22 July 2020 in Chemical Science
Linking fragments to generate a focused compound library for a specific drug target is one of the challenges in fragment-based drug design (FBDD). Hereby, we propose a new program named SyntaLinker, which is based on a syntactic pattern recognition approach using deep conditional transformer neural networks. This state-of-the-art transformer can link molecular fragments automatically by learning from the knowledge of structures in medicinal chemistry databases (e.g. ChEMBL database). Conventionally, linking molecular fragments was viewed as connecting substructures that were predefined by empirical rules. In SyntaLinker, however, the rules of linking fragments can be learned implicitly from known chemical structures by recognizing syntactic patterns embedded in SMILES notations. With deep conditional transformer neural networks, SyntaLinker can generate molecular structures based on a given pair of fragments and additional restrictions. Case studies have demonstrated the advantages and usefulness of SyntaLinker in FBDD.
3 February 2020 in Journal of Chemical Information and Modeling
27 September 2024 in The Journal of Chemical Physics
The nitrile (C≡N) stretching vibration is widely used as a site-specific environmental probe of proteins and, as such, many computational studies have been used to investigate the factors that affect its frequency (νCN). These studies, most of which were carried out in the ground electronic state of the molecule of interest, revealed that the formation of a normal or linear hydrogen bond (H-bond) with the nitrile group results in a blueshift in its νCN. Recently, however, several experimental studies showed that for certain aromatic nitriles, solvent relaxations in their excited electronic state(s) induce a redshift (blueshift) in νCN in protic (aprotic) solvents, suggesting that the effect of hydrogen-bonding (H-bonding) interactions on νCN may depend on the electronic state of the molecule. To test this possibility, herein we combine molecular dynamics simulations and quantum mechanical calculations to assess the effect of H-bonding interactions on the νCN of 5-cyanoindole (5-CNI) in its different electronic states. We find that its C≡N group can form either one H-bond (single-H-bond) or two H-bonds (d-H-bonds) with the solvent molecules and that in the ground electronic state, a single-H-bond can lead νCN to shift either to a higher or lower frequency, depending on its angle, which is consistent with previous studies, whereas the d-H-bonds cause νCN to redshift. However, in its lowest-lying excited electronic state (i.e., S1), which has the characteristics of a charge-transfer state, all H-bonds induce a redshift in νCN, with the d-H-bonds being most effective in this regard.
26 April 2022 in Artificial Intelligence in the Life Sciences
12 November 2015 in Proceedings of IAHS
The Yangtze River Delta and North China Plain are experiencing serious land subsidence development and are also the areas that have undergone the fastest urbanization. Rapid urban development inevitably requires more water resources. However, China is a country with small per capita water resources, nonuniform distribution of water resources, and over-exploitation of groundwater – all of which are critical factors contributing to the potential for a land subsidence disaster. In addition, land subsidence has brought about elevation loss, damaged buildings, decreased safety of rail transit projects, lowered land value, and other huge economic losses and potential safety hazards in China. In this paper, Beijing, a typical northern Chinese city deficient in water, is taken as an example to explore (a) the problems of urban development, utilization of water resources, and land subsidence development; (b) the harm and influence of land subsidence hazards on urban construction; and (c) the relationship between urban development and land subsidence. Based on the results, the author has predicted the trend of urban development and land subsidence in Beijing and puts forward her viewpoints and suggestions.
23 April 2022 in Mathematical Problems in Engineering
A new constrained multi-objective optimization coevolutionary algorithm (CCMO) based on the NSGA-II algorithm is proposed to cope with the efficient optimization of multiple objectives containing constraints in the optimal combined carbon-energy flow (OCECF). The algorithm improves the convergence of the population by evolving a new auxiliary population that shares effective information with the original population for weak cooperation, offering significant performance advantages. Applying the algorithm for reactive power control on two different-sized IEEE benchmark systems (IEEE-57 and IEEE-300 bus systems), respectively, minimizes carbon emissions and voltage deviations in the grid. Simulation results show that the CCMO algorithm has significant advantages in terms of the convergence speed and Pareto front.