Deep Augmented Metric Learning Network for Prostate Cancer Classification in Ultrasound Images.

Prostate cancer screening often relies on cost-intensive MRIs and invasive needle biopsies. Transrectal ultrasound imaging, as a more affordable and non-invasive alternative, faces the challenge of high inter-class similarity and intra-class variability between benign and malignant prostate cancers. This complexity requires more stringent differentiation of subtle features for accurate auxiliary diagnosis. In response, we introduce the novel Deep Augmented Metric Learning (DAML) network, specifically tailored for ultrasound-based prostate cancer classification. The DAML network represents a significant innovation in the metric learning space, introducing the Semantic Differences Mining Strategy (SDMS) to effectively discern and represent subtle differences in prostate ultrasound images, thereby enhancing tumor classification accuracy. Additionally, the DAML network strategically addresses class variability and limited sample sizes by combining the Linear Interpolation Augmentation Strategy (LIAS) and Permutation-Aided Reconstruction Loss (PARL). This approach enriches feature representation and introduces variability with straightforward structures, mirroring the efficacy of advanced sample generation techniques. We carried out comprehensive empirical assessments of the DAML model by testing its key components against a range of models, ensuring its effectiveness. Our results demonstrate the enhanced performance of the DAML model, achieving classification accuracies of 0.857 and 0.888 for benign and malignant cancers, respectively, underscoring its effectiveness in prostate cancer classification via medical imaging.

RFEM: A framework for essential microRNA identification in mice based on rotation forest and multiple feature fusion.

With the increasing number of microRNAs (miRNAs), identifying essential miRNAs has become an important task that needs to be solved urgently. However, there are few computational methods for essential miRNA identification. Here, we proposed a novel framework called Rotation Forest for Essential MicroRNA identification (RFEM) to predict the essentiality of miRNAs in mice. We first constructed 1,264 miRNA features of all miRNA samples by fusing 38 miRNA features obtained from the PESM paper and 1,226 miRNA functional features calculated based on miRNA-target gene interactions. Then, we employed 182 training samples with 1,264 features to train the rotation forest model, which was applied to compute the essentiality scores of the candidate samples. The main innovations of RFEM were as follows: 1) miRNA functional features were introduced to enrich the diversity of miRNA features; 2) the rotation forest model used decision tree as the base classifier and could increase the difference among base classifiers through feature transformation to achieve better ensemble results. Experimental results show that RFEM significantly outperformed two previous models with the AUC (AUPR) of 0.942 (0.944) in three comparison experiments under 5-fold cross validation, which proved the model's reliable performance. Moreover, ablation study was further conducted to demonstrate the effectiveness of the novel miRNA functional features. Additionally, in the case studies of assessing the essentiality of unlabeled miRNAs, experimental literature confirmed that 7 of the top 10 predicted miRNAs have crucial biological functions in mice. Therefore, RFEM would be a reliable tool for identifying essential miRNAs.

GPCNDTA: Prediction of drug-target binding affinity through cross-attention networks augmented with graph features and pharmacophores.

Drug-target affinity prediction is a challenging task in drug discovery. The latest computational models have limitations in mining edge information in molecule graphs, accessing to knowledge in pharmacophores, integrating multimodal data of the same biomolecule and realizing effective interactions between two different biomolecules. To solve these problems, we proposed a method called Graph features and Pharmacophores augmented Cross-attention Networks based Drug-Target binding Affinity prediction (GPCNDTA). First, we utilized the GNN module, the linear projection unit and self-attention layer to correspondingly extract features of drugs and proteins. Second, we devised intramolecular and intermolecular cross-attention to respectively fuse and interact features of drugs and proteins. Finally, the linear projection unit was applied to gain final features of drugs and proteins, and the Multi-Layer Perceptron was employed to predict drug-target binding affinity. Three major innovations of GPCNDTA are as follows: (i) developing the residual CensNet and the residual EW-GCN to correspondingly extract features of drug and protein graphs, (ii) regarding pharmacophores as a new type of priors to heighten drug-target affinity prediction performance, and (iii) devising intramolecular and intermolecular cross-attention, in which the intramolecular cross-attention realizes the effective fusion of different modal data related to the same biomolecule, and the intermolecular cross-attention fulfills the information interaction between two different biomolecules in attention space. The test results on five benchmark datasets imply that GPCNDTA achieves the best performance compared with state-of-the-art computational models. Besides, relying on ablation experiments, we proved effectiveness of GNN modules, pharmacophores and two cross-attention strategies in improving the prediction accuracy, stability and reliability of GPCNDA. In case studies, we applied GPCNDTA to predict binding affinities between 3C-like proteinase and 185 drugs, and observed that most binding affinities predicted by GPCNDTA are close to corresponding experimental measurements.

MCFF-MTDDI: multi-channel feature fusion for multi-typed drug-drug interaction prediction.

Adverse drug-drug interactions (DDIs) have become an increasingly serious problem in the medical and health system. Recently, the effective application of deep learning and biomedical knowledge graphs (KGs) have improved the DDI prediction performance of computational models. However, the problems of feature redundancy and KG noise also arise, bringing new challenges for researchers. To overcome these challenges, we proposed a Multi-Channel Feature Fusion model for multi-typed DDI prediction (MCFF-MTDDI). Specifically, we first extracted drug chemical structure features, drug pairs' extra label features, and KG features of drugs. Then, these different features were effectively fused by a multi-channel feature fusion module. Finally, multi-typed DDIs were predicted through the fully connected neural network. To our knowledge, we are the first to integrate the extra label information into KG-based multi-typed DDI prediction; besides, we innovatively proposed a novel KG feature learning method and a State Encoder to obtain target drug pairs' KG-based features which contained more abundant and more key drug-related KG information with less noise; furthermore, a Gated Recurrent Unit-based multi-channel feature fusion module was proposed in an innovative way to yield more comprehensive feature information about drug pairs, effectively alleviating the problem of feature redundancy. We experimented with four datasets in the multi-class and the multi-label prediction tasks to comprehensively evaluate the performance of MCFF-MTDDI for predicting interactions of known-known drugs, known-new drugs and new-new drugs. In addition, we further conducted ablation studies and case studies. All the results fully demonstrated the effectiveness of MCFF-MTDDI.

SNRMPACDC: computational model focused on Siamese network and random matrix projection for anticancer synergistic drug combination prediction.

Synergistic drug combinations can improve the therapeutic effect and reduce the drug dosage to avoid toxicity. In previous years, an in vitro approach was utilized to screen synergistic drug combinations. However, the in vitro method is time-consuming and expensive. With the rapid growth of high-throughput data, computational methods are becoming efficient tools to predict potential synergistic drug combinations. Considering the limitations of the previous computational methods, we developed a new model named Siamese Network and Random Matrix Projection for AntiCancer Drug Combination prediction (SNRMPACDC). Firstly, the Siamese convolutional network and random matrix projection were used to process the features of the two drugs into drug combination features. Then, the features of the cancer cell line were processed through the convolutional network. Finally, the processed features were integrated and input into the multi-layer perceptron network to get the predicted score. Compared with the traditional method of splicing drug features into drug combination features, SNRMPACDC improved the interpretability of drug combination features to a certain extent. In addition, the introduction of convolutional networks can better extract the potential information in the features. SNRMPACDC achieved the root mean-squared error of 15.01 and the Pearson correlation coefficient of 0.75 in 5-fold cross-validation of regression prediction for response data. In addition, SNRMPACDC achieved the AUC of 0.91 ± 0.03 and the AUPR of 0.62 ± 0.05 in 5-fold cross-validation of classification prediction of synergistic or not. These results are almost better than all the previous models. SNRMPACDC would be an effective approach to infer potential anticancer synergistic drug combinations.

Predicting drug-target binding affinity through molecule representation block based on multi-head attention and skip connection.

Exiting computational models for drug-target binding affinity prediction have much room for improvement in prediction accuracy, robustness and generalization ability. Most deep learning models lack interpretability analysis and few studies provide application examples. Based on these observations, we presented a novel model named Molecule Representation Block-based Drug-Target binding Affinity prediction (MRBDTA). MRBDTA is composed of embedding and positional encoding, molecule representation block and interaction learning module. The advantages of MRBDTA are reflected in three aspects: (i) developing Trans block to extract molecule features through improving the encoder of transformer, (ii) introducing skip connection at encoder level in Trans block and (iii) enhancing the ability to capture interaction sites between proteins and drugs. The test results on two benchmark datasets manifest that MRBDTA achieves the best performance compared with 11 state-of-the-art models. Besides, through replacing Trans block with single Trans encoder and removing skip connection in Trans block, we verified that Trans block and skip connection could effectively improve the prediction accuracy and reliability of MRBDTA. Then, relying on multi-head attention mechanism, we performed interpretability analysis to illustrate that MRBDTA can correctly capture part of interaction sites between proteins and drugs. In case studies, we firstly employed MRBDTA to predict binding affinities between Food and Drug Administration-approved drugs and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) replication-related proteins. Secondly, we compared true binding affinities between 3C-like proteinase and 185 drugs with those predicted by MRBDTA. The final results of case studies reveal reliable performance of MRBDTA in drug design for SARS-CoV-2.

Prediction of potential miRNA-disease associations based on stacked autoencoder.

In recent years, increasing biological experiments and scientific studies have demonstrated that microRNA (miRNA) plays an important role in the development of human complex diseases. Therefore, discovering miRNA-disease associations can contribute to accurate diagnosis and effective treatment of diseases. Identifying miRNA-disease associations through computational methods based on biological data has been proven to be low-cost and high-efficiency. In this study, we proposed a computational model named Stacked Autoencoder for potential MiRNA-Disease Association prediction (SAEMDA). In SAEMDA, all the miRNA-disease samples were used to pretrain a Stacked Autoencoder (SAE) in an unsupervised manner. Then, the positive samples and the same number of selected negative samples were utilized to fine-tune SAE in a supervised manner after adding an output layer with softmax classifier to the SAE. SAEMDA can make full use of the feature information of all unlabeled miRNA-disease pairs. Therefore, SAEMDA is suitable for our dataset containing small labeled samples and large unlabeled samples. As a result, SAEMDA achieved AUCs of 0.9210 and 0.8343 in global and local leave-one-out cross validation. Besides, SAEMDA obtained an average AUC and standard deviation of 0.9102 ± /-0.0029 in 100 times of 5-fold cross validation. These results were better than those of previous models. Moreover, we carried out three case studies to further demonstrate the predictive accuracy of SAEMDA. As a result, 82% (breast neoplasms), 100% (lung neoplasms) and 90% (esophageal neoplasms) of the top 50 predicted miRNAs were verified by databases. Thus, SAEMDA could be a useful and reliable model to predict potential miRNA-disease associations.

Ensemble of kernel ridge regression-based small molecule-miRNA association prediction in human disease.

MicroRNAs (miRNAs) play crucial roles in human disease and can be targeted by small molecule (SM) drugs according to numerous studies, which shows that identifying SM-miRNA associations in human disease is important for drug development and disease treatment. We proposed the method of Ensemble of Kernel Ridge Regression-based Small Molecule-MiRNA Association prediction (EKRRSMMA) to uncover potential SM-miRNA associations by combing feature dimensionality reduction and ensemble learning. First, we constructed different feature subsets for both SMs and miRNAs. Then, we trained homogeneous base learners based on distinct feature subsets and took the average of scores obtained from these base learners as SM-miRNA association score. In EKRRSMMA, feature dimensionality reduction technology was employed in the process of construction of feature subsets to reduce the influence of noisy data. Besides, the base learner, namely KRR_avg, was the combination of two classifiers constructed under SM space and miRNA space, which could make full use of the information of SM and miRNA. To assess the prediction performance of EKRRSMMA, we conducted Leave-One-Out Cross-Validation (LOOCV), SM-fixed local LOOCV, miRNA-fixed local LOOCV and 5-fold CV based on two datasets. For Dataset 1 (Dataset 2), EKRRSMMA got the Area Under receiver operating characteristic Curves (AUCs) of 0.9793 (0.8871), 0.8071 (0.7705), 0.9732 (0.8586) and 0.9767 ± 0.0014 (0.8560 ± 0.0027). Besides, we conducted four case studies. As a result, 32 (5-Fluorouracil), 19 (17ß-Estradiol), 26 (5-Aza-2'-deoxycytidine) and 11 (cyclophosphamide) out of top 50 predicted potentially associated miRNAs were confirmed by database or experimental literature. Above evaluation results demonstrated that EKRRSMMA is reliable for predicting SM-miRNA associations.

Real-world effectiveness and safety of golimumab in rheumatoid arthritis treatment: A two-center study in Taiwan.

BACKGROUND: The real-world outcomes of golimumab (GLM) use have been rarely studied in Asian patients with rheumatoid arthritis (RA). This study assessed the real-world effectiveness and safety of GLM in a Taiwanese cohort. METHODS: One hundred and eight GLM-treated RA patients were enrolled. Predictors of a good European League Against Rheumatism (EULAR) response at 24 months and drug retention were identified through multivariate analyses. RESULTS: After 24 months of GLM treatment, the mean Disease Activity Score using 28 joint counts with the erythrocyte sedimentation rate (DAS28-ESR) decreased from 6.7 to 3.1 (p < 0.001). Up to 58.9% of patients achieved a good EULAR response at 24 months. Multivariate logistic regression analysis revealed that after adjustment for other variables, a higher baseline C-reactive protein was an independent negative predictor of good EULAR responses (odds ratio, 0.82; 95% confidence interval [CI], 0.67-0.99; p = 0.043). During the mean follow-up period of 38.3 months, 15 (13.9%) patients discontinued GLM due to treatment failure. In multivariate analysis, high baseline ESR level, high DAS28-ESR, and the experience of biologic therapy were independent risk factors for GLM discontinuation (adjusted hazard ratio [HR], 1.03; 95% CI, 1.01-1.05; p = 0.003; adjusted HR, 2.93; 95% CI, 1.42-6.08; p = 0.004; and adjusted HR, 5.00; 95% CI, 1.75-14.26; p = 0.003, respectively). In receiver operator characteristic curve analysis, the optimal cutoff values of baseline ESR and DAS28-ESR for predicting drug survival were 52 mm/h (sensitivity: 60.0% and specificity: 77.4%) and 7.7 (sensitivity: 46.7% and specificity: 94.3%), respectively. During the follow-up period, 22 patients (20.4%) developed adverse events. The safety profile of GLM in this study was comparable with that in previous clinical trials. CONCLUSION: GLM was effective and safe for the real-life management of Taiwanese RA patients and showed a high retention rate in biologic-naive patients compared with biologic-experienced patients.

Dual-Network Collaborative Matrix Factorization for predicting small molecule-miRNA associations.

MicroRNAs (miRNAs) play crucial roles in multiple biological processes and human diseases and can be considered as therapeutic targets of small molecules (SMs). Because biological experiments used to verify SM-miRNA associations are time-consuming and expensive, it is urgent to propose new computational models to predict new SM-miRNA associations. Here, we proposed a novel method called Dual-network Collaborative Matrix Factorization (DCMF) for predicting the potential SM-miRNA associations. Firstly, we utilized the Weighted K Nearest Known Neighbors (WKNKN) method to preprocess SM-miRNA association matrix. Then, we constructed matrix factorization model to obtain two feature matrices containing latent features of SM and miRNA, respectively. Finally, the predicted SM-miRNA association score matrix was obtained by calculating the inner product of two feature matrices. The main innovations of this method were that the use of WKNKN method can preprocess the missing values of association matrix and the introduction of dual network can integrate more diverse similarity information into DCMF. For evaluating the validity of DCMF, we implemented four different cross validations (CVs) based on two distinct datasets and two different case studies. Finally, based on dataset 1 (dataset 2), DCMF achieved Area Under receiver operating characteristic Curves (AUC) of 0.9868 (0.8770), 0.9833 (0.8836), 0.8377 (0.7591) and 0.9836 ± 0.0030 (0.8632 ± 0.0042) in global Leave-One-Out Cross Validation (LOOCV), miRNA-fixed local LOOCV, SM-fixed local LOOCV and 5-fold CV, respectively. For case studies, plenty of predicted associations have been confirmed by published experimental literature. Therefore, DCMF is an effective tool to predict potential SM-miRNA associations.

Biased Random Walk With Restart on Multilayer Heterogeneous Networks for MiRNA-Disease Association Prediction.

Numerous experiments have proved that microRNAs (miRNAs) could be used as diagnostic biomarkers for many complex diseases. Thus, it is conceivable that predicting the unobserved associations between miRNAs and diseases is extremely significant for the medical field. Here, based on heterogeneous networks built on the information of known miRNA-disease associations, miRNA function similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity for miRNAs and diseases, we developed a computing model of biased random walk with restart on multilayer heterogeneous networks for miRNA-disease association prediction (BRWRMHMDA) through enforcing degree-based biased random walk with restart (BRWR). Assessment results reflected that an AUC of 0.8310 was gained in local leave-one-out cross-validation (LOOCV), which proved the calculation algorithm's good performance. Besides, we carried out BRWRMHMDA to prioritize candidate miRNAs for esophageal neoplasms based on HMDD v2.0. We further prioritize candidate miRNAs for breast neoplasms based on HMDD v1.0. The local LOOCV results and performance analysis of the case study all showed that the proposed model has good and stable performance.

Identification of miRNA-disease associations via multiple information integration with Bayesian ranking.

In recent years, increasing microRNA (miRNA)-disease associations were identified through traditionally biological experiments. These associations contribute to revealing molecular mechanism of diseases and preventing and curing diseases. To improve the efficiency of miRNA-disease association discovery, some calculation methods were developed as auxiliary tools for researchers. In the current study, we raised a novel model named Bayesian Ranking for MiRNA-Disease Association prediction (BRMDA) by improving Bayesian Personalized Ranking from three aspects: (i) taking advantage of similarity of diseases and miRNAs; (ii) incorporating miRNA bias for miRNAs associated with different number of diseases; and (iii) implementing neighborhood-based approach for new miRNAs and diseases. For each investigated disease, BRMDA used the set of triples (i.e. disease, labeled miRNA, unlabeled miRNA) that reflected association preference of the disease to miRNAs as training set, which made full use of unknown samples rather than simply considering them as negative samples. To investigate the predictive performance of BRMDA, we employed leave-one-out cross-validation and obtained Area Under the Curve of 0.8697, which outperformed many classical methods. Besides, we further implemented three distinct classes of case studies for three common Neoplasms. As a result, there are 44 (Colon Neoplasms), 49 (Esophageal Neoplasms) and 49 (Lung Neoplasms) among the top 50 predicted miRNAs validated through experiments. In short, BRMDA would be a trustable tool for inferring valuable associations.

Predicting potential small molecule-miRNA associations based on bounded nuclear norm regularization.

Mounting evidence has demonstrated the significance of taking microRNAs (miRNAs) as the target of small molecule (SM) drugs for disease treatment. Given the fact that exploring new SM-miRNA associations through biological experiments is extremely expensive, several computing models have been constructed to reveal the possible SM-miRNA associations. Here, we built a computing model of Bounded Nuclear Norm Regularization for SM-miRNA Associations prediction (BNNRSMMA). Specifically, we first constructed a heterogeneous SM-miRNA network utilizing miRNA similarity, SM similarity, confirmed SM-miRNA associations and defined a matrix to represent the heterogeneous network. Then, we constructed a model to complete this matrix by minimizing its nuclear norm. The Alternating Direction Method of Multipliers was adopted to minimize the nuclear norm and obtain predicted scores. The main innovation lies in two aspects. During completion, we limited all elements of the matrix within the interval of (0,1) to make sure they have practical significance. Besides, instead of strictly fitting all known elements, a regularization term was incorporated to tolerate the noise in integrated similarities. Furthermore, four kinds of cross-validations on two datasets and two types of case studies were performed to evaluate the predictive performance of BNNRSMMA. Finally, BNNRSMMA attained areas under the curve of 0.9822 (0.8433), 0.9793 (0.8852), 0.8253 (0.7350) and 0.9758 ± 0.0029 (0.8759 ± 0.0041) under global leave-one-out cross-validation (LOOCV), miRNA-fixed LOOCV, SM-fixed LOOCV and 5-fold cross-validation based on Dataset 1(Dataset 2), respectively. With regard to case studies, plenty of predicted associations have been verified by experimental literatures. All these results confirmed that BNNRSMMA is a reliable tool for inferring associations.

Circular RNAs and complex diseases: from experimental results to computational models.

Circular RNAs (circRNAs) are a class of single-stranded, covalently closed RNA molecules with a variety of biological functions. Studies have shown that circRNAs are involved in a variety of biological processes and play an important role in the development of various complex diseases, so the identification of circRNA-disease associations would contribute to the diagnosis and treatment of diseases. In this review, we summarize the discovery, classifications and functions of circRNAs and introduce four important diseases associated with circRNAs. Then, we list some significant and publicly accessible databases containing comprehensive annotation resources of circRNAs and experimentally validated circRNA-disease associations. Next, we introduce some state-of-the-art computational models for predicting novel circRNA-disease associations and divide them into two categories, namely network algorithm-based and machine learning-based models. Subsequently, several evaluation methods of prediction performance of these computational models are summarized. Finally, we analyze the advantages and disadvantages of different types of computational models and provide some suggestions to promote the development of circRNA-disease association identification from the perspective of the construction of new computational models and the accumulation of circRNA-related data.

Deep-belief network for predicting potential miRNA-disease associations.

MicroRNA (miRNA) plays an important role in the occurrence, development, diagnosis and treatment of diseases. More and more researchers begin to pay attention to the relationship between miRNA and disease. Compared with traditional biological experiments, computational method of integrating heterogeneous biological data to predict potential associations can effectively save time and cost. Considering the limitations of the previous computational models, we developed the model of deep-belief network for miRNA-disease association prediction (DBNMDA). We constructed feature vectors to pre-train restricted Boltzmann machines for all miRNA-disease pairs and applied positive samples and the same number of selected negative samples to fine-tune DBN to obtain the final predicted scores. Compared with the previous supervised models that only use pairs with known label for training, DBNMDA innovatively utilizes the information of all miRNA-disease pairs during the pre-training process. This step could reduce the impact of too few known associations on prediction accuracy to some extent. DBNMDA achieves the AUC of 0.9104 based on global leave-one-out cross validation (LOOCV), the AUC of 0.8232 based on local LOOCV and the average AUC of 0.9048 ± 0.0026 based on 5-fold cross validation. These AUCs are better than other previous models. In addition, three different types of case studies for three diseases were implemented to demonstrate the accuracy of DBNMDA. As a result, 84% (breast neoplasms), 100% (lung neoplasms) and 88% (esophageal neoplasms) of the top 50 predicted miRNAs were verified by recent literature. Therefore, we could conclude that DBNMDA is an effective method to predict potential miRNA-disease associations.

Microbes and complex diseases: from experimental results to computational models.

Studies have shown that the number of microbes in humans is almost 10 times that of cells. These microbes have been proven to play an important role in a variety of physiological processes, such as enhancing immunity, improving the digestion of gastrointestinal tract and strengthening metabolic function. In addition, in recent years, more and more research results have indicated that there are close relationships between the emergence of the human noncommunicable diseases and microbes, which provides a novel insight for us to further understand the pathogenesis of the diseases. An in-depth study about the relationships between diseases and microbes will not only contribute to exploring new strategies for the diagnosis and treatment of diseases but also significantly heighten the efficiency of new drugs development. However, applying the methods of biological experimentation to reveal the microbe-disease associations is costly and inefficient. In recent years, more and more researchers have constructed multiple computational models to predict microbes that are potentially associated with diseases. Here, we start with a brief introduction of microbes and databases as well as web servers related to them. Then, we mainly introduce four kinds of computational models, including score function-based models, network algorithm-based models, machine learning-based models and experimental analysis-based models. Finally, we summarize the advantages as well as disadvantages of them and set the direction for the future work of revealing microbe-disease associations based on computational models. We firmly believe that computational models are expected to be important tools in large-scale predictions of disease-related microbes.

Drug-pathway association prediction: from experimental results to computational models.

Effective drugs are urgently needed to overcome human complex diseases. However, the research and development of novel drug would take long time and cost much money. Traditional drug discovery follows the rule of one drug-one target, while some studies have demonstrated that drugs generally perform their task by affecting related pathway rather than targeting single target. Thus, the new strategy of drug discovery, namely pathway-based drug discovery, have been proposed. Obviously, identifying associations between drugs and pathways plays a key role in the development of pathway-based drug discovery. Revealing the drug-pathway associations by experiment methods would take much time and cost. Therefore, some computational models were established to predict potential drug-pathway associations. In this review, we first introduced the background of drug and the concept of drug-pathway associations. Then, some publicly accessible databases and web servers about drug-pathway associations were listed. Next, we summarized some state-of-the-art computational methods in the past years for inferring drug-pathway associations and divided these methods into three classes, namely Bayesian spare factor-based, matrix decomposition-based and other machine learning methods. In addition, we introduced several evaluation strategies to estimate the predictive performance of various computational models. In the end, we discussed the advantages and limitations of existing computational methods and provided some suggestions about the future directions of the data collection and the calculation models development.

Computational Models in Non-Coding RNA and Human Disease.

The central dogma of molecular biology has told that DNA sequences encode proteins through RNAs, which function as an information intermediary [...].

Potential miRNA-disease association prediction based on kernelized Bayesian matrix factorization.

Many biological experimental studies have confirmed that microRNAs (miRNAs) play a significant role in human complex diseases. Exploring miRNA-disease associations could be conducive to understanding disease pathogenesis at the molecular level and developing disease diagnostic biomarkers. However, since conducting traditional experiments is a costly and time-consuming way, plenty of computational models have been proposed to predict miRNA-disease associations. In this study, we presented a neoteric Bayesian model (KBMFMDA) that combines kernel-based nonlinear dimensionality reduction, matrix factorization and binary classification. The main idea of KBMFMDA is to project miRNAs and diseases into a unified subspace and estimate the association network in that subspace. KBMFMDA obtained the AUCs of 0.9132, 0.8708, 0.9008±0.0044 in global and local leave-one-out and five-fold cross validation. Moreover, KBMFMDA was applied to three important human cancers in three different kinds of case studies and most of the top 50 potential disease-related miRNAs were confirmed by many experimental reports.

In silico prediction of potential miRNA-disease association using an integrative bioinformatics approach based on kernel fusion.

Accumulating experimental evidence has demonstrated that microRNAs (miRNAs) have a huge impact on numerous critical biological processes and they are associated with different complex human diseases. Nevertheless, the task to predict potential miRNAs related to diseases remains difficult. In this paper, we developed a Kernel Fusion-based Regularized Least Squares for MiRNA-Disease Association prediction model (KFRLSMDA), which applied kernel fusion technique to fuse similarity matrices and then utilized regularized least squares to predict potential miRNA-disease associations. To prove the effectiveness of KFRLSMDA, we adopted leave-one-out cross-validation (LOOCV) and 5-fold cross-validation and then compared KFRLSMDA with 10 previous computational models (MaxFlow, MiRAI, MIDP, RKNNMDA, MCMDA, HGIMDA, RLSMDA, HDMP, WBSMDA and RWRMDA). Outperforming other models, KFRLSMDA achieved AUCs of 0.9246 in global LOOCV, 0.8243 in local LOOCV and average AUC of 0.9175 ± 0.0008 in 5-fold cross-validation. In addition, respectively, 96%, 100% and 90% of the top 50 potential miRNAs for breast neoplasms, colon neoplasms and oesophageal neoplasms were confirmed by experimental discoveries. We also predicted potential miRNAs related to hepatocellular cancer by removing all known related miRNAs of this cancer and 98% of the top 50 potential miRNAs were verified. Furthermore, we predicted potential miRNAs related to lymphoma using the data set in the old version of the HMDD database and 80% of the top 50 potential miRNAs were confirmed. Therefore, it can be concluded that KFRLSMDA has reliable prediction performance.