DDAffinity: predicting the changes in binding affinity of multiple point mutations using protein 3D structure.

MOTIVATION: Mutations are the crucial driving force for biological evolution as they can disrupt protein stability and protein-protein interactions which have notable impacts on protein structure, function, and expression. However, existing computational methods for protein mutation effects prediction are generally limited to single point mutations with global dependencies, and do not systematically take into account the local and global synergistic epistasis inherent in multiple point mutations. RESULTS: To this end, we propose a novel spatial and sequential message passing neural network, named DDAffinity, to predict the changes in binding affinity caused by multiple point mutations based on protein 3D structures. Specifically, instead of being on the whole protein, we perform message passing on the k-nearest neighbor residue graphs to extract pocket features of the protein 3D structures. Furthermore, to learn global topological features, a two-step additive Gaussian noising strategy during training is applied to blur out local details of protein geometry. We evaluate DDAffinity on benchmark datasets and external validation datasets. Overall, the predictive performance of DDAffinity is significantly improved compared with state-of-the-art baselines on multiple point mutations, including end-to-end and pre-training based methods. The ablation studies indicate the reasonable design of all components of DDAffinity. In addition, applications in nonredundant blind testing, predicting mutation effects of SARS-CoV-2 RBD variants, and optimizing human antibody against SARS-CoV-2 illustrate the effectiveness of DDAffinity. AVAILABILITY AND IMPLEMENTATION: DDAffinity is available at https://github.com/ak422/DDAffinity.

DTKGIN: Predicting drug-target interactions based on knowledge graph and intent graph.

Knowledge graph intent graph attention mechanism Predicting drug-target interactions (DTIs) plays a crucial role in drug discovery and drug development. Considering the high cost and risk of biological experiments, developing computational approaches to explore the interactions between drugs and targets can effectively reduce the time and cost of drug development. Recently, many methods have made significant progress in predicting DTIs. However, existing approaches still suffer from the high sparsity of DTI datasets and the cold start problem. In this paper, we develop a new model to predict drug-target interactions via a knowledge graph and intent graph named DTKGIN. Our method can effectively capture biological environment information for targets and drugs by mining their associated relations in the knowledge graph and considering drug-target interactions at a fine-grained level in the intent graph. DTKGIN learns the representation of drugs and targets from the knowledge graph and the intent graph. Then the probabilities of interactions between drugs and targets are obtained through the inner product of the representation of drugs and targets. Experimental results show that our proposed method outperforms other state-of-the-art methods in 10-fold cross-validation, especially in cold-start experimental settings. Furthermore, the case studies demonstrate the effectiveness of DTKGIN in predicting potential drug-target interactions. The code is available on GitHub: https://github.com/Royluoyi123/DTKGIN.

SSLpheno: a self-supervised learning approach for gene-phenotype association prediction using protein-protein interactions and gene ontology data.

MOTIVATION: Medical genomics faces significant challenges in interpreting disease phenotype and genetic heterogeneity. Despite the establishment of standardized disease phenotype databases, computational methods for predicting gene-phenotype associations still suffer from imbalanced category distribution and a lack of labeled data in small categories. RESULTS: To address the problem of labeled-data scarcity, we propose a self-supervised learning strategy for gene-phenotype association prediction, called SSLpheno. Our approach utilizes an attributed network that integrates protein-protein interactions and gene ontology data. We apply a Laplacian-based filter to ensure feature smoothness and use self-supervised training to optimize node feature representation. Specifically, we calculate the cosine similarity of feature vectors and select positive and negative sample nodes for reconstruction training labels. We employ a deep neural network for multi-label classification of phenotypes in the downstream task. Our experimental results demonstrate that SSLpheno outperforms state-of-the-art methods, especially in categories with fewer annotations. Moreover, our case studies illustrate the potential of SSLpheno as an effective prescreening tool for gene-phenotype association identification. AVAILABILITY AND IMPLEMENTATION: https://github.com/bixuehua/SSLpheno.

Predicting disease genes based on multi-head attention fusion.

BACKGROUND: The identification of disease-related genes is of great significance for the diagnosis and treatment of human disease. Most studies have focused on developing efficient and accurate computational methods to predict disease-causing genes. Due to the sparsity and complexity of biomedical data, it is still a challenge to develop an effective multi-feature fusion model to identify disease genes. RESULTS: This paper proposes an approach to predict the pathogenic gene based on multi-head attention fusion (MHAGP). Firstly, the heterogeneous biological information networks of disease genes are constructed by integrating multiple biomedical knowledge databases. Secondly, two graph representation learning algorithms are used to capture the feature vectors of gene-disease pairs from the network, and the features are fused by introducing multi-head attention. Finally, multi-layer perceptron model is used to predict the gene-disease association. CONCLUSIONS: The MHAGP model outperforms all of other methods in comparative experiments. Case studies also show that MHAGP is able to predict genes potentially associated with diseases. In the future, more biological entity association data, such as gene-drug, disease phenotype-gene ontology and so on, can be added to expand the information in heterogeneous biological networks and achieve more accurate predictions. In addition, MHAGP with strong expansibility can be used for potential tasks such as gene-drug association and drug-disease association prediction.

Prediction and risk stratification from hospital discharge records based on Hierarchical sLDA.

BACKGROUND: The greatly accelerated development of information technology has conveniently provided adoption for risk stratification, which means more beneficial for both patients and clinicians. Risk stratification offers accurate individualized prevention and therapeutic decision making etc. Hospital discharge records (HDRs) routinely include accurate conclusions of diagnoses of the patients. For this reason, in this paper, we propose an improved model for risk stratification in a supervised fashion by exploring HDRs about coronary heart disease (CHD). METHODS: We introduced an improved four-layer supervised latent Dirichlet allocation (sLDA) approach called Hierarchical sLDA model, which categorized patient features in HDRs as patient feature-value pairs in one-hot way according to clinical guidelines for lab test of CHD. To address the data missing and imbalance problem, RFs and SMOTE methods are used respectively. After TF-IDF processing of datasets, variational Bayes expectation-maximization method and generalized linear model were used to recognize the latent clinical state of a patient, i.e., risk stratification, as well as to predict CHD. Accuracy, macro-F1, training and testing time performance were used to evaluate the performance of our model. RESULTS: According to the characteristics of our datasets, i.e., patient feature-value pairs, we construct a supervised topic model by adding one more Dirichlet distribution hyperparameter to sLDA. Compared with established supervised algorithm Multi-class sLDA model, we demonstrate that our proposed approach enhances training time by 59.74% and testing time by 25.58% but almost no loss of average prediction accuracy on our datasets. CONCLUSIONS: A model for risk stratification and prediction of CHD based on sLDA model was proposed. Experimental results show that Hierarchical sLDA model we proposed is competitive in time performance and accuracy. Hierarchical processing of patient features can significantly improve the disadvantages of low efficiency and time-consuming Gibbs sampling of sLDA model.