Epigenetic regulation, mediated by dynamic modifications of DNA, histones, and non-coding RNAs, plays a pivotal role in diseases such as cancer, neurodegenerative disorders, and metabolic syndromes, making epigenetic regulators promising therapeutic targets. However, the development of effective epigenetic drugs remains challenging due to limited selectivity, complex cross-regulatory networks, and data scarcity. While computational approaches, particularly deep learning, have advanced inhibitor discovery, conventional single-task learning (STL) models struggle with data sparsity and fail to capture system-level regulatory effects. Multi-task learning (MTL) offers advantages by leveraging shared biological correlations among targets, improving generalization, and enhancing data efficiency. Despite these benefits, existing MTL methods lack reliable uncertainty quantification, risking false positives for novel molecules. To address these limitations, we introduce BMT-EpiPred, a Bayesian MTL framework that integrates a shared feature encoder with probabilistic prediction heads optimized via variational inference. Our model provides probabilistic activity predictions across 78 epigenetic targets while quantifying uncertainty to identify out-of-distribution (OOD) compounds. Comparative evaluations demonstrate that BMT-EpiPred achieves superior accuracy and provides the capabilities for multiple targets prediction of small-molecule epigenetic modulators, particularly in terms of uncertainty calibration and OOD detection.

MOTIVATION: Identifying Compound-Protein Interaction (CPI) plays an important role in the discovery and development of drugs. In contrast with traditional wet experiments which are time-consuming and expensive, computational approaches for CPI prediction are time-saving and cost-effective that are highly desired for us. However, the existing methods cannot provide confidence measure for prediction results which maybe risky for drug research and development. RESULTS: We present a novel data-driven end-to-end learning-based method for trustworthy predicting compound-protein interactions (named TrustworthyCPI). The TrustworthyCPI has two main components: 1) Convolutional encoder of sequence operates directly on compound SMILEs and protein amino acid sequences to learn compound and protein latent representations respectively. 2) Evidence classifier not only predicts the compound-protein interaction probability but also yields the confidence level of predicted results as well. The parameters of two components are simultaneously trained by backpropagation in an end-to-end learning manner. The experimental results show that TrustworthyCPI achieves the prediction performance compared with the state-of-the-art CPI prediction methods in terms of ACC, AUC, and AUPRC, and has a good performance in the reliability measurement of predicted output. Additionally, case studies are provided for predicting interactions between existing drugs and SARS-CoV2 3C-Like Protease ($\rm {3CL}^{Pro}$), which further validates the effectiveness and feasibility of the proposed method.

Finding target molecules with specific chemical properties plays a decisive role in drug development. We proposed GEOM-CVAE, a constrained variational autoencoder based on geometric representation for molecular generation with specific properties, which is protein-context-dependent. In terms of machine learning, it includes continuous feature embedding encoder and molecular generation decoder. Our key contribution is to propose an efficient geometric embedding method, including the spatial structure representations of drug molecule (converting the 3-D coordinates into image) and the geometric graph representations of protein target (modeling the protein surface as a mesh). The 3-D geometric information is vital to successful molecular generation, which is different from previous molecular generative methods based on 1-D or 2-D. Our model framework generates specific molecules in two phases, by first generating special image with molecular 3-D information to learn latent representations and generating molecules with constrained condition based on geometric graph convolution for specific protein and then inputting the generated structural molecules into a parser network for obtaining Simplified Molecular Input Line Entry System (SMILES) strings. Our model achieves competitive performance that implies its potential effectiveness to enable the exploration of the vast chemical space for drug discovery.

Identification of targets among known drugs plays an important role in drug repurposing and discovery. Computational approaches for prediction of drug-target interactions (DTIs)are highly desired in comparison to traditional biological experiments as its fast and low price. Moreover, recent advances of systems biology approaches have generated large-scale heterogeneous, biological information networks data, which offer opportunities for machine learning-based identification of DTIs. We present a novel Inductive Matrix Completion with Heterogeneous Graph Attention Network approach (IMCHGAN)for predicting DTIs. IMCHGAN first adopts a two-level neural attention mechanism approach to learn drug and target latent feature representations from the DTI heterogeneous network respectively. Then, the learned latent features are fed into the Inductive Matrix Completion (IMC)prediction score model which computes the best projection from drug space onto target space and output DTI score via the inner product of projected drug and target feature representations. IMCHGAN is an end-to-end neural network learning framework where the parameters of both the prediction score model and the feature representation learning model are simultaneously optimized via backpropagation under supervising of the observed known drug-target interactions data. We compare IMCHGAN with other state-of-the-art baselines on two real DTI experimental datasets. The results show that our method is superior to existing methods in term of AUC and AUPR. Moreover, IMCHGAN also shows it has strong predictive power for novel (unknown)DTIs. All datasets and code can be obtained from https://github.com/ljatynu/IMCHGAN/.

MiRNA-disease association prediction plays an important role in identifying human disease-related miRNAs. This approach is helpful not only to formulate individualized diagnosis schemes, but also to understand the pathogenesis of diseases. Many studies have focused on enhancing the prediction performance using explicit side information, such as miRNA functional similarity and disease semantic similarity. The existing approaches, however, often ignore the higher-order implicit proximity among miRNAs and diseases. To this end, in this paper, we first propose a novel approach HOP_MDA (Higher-Order Proximity based MiRNA and Disease Association Prediction) for predicting potential association between miRNA and disease. Both explicit interaction information and implicit higher-order proximity information between miRNA and disease are encoded with different order proximity matrices which are weightily combined into a parameterized prediction matrix. A supervised learning approach based on the known miRNAs-disease associations is proposed to determine the optimal weight parameters. The prediction matrix is then used to achieve effective prediction. Additionally, a higher-order proximity approximation technique (HOPA_MDA) is presented to make more efficient predictions. 5-fold cross validation is used to evaluate the performance of our proposed method. The average AUC values of HOPA_MDA for two real datasets are 0.921+/-0.002 and 0.944+/-0.0015, respectively. Our method can also predict potential miRNAs specific to new diseases with no known related miRNAs.

Studying the deep learning-based molecular representation has great significance on predicting molecular property, promoted the development of drug screening and new drug discovery, and improving human well-being for avoiding illnesses. It is essential to learn the characterization of drug for various downstream tasks, such as molecular property prediction. In particular, the 3D structure features of molecules play an important role in biochemical function and activity prediction. The 3D characteristics of molecules largely determine the properties of the drug and the binding characteristics of the target. However, most current methods merely rely on 1D or 2D properties while ignoring the 3D topological structure, thereby degrading the performance of molecular inferring. In this paper, we propose 3DMol-Net to enhance the molecular representation, considering both the topology and rotation invariance (RI) of the 3D molecular structure. Specifically, we construct a molecular graph with soft relations related to the spatial arrangement of the 3D coordinates to learn 3D topology of arbitrary graph structure and employ an adaptive graph convolutional network to predict molecular properties and biochemical activities. Comparing with current graph-based methods, 3DMol-Net demonstrates superior performance in terms of both regression and classification tasks. Further verification of RI and visualization also show better robustness and representation capacity of our model.

MOTIVATION: There is growing evidence showing that the dysregulations of miRNAs cause diseases through various kinds of the underlying mechanism. Thus, predicting the multiple-category associations between microRNAs (miRNAs) and diseases plays an important role in investigating the roles of miRNAs in diseases. Moreover, in contrast with traditional biological experiments which are time-consuming and expensive, computational approaches for the prediction of multicategory miRNA-disease associations are time-saving and cost-effective that are highly desired for us. RESULTS: We present a novel data-driven end-to-end learning-based method of neural multiple-category miRNA-disease association prediction (NMCMDA) for predicting multiple-category miRNA-disease associations. The NMCMDA has two main components: (i) encoder operates directly on the miRNA-disease heterogeneous network and leverages Graph Neural Network to learn miRNA and disease latent representations, respectively. (ii) Decoder yields miRNA-disease association scores with the learned latent representations as input. Various kinds of encoders and decoders are proposed for NMCMDA. Finally, the NMCMDA with the encoder of Relational Graph Convolutional Network and the neural multirelational decoder (NMR-RGCN) achieves the best prediction performance. We compared the NMCMDA with other baselines on three experimental datasets. The experimental results show that the NMR-RGCN is significantly superior to the state-of-the-art method TDRC in terms of Top-1 precision, Top-1 Recall, and Top-1 F1. Additionally, case studies are provided for two high-risk human diseases (namely, breast cancer and lung cancer) and we also provide the prediction and validation of top-10 miRNA-disease-category associations based on all known data of HMDD v3.2, which further validate the effectiveness and feasibility of the proposed method.

MOTIVATION: Predicting the association between microRNAs (miRNAs) and diseases plays an import role in identifying human disease-related miRNAs. As identification of miRNA-disease associations via biological experiments is time-consuming and expensive, computational methods are currently used as effective complements to determine the potential associations between disease and miRNA. RESULTS: We present a novel method of neural inductive matrix completion with graph convolutional network (NIMCGCN) for predicting miRNA-disease association. NIMCGCN first uses graph convolutional networks to learn miRNA and disease latent feature representations from the miRNA and disease similarity networks. Then, learned features were input into a novel neural inductive matrix completion (NIMC) model to generate an association matrix completion. The parameters of NIMCGCN were learned based on the known miRNA-disease association data in a supervised end-to-end way. We compared the proposed method with other state-of-the-art methods. The area under the receiver operating characteristic curve results showed that our method is significantly superior to existing methods. Furthermore, 50, 47 and 48 of the top 50 predicted miRNAs for three high-risk human diseases, namely, colon cancer, lymphoma and kidney cancer, were verified using experimental literature. Finally, 100% prediction accuracy was achieved when breast cancer was used as a case study to evaluate the ability of NIMCGCN for predicting a new disease without any known related miRNAs. AVAILABILITY AND IMPLEMENTATION: https://github.com/ljatynu/NIMCGCN/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Bayesian network (BN) has been adopted as the underlying model for representing and inferring uncertain knowledge. As the basis of realistic applications centered on probabilistic inferences, learning a BN from data is a critical subject of machine learning, artificial intelligence, and big data paradigms. Currently, it is necessary to extend the classical methods for learning BNs with respect to data-intensive computing or in cloud environments. In this paper, we propose a parallel and incremental approach for data-intensive learning of BNs from massive, distributed, and dynamically changing data by extending the classical scoring and search algorithm and using MapReduce. First, we adopt the minimum description length as the scoring metric and give the two-pass MapReduce-based algorithms for computing the required marginal probabilities and scoring the candidate graphical model from sample data. Then, we give the corresponding strategy for extending the classical hill-climbing algorithm to obtain the optimal structure, as well as that for storing a BN by pairs. Further, in view of the dynamic characteristics of the changing data, we give the concept of influence degree to measure the coincidence of the current BN with new data, and then propose the corresponding two-pass MapReduce-based algorithms for BNs incremental learning. Experimental results show the efficiency, scalability, and effectiveness of our methods.

This paper is to compute a Nash equilibrium in a fuzzy environment, which is represented by a fuzzy approximate Nash equilibrium in a space of discrete mixed strategies. For discrete mixed strategies, the relationship between the discrete degree and the approximate degree is discussed. Based on the fuzzy regret degree, a genetic algorithm for computing a fuzzy Nash equilibrium is given.