Search

The task of next basket recommendation is pivotal for recommender systems. It involves predicting user actions, such as the next product purchase or movie selection, by exploring sequential purchase behavior and integrating users’ general preferences. These elements may converge and influence users’ subsequent choices. The challenge intensifies with the presence of varied user purchase sequences in the training set, as indiscriminate incorporation of these sequences can introduce superfluous noise. In response to these challenges, we propose an innovative approach: the Selective Hierarchical Representation Model (SHRM). This model effectively integrates transactional data and user profiles to discern both sequential purchase transactions and general user preferences. The SHRM’s adaptability, particularly in employing nonlinear aggregation operations on user representations, enables it to model complex interactions among various influencing factors. Notably, the SHRM employs a Recurrent Neural Network (RNN) to capture extended dependencies in recent purchasing activities. Moreover, it incorporates an innovative sequence similarity task, grounded in a k-plet sampling strategy. This strategy clusters similar sequences, significantly mitigating the learning process’s noise impact. Through empirical validation on three diverse real-world datasets, we demonstrate that our model consistently surpasses leading benchmarks across various evaluation metrics, establishing a new standard in next-basket recommendation.

Abstract Background Anticancer peptide (ACP) inhibits and kills tumor cells. Research on ACP is of great significance for the development of new drugs, and the prediction of ACPs and non-ACPs is the new hotspot. Results We propose a new machine learning-based method named GCNCPR-ACPs (a Graph Convolutional Neural Network Method based on collapse pooling and residual network to predict the ACPs), which automatically and accurately predicts ACPs using residual graph convolution networks, differentiable graph pooling, and features extracted using peptide sequence information extraction. The GCNCPR-ACPs method can effectively capture different levels of node attributes for amino acid node representation learning, GCNCPR-ACPs uses node2vec and one-hot embedding methods to extract initial amino acid features for ACP prediction. Conclusions Experimental results of ten-fold cross-validation and independent validation based on different metrics showed that GCNCPR-ACPs significantly outperformed state-of-the-art methods. Specifically, the evaluation indicators of Matthews Correlation Coefficient (MCC) and AUC of our predicator were 69.5% and 90%, respectively, which were 4.3% and 2% higher than those of the other predictors, respectively, in ten-fold cross-validation. And in the independent test, the scores of MCC and SP were 69.6% and 93.9%, respectively, which were 37.6% and 5.5% higher than those of the other predictors, respectively. The overall results showed that the GCNCPR-ACPs method proposed in the current paper can effectively predict ACPs.

Abstract Background Experimental verification of a drug discovery process is expensive and time-consuming. Therefore, recently, the demand to more efficiently and effectively identify drug–target interactions (DTIs) has intensified. Results We treat the prediction of DTIs as a ranking problem and propose a neural network architecture, NeuRank, to address it. Also, we assume that similar drug compounds are likely to interact with similar target proteins. Thus, in our model, we add drug and target similarities, which are very effective at improving the prediction of DTIs. Then, we develop NeuRank from a point-wise to a pair-wise, and further to list-wise model. Conclusion Finally, results from extensive experiments on five public data sets (DrugBank, Enzymes, Ion Channels, G-Protein-Coupled Receptors, and Nuclear Receptors) show that, in identifying DTIs, our models achieve better performance than other state-of-the-art methods.

Background: Modern lifestyles mean that people are more likely to suffer from some form of cancer. As anticancer peptides can effectively kill cancer cells and play an important role in fighting cancer, they have been a subject of increasing research interest.Methods: This study presents a useful tool to identify the anticancer peptides based on a multi-kernel CNN and attention model, called ACP-MCAM. This model can automatically learn adaptive embedding and the context sequence features of ACP. In addition, to obtain better interpretability and integrity, we visualized the model.Results: Benchmarking comparison shows that ACP-MCAM significantly outperforms several state-of-the-art models. Different encoding schemes have different impacts on the performance of the model. We also studied tmethod parameter optimization.Conclusion: The ACP-MCAM can integrate multi-kernel CNN and self-attention mechanism, which outperforms the previous model in identifying anticancer peptides. It is expected that the work will provide new research ideas for anticancer peptide prediction in the future. In addition, this work will promote the development of the interdisciplinary field of artificial intelligence and biomedicine.

As living data growing and evolving rapidly, traditional machine learning algorithms are hard to update models when dealing with new training data. When new data arrives, traditional collaborative filtering methods have to train their model from scratch. It is expensive for them to retrain a model and update their parameters. Compared with traditional collaborative filtering, the online collaborative filtering is effective to update the models instantly when new data arrives. But the cold start and data sparsity remain major problems for online collaborative filtering. In this paper, we try to utilize the convolutional neural network to extract user/item features from user/item side information to address these problems. First, we proposed a deep bias probabilistic matrix factorization (DBPMF) model by utilizing the convolutional neural network to extract latent user/item features and adding the bias into probabilistic matrix factorization to track user rating behavior and item popularity. Second, we constrain user-specific and item-specific feature vectors to further improve the performance of the DBPMF. Third, we update two models by an online learning algorithm. The extensive experiments for three datasets (MovieLens100K, MovieLens1M, and HetRec2011) show that our methods have a better performance than baseline approaches.

Microbe-RNAs (miRNAs) play an important role and are associated with human diseases. However, considering the high cost and time-consuming biological experiments, using effective computational methods to discover the underlying association between the miRNAs and diseases would be valuable. This study presents a novel computational prediction model based on multiple-similarity and arbitrarily-order proximity network embedding. We obtain the Gaussian similarity from the disease-miRNA interaction matrix for the miRNA and disease. Then, considering the Gaussian similarity, disease semantic, phenotype similarity, and the miRNA functional similarity, we compute the miRNA-miRNA similarity matrix and the disease-disease similarity matrix. Most importantly, we improved the SVD matrix decomposition to extract the primary feature vector. We called it arbitrarily-order proximity network embedding method. By multiplying the feature vectors together, we calculate the final miRNA-disease association score matrix. According to the ranking scores, we can know which miRNA is mostly relevant to a disease. This process proved that our method achieved better prediction performance than other methods. In the experiment, after adding arbitrarily-order proximity network embedding to the inductive matrix completion method [1], the AUC of our method in leave-one-out cross-validation increased dramatically from 0.8034 to 0.92306. Meanwhile, the studies of three cases, namely, prostate neoplasms, breast neoplasms, and lung neoplasms, of the top 50 potential miRNAs predicted by our method were validated by the database of dbDEMC and mir2disease. This finding indicated that our method can effectively obtain the potential disease miRNA candidates. Comparison of our work with other algorithms reveals its reliable performance.

In this paper, the runoff of Huayuankou and Lijin Hydrologic Stations of the downstream areas of the Yellow River from 1951 to 2012 were calculated and analyzed in order to explore the runoff variable characteristics and their response to climatic factors. The following conclusions can be drawn:(1)Annual runoff of the river shows a clear downward trend as a whole, especially in the 1990s, but shifted to increase in the early 21st century.(2)Runoff can be affected by climate change; climatic factors and runoff change in the same time or precedes the latter.(3)The response of runoff to climatic factors is not stable, in other words, changing with time; (4)the response of runoff to precipitation is more sensitive than that of temperature.(5)Precipitation and temperature both contribute to the change of runoff, but the former is a positive contribution and the latter is opposite.

An enhanced differential evolution based algorithm, named multi-objective differential evolution with simulated annealing algorithm (MODESA), is presented for solving multiobjective optimization problems (MOPs). The proposed algorithm utilizes the advantage of simulated annealing for guiding the algorithm to explore more regions of the search space for a better convergence to the true Pareto-optimal front. In the proposed simulated annealing approach, a new acceptance probability computation function based on domination is proposed and some potential solutions are assigned a life cycle to have a priority to be selected entering the next generation. Moreover, it incorporates an efficient diversity maintenance approach, which is used to prune the obtained nondominated solutions for a good distributed Pareto front. The feasibility of the proposed algorithm is investigated on a set of five biobjective and two triobjective optimization problems and the results are compared with three other algorithms. The experimental results illustrate the effectiveness of the proposed algorithm.