Hybrid of the above

Data mining, Fragments-in-Structural-environments, Deep learning, De novo design, Ligand-based screening, Free energy perturbati

FRASE-bot is a computational platform enabling de novo construction of small-molecule ligands directly in the binding pocket of a target protein. It makes use of machine learning to distill 3D information relevant to the protein of interest from thousands of 3D protein-ligand complexes in the Protein Data Bank (PDB) and respective structure-activity relationships (SAR). In the first step of FRASE-based design, the target protein is seeded with ligand fragments through screening of FRASE database. DeepSPLIF, an original graph-convolutional neural network model, is used to recongnize most relevant, native-like fragment poses. Next, the seeded fragments are exploited to inform either (i) de novo design of 3D ligand structures or (ii) ultra-large-scale virtual screening of commercially available compounds. We introduce TransFusion, a unique 3D chemical transformer, to generate novel chemical ligands satisfying structural and geometric constraints imposed by seeded fragments. FRASE-bot can be considered as a step toward a "virtual medicinal chemist". It exploits the concept of FRAgments in Structural Environments (FRASE) developed by Kireev group and applied to design potent in vivo antitumor agents [1]. Most recently, FRASE-bot was used to identify small-molecule ligands for Calcium and Integrin Binding protein 1 (CIB1) [2], a promising target against triple negative breast cancer (TNBC). The signaling function of CIB1 relies on protein-protein interactions and its structure does not feature any natural ligand-binding pocket. No small-molecule CIB1 inhibitors have been reported yet. [1] Da, C.; Zhang, D.; Stashko, M.; Vasileiadi, E.; Parker, R. E.; Minson, K. A.; Huey, M. G.; Huelse, J. M.; Hunter, D.; Gilbert, T. S. K.; Norris-Drouin, J.; Miley, M.; Herring, L. E.; Graves, L. M.; Deryckere, D.; Earp, H. S.; Graham, D. K.; Frye, S. V.; Wang, X.; Kireev, D. Data-Driven Construction of Antitumor Agents with Controlled Polypharmacology. J. Am. Chem. Soc. 2019, 141, 15700–15709. [2] Leisner, T. M.; Freeman, T. C.; Black, J. L.; Parise, L. V. CIB1: A Small Protein with Big Ambitions. FASEB J. 2016, 30, 2640–2650.

FRASE-bot

Pipeline Pilot, Schrodinger suite

KNIME, RDKit, PyTorch

1) Da et al, Data-Driven Construction of Antitumor Agents with Controlled Polypharmacology. J. Am. Chem. Soc. 2019, 141, 15700–15709 2) Da, C.; Kireev, D. Structural Protein–Ligand Interaction Fingerprints (SPLIF) for Structure-Based Virtual Screening: Method and Benchmark Study. J. Chem. Inf. Model. 54, 2555–2561. 3) Da, C.; Stashko, M.; Jayakody, C.; Wang, X.; Janzen, W.; Frye, S.; Kireev, D. Discovery of Mer Kinase Inhibitors by Virtual Screening Using Structural Protein–Ligand Interaction Fingerprints. Bioorg. Med. Chem. 2015, 23, 1096–1101. 4) Kireev, D. ChemNet: A Novel Neural Network Based Method for Graph/Property Mapping. J. Chem. Inf. Comput. Sci. 1995, 35, 175–180.