Motivation
Accurately predicting drug–target interactions (DTIs) in silico can guide the drug discovery process and thus facilitate drug development. Computational approaches for DTI prediction that adopt the systems biology perspective generally exploit the rationale that the properties of drugs and targets can be characterized by their functional roles in biological networks.
Results
Inspired by recent advance of information passing and aggregation techniques that generalize the convolution neural networks to mine large-scale graph data and greatly improve the performance of many network-related prediction tasks, we develop a new nonlinear end-to-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns topology-preserving representations of drugs and targets to facilitate DTI prediction. The substantial prediction performance improvement over other state-of-the-art DTI prediction methods as well as several novel predicted DTIs with evidence supports from previous studies have demonstrated the superior predictive power of NeoDTI. In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g. compound–protein binding affinity data). All these results suggest that NeoDTI can offer a powerful and robust tool for drug development and drug repositioning.
Availability and implementation
The source code and data used in NeoDTI are available at: https://github.com/FangpingWan/NeoDTI.
Supplementary information
Supplementary data are available at Bioinformatics online.
Accurately predicting drug-target interactions (DTIs) in silico can guide the drug discovery process and thus facilitate drug development. Computational approaches for DTI prediction that adopt the systems biology perspective generally exploit the rationale that the properties of drugs and targets can be characterized by their functional roles in biological networks. Inspired by recent advance of information passing and aggregation techniques that generalize the convolution neural networks (CNNs) to mine large-scale graph data and greatly improve the performance of many network-related prediction tasks, we develop a new nonlinear endto-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns topology-preserving representations of drugs and targets to facilitate DTI prediction. The substantial prediction performance improvement over other state-of-the-art DTI prediction methods as well as several novel predicted DTIs with evidence supports from previous studies have demonstrated the superior predictive power of NeoDTI. In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g., compound-protein binding affinity data). All these results suggest that NeoDTI can offer a powerful and robust tool for drug development and drug repositioning.
A novel separation concept based on the stepped behaviors of adsorption in nanoporous materials was brought out in this work. Molecular simulations were performed to investigate the effect of such stepped phenomena on the separation of CO 2 / N 2 gas mixture in metal-organic frameworks (MOFs). The simulation results show that the stepped behaviors occurring in the isotherms of CO 2 can significantly enhance the adsorption selectivity of CO 2 from the mixture. The underlying mechanism examined at the molecular level reveals that the stepped phenomenon is mainly caused by the electrostatic interactions between CO 2 molecules. In addition, this work shows that the lithiummodified MOFs can greatly reduce the pressure at which the stepped behavior occurs and also enhance the selectivity of CO 2 from CO 2 /N 2 gas mixture.
A new homo-trinuclear Ni(II) half-salamo-based complex [Ni3(L)2(μ-OAc)2(OAc)2(CH3OH)2]·2CH3OH was synthesized via the reaction of a tridentate ligand HL (2-[O-(1-ethyloxyamide)]oxime-4-bromophenol) and Ni(OAc)2·4H2O, and characterized using elemental analyses, IR spectra, UV-Vis absorption spectra, X-ray crystallography, and Hirshfeld analysis. Interestingly, single-crystal X-ray analysis showed that the two acetate molecules were bonded simultaneously with the Ni(II) atoms by mono-dentate chelating and bidentate bridging coordination modes, respectively, and the resulting hexa-coordinate geometries were ultimately formed. Furthermore, the Hirshfeld analysis of the complex was studied. Compared with HL, the complex fluorescence intensity was significantly lowered, indicating that the Ni(II) ions have fluorescence quenching characteristics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.