs) is yet far from complete due to the complicated mechanism inherent in multi-target and multi-component (MTMC) botanical therapeutics. Most of the existing prediction models fail to incorporate the MTMC mechanism. To overcome this problem, we propose a novel dual-channel hypergraph convolutional network, namely HGHDA, for HDA prediction. Technically, HGHDA first adopts an autoencoder to project components and target protein onto a low-dimensional latent space so as to obtain their embeddings by preserving similarity characteristics in their original feature spaces. To model the high-order relations between herbs and their components, we design a channel in HGHDA to encode a hypergraph that describes the high-order patterns of herb-component relations via hypergraph convolution. The other channel in HGHDA is also established in the same way to model the high-order relations between diseases and target proteins. The embeddings of drugs and diseases are then aggregated through our dual-channel network to obtain the prediction results with a scoring function. To evaluate the performance of HGHDA, a series of extensive experiments have been conducted on two benchmark datasets, and the results demonstrate the superiority of HGHDA over the state-of-the-art algorithms proposed for HDA prediction. Besides, our case study on Chuan Xiong and Astragalus membranaceus is a strong indicator to verify the effectiveness of HGHDA, as seven and eight out of the top 10 diseases predicted by HGHDA for Chuan-Xiong and Astragalus-membranaceus, respectively, have been reported in literature.

Attention-based Knowledge Graph Representation Learning for Predicting Drug-drug Interactions.

Drug-drug interactions (DDIs) are known as the main cause of life-threatening adverse events, and their identification is a key task in drug development. Existing computational algorithms mainly solve this problem by using advanced representation learning techniques. Though effective, few of them are capable of performing their tasks on biomedical knowledge graphs (KGs) that provide more detailed information about drug attributes and drug-related triple facts. In this work, an attention-based KG representation learning framework, namely DDKG, is proposed to fully utilize the information of KGs for improved performance of DDI prediction. In particular, DDKG first initializes the representations of drugs with their embeddings derived from drug attributes with an encoder-decoder layer, and then learns the representations of drugs by recursively propagating and aggregating first-order neighboring information along top-ranked network paths determined by neighboring node embeddings and triple facts. Last, DDKG estimates the probability of being interacting for pairwise drugs with their representations in an end-to-end manner. To evaluate the effectiveness of DDKG, extensive experiments have been conducted on two practical datasets with different sizes, and the results demonstrate that DDKG is superior to state-of-the-art algorithms on the DDI prediction task in terms of different evaluation metrics across all datasets.

A deep learning method for repurposing antiviral drugs against new viruses via multi-view nonnegative matrix factorization and its application to SARS-CoV-2.

The outbreak of COVID-19 caused by SARS-coronavirus (CoV)-2 has made millions of deaths since 2019. Although a variety of computational methods have been proposed to repurpose drugs for treating SARS-CoV-2 infections, it is still a challenging task for new viruses, as there are no verified virus-drug associations (VDAs) between them and existing drugs. To efficiently solve the cold-start problem posed by new viruses, a novel constrained multi-view nonnegative matrix factorization (CMNMF) model is designed by jointly utilizing multiple sources of biological information. With the CMNMF model, the similarities of drugs and viruses can be preserved from their own perspectives when they are projected onto a unified latent feature space. Based on the CMNMF model, we propose a deep learning method, namely VDA-DLCMNMF, for repurposing drugs against new viruses. VDA-DLCMNMF first initializes the node representations of drugs and viruses with their corresponding latent feature vectors to avoid a random initialization and then applies graph convolutional network to optimize their representations. Given an arbitrary drug, its probability of being associated with a new virus is computed according to their representations. To evaluate the performance of VDA-DLCMNMF, we have conducted a series of experiments on three VDA datasets created for SARS-CoV-2. Experimental results demonstrate that the promising prediction accuracy of VDA-DLCMNMF. Moreover, incorporating the CMNMF model into deep learning gains new insight into the drug repurposing for SARS-CoV-2, as the results of molecular docking experiments reveal that four antiviral drugs identified by VDA-DLCMNMF have the potential ability to treat SARS-CoV-2 infections.

A geometric deep learning framework for drug repositioning over heterogeneous information networks.

Drug repositioning (DR) is a promising strategy to discover new indicators of approved drugs with artificial intelligence techniques, thus improving traditional drug discovery and development. However, most of DR computational methods fall short of taking into account the non-Euclidean nature of biomedical network data. To overcome this problem, a deep learning framework, namely DDAGDL, is proposed to predict drug-drug associations (DDAs) by using geometric deep learning (GDL) over heterogeneous information network (HIN). Incorporating complex biological information into the topological structure of HIN, DDAGDL effectively learns the smoothed representations of drugs and diseases with an attention mechanism. Experiment results demonstrate the superior performance of DDAGDL on three real-world datasets under 10-fold cross-validation when compared with state-of-the-art DR methods in terms of several evaluation metrics. Our case studies and molecular docking experiments indicate that DDAGDL is a promising DR tool that gains new insights into exploiting the geometric prior knowledge for improved efficacy.

iGRLDTI: an improved graph representation learning method for predicting drug-target interactions over heterogeneous biological information network.

MOTIVATION: The task of predicting drug-target interactions (DTIs) plays a significant role in facilitating the development of novel drug discovery. Compared with laboratory-based approaches, computational methods proposed for DTI prediction are preferred due to their high-efficiency and low-cost advantages. Recently, much attention has been attracted to apply different graph neural network (GNN) models to discover underlying DTIs from heterogeneous biological information network (HBIN). Although GNN-based prediction methods achieve better performance, they are prone to encounter the over-smoothing simulation when learning the latent representations of drugs and targets with their rich neighborhood information in HBIN, and thereby reduce the discriminative ability in DTI prediction. RESULTS: In this work, an improved graph representation learning method, namely iGRLDTI, is proposed to address the above issue by better capturing more discriminative representations of drugs and targets in a latent feature space. Specifically, iGRLDTI first constructs an HBIN by integrating the biological knowledge of drugs and targets with their interactions. After that, it adopts a node-dependent local smoothing strategy to adaptively decide the propagation depth of each biomolecule in HBIN, thus significantly alleviating over-smoothing by enhancing the discriminative ability of feature representations of drugs and targets. Finally, a Gradient Boosting Decision Tree classifier is used by iGRLDTI to predict novel DTIs. Experimental results demonstrate that iGRLDTI yields better performance that several state-of-the-art computational methods on the benchmark dataset. Besides, our case study indicates that iGRLDTI can successfully identify novel DTIs with more distinguishable features of drugs and targets. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at https://github.com/stevejobws/iGRLDTI/.

Genomic epidemiology of CVA10 in Guangdong, China, 2013-2021.

Hand, Foot and Mouth Disease (HFMD) is a highly contagious viral illness primarily affecting children globally. A significant epidemiological transition has been noted in mainland China, characterized by a substantial increase in HFMD cases caused by non-Enterovirus A71 (EV-A71) and non-Coxsackievirus A16 (CVA16) enteroviruses (EVs). Our study conducts a retrospective examination of 36,461 EV-positive specimens collected from Guangdong, China, from 2013 to 2021. Epidemiological trends suggest that, following 2013, Coxsackievirus A6 (CVA6) and Coxsackievirus A10 (CVA10) have emerged as the primary etiological agents for HFMD. In stark contrast, the incidence of EV-A71 has sharply declined, nearing extinction after 2018. Notably, cases of CVA10 infection were considerably younger, with a median age of 1.8 years, compared to 2.3 years for those with EV-A71 infections, possibly indicating accumulated EV-A71-specific herd immunity among young children. Through extensive genomic sequencing and analysis, we identified the N136D mutation in the 2 A protein, contributing to a predominant subcluster within genogroup C of CVA10 circulating in Guangdong since 2017. Additionally, a high frequency of recombination events was observed in genogroup F of CVA10, suggesting that the prevalence of this lineage might be underrecognized. The dynamic landscape of EV genotypes, along with their potential to cause outbreaks, underscores the need to broaden surveillance efforts to include a more diverse spectrum of EV genotypes. Moreover, given the shifting dominance of EV genotypes, it may be prudent to re-evaluate and optimize existing vaccination strategies, which are currently focused primarily target EV-A71.

Knowledge graph embedding for profiling the interaction between transcription factors and their target genes.

Interactions between transcription factor and target gene form the main part of gene regulation network in human, which are still complicating factors in biological research. Specifically, for nearly half of those interactions recorded in established database, their interaction types are yet to be confirmed. Although several computational methods exist to predict gene interactions and their type, there is still no method available to predict them solely based on topology information. To this end, we proposed here a graph-based prediction model called KGE-TGI and trained in a multi-task learning manner on a knowledge graph that we specially constructed for this problem. The KGE-TGI model relies on topology information rather than being driven by gene expression data. In this paper, we formulate the task of predicting interaction types of transcript factor and target genes as a multi-label classification problem for link types on a heterogeneous graph, coupled with solving another link prediction problem that is inherently related. We constructed a ground truth dataset as benchmark and evaluated the proposed method on it. As a result of the 5-fold cross experiments, the proposed method achieved average AUC values of 0.9654 and 0.9339 in the tasks of link prediction and link type classification, respectively. In addition, the results of a series of comparison experiments also prove that the introduction of knowledge information significantly benefits to the prediction and that our methodology achieve state-of-the-art performance in this problem.

Drug-disease association prediction using semantic graph and function similarity representation learning over heterogeneous information networks.

Discovering new indications for existing drugs is a promising development strategy at various stages of drug research and development. However, most of them complete their tasks by constructing a variety of heterogeneous networks without considering available higher-order connectivity patterns in heterogeneous biological information networks, which are believed to be useful for improving the accuracy of new drug discovering. To this end, we propose a computational-based model, called SFRLDDA, for drug-disease association prediction by using semantic graph and function similarity representation learning. Specifically, SFRLDDA first integrates a heterogeneous information network (HIN) by drug-disease, drug-protein, protein-disease associations, and their biological knowledge. Second, different representation learning strategies are applied to obtain the feature representations of drugs and diseases from different perspectives over semantic graph and function similarity graphs constructed, respectively. At last, a Random Forest classifier is incorporated by SFRLDDA to discover potential drug-disease associations (DDAs). Experimental results demonstrate that SFRLDDA yields a best performance when compared with other state-of-the-art models on three benchmark datasets. Moreover, case studies also indicate that the simultaneous consideration of semantic graph and function similarity of drugs and diseases in the HIN allows SFRLDDA to precisely predict DDAs in a more comprehensive manner.

Retrospective charts for reporting, analysing, and evaluating disaster emergency response: a systematic review.

OBJECTIVE: Given the frequency of disasters worldwide, there is growing demand for efficient and effective emergency responses. One challenge is to design suitable retrospective charts to enable knowledge to be gained from disasters. This study provides comprehensive understanding of published retrospective chart review templates for designing and updating retrospective research. METHODS: We conducted a systematic review and text analysis of peer-reviewed articles and grey literature on retrospective chart review templates for reporting, analysing, and evaluating emergency responses. The search was performed on PubMed, Cochrane, and Web of Science and pre-identified government and non-government organizational and professional association websites to find papers published before July 1, 2022. Items and categories were grouped and organised using visual text analysis. The study is registered in PROSPERO (374,928). RESULTS: Four index groups, 12 guidelines, and 14 report formats (or data collection templates) from 21 peer-reviewed articles and 9 grey literature papers were eligible. Retrospective tools were generally designed based on group consensus. One guideline and one report format were designed for the entire health system, 23 studies focused on emergency systems, while the others focused on hospitals. Five papers focused specific incident types, including chemical, biological, radiological, nuclear, mass burning, and mass paediatric casualties. Ten papers stated the location where the tools were used. The text analysis included 123 categories and 1210 specific items; large heterogeneity was observed. CONCLUSION: Existing retrospective chart review templates for emergency response are heterogeneous, varying in type, hierarchy, and theoretical basis. The design of comprehensive, standard, and practicable retrospective charts requires an emergency response paradigm, baseline for outcomes, robust information acquisition, and among-region cooperation.

Biocaiv: an integrative webserver for motif-based clustering analysis and interactive visualization of biological networks.

BACKGROUND: As an important task in bioinformatics, clustering analysis plays a critical role in understanding the functional mechanisms of many complex biological systems, which can be modeled as biological networks. The purpose of clustering analysis in biological networks is to identify functional modules of interest, but there is a lack of online clustering tools that visualize biological networks and provide in-depth biological analysis for discovered clusters. RESULTS: Here we present BioCAIV, a novel webserver dedicated to maximize its accessibility and applicability on the clustering analysis of biological networks. This, together with its user-friendly interface, assists biological researchers to perform an accurate clustering analysis for biological networks and identify functionally significant modules for further assessment. CONCLUSIONS: BioCAIV is an efficient clustering analysis webserver designed for a variety of biological networks. BioCAIV is freely available without registration requirements at http://bioinformatics.tianshanzw.cn:8888/BioCAIV/ .

A survey on computational models for predicting protein-protein interactions.

Proteins interact with each other to play critical roles in many biological processes in cells. Although promising, laboratory experiments usually suffer from the disadvantages of being time-consuming and labor-intensive. The results obtained are often not robust and considerably uncertain. Due recently to advances in high-throughput technologies, a large amount of proteomics data has been collected and this presents a significant opportunity and also a challenge to develop computational models to predict protein-protein interactions (PPIs) based on these data. In this paper, we present a comprehensive survey of the recent efforts that have been made towards the development of effective computational models for PPI prediction. The survey introduces the algorithms that can be used to learn computational models for predicting PPIs, and it classifies these models into different categories. To understand their relative merits, the paper discusses different validation schemes and metrics to evaluate the prediction performance. Biological databases that are commonly used in different experiments for performance comparison are also described and their use in a series of extensive experiments to compare different prediction models are discussed. Finally, we present some open issues in PPI prediction for future work. We explain how the performance of PPI prediction can be improved if these issues are effectively tackled.

Predicting microRNA-disease associations from lncRNA-microRNA interactions via Multiview Multitask Learning.

MOTIVATION: Identifying microRNAs that are associated with different diseases as biomarkers is a problem of great medical significance. Existing computational methods for uncovering such microRNA-diseases associations (MDAs) are mostly developed under the assumption that similar microRNAs tend to associate with similar diseases. Since such an assumption is not always valid, these methods may not always be applicable to all kinds of MDAs. Considering that the relationship between long noncoding RNA (lncRNA) and different diseases and the co-regulation relationships between the biological functions of lncRNA and microRNA have been established, we propose here a multiview multitask method to make use of the known lncRNA-microRNA interaction to predict MDAs on a large scale. The investigation is performed in the absence of complete information of microRNAs and any similarity measurement for it and to the best knowledge, the work represents the first ever attempt to discover MDAs based on lncRNA-microRNA interactions. RESULTS: In this paper, we propose to develop a deep learning model called MVMTMDA that can create a multiview representation of microRNAs. The model is trained based on an end-to-end multitasking approach to machine learning so that, based on it, missing data in the side information can be determined automatically. Experimental results show that the proposed model yields an average area under ROC curve of 0.8410+/-0.018, 0.8512+/-0.012 and 0.8521+/-0.008 when k is set to 2, 5 and 10, respectively. In addition, we also propose here a statistical approach to predicting lncRNA-disease associations based on these associations and the MDA discovered using MVMTMDA. AVAILABILITY: Python code and the datasets used in our studies are made available at https://github.com/yahuang1991polyu/MVMTMDA/.

Effectively predicting HIV-1 protease cleavage sites by using an ensemble learning approach.

BACKGROUND: The site information of substrates that can be cleaved by human immunodeficiency virus 1 proteases (HIV-1 PRs) is of great significance for designing effective inhibitors against HIV-1 viruses. A variety of machine learning-based algorithms have been developed to predict HIV-1 PR cleavage sites by extracting relevant features from substrate sequences. However, only relying on the sequence information is not sufficient to ensure a promising performance due to the uncertainty in the way of separating the datasets used for training and testing. Moreover, the existence of noisy data, i.e., false positive and false negative cleavage sites, could negatively influence the accuracy performance. RESULTS: In this work, an ensemble learning algorithm for predicting HIV-1 PR cleavage sites, namely EM-HIV, is proposed by training a set of weak learners, i.e., biased support vector machine classifiers, with the asymmetric bagging strategy. By doing so, the impact of data imbalance and noisy data can thus be alleviated. Besides, in order to make full use of substrate sequences, the features used by EM-HIV are collected from three different coding schemes, including amino acid identities, chemical properties and variable-length coevolutionary patterns, for the purpose of constructing more relevant feature vectors of octamers. Experiment results on three independent benchmark datasets demonstrate that EM-HIV outperforms state-of-the-art prediction algorithm in terms of several evaluation metrics. Hence, EM-HIV can be regarded as a useful tool to accurately predict HIV-1 PR cleavage sites.

Multi-view heterogeneous molecular network representation learning for protein-protein interaction prediction.

BACKGROUND: Protein-protein interaction (PPI) plays an important role in regulating cells and signals. Despite the ongoing efforts of the bioassay group, continued incomplete data limits our ability to understand the molecular roots of human disease. Therefore, it is urgent to develop a computational method to predict PPIs from the perspective of molecular system. METHODS: In this paper, a highly efficient computational model, MTV-PPI, is proposed for PPI prediction based on a heterogeneous molecular network by learning inter-view protein sequences and intra-view interactions between molecules simultaneously. On the one hand, the inter-view feature is extracted from the protein sequence by k-mer method. On the other hand, we use a popular embedding method LINE to encode the heterogeneous molecular network to obtain the intra-view feature. Thus, the protein representation used in MTV-PPI is constructed by the aggregation of its inter-view feature and intra-view feature. Finally, random forest is integrated to predict potential PPIs. RESULTS: To prove the effectiveness of MTV-PPI, we conduct extensive experiments on a collected heterogeneous molecular network with the accuracy of 86.55%, sensitivity of 82.49%, precision of 89.79%, AUC of 0.9301 and AUPR of 0.9308. Further comparison experiments are performed with various protein representations and classifiers to indicate the effectiveness of MTV-PPI in predicting PPIs based on a complex network. CONCLUSION: The achieved experimental results illustrate that MTV-PPI is a promising tool for PPI prediction, which may provide a new perspective for the future interactions prediction researches based on heterogeneous molecular network.

Incorporation of Sequence Aza-Substitution and Thiophene Bridge in Linear Conjugated Polymers Toward Highly Efficient Photo-Catalytic Hydrogen Evolution.

The hydrogen evolution performance of organic photo-catalysts is lagged by numerous factors, such as the narrow photon absorption window, low charge transport, and so on. In this paper, four linear conjugated polymers are designed and synthesized based on dibenzothiophene-S,S-dioxide as an acceptor, and aza-substituted thiophene-phenyl-thiophene with different substitution numbers as co-units. The polymers with the thiophene bridge and aza-substitution exhibit broad visible absorption because of the extended conjugated length and improved planar structures resulting from the intramolecular non-covalent interactions (S···N or CH···N). The mono-substitution polymer without the addition of any co-catalysts shows the highest photo-catalytic performances with the hydrogen evolution rates of 8950 and 7388 µmol g-1 h-1 under the UV-vis (>295 nm) and visible (>420 nm) irradiation, respectively. The corresponding apparent quantum yields are as high as 8.34, 5.37, and 1.96% for the 420, 500, and 550 nm monochromatic light irradiation, respectively, which are much higher than those of the classic polymer (P7) without thiophene bridge and aza-substitution. This work indicats that the incorporation of thiophene bridge enhances visible absorption and aza-substitution optimized co-planarity and activate reactive sites, which should be an effective strategy to improve the photo-catalytic performance of linear conjugated polymers.

Health Beliefs, Trust in Media Sources, Health Literacy, and Preventive Behaviors among High-Risk Chinese for COVID-19.

The coronavirus disease (COVID-19) broke out in China in January 2020 and has been effectively controlled in April 2020 after China's relentless efforts. People's engagement in disease-related preventive behaviors is crucial in containing such infectious disease. Vulnerable populations often have higher chances of developing severe illness from COVID-19 and the mortality rate is also higher. Thus, at-risk populations for COVID-19 request extra attention. The current study conducted a national online survey among vulnerable populations in China in early February 2020 to examine their engagement in coronavirus-related preventive health behaviors (e.g., frequent handwashing) and the potential determinants including factors from the Health Belief Model, trust in different media sources, and health literacy. The results suggested that the vulnerable populations' engagement in coronavirus-related preventive behaviors were significantly associated with barriers, benefits, self-efficacy, trust in doctors' social media, and trust in TV for COVID-19-related information. Besides, barriers, benefits, self-efficacy, trust in doctors' social media, and trust in TV mediated the effects of health literacy on preventive behaviors. Our findings provided directions for future health promotions and interventions targeting vulnerable populations to enhance their preventive behaviors in China.

A 3D Attitude Estimation Method Based on Attitude Angular Partial Feedback for Polarization-Based Integrated Navigation System.

Polarization (POL) navigation is inspired by insects' behavior of precepting celestial polarization patterns to orient themselves. It has the advantages of being autonomous and having no accumulative error, which allows it to be used to correct the errors of the inertial navigation system (INS). The integrated navigation system of the POL-based solar vector with INS is capable of 3D attitude determination. However, the commonly used POL-based integrated navigation system generally implements the attitude update procedure without considering the performance difference with different magnitudes of the angles between the solar-vector and body-axes of the platform (S-B angles). When one of the S-B angles is small enough, the estimated accuracy of the attitude angle by the INS/POL is worse than that of the strapdown inertial navigation system. To minimize the negative impact of POL in this situation, an attitude angular adaptive partial feedback method is proposed. The S-B angles are used to construct a partial feedback factor matrix to adaptively adjust the degree of error correction for INS. The results of simulation and real-world experiments demonstrate that the proposed method can improve the accuracy of 3D attitude estimation compared with the conventional all-feedback method for small S-B angles especially for yaw angle estimation.

Prevalence of Familial Hypercholesterolemia Among the General Population and Patients With Atherosclerotic Cardiovascular Disease: A Systematic Review and Meta-Analysis.

BACKGROUND: Contemporary studies suggest that familial hypercholesterolemia (FH) is more frequent than previously reported and increasingly recognized as affecting individuals of all ethnicities and across many regions of the world. Precise estimation of its global prevalence and prevalence across World Health Organization regions is needed to inform policies aiming at early detection and atherosclerotic cardiovascular disease (ASCVD) prevention. The present study aims to provide a comprehensive assessment and more reliable estimation of the prevalence of FH than hitherto possible in the general population (GP) and among patients with ASCVD. METHODS: We performed a systematic review and meta-analysis including studies reporting on the prevalence of heterozygous FH in the GP or among those with ASCVD. Studies reporting gene founder effects and focused on homozygous FH were excluded. The search was conducted through Medline, Embase, Cochrane, and Global Health, without time or language restrictions. A random-effects model was applied to estimate the overall pooled prevalence of FH in the general and ASCVD populations separately and by World Health Organization regions. RESULTS: From 3225 articles, 42 studies from the GP and 20 from populations with ASCVD were eligible, reporting on 7 297 363 individuals/24 636 cases of FH and 48 158 patients/2827 cases of FH, respectively. More than 60% of the studies were from Europe. Use of the Dutch Lipid Clinic Network criteria was the commonest diagnostic method. Within the GP, the overall pooled prevalence of FH was 1:311 (95% CI, 1:250-1:397; similar between children [1:364] and adults [1:303], P=0.60; across World Health Organization regions where data were available, P=0.29; and between population-based and electronic health records-based studies, P=0.82). Studies with ≤10 000 participants reported a higher prevalence (1:200-289) compared with larger cohorts (1:365-407; P<0.001). The pooled prevalence among those with ASCVD was 18-fold higher than in the GP (1:17 [95% CI, 1:12-1:24]), driven mainly by coronary artery disease (1:16; [95% CI, 1:12-1:23]). Between-study heterogeneity was large (I2>95%). Tests assessing bias were nonsignificant (P>0.3). CONCLUSIONS: With an overall prevalence of 1:311, FH is among the commonest genetic disorders in the GP, similarly present across different regions of the world, and is more frequent among those with ASCVD. The present results support the advocacy for the institution of public health policies, including screening programs, to identify FH early and to prevent its global burden.

Graph convolution for predicting associations between miRNA and drug resistance.

MOTIVATION: MicroRNA (miRNA) therapeutics is becoming increasingly important. However, aberrant expression of miRNAs is known to cause drug resistance and can become an obstacle for miRNA-based therapeutics. At present, little is known about associations between miRNA and drug resistance and there is no computational tool available for predicting such association relationship. Since it is known that miRNAs can regulate genes that encode specific proteins that are keys for drug efficacy, we propose here a computational approach, called GCMDR, for finding a three-layer latent factor model that can be used to predict miRNA-drug resistance associations. RESULTS: In this paper, we discuss how the problem of predicting such associations can be formulated as a link prediction problem involving a bipartite attributed graph. GCMDR makes use of the technique of graph convolution to build a latent factor model, which can effectively utilize information of high-dimensional attributes of miRNA/drug in an end-to-end learning scheme. In addition, GCMDR also learns graph embedding features for miRNAs and drugs. We leveraged the data from multiple databases storing miRNA expression profile, drug substructure fingerprints, gene ontology and disease ontology. The test for performance shows that the GCMDR prediction model can achieve AUCs of 0.9301 ± 0.0005, 0.9359 ± 0.0006 and 0.9369 ± 0.0003 based on 2-fold, 5-fold and 10-fold cross validation, respectively. Using this model, we show that the associations between miRNA and drug resistance can be reliably predicted by properly introducing useful side information like miRNA expression profile and drug structure fingerprints. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at https://github.com/yahuang1991polyu/GCMDR/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Learning from low-rank multimodal representations for predicting disease-drug associations.

BACKGROUND: Disease-drug associations provide essential information for drug discovery and disease treatment. Many disease-drug associations remain unobserved or unknown, and trials to confirm these associations are time-consuming and expensive. To better understand and explore these valuable associations, it would be useful to develop computational methods for predicting unobserved disease-drug associations. With the advent of various datasets describing diseases and drugs, it has become more feasible to build a model describing the potential correlation between disease and drugs. RESULTS: In this work, we propose a new prediction method, called LMFDA, which works in several stages. First, it studies the drug chemical structure, disease MeSH descriptors, disease-related phenotypic terms, and drug-drug interactions. On this basis, similarity networks of different sources are constructed to enrich the representation of drugs and diseases. Based on the fused disease similarity network and drug similarity network, LMFDA calculated the association score of each pair of diseases and drugs in the database. This method achieves good performance on Fdataset and Cdataset, AUROCs were 91.6% and 92.1% respectively, higher than many of the existing computational models. CONCLUSIONS: The novelty of LMFDA lies in the introduction of multimodal fusion using low-rank tensors to fuse multiple similar networks and combine matrix complement technology to predict potential association. We have demonstrated that LMFDA can display excellent network integration ability for accurate disease-drug association inferring and achieve substantial improvement over the advanced approach. Overall, experimental results on two real-world networks dataset demonstrate that LMFDA able to delivers an excellent detecting performance. Results also suggest that perfecting similar networks with as much domain knowledge as possible is a promising direction for drug repositioning.