Predicting the effect of drug-drug interactions (DDIs) precisely is important for safer and more effective drug co-prescription. Many computational approaches to predict the effect of DDIs have been proposed, with the aim of reducing the effort of identifying these interactions in vivo or in vitro, but room remains for improvement in prediction performance. In this study, we propose a novel deep learning model to predict the effect of DDIs more accurately.. The proposed model uses autoencoders and a deep feed-forward network that are trained using the structural similarity profiles (SSP), Gene Ontology (GO) term similarity profiles (GSP), and target gene similarity profiles (TSP) of known drug pairs to predict the pharmacological effects of DDIs. The results show that GSP and TSP increase the prediction accuracy when using SSP alone, and the autoencoder is more effective than PCA for reducing the dimensions of each profile. Our model showed better performance than the existing methods, and identified a number of novel DDIs that are supported by medical databases or existing research. We present a novel deep learning model for more accurate prediction of DDIs and their effects, which may assist in future research to discover novel DDIs and their pharmacological effects.

Background: Accurate prediction of protein–ligand binding affinity is important for lowering the overall cost of drug discovery in structure-based drug design. For accurate predictions, many classical scoring functions and machine learning-based methods have been developed. However, these techniques tend to have limitations, mainly resulting from a lack of sufficient energy terms to describe the complex interactions between proteins and ligands. Recent deep-learning techniques can potentially solve this problem. However, the search for more efficient and appropriate deep-learning architectures and methods to represent protein–ligand complex is ongoing.Results: In this study, we proposed a deep-neural network model to improve the prediction accuracy of protein–ligand complex binding affinity. The proposed model has two important features, descriptor embeddings with information on the local structures of a protein–ligand complex and an attention mechanism to highlight important descriptors for binding affinity prediction. The proposed model performed better than existing binding affinity prediction models on most benchmark datasets.Conclusions: We confirmed that an attention mechanism can capture the binding sites in a protein–ligand complex to improve prediction performance. Our code is available athttps://github.com/Blue1993/BAPA.

Cancer is one of the most difficult diseases to treat owing to the drug resistance of tumour cells. Recent studies have revealed that drug responses are closely associated with genomic alterations in cancer cells. Numerous state-of-the-art machine learning models have been developed for prediction of drug responses using various genomic data and diverse drug molecular information, but those methods are ineffective to predict drug response to untrained drugs and gene expression patterns, which is known as the cold-start problem. In this study, we present a novel deep neural network model, termed RefDNN, for improved prediction of drug resistance and identification of biomarkers related to drug response. RefDNN exploits a collection of drugs, called reference drugs, to learn representations for a high-dimensional gene expression vector and a molecular structure vector of a drug and predicts drug response labels using the reference drug-based representations. These calculations come from the observation that similar chemicals have similar effects. The proposed model not only outperformed existing computational prediction models in most comparative experiments, but also showed more robust prediction for untrained drugs and cancer types than traditional machine learning models. RefDNN exploits the ElasticNet regularization to deal with high-dimensional gene expression data, which allows identification of gene markers associated with drug resistance. Lastly, we described an application of RefDNN in exploring a new candidate drug for liver cancer. As the proposed model can guarantee good prediction of drug responses to untrained drugs for given gene expression patterns, it may be of potential benefit in drug repositioning and personalized medicine.

Accurate identification of prognostic biomarkers is an important yet challenging goal in bioinformatics. Many bioinformatics approaches have been proposed for this purpose, but there is still room for improvement. In this paper, we propose a novel machine learning-based method for more accurate identification of prognostic biomarker genes and use them for prediction of cancer prognosis. The proposed method specifies the candidate prognostic gene module by graph learning using the generative adversarial networks (GANs) model, and scores genes using a PageRank algorithm. We applied the proposed method to multiple-omics data that included copy number, gene expression, DNA methylation, and somatic mutation data for five cancer types. The proposed method showed better prediction accuracy than did existing methods. We identified many prognostic genes and their roles in their biological pathways. We also showed that the genes identified from different omics data were complementary, which led to improved accuracy in prediction using multi-omics data.

Identification of genes that can be used to predict prognosis in patients with cancer is important in that it can lead to improved therapy, and can also promote our understanding of tumor progression on the molecular level. One of the common but fundamental problems that render identification of prognostic genes and prediction of cancer outcomes difficult is the heterogeneity of patient samples. To reduce the effect of sample heterogeneity, we clustered data samples using K-means algorithm and applied modified PageRank to functional interaction (FI) networks weighted using gene expression values of samples in each cluster. Hub genes among resulting prioritized genes were selected as biomarkers to predict the prognosis of samples. This process outperformed traditional feature selection methods as well as several network-based prognostic gene selection methods when applied to Random Forest. We were able to find many cluster-specific prognostic genes for each dataset. Functional study showed that distinct biological processes were enriched in each cluster, which seems to reflect different aspect of tumor progression or oncogenesis among distinct patient groups. Taken together, these results provide support for the hypothesis that our approach can effectively identify heterogeneous prognostic genes, and these are complementary to each other, improving prediction accuracy. https://github.com/mathcom/CPR Supplementary data are available at Bioinformatics online.

Identification of cancer prognostic genes is important in that it can lead to accurate outcome prediction and better therapeutic trials for cancer patients. Many computational approaches have been proposed to achieve this goal; however, there is room for improvement. Recent developments in deep learning techniques can aid in the identification of better prognostic genes and more accurate outcome prediction, but one of the main problems in the adoption of deep learning for this purpose is that data from cancer patients have too many dimensions, while the number of samples is relatively small. In this study, we propose a novel network-based deep learning method to identify prognostic gene signatures via distributed gene representations generated by G2Vec, which is a modified Word2Vec model originally used for natural language processing. We applied the proposed method to five cancer types including liver cancer and showed that G2Vec outperformed extant feature selection methods, especially for small number of samples. Moreover, biomarkers identified by G2Vec was useful to find significant prognostic gene modules associated with hepatocellular carcinoma.