TransFoxMol: predicting molecular property with focused attention.

Predicting the biological properties of molecules is crucial in computer-aided drug development, yet it's often impeded by data scarcity and imbalance in many practical applications. Existing approaches are based on self-supervised learning or 3D data and using an increasing number of parameters to improve performance. These approaches may not take full advantage of established chemical knowledge and could inadvertently introduce noise into the respective model. In this study, we introduce a more elegant transformer-based framework with focused attention for molecular representation (TransFoxMol) to improve the understanding of artificial intelligence (AI) of molecular structure property relationships. TransFoxMol incorporates a multi-scale 2D molecular environment into a graph neural network + Transformer module and uses prior chemical maps to obtain a more focused attention landscape compared to that obtained using existing approaches. Experimental results show that TransFoxMol achieves state-of-the-art performance on MoleculeNet benchmarks and surpasses the performance of baselines that use self-supervised learning or geometry-enhanced strategies on small-scale datasets. Subsequent analyses indicate that TransFoxMol's predictions are highly interpretable and the clever use of chemical knowledge enables AI to perceive molecules in a simple but rational way, enhancing performance.

ClusterX: a novel representation learning-based deep clustering framework for accurate visual inspection in virtual screening.

Molecular clustering analysis has been developed to facilitate visual inspection in the process of structure-based virtual screening. However, traditional methods based on molecular fingerprints or molecular descriptors limit the accuracy of selecting active hit compounds, which may be attributed to the lack of representations of receptor structural and protein-ligand interaction during the clustering. Here, a novel deep clustering framework named ClusterX is proposed to learn molecular representations of protein-ligand complexes and cluster the ligands. In ClusterX, the graph was used to represent the protein-ligand complex, and the joint optimisation can be used efficiently for learning the cluster-friendly features. Experiments on the KLIFs database show that the model can distinguish well between the binding modes of different kinase inhibitors. To validate the effectiveness of the model, the clustering results on the virtual screening dataset further demonstrated that ClusterX achieved better or more competitive performance against traditional methods, such as SIFt and extended connectivity fingerprints. This framework may provide a unique tool for clustering analysis and prove to assist computational medicinal chemists in visual decision-making.

Identification of Potential WSB1 Inhibitors by AlphaFold Modeling, Virtual Screening, and Molecular Dynamics Simulation Studies.

WD40 repeat and SOCS box containing 1 (WSB1) consists of seven WD40 repeat structural domains at the N-terminal end and one SOCS box structural domain at the C-terminal end. WSB1 promotes cancer progression by affecting the Von Hippel-Lindau tumor suppressor protein (pVHL) and upregulating hypoxia inducible factor-1α (HIF-1α) target gene expression. However, the crystal structure of WSB1 has not been reported, which is not beneficial to the research on WSB1 inhibitors. Therefore, we focused on specific small molecule inhibitors of WSB1. This study applied virtual screening and molecular dynamics simulations; finally, 20 compounds were obtained. Among them, compound G490-0341 showed the best stable structure and was a promising composite for further development of WSB1 inhibitors.

Identification of Novel Covalent XPO1 Inhibitors Based on a Hybrid Virtual Screening Strategy.

Nuclear export protein 1 (XPO1), a member of the nuclear export protein-p (Karyopherin-P) superfamily, regulates the transport of "cargo" proteins. To facilitate this important process, which is essential for cellular homeostasis, XPO1 must first recognize and bind the cargo proteins. To inhibit this process, small molecule inhibitors have been designed that inhibit XPO1 activity through covalent binding. However, the scaffolds for these inhibitors are very limited. While virtual screening may be used to expand the diversity of the XPO1 inhibitor skeleton, enormous computational resources would be required to accomplish this using traditional screening methods. In the present study, we report the development of a hybrid virtual screening workflow and its application in XPO1 covalent inhibitor screening. After screening, several promising XPO1 covalent molecules were obtained. Of these, compound 8 performed well in both tumor cell proliferation assays and a nuclear export inhibition assay. In addition, molecular dynamics simulations were performed to provide information on the mode of interaction of compound 8 with XPO1. This research has identified a promising new scaffold for XPO1 inhibitors, and it demonstrates an effective and resource-saving workflow for identifying new covalent inhibitors.

Discover Novel Covalent Inhibitors Targeting FLT3 through Hybrid Virtual Screening Strategy.

FMS-like tyrosine kinase 3 (FLT3) plays a very important role in regulating the proliferation, differentiation and survival of normal hematopoietic stem cells. Internal tandem duplications of the FLT3 gene (FLT3-ITD) mutations are present in 25% of all acute myeloid leukemia (AML) patients and are frequently associated with adverse clinical outcomes. Therefore, FLT3-ITD is a promising target for the treatment of AML. The use of covalent virtual screenings has shown that efficient rational approaches for the rapid discovery of new drugs scaffold. Herein, we report a hybrid virtual screening strategy that led to the discovery of FLT3 inhibitors. Using the combination of non-covalent docking and covalent docking, 8 compounds were found to inhibit FLT3, and G856-8335, S346-0154 are also effective against mutant FLT3. These two compounds also show selectivity to receptor tyrosine kinase (C-KIT), which has the potential for optimization. And this work can be extended to the screening of other covalent inhibitors.

Discovery of phenyl-linked symmetric small molecules as inhibitors of the programmed cell death-1/programmed cell death-ligand 1 interaction.

Programmed cell death-1/programmed cell death ligand 1 (PD-1/PD-L1) is one of the most promising targets in the field of immune checkpoint blockade therapy. Beginning with our exploration of linkers and structure-activity relationship research, we found that the aromatic ring could replace the linker and aryl group to maintain the satisfactory activity of classic triaryl scaffold inhibitor. Based on previous studies, we designed and synthesized a series of C2-symmetric phenyl-linked compounds, and further tail optimization afforded the inhibitors, which displayed promising inhibitory activity against the PD-1/PD-L1 interaction with IC50 value at the single nanomolar range (C13-C15). Further cell-based PD-1/PD-L1 blockade bioassays indicated that these C2-symmetric molecules could significantly inhibit the PD-1/PD-L1 interaction at the cellular level and restore T cells' immune function at the safety concentrations. The discovery of these phenyl-linked symmetric small molecules showed the potential of simplified-linker and C2-symmetric strategy and provided a basis for developing symmetric small molecule inhibitors of PD-1/PD-L1 interaction. Moreover, C13 and C15 performed stable binding modes to PD-L1 dimeric after computational docking and dynamic simulation, which may serve as a good starting point for further development.

Facile fabrication of a highly (110)-oriented ZIF-7 film with rod-shaped seeds.

In this study, we report a novel synthetic strategy to prepare a highly (110)-oriented ZIF-7 film possessing superior anti-corrosion properties via oriented epitaxial growth. Our work provides insights into facile preparation of oriented uniform MOF single seed layers and films with rod-shaped MOF seeds as building blocks.