Enhancer-promoter interactions (EPIs) play an important role in transcriptional regulation. Recently, machine learning-based methods have been widely used in the genome-scale identification of EPIs due to their promising predictive performance. In this paper, we propose a novel method, termed EPI-DLMH, for predicting EPIs with the use of DNA sequences only. EPI-DLMH consists of three major steps. First, a two-layer convolutional neural network is used to learn local features, and an bidirectional gated recurrent unit network is used to capture long-range dependencies on the sequences of promoters and enhancers. Second, an attention mechanism is used for focusing on relatively important features. Finally, a matching heuristic mechanism is introduced for the exploration of the interaction between enhancers and promoters. We use benchmark datasets in evaluating and comparing the proposed method with existing methods. Comparative results show that our model is superior to currently existing models in multiple cell lines. Specifically, we found that the matching heuristic mechanism introduced into the proposed model mainly contributes to the improvement of performance in terms of overall accuracy. Additionally, compared with existing models, our model is more efficient with regard to computational speed.

Accurate prioritization of potential disease genes is a fundamental challenge in biomedical research. Various algorithms have been developed to solve such problems. Inductive Matrix Completion (IMC) is one of the most reliable models for its well established framework and its superior performance in predicting gene-disease associations. However, the IMC method does not hierarchically extract deep features, which might limit the quality of recovery. In this case, the architecture of deep learning, which obtains high-level representations and handles noises and outliers presented in large-scale biological datasets, is introduced into the side information of genes in our Deep Collaborative Filtering (DCF) model. Further, for lack of negative examples, we also exploit Positive-Unlabeled (PU) learning formulation to low-rank matrix completion.Our approach achieves substantially improved performance over other state-of-the-art methods on diseases from the Online Mendelian Inheritance in Man (OMIM) database. Our approach is 6% more efficient than standard IMC in detecting a true association, and significantly outperforms other alternatives in terms of the precision-recall metric at the top-k predictions. Moreover, we also validate the disease with no previously known gene associations and newly reported OMIM associations. The experimental results show that DCF is still satisfactory for ranking novel disease phenotypes as well as mining unexplored relationships. The source code and the data are available at https://github.com/xzenglab/Deep-Collaborative-Filtering.

Heterogeneous information networks (HINs) currently play an important role in daily life. HINs are applied in many fields, such as science research, e-commerce, recommendation systems, and bioinformatics. Particularly, HINs have been used in biomedical research. Algorithms have been proposed to calculate the correlations between drugs and targets and between diseases and genes. Recently, the interaction between drugs and human genes has become an important subject in the research on drug efficacy and human genomics. In previous studies, numerous prediction methods using machine learning and statistical prediction models were proposed to explore this interaction on the biological network. In the current work, we introduce a representation learning method into the biological heterogeneous network and use the representation learning models metapath2vec and metapath2vec++; on our dataset. We combine the adverse drug reaction (ADR) data in the drug–gene network with causal relationship between drugs and ADRs. This article first presents an analysis of the importance of predicting drug–gene relationships and discusses the existing prediction methods. Second, the skip-gram model commonly used in representation learning for natural language processing tasks is explained. Third, the metapath2vec and metapath2vec++; models for the example of drug–gene-ADR network are described. Next, the kernelized Bayesian matrix factorization algorithm is used to complete the prediction. Finally, the experimental results of both models are compared with Katz, CATAPULT, and matrix factorization, the prediction visualized using the receiver operating characteristic curves are presented, and the area under the receiver operating characteristic values for three varying algorithm parameters are calculated.

Artificial intelligence, such as deep generative methods, represents a promising solution to de novo design of molecules with the desired properties. However, generating new molecules with biological activities toward two specific targets remains an extremely difficult challenge. In this work, we conceive a novel computational framework, herein called dual-target ligand generative network (DLGN), for the de novo generation of bioactive molecules toward two given objectives. Via adversarial training and reinforcement learning, DLGN treats a sequence-based simplified molecular input line entry system (SMILES) generator as a stochastic policy for exploring chemical spaces. Two discriminators are then used to encourage the generation of molecules that belong to the intersection of two bioactive-compound distributions. In a case study, we employ our methods to design a library of dual-target ligands targeting dopamine receptor D2 and 5-hydroxytryptamine receptor 1A as new antipsychotics. Experimental results demonstrate that the proposed model can generate novel compounds with high similarity to both bioactive datasets in several structure-based metrics. Our model exhibits a performance comparable to that of various state-of-the-art multi-objective molecule generation models. We envision that this framework will become a generally applicable approach for designing dual-target drugs in silico.

Protein-protein interactions (PPIs) refer to the phenomenon of protein binding through various types of bonds to execute biological functions. These interactions are critical for understanding biological mechanisms and drug research. Among these, the protein binding interface is a critical region involved in protein-protein interactions, particularly the hotspot residues on it that play a key role in protein interactions. Current deep learning methods trained on large-scale data can characterize proteins to a certain extent, but they often struggle to adequately capture information about protein binding interfaces. To address this limitation, we propose the PPI-Graphomer module, which integrates pretrained features from large-scale language models and inverse folding models. This approach enhances the characterization of protein binding interfaces by defining edge relationships and interface masks on the basis of molecular interaction information. Our model outperforms existing methods across multiple benchmark datasets and demonstrates strong generalization capabilities.