Yuyao Yang

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.

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.

Scaffold hopping is a widely used strategy for drug design towards kinase inhibitors. In current study, we proposed a fragment-based deep learning strategy for scaffold hopping towards the conserved hinge binding motif of kinase inhibitors in a large scale.

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.

Fragment based drug design represents a promising drug discovery paradigm complimentary to the traditional HTS based lead generation strategy. How to link fragment structures to increase compound affinity is remaining a challenge task in this paradigm. Hereby a novel deep generative model (SyntaLinker) for linking fragments is developed with the potential for applying in the fragment-based lead generation scenario. The state-of-the-art transformer architecture was employed to learn the linker grammar and generate novel linker. Our results show that, given starting fragments and user customized linker constraints, our SyntaLinker model can design abundant drug-like molecules fulfilling these constraints and its performance was superior to other reference models. Moreover, several examples were showcased that SyntaLinkercan be useful tools for carrying out drug design tasks such as fragment linking, lead optimization and scaffold hopping.

Fragment based drug design represents a promising drug discovery paradigm complimentary to the traditional HTS based lead generation strategy. How to link fragment structures to increase compound affinity is remaining a challenge task in this paradigm. Hereby a novel deep generative model (SyntaLinker) for linking fragments is developed with the potential for applying in the fragment-based lead generation scenario. The state-of-the-art transformer architecture was employed to learn the linker grammar and generate novel linker. Our results show that, given starting fragments and user customized linker constraints, our SyntaLinker model can design abundant drug-like molecules fulfilling these constraints and its performance was superior to other reference models. Moreover, several examples were showcased that SyntaLinkercan be useful tools for carrying out drug design tasks such as fragment linking, lead optimization and scaffold hopping.

Fragment based drug design represents a promising drug discovery paradigm complimentary to the traditional HTS based lead generation strategy. How to link fragment structures to increase compound affinity is remaining a challenge task in this paradigm. Hereby a novel deep generative model (AutoLinker) for linking fragments is developed with the potential for applying in the fragment-based lead generation scenario. The state-of-the-art transformer architecture was employed to learn the linker grammar and generate novel linker. Our results show that, given starting fragments and user customized linker constraints, our AutoLinker model can design abundant drug-like molecules fulfilling these constraints and its performance was superior to other reference models. Moreover, several examples were showcased that AutoLinker can be useful tools for carrying out drug design tasks such as fragment linking, lead optimization and scaffold hopping.

Fragment based drug design represents a promising drug discovery paradigm complimentary to the traditional HTS based lead generation strategy. How to link fragment structures to increase compound affinity is remaining a challenge task in this paradigm. Hereby a novel deep generative model (AutoLinker) for linking fragments is developed with the potential for applying in the fragment-based lead generation scenario. The state-of-the-art transformer architecture was employed to learn the linker grammar and generate novel linker. Our results show that, given starting fragments and user customized linker constraints, our AutoLinker model can design abundant drug-like molecules fulfilling these constraints and its performance was superior to other reference models. Moreover, several examples were showcased that AutoLinker can be useful tools for carrying out drug design tasks such as fragment linking, lead optimization and scaffold hopping.

Fragment based drug design represents a promising drug discovery paradigm complimentary to the traditional HTS based lead generation strategy. How to link fragment structures to increase compound affinity is remaining a challenge task in this paradigm. Hereby a novel deep generative model (AutoLinker) for linking fragments is developed with the potential for applying in the fragment-based lead generation scenario. The state-of-the-art transformer architecture was employed to learn the linker grammar and generate novel linker. Our results show that, given starting fragments and user customized linker constraints, our AutoLinker model can design abundant drug-like molecules fulfilling these constraints and its performance was superior to other reference models. Moreover, several examples were showcased that AutoLinker can be useful tools for carrying out drug design tasks such as fragment linking, lead optimization and scaffold hopping.