Background: Drug–drug interactions (DDIs) are the reactions between drugs. They are compartmentalized into three types: synergistic, antagonistic and no reaction. As a rapidly developing technology, predicting DDIs-associated events is getting more and more attention and application in drug development and disease diagnosis fields. In this work, we study not only whether the two drugs interact, but also specific interaction types. And we propose a learning-based method using convolution neural networks to learn feature representations and predict DDIs. Results: In this paper, we proposed a novel algorithm using a CNN architecture, named CNN-DDI, to predict drug–drug interactions. First, we extract feature interactions from drug categories, targets, pathways and enzymes as feature vectors and employ the Jaccard similarity as the measurement of drugs similarity. Then, based on the representation of features, we build a new convolution neural network as the DDIs’ predictor. Conclusion: The experimental results indicate that drug categories is effective as a new feature type applied to CNN-DDI method. And using multiple features is more informative and more effective than single feature. It can be concluded that CNN-DDI has more superiority than other existing algorithms on task of predicting DDIs.

Metabolites disrupted by abnormal state of human body are deemed as the effect of diseases. In comparison with the cause of diseases like genes, these markers are easier to be captured for the prevention and diagnosis of metabolic diseases. Currently, a large number of metabolic markers of diseases need to be explored, which drive us to do this work. The existing metabolite-disease associations were extracted from Human Metabolome Database (HMDB) using a text mining tool NCBO annotator as priori knowledge. Next we calculated the similarity of a pair-wise metabolites based on the similarity of disease sets of them. Then, all the similarities of metabolite pairs were utilized for constructing a weighted metabolite association network (WMAN). Subsequently, the network was utilized for predicting novel metabolic markers of diseases using random walk. Totally, 604 metabolites and 228 diseases were extracted from HMDB. From 604 metabolites, 453 metabolites are selected to construct the WMAN, where each metabolite is deemed as a node, and the similarity of two metabolites as the weight of the edge linking them. The performance of the network is validated using the leave one out method. As a result, the high area under the receiver operating characteristic curve (AUC) (0.7048) is achieved. The further case studies for identifying novel metabolites of diabetes mellitus were validated in the recent studies. In this paper, we presented a novel method for prioritizing metabolite-disease pairs. The superior performance validates its reliability for exploring novel metabolic markers of diseases.

The alignment of long-read RNA sequencing reads is non-trivial due to high sequencing errors and complicated gene structures. We propose deSALT, a tailored two-pass alignment approach, which constructs graph-based alignment skeletons to infer exons and uses them to generate spliced reference sequences to produce refined alignments. deSALT addresses several difficult technical issues, such as small exons and sequencing errors, which break through bottlenecks of long RNA-seq read alignment. Benchmarks demonstrate that deSALT has a greater ability to produce accurate and homogeneous full-length alignments. deSALT is available at: https://github.com/hitbc/deSALT.

It is estimated that the impact of related genes on the risk of Alzheimer’s disease (AD) is nearly 70%. Identifying candidate causal genes can help treatment and diagnosis. The maturity of sequencing technology and the reduction of cost make genome-wide association study (GWAS) become an important means to find disease-related mutation sites. Because of linkage disequilibrium (LD), neither the gene regulated by SNP nor the specific SNP can be determined. Because GWAS is affected by sample size and interaction, we introduced empirical Bayes (EB) to make a meta-analysis of GWAS to greatly eliminate the bias caused by sample and the interaction of SNP. In addition, most SNPs are in the noncoding region, so it is not clear how they relate to phenotype. In this paper, expression quantitative trait locus (eQTL) studies and methylation quantitative trait locus (mQTL) studies are combined with GWAS to find the genes associated with Alzheimer disease in expression levels by pleiotropy. Summary data-based Mendelian randomization (SMR) is introduced to integrate GWAS and eQTL/mQTL data. Finally, we prioritized 274 significant SNPs, which belong to 20 genes by eQTL analysis and 379 significant SNPs, which belong to seven known genes by mQTL. Among them, 93 SNPs and 2 genes are overlapped. Finally, we did 10 case studies to prove the effectiveness of our method.

Alzheimer disease (AD) is the fourth major cause of death in the elderly following cancer, heart disease and cerebrovascular disease. Finding candidate causal genes can help in the design of Gene targeted drugs and effectively reduce the risk of the disease. Complex diseases such as AD are usually caused by multiple genes. The Genome-wide association study (GWAS), has identified the potential genetic variants for most diseases. However, because of linkage disequilibrium (LD), it is difficult to identify the causative mutations that directly cause diseases. In this study, we combined expression quantitative trait locus (eQTL) studies with the GWAS, to comprehensively define the genes that cause Alzheimer disease. The method used was the Summary Mendelian randomization (SMR), which is a novel method to integrate summarized data. Two GWAS studies and five eQTL studies were referenced in this paper. We found several candidate SNPs that have a strong relationship with AD. Most of these SNPs overlap in different data sets, providing relatively strong reliability. We also explain the function of the novel AD-related genes we have discovered.

Predicting the binding of peptide and major histocompatibility complex (MHC) plays a vital role in immunotherapy for cancer. The success of Alphafold of applying natural language processing (NLP) algorithms in protein secondary struction prediction has inspired us to explore the possibility of NLP methods in predicting peptide–MHC class I binding. Based on the above motivations, we propose the MHCRoBERTa method, RoBERTa pre-training approach, for predicting the binding affinity between type I MHC and peptides. Analysis of the results on benchmark dataset demonstrates that MHCRoBERTa can outperform other state-of-art prediction methods with an increase of the Spearman rank correlation coefficient (SRCC) value. Notably, our model gave a significant improvement on IC50 value. Our method has achieved SRCC value and AUC value as 0.785 and 0.817, respectively. Our SRCC value is 14.3% higher than NetMHCpan3.0 (the second highest SRCC value on pan-specific) and is 3% higher than MHCflurry (the second highest SRCC value on all methods). The AUC value is also better than any other pan-specific methods. Moreover, we visualize the multi-head self-attention for the token representation across the layers and heads by this method. Through the analysis of the representation of each layer and head, we can show whether the model has learned the syntax and semantics necessary to perform the prediction task well. All these results demonstrate that our model can accurately predict the peptide–MHC class I binding affinity and that MHCRoBERTa is a powerful tool for screening potential neoantigens for cancer immunotherapy. MHCRoBERTa is available as an open source software at github (https://github.com/FuxuWang/MHCRoBERTa).