Search for: All records

Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug–drug interactions (DDIs). DDIs refer to a change in the effect of one drug to the presence of another drug in the human body, which plays an essential role in drug discovery and clinical research. DDIs prediction through traditional clinical trials and experiments is an expensive and time-consuming process. To correctly apply the advanced AI and deep learning, the developer and user meet various challenges such as the availability and encoding of data resources, and the design of computational methods. This review summarizes chemical structure based, network based, natural language processing based and hybrid methods, providing an updated and accessible guide to the broad researchers and development community with different domain knowledge. We introduce widely used molecular representation and describe the theoretical frameworks of graph neural network models for representing molecular structures. We present the advantages and disadvantages of deep and graph learning methods by performing comparative experiments. We discuss the potential technical challenges and highlight future directions of deep and graph learning models for accelerating DDIs prediction.

 

The discovery of carbon dots opens a new avenue to the applications of nanomaterials in biosensing and bioimaging. In this work, we develop simple methods to prepare carbon nanoparticles from xylose and to tune the photoluminescence (PL) characteristics of the xylose-derived carbon nanoparticles via the combination of three different processes: hydrothermal carbonization (HTC), annealing at 850 °C and laser ablation (LA) in a NH₄OH solution. The HTC-synthesized carbon dots (CDs) exhibit green emission under the 365 nm UV excitation, the annealing of the HTC-synthesized CDs leads to complete loss of the PL characteristics, and the LA processing of the annealed carbon nanoparticles recovers the PL characteristics with blue shift in comparison to the HTC-synthesized CDs under the same UV excitation. the PL characteristics of the HTC-CDs and the LA-CDs are dependent on theπ-π* transition of C-containing surface-functional groups andπ-π* and n-π* transitions of N-containing surface-functional groups, respectively, which are responsible for the difference in the PL characteristics between the HTC-synthesized CDs and the LA-processed CDs. The approaches demonstrated in this work provide a viable method to introduce and tune surface-functional groups on the surface of carbon nanoparticles.

 

Biomass-derived carbon dots (CDs) are biocompatible and have potential for a variety of applications, including bioimaging and biosensing. In this work, we use ground soybean residuals to synthesize carbon nanoparticles by hydrothermal carbonization (HTC), annealing at high temperature, and laser ablation (LA) in a NH 4 OH solution. The carbon nanoparticles synthesized with the HTC process (HTC-CDs) exhibit photoluminescent characteristics with strong blue emission. The annealing of the HTC-processed carbon particles in the range of 250 to 850 °C causes a loss of the photoluminescent characteristics of the CDs without any significant change in the microstructure (amorphous structure) of the carbon particles. The LA processing of the annealed HTC-processed carbon particles introduces nitrogen-containing surface-functional groups and leads to the recovery of the photoluminescent features that are different from those of the HTC-CDs and dependent on the fraction of nitrogen in the surface-functional groups. The photoluminescence of both the HTC-CDs and LA-CDs is largely due to the presence of N-containing surface-functional groups. The quantum yield of the LA-CDs is more constant than that of the HTC-CDs under continuous UV excitation and does not exhibit a significant reduction after 150 min of excitation. The methods used in this work provide a simple and green strategy to introduce N-surface-functional groups to carbon nanoparticles made from biomass and biowaste and to produce stable photoluminescent CDs with excellent water-wettability.