Publication


Chemi-Net: A molecular graph convolutional network for accurate drug property prediction

Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME property prediction. To compare the relative performance of Chemi-Net with Cubist, one of the popular machine learning programs used by Amgen, a large-scale ADME property prediction study was performed on-site at Amgen. The results showed that our deep neural network method improved current methods by a large margin. We foresee that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery.

Prediction of amino acid side chain conformation using a deep neural network

A deep neural network based architecture was constructed to predict amino acid side chain conformation with unprecedented accuracy. Amino acid side chain conformation prediction is essential for protein homology modeling and protein design. Current widely-adopted methods use physics-based energy functions to evaluate side chain conformation. Here, using a deep neural network architecture without physics-based assumptions, we have demonstrated that side chain conformation prediction accuracy can be improved by more than 25%, especially for aromatic residues compared with current standard methods. More strikingly, the prediction method presented here is robust enough to identify individual conformational outliers from high resolution structures in a protein data bank without providing its structural factors. We envisage that our amino acid side chain predictor could be used as a quality check step for future protein structure model validation and many other potential applications such as side chain assignment in Cryo-electron microscopy, crystallography model auto-building, protein folding and small molecule ligand docking.

Discovery of Bisubstrate Inhibitors of Nicotinamide N-Methyltransferase (NNMT)

Nicotinamide N-methyltransferase (NNMT) catalyzes the N-methylation of pyridine-containing compounds using the cofactor S-5′-adenosyl-L-methionine (SAM) as the methyl group donor. Through the regulation of the levels of its substrates, cofactor, and products, NNMT plays important role in physiology and pathophysiology. Overexpression of NNMT has been implicated in various human diseases. Potent and selective small-molecule NNMT inhibitors are valuable chemical tools for testing biological and therapeutic hypotheses. However, very few NNMT inhibitors have been reported. Here, we describe the discovery of a bisubstrate NNMT inhibitor MS2734 (6), and characterization of this inhibitor in biochemical, biophysical, kinetic, and structural studies. Importantly, we obtained the first crystal structure of human NNMT in complex with a small-molecule inhibitor. The structure of the NNMT–6 complex has unambiguously demonstrated that 6 occupied both substrate and cofactor binding sites. The findings paved the way for developing more potent and selective NNMT inhibitors in the future.