Structure-Kinetic Relationship for Drug Design Revealed by a PLS Model with Retrosynthesis-Based Pre-Trained Molecular Representation and Molecular Dynamics Simulation.

Drug design based on kinetic properties is growing in application. Here, we applied retrosynthesis-based pre-trained molecular representation (RPM) in machine learning (ML) to train 501 inhibitors of 55 proteins and successfully predicted the dissociation rate constant (koff) values of 38 inhibitors from an independent dataset for the N-terminal domain of heat shock protein 90α (N-HSP90). Our RPM molecular representation outperforms other pre-trained molecular representations such as GEM, MPG, and general molecular descriptors from RDKit. Furthermore, we optimized the accelerated molecular dynamics to calculate the relative retention time (RT) for the 128 inhibitors of N-HSP90 and obtained the protein-ligand interaction fingerprints (IFPs) on their dissociation pathways and their influencing weights on the koff value. We observed a high correlation among the simulated, predicted, and experimental -log(koff) values. Combining ML, molecular dynamics (MD) simulation, and IFPs derived from accelerated MD helps design a drug for specific kinetic properties and selectivity profiles to the target of interest. To further validate our koff predictive ML model, we tested our model on two new N-HSP90 inhibitors, which have experimental koff values and are not in our ML training dataset. The predicted koff values are consistent with experimental data, and the mechanism of their kinetic properties can be explained by IFPs, which shed light on the nature of their selectivity against N-HSP90 protein. We believe that the ML model described here is transferable to predict koff of other proteins and will enhance the kinetics-based drug design endeavor.

G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training.

Retrosynthesis prediction, the task of identifying reactant molecules that can be used to synthesize product molecules, is a fundamental challenge in organic chemistry and related fields. To address this challenge, we propose a novel graph-to-graph transformation model, G2GT. The model is built on the standard transformer structure and utilizes graph encoders and decoders. Additionally, we demonstrate the effectiveness of self-training, a data augmentation technique that utilizes unlabeled molecular data, in improving the performance of the model. To further enhance diversity, we propose a weak ensemble method, inspired by reaction-type labels and ensemble learning. This method incorporates beam search, nucleus sampling, and top-k sampling to improve inference diversity. A simple ranking algorithm is employed to retrieve the final top-10 results. We achieved new state-of-the-art results on both the USPTO-50K data set, with a top-1 accuracy of 54%, and the larger more challenging USPTO-Full data set, with a top-1 accuracy of 49.3% and competitive top-10 results. Our model can also be generalized to all other graph-to-graph transformation tasks. Data and code are available at https://github.com/Anonnoname/G2GT_2.

Observing Noncovalent Interactions in Experimental Electron Density for Macromolecular Systems: A Novel Perspective for Protein-Ligand Interaction Research.

We report for the first time the use of experimental electron density (ED) in the Protein Data Bank for modeling of noncovalent interactions (NCIs) for protein-ligand complexes. Our methodology is based on reduced electron density gradient (RDG) theory describing intermolecular NCIs by ED and its first derivative. We established a database named Experimental NCI Database (ExptNCI; http://ncidatabase.stonewise.cn/#/nci) containing ED saddle points, indicating ∼200,000 NCIs from over 12,000 protein-ligand complexes. We also demonstrated the usage of the database in the case of depicting amide-π interactions in protein-ligand binding systems. In summary, the database provides details on experimentally observed NCIs for protein-ligand complexes and can support future studies including studies on rarely documented NCIs and the development of artificial intelligence models for protein-ligand binding prediction.

AIScaffold: A Web-Based Tool for Scaffold Diversification Using Deep Learning.

Molecular scaffolds are widely used in drug design. Many methods and tools have been developed to utilize the information in scaffolds. Scaffold diversification is frequently used by medicinal chemists in tasks such as lead compound optimization, but tools for scaffold diversification are still lacking. Here, we propose AIScaffold (https://iaidrug.stonewise.cn), a web-based tool for scaffold diversification using the deep generative model. This tool can perform large-scale (up to 500,000 molecules) diversification in several minutes and recommend the top 500 (top 0.1%) molecules. Features such as site-specific diversification are also supported. This tool can facilitate the scaffold diversification process for medicinal chemists, thereby accelerating drug design.