Search

Abstract Ligand-receptor interaction (LRI) prediction has great significance in biological and medical research and facilitates to infer and analyze cell-to-cell communication. However, wet experiments for new LRI discovery are costly and time-consuming. Here, we propose a computational model called THGB to uncover new LRIs. THGB first extracts feature information of Ligand-Receptor (LR) pairs using iFeature. Next, it adopts a tree boosting model to obtain representative LR features. Finally, it devises the histogram-based gradient boosting model to capture high-quality LRIs. To assess the THGB performance, we compared it with three new LRI prediction models (i.e., CellEnBoost, CellGiQ, and CellComNet) and one classical protein-protein interaction inference model PIPR. The results demonstrated that THGB achieved the best overall predictions in terms of six evaluation indictors (i.e., precision, recall, accuracy, F1-score, AUC, and AUPR). To measure the effect of LR feature selection on the prediction, THGB was compared with four feature selection methods (i.e., PCA, NMF, LLE, and TSVD). The results showed that the tree boosting model was more appropriate to select representative LR features and improve LRI prediction. We also conducted ablation study and found that THGB with feature selection outperformed THGB without feature selection. We hope that THGB is a useful tool to find new LRIs and further infer cell-to-cell communication.

Abstract Long noncoding RNAs (lncRNAs) regulate many biological processes by interacting with corresponding RNA-binding proteins. The identification of lncRNA–protein Interactions (LPIs) is significantly important to well characterize the biological functions and mechanisms of lncRNAs. Existing computational methods have been effectively applied to LPI prediction. However, the majority of them were evaluated only on one LPI dataset, thereby resulting in prediction bias. More importantly, part of models did not discover possible LPIs for new lncRNAs (or proteins). In addition, the prediction performance remains limited. To solve with the above problems, in this study, we develop a Deep Forest-based LPI prediction method (LPIDF). First, five LPI datasets are obtained and the corresponding sequence information of lncRNAs and proteins are collected. Second, features of lncRNAs and proteins are constructed based on four-nucleotide composition and BioSeq2vec with encoder-decoder structure, respectively. Finally, a deep forest model with cascade forest structure is developed to find new LPIs. We compare LPIDF with four classical association prediction models based on three fivefold cross validations on lncRNAs, proteins, and LPIs. LPIDF obtains better average AUCs of 0.9012, 0.6937 and 0.9457, and the best average AUPRs of 0.9022, 0.6860, and 0.9382, respectively, for the three CVs, significantly outperforming other methods. The results show that the lncRNA FTX may interact with the protein P35637 and needs further validation.

Abstract The outbreak of a novel febrile respiratory disease called COVID-19, caused by a newfound coronavirus SARS-CoV-2, has brought a worldwide attention. Prioritizing approved drugs is critical for quick clinical trials against COVID-19. In this study, we first manually curated three Virus-Drug Association (VDA) datasets. By incorporating VDAs with the similarity between drugs and that between viruses, we constructed a heterogeneous Virus-Drug network. A novel Random Walk with Restart method (VDA-RWR) was then developed to identify possible VDAs related to SARS-CoV-2. We compared VDA-RWR with three state-of-the-art association prediction models based on fivefold cross-validations (CVs) on viruses, drugs and virus-drug associations on three datasets. VDA-RWR obtained the best AUCs for the three fivefold CVs, significantly outperforming other methods. We found two small molecules coming together on the three datasets, that is, remdesivir and ribavirin. These two chemical agents have higher molecular binding energies of − 7.0 kcal/mol and − 6.59 kcal/mol with the domain bound structure of the human receptor angiotensin converting enzyme 2 (ACE2) and the SARS-CoV-2 spike protein, respectively. Interestingly, for the first time, experimental results suggested that navitoclax could be potentially applied to stop SARS-CoV-2 and remains to further validation.