HHOMR: a hybrid high-order moment residual model for miRNA-disease association prediction.

Numerous studies have demonstrated that microRNAs (miRNAs) are critically important for the prediction, diagnosis, and characterization of diseases. However, identifying miRNA-disease associations through traditional biological experiments is both costly and time-consuming. To further explore these associations, we proposed a model based on hybrid high-order moments combined with element-level attention mechanisms (HHOMR). This model innovatively fused hybrid higher-order statistical information along with structural and community information. Specifically, we first constructed a heterogeneous graph based on existing associations between miRNAs and diseases. HHOMR employs a structural fusion layer to capture structure-level embeddings and leverages a hybrid high-order moments encoder layer to enhance features. Element-level attention mechanisms are then used to adaptively integrate the features of these hybrid moments. Finally, a multi-layer perceptron is utilized to calculate the association scores between miRNAs and diseases. Through five-fold cross-validation on HMDD v2.0, we achieved a mean AUC of 93.28%. Compared with four state-of-the-art models, HHOMR exhibited superior performance. Additionally, case studies on three diseases-esophageal neoplasms, lymphoma, and prostate neoplasms-were conducted. Among the top 50 miRNAs with high disease association scores, 46, 47, and 45 associated with these diseases were confirmed by the dbDEMC and miR2Disease databases, respectively. Our results demonstrate that HHOMR not only outperforms existing models but also shows significant potential in predicting miRNA-disease associations.

SPRDA: a link prediction approach based on the structural perturbation to infer disease-associated Piwi-interacting RNAs.

piRNA and PIWI proteins have been confirmed for disease diagnosis and treatment as novel biomarkers due to its abnormal expression in various cancers. However, the current research is not strong enough to further clarify the functions of piRNA in cancer and its underlying mechanism. Therefore, how to provide large-scale and serious piRNA candidates for biological research has grown up to be a pressing issue. In this study, a novel computational model based on the structural perturbation method is proposed to predict potential disease-associated piRNAs, called SPRDA. Notably, SPRDA belongs to positive-unlabeled learning, which is unaffected by negative examples in contrast to previous approaches. In the 5-fold cross-validation, SPRDA shows high performance on the benchmark dataset piRDisease, with an AUC of 0.9529. Furthermore, the predictive performance of SPRDA for 10 diseases shows the robustness of the proposed method. Overall, the proposed approach can provide unique insights into the pathogenesis of the disease and will advance the field of oncology diagnosis and treatment.

BEROLECMI: a novel prediction method to infer circRNA-miRNA interaction from the role definition of molecular attributes and biological networks.

Circular RNA (CircRNA)-microRNA (miRNA) interaction (CMI) is an important model for the regulation of biological processes by non-coding RNA (ncRNA), which provides a new perspective for the study of human complex diseases. However, the existing CMI prediction models mainly rely on the nearest neighbor structure in the biological network, ignoring the molecular network topology, so it is difficult to improve the prediction performance. In this paper, we proposed a new CMI prediction method, BEROLECMI, which uses molecular sequence attributes, molecular self-similarity, and biological network topology to define the specific role feature representation for molecules to infer the new CMI. BEROLECMI effectively makes up for the lack of network topology in the CMI prediction model and achieves the highest prediction performance in three commonly used data sets. In the case study, 14 of the 15 pairs of unknown CMIs were correctly predicted.

Immune patterns of cuproptosis in ischemic heart failure: A transcriptome analysis.

Cuproptosis is a recently discovered programmed cell death pattern that affects the tricarboxylic acid (TCA) cycle by disrupting the lipoylation of pyruvate dehydrogenase (PDH) complex components. However, the role of cuproptosis in the progression of ischemic heart failure (IHF) has not been investigated. In this study, we investigated the expression of 10 cuproptosis-related genes in samples from both healthy individuals and those with IHF. Utilizing these differential gene expressions, we developed a risk prediction model that effectively distinguished healthy and IHF samples. Furthermore, we conducted a comprehensive evaluation of the association between cuproptosis and the immune microenvironment in IHF, encompassing infiltrated immunocytes, immune reaction gene-sets and human leukocyte antigen (HLA) genes. Moreover, we identified two different cuproptosis-mediated expression patterns in IHF and explored the immune characteristics associated with each pattern. In conclusion, this study elucidates the significant influence of cuproptosis on the immune microenvironment in ischemic heart failure (IHF), providing valuable insights for future mechanistic research exploring the association between cuproptosis and IHF.

Predicting miRNA-disease associations based on graph random propagation network and attention network.

Numerous experiments have demonstrated that abnormal expression of microRNAs (miRNAs) in organisms is often accompanied by the emergence of specific diseases. The research of miRNAs can promote the prevention and drug research of specific diseases. However, there are still many undiscovered links between miRNAs and diseases, which greatly limits the research of miRNAs. Therefore, for exploring the unknown miRNA-disease associations, we combine the graph random propagation network based on DropFeature with attention network to propose a novel deep learning model to predict the miRNA-disease associations (GRPAMDA). Specifically, we firstly construct the miRNA-disease heterogeneous graph based on miRNA-disease association information. Secondly, we adopt DropFeature to randomly delete the features of nodes in the graph and then perform propagation operations to enhance the features of miRNA and disease nodes. Thirdly, we employ the attention mechanism to fuse the features of random propagation by aggregating the enhanced neighbor features of miRNA and disease nodes. Finally, miRNA-disease association scores are generated by a fully connected layer. The average area under the curve of GRPAMDA model based on 5-fold cross-validation is 93.46% on HMDD v2.0. Case studies of esophageal tumors, lymphomas and prostate tumors show that 48, 47 and 46 of the top 50 miRNAs associated with these diseases are confirmed by dbDEMC and miR2Disease database, respectively. In short, the GRPAMDA model can be used as a valuable method to study miRNA-disease associations.

A machine learning framework based on multi-source feature fusion for circRNA-disease association prediction.

Circular RNAs (circRNAs) are involved in the regulatory mechanisms of multiple complex diseases, and the identification of their associations is critical to the diagnosis and treatment of diseases. In recent years, many computational methods have been designed to predict circRNA-disease associations. However, most of the existing methods rely on single correlation data. Here, we propose a machine learning framework for circRNA-disease association prediction, called MLCDA, which effectively fuses multiple sources of heterogeneous information including circRNA sequences and disease ontology. Comprehensive evaluation in the gold standard dataset showed that MLCDA can successfully capture the complex relationships between circRNAs and diseases and accurately predict their potential associations. In addition, the results of case studies on real data show that MLCDA significantly outperforms other existing methods. MLCDA can serve as a useful tool for circRNA-disease association prediction, providing mechanistic insights for disease research and thus facilitating the progress of disease treatment.

iGRLCDA: identifying circRNA-disease association based on graph representation learning.

While the technologies of ribonucleic acid-sequence (RNA-seq) and transcript assembly analysis have continued to improve, a novel topology of RNA transcript was uncovered in the last decade and is called circular RNA (circRNA). Recently, researchers have revealed that they compete with messenger RNA (mRNA) and long noncoding for combining with microRNA in gene regulation. Therefore, circRNA was assumed to be associated with complex disease and discovering the relationship between them would contribute to medical research. However, the work of identifying the association between circRNA and disease in vitro takes a long time and usually without direction. During these years, more and more associations were verified by experiments. Hence, we proposed a computational method named identifying circRNA-disease association based on graph representation learning (iGRLCDA) for the prediction of the potential association of circRNA and disease, which utilized a deep learning model of graph convolution network (GCN) and graph factorization (GF). In detail, iGRLCDA first derived the hidden feature of known associations between circRNA and disease using the Gaussian interaction profile (GIP) kernel combined with disease semantic information to form a numeric descriptor. After that, it further used the deep learning model of GCN and GF to extract hidden features from the descriptor. Finally, the random forest classifier is introduced to identify the potential circRNA-disease association. The five-fold cross-validation of iGRLCDA shows strong competitiveness in comparison with other excellent prediction models at the gold standard data and achieved an average area under the receiver operating characteristic curve of 0.9289 and an area under the precision-recall curve of 0.9377. On reviewing the prediction results from the relevant literature, 22 of the top 30 predicted circRNA-disease associations were noted in recent published papers. These exceptional results make us believe that iGRLCDA can provide reliable circRNA-disease associations for medical research and reduce the blindness of wet-lab experiments.

Adversarial dense graph convolutional networks for single-cell classification.

MOTIVATION: In single-cell transcriptomics applications, effective identification of cell types in multicellular organisms and in-depth study of the relationships between genes has become one of the main goals of bioinformatics research. However, data heterogeneity and random noise pose significant difficulties for scRNA-seq data analysis. RESULTS: We have proposed an adversarial dense graph convolutional network architecture for single-cell classification. Specifically, to enhance the representation of higher-order features and the organic combination between features, dense connectivity mechanism and attention-based feature aggregation are introduced for feature learning in convolutional neural networks. To preserve the features of the original data, we use a feature reconstruction module to assist the goal of single-cell classification. In addition, HNNVAT uses virtual adversarial training to improve the generalization and robustness. Experimental results show that our model outperforms the existing classical methods in terms of classification accuracy on benchmark datasets. AVAILABILITY AND IMPLEMENTATION: The source code of HNNVAT is available at https://github.com/DisscLab/HNNVAT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SiSGC: A Drug Repositioning Prediction Model Based on Heterogeneous Simplifying Graph Convolution.

Drug repositioning plays a key role in disease treatment. With the large-scale chemical data increasing, many computational methods are utilized for drug-disease association prediction. However, most of the existing models neglect the positive influence of non-Euclidean data and multisource information, and there is still a critical issue for graph neural networks regarding how to set the feature diffuse distance. To solve the problems, we proposed SiSGC, which makes full use of the biological knowledge information as initial features and learns the structure information from the constructed heterogeneous graph with the adaptive selection of the information diffuse distance. Then, the structural features are fused with the denoised similarity information and fed to the advanced classifier of CatBoost to make predictions. Three different data sets are used to confirm the robustness and generalization of SiSGC under two splitting strategies. Experiment results demonstrate that the proposed model achieves superior performance compared with the six leading methods and four variants. Our case study on breast neoplasms further indicates that SiSGC is trustworthy and robust yet simple. We also present four drugs for breast cancer treatment with high confidence and further give an explanation for demonstrating the rationality. There is no doubt that SiSGC can be used as a beneficial supplement for drug repositioning.

Bioaccumulation Characteristics of Typical Perfluoroalkyl Compounds in Alfalfa Under Salt Stress.

Medicago sativa, commonly known as alfalfa, is widely distributed worldwide, known for its strong stress resistance and well-developed root system, making it an important plant in ecological restoration research. To investigate the absorption and transport characteristics of alfalfa for typical perfluoroalkyl substances (PFAS) under salt stress, a 30-day indoor greenhouse experiment was conducted. The results showed that alfalfa exhibited varying degrees of absorption and transport for the selected PFAS. The highest BCF (Bioconcentration Factor) for shoot tissue reached 725.4 (for PFBA), and the highest TF (Translocation Factor) reached 53.8 (for PFPeA). Different PFAS compounds exhibited distinct bioaccumulation behaviors, with short-chain PFAS more readily entering the plant's root system and being transported upwards, while long-chain PFAS tended to adsorb to the surface of the root system. Furthermore, salt stress did not significantly affect the uptake of PFAS by alfalfa. This suggests that alfalfa is salt-tolerant and holds great potential for ecological restoration in short-chain PFAS-contaminated sites.

[Expression and significance of hypoxia-inducible factor 1α and Bcl-2/adenovirus E1B19kDa-interacting protein 3 in children with traumatic brain injury]. / ç¼ºæ°§è¯±å¯¼å› å­1α、Bcl-2/è ºç— æ¯’E1B19kDa相互作用蛋白3在儿童创伤性脑损伤中的表达及意义.

OBJECTIVES: To dynamically observe the changes in hypoxia-inducible factor 1α (HIF-1α) and Bcl-2/adenovirus E1B19kDa-interacting protein 3 (BNIP3) in children with traumatic brain injury (TBI) and evaluate their clinical value in predicting the severity and prognosis of pediatric TBI. METHODS: A prospective study included 47 children with moderate to severe TBI from January 2021 to July 2023, categorized into moderate (scores 9-12) and severe (scores 3-8) subgroups based on the Glasgow Coma Scale. A control group consisted of 30 children diagnosed and treated for inguinal hernia during the same period, with no underlying diseases. The levels of HIF-1α, BNIP3, autophagy-related protein Beclin-1, and S100B were compared among groups. The predictive value of HIF-1α, BNIP3, Beclin-1, and S100B for the severity and prognosis of TBI was assessed using receiver operating characteristic (ROC) curves. RESULTS: Serum levels of HIF-1α, BNIP3, Beclin-1, and S100B in the TBI group were higher than those in the control group (P<0.05). Among the TBI patients, the severe subgroup had higher levels of HIF-1α, BNIP3, Beclin-1, and S100B than the moderate subgroup (P<0.05). Correlation analysis showed that the serum levels of HIF-1α, BNIP3, Beclin-1, and S100B were negatively correlated with the Glasgow Coma Scale scores (P<0.05). After 7 days of treatment, serum levels of HIF-1α, BNIP3, Beclin-1, and S100B in both non-surgical and surgical TBI patients decreased compared to before treatment (P<0.05). ROC curve analysis indicated that the areas under the curve for predicting severe TBI based on serum levels of HIF-1α, BNIP3, Beclin-1, and S100B were 0.782, 0.835, 0.872, and 0.880, respectively (P<0.05), and for predicting poor prognosis of TBI were 0.749, 0.775, 0.814, and 0.751, respectively (P<0.05). CONCLUSIONS: Serum levels of HIF-1α, BNIP3, and Beclin-1 are significantly elevated in children with TBI, and their measurement can aid in the clinical assessment of the severity and prognosis of pediatric TBI.

A graph auto-encoder model for miRNA-disease associations prediction.

Emerging evidence indicates that the abnormal expression of miRNAs involves in the evolution and progression of various human complex diseases. Identifying disease-related miRNAs as new biomarkers can promote the development of disease pathology and clinical medicine. However, designing biological experiments to validate disease-related miRNAs is usually time-consuming and expensive. Therefore, it is urgent to design effective computational methods for predicting potential miRNA-disease associations. Inspired by the great progress of graph neural networks in link prediction, we propose a novel graph auto-encoder model, named GAEMDA, to identify the potential miRNA-disease associations in an end-to-end manner. More specifically, the GAEMDA model applies a graph neural networks-based encoder, which contains aggregator function and multi-layer perceptron for aggregating nodes' neighborhood information, to generate the low-dimensional embeddings of miRNA and disease nodes and realize the effective fusion of heterogeneous information. Then, the embeddings of miRNA and disease nodes are fed into a bilinear decoder to identify the potential links between miRNA and disease nodes. The experimental results indicate that GAEMDA achieves the average area under the curve of $93.56\pm 0.44\%$ under 5-fold cross-validation. Besides, we further carried out case studies on colon neoplasms, esophageal neoplasms and kidney neoplasms. As a result, 48 of the top 50 predicted miRNAs associated with these diseases are confirmed by the database of differentially expressed miRNAs in human cancers and microRNA deregulation in human disease database, respectively. The satisfactory prediction performance suggests that GAEMDA model could serve as a reliable tool to guide the following researches on the regulatory role of miRNAs. Besides, the source codes are available at https://github.com/chimianbuhetang/GAEMDA.

Bioaccumulation of Per- and Polyfluoroalkyl Substances (PFAS) in Ferns: Effect of PFAS Molecular Structure and Plant Root Characteristics.

The present study assessed the bioaccumulation potential of per- and polyfluoroalkyl substances (PFAS) in ferns and linked root uptake behaviors to root characteristics and PFAS molecular structure. Tissue and subcellular-level behavioral differences between alternative and legacy PFAS were compared via an electron probe microanalyzer with energy dispersive spectroscopy (EPMA-EDS) and differential centrifugation. Our results show that ferns can accumulate PFAS from water, immobilize them in roots, and store them in harvestable tissue. The PFAS loading in roots was dominated by PFOS; however, a substantial amount of associated PFOS could be rinsed off by methanol. Correlation analyses indicated that root length, surface and project area, surface area per unit length of the root system, and molecular size and hydrophobicity of PFAS were the most significant factors affecting the magnitude of root uptake and upward translocation. EPMA-EDS images together with exposure experiments suggested that long-chain hydrophobic compounds tend to be adsorbed and retained on the root epidermis, while short-chain compounds are absorbed and quickly translocated upward. Our findings demonstrated the feasibility of using ferns in phytostabilization and phytoextraction initiatives of PFAS in the future.

Hierarchical graph attention network for miRNA-disease association prediction.

Many biological studies show that the mutation and abnormal expression of microRNAs (miRNAs) could cause a variety of diseases. As an important biomarker for disease diagnosis, miRNA is helpful to understand pathogenesis, and could promote the identification, diagnosis and treatment of diseases. However, the pathogenic mechanism how miRNAs affect these diseases has not been fully understood. Therefore, predicting the potential miRNA-disease associations is of great importance for the development of clinical medicine and drug research. In this study, we proposed a novel deep learning model based on hierarchical graph attention network for predicting miRNA-disease associations (HGANMDA). Firstly, we constructed a miRNA-disease-lncRNA heterogeneous graph based on known miRNA-disease associations, miRNA-lncRNA associations and disease-lncRNA associations. Secondly, the node-layer attention was applied to learn the importance of neighbor nodes based on different meta-paths. Thirdly, the semantic-layer attention was applied to learn the importance of different meta-paths. Finally, a bilinear decoder was employed to reconstruct the connections between miRNAs and diseases. The extensive experimental results indicated that our model achieved good performance and satisfactory results in predicting miRNA-disease associations.

MKRN3-mediated ubiquitination of Poly(A)-binding proteins modulates the stability and translation of GNRH1 mRNA in mammalian puberty.

The family of Poly(A)-binding proteins (PABPs) regulates the stability and translation of messenger RNAs (mRNAs). Here we reported that the three members of PABPs, including PABPC1, PABPC3 and PABPC4, were identified as novel substrates for MKRN3, whose deletion or loss-of-function mutations were genetically associated with human central precocious puberty (CPP). MKRN3-mediated ubiquitination was found to attenuate the binding of PABPs to the poly(A) tails of mRNA, which led to shortened poly(A) tail-length of GNRH1 mRNA and compromised the formation of translation initiation complex (TIC). Recently, we have shown that MKRN3 epigenetically regulates the transcription of GNRH1 through conjugating poly-Ub chains onto methyl-DNA bind protein 3 (MBD3). Therefore, MKRN3-mediated ubiquitin signalling could control both transcriptional and post-transcriptional switches of mammalian puberty initiation. While identifying MKRN3 as a novel tissue-specific translational regulator, our work also provided new mechanistic insights into the etiology of MKRN3 dysfunction-associated human CPP.

ICGA combined with EP monitoring in microclipping of cerebral aneurysms.

Cerebral aneurysm is one of the common cerebrovascular diseases in neurosurgery, and rupture of cerebral aneurysm is the most important cause of spontaneous subarachnoid hemorrhage. How to precisely clip the aneurysm has been a topic worth discussing, so the authors explore the value of ICGA combined with electrophysiological monitoring in the microclipping of cerebral aneurysms. Using the method of retrospective analysis of cases, 661 patients with cerebral aneurysms admitted to the Department of Neurosurgery, Zhongnan Hospital of Wuhan University, from 2021.8 to 2022.10 were studied, 390 patients with aneurysm clipping were included, and patients with Hunt-Hess classification ≥ 4 were excluded, and whether to use ICGA combined with EP in microclipping of the ruptured and unruptured aneurysm in pterional approach was investigated at the time of discharge, respectively. The MRS and total hospital days were compared to investigate the value of ICGA combined with EP in the microclipping of cerebral aneurysms. All 390 patients enrolled in the group had successful aneurysm clipping, 178 patients were screened for ruptured aneurysm pterional approach and 120 patients for unruptured aneurysm pterional approach access; the MRS at discharge was significantly lower in the ICGA combined with EP group than in the no-EP group for ruptured aneurysm pterional approach microclipping (p < 0.001), and the mean number of days in hospital was significantly lower (p < 0.01). Patients in the ICGA combined with EP group in microclipping of unruptured aneurysms with pterional approach also had significantly lower MRS at discharge compared with patients in the ICGA alone group (p < 0.001), with no statistically significant difference in the mean number of days in hospital (p = 0.09). In open cerebral aneurysm microclipping, ICGA combined with EP monitoring for both ruptured and unruptured aneurysms can effectively reduce the false-negative rate of ICGA, significantly reduce the incidence of postoperative neurological deficits, and shorten the total hospital stay to some extent. ICGA combined with EP monitoring may be an effective means to reduce the rate of false clipping of the penetrating vessels and to avoid stenosis or occlusion of the aneurysm-carrying artery and is worth promoting in microclipping of cerebral aneurysms except for Hunt-Hess ≥ 4.

Comparison of reconstruction nails versus dual implants in the treatment of ipsilateral femoral neck and shaft fractures in adults: a meta-analysis and systematic review.

OBJECTIVE: There is no consensus on the optimal treatment for ipsilateral femoral neck and shaft fractures. This meta-analysis aims to assess the effectiveness of reconstruction nails and dual implants in treating ipsilateral femoral neck and shaft fractures to provide a basis for decision-making when selecting the optimal approach. METHODS: Relevant articles were retrieved from Pubmed, Embase, and Cochrane databases using the keywords "neck of femur", "shaft" and "fracture fixation" from inception until November 17, 2022. The screening process of the studies was conducted independently by two assessors, who assessed each study's eligibility and two assessors assessed the quality. Then compared differences in outcome measures using RevMan 5.3 software. RESULTS: A total of ten retrospective cohort studies were included. There were no significant differences in union time, union rate, union-related complications (malunion, nonunion, delayed union) of femoral neck and shaft fractures, osteonecrosis of the femoral head, and functional outcomes (Friedman-Wyman scoring system) (P > 0.05). CONCLUSION: Our pooled estimates indicated that reconstruction nails and dual implants for ipsilateral femoral neck and shaft fractures could yield satisfactory surgical results, and that there is no difference between the two treatment methods. TRIAL REGISTRATION: This meta-analysis was registered on the PROSPERO website (registration number: CRD42022379606).

Comparison of diagnostic accuracy of immediate angiography derived residual quantitative flow ratio after bioresorbable scaffold and drug eluting stent implantation.

BACKGROUND: Quantitative flow ratio (QFR) is a novel angiography derived fractional flow reserve (FFR) technique. However, its diagnostic accuracy has only be validated in native coronary lesions but not in vessels after bioresorbable scaffold (BRS) implantation. This study aims to evaluate the diagnostic accuracy of residual QFR in coronary vessels immediately post-BRS implantation. METHODS: This is a retrospective, two center, validation cohort study. 73 stable angina patients who received at least one de novo lesion of an everolimus eluting stent (EES)/BRS implantation with subsequent residual FFR assessment were screened. Patients with aorta-ostial stenoses, bridge vessels at the distal segment of targeted vessels, acute coronary syndrome, previous coronary artery bypass grafting, age <18 years, lack of ≥2 final angiographic projections were excluded. Contrast QFR assessment was performed blinded to FFR assessment. RESULTS: A good correlation (r = 0.680, p < 0.001) was found between residual QFR and FFR. In the EES implantation cohort, a good correlation (r = 0.769, p < 0.001) was found between residual QFR and FFR, and a moderate correlation (r = 0.446, p = 0.038) in the BRS cohort. The area under the Receiver operator characteristic (ROC) curve for detecting FFR ≤0.86 was 0.883 for all patients. CONCLUSION: Residual QFR assessment after BRS implantation is feasible, and has a moderate correlation and agreement with residual FFR. QFR may be a promising tool similar to FFR to evaluate post-BRS effect.

Experimental Realization of Weyl Exceptional Rings in a Synthetic Three-Dimensional Non-Hermitian Phononic Crystal.

Weyl points-topological monopoles of quantized Berry flux-are predicted to spread to Weyl exceptional rings in the presence of non-Hermiticity. Here, we use a one-dimensional Aubry-Andre-Harper model to construct a Weyl semimetal in a three-dimensional parameter space comprising one reciprocal dimension and two synthetic dimensions. The inclusion of non-Hermiticity in the form of gain and loss produces a synthetic Weyl exceptional ring (SWER). The topology of the SWER is characterized by both its topological charge and non-Hermitian winding numbers. We experimentally observe the SWER and synthetic Fermi arc in a one-dimensional phononic crystal with the non-Hermiticity introduced by active acoustic components. Our findings pave the way for studying the high-dimensional non-Hermitian topological physics in acoustics.

DF-MDA: An effective diffusion-based computational model for predicting miRNA-disease association.

It is reported that microRNAs (miRNAs) play an important role in various human diseases. However, the mechanisms of miRNA in these diseases have not been fully understood. Therefore, detecting potential miRNA-disease associations has far-reaching significance for pathological development and the diagnosis and treatment of complex diseases. In this study, we propose a novel diffusion-based computational method, DF-MDA, for predicting miRNA-disease association based on the assumption that molecules are related to each other in human physiological processes. Specifically, we first construct a heterogeneous network by integrating various known associations among miRNAs, diseases, proteins, long non-coding RNAs (lncRNAs), and drugs. Then, more representative features are extracted through a diffusion-based machine-learning method. Finally, the Random Forest classifier is adopted to classify miRNA-disease associations. In the 5-fold cross-validation experiment, the proposed model obtained the average area under the curve (AUC) of 0.9321 on the HMDD v3.0 dataset. To further verify the prediction performance of the proposed model, DF-MDA was applied in three significant human diseases, including lymphoma, lung neoplasms, and colon neoplasms. As a result, 47, 46, and 47 out of top 50 predictions were validated by independent databases. These experimental results demonstrated that DF-MDA is a reliable and efficient method for predicting potential miRNA-disease associations.