Computational Screening for Active Compounds Targeting Protein Sequences: Methodology and Experimental Validation

• Published in: Journal of chemical information and modeling Vol. 51; no. 11; pp. 2821 - 2828
• Main Authors: Wang, Fei, Liu, Dongxiang, Wang, Heyao, Luo, Cheng, Zheng, Mingyue, Liu, Hong, Zhu, Weiliang, Luo, Xiaomin, Zhang, Jian, Jiang, Hualiang
• Format: Journal Article
• Language: English
• Published: Washington, DC American Chemical Society 28.11.2011
• Subjects: 3-D technology; Analytical, structural and metabolic biochemistry; Binding Sites; Biological and medical sciences; Chemical compounds; Chemical Information; Cloning, Molecular; Computational Biology - methods; Computational Biology - statistics & numerical data; Databases, Factual; Drug Discovery; Escherichia coli; Fundamental and applied biological sciences. Psychology; General aspects, investigation methods; General pharmacology; Glycogen Synthase Kinase 3 - antagonists & inhibitors; Glycogen Synthase Kinase 3 - chemistry; Glycogen Synthase Kinase 3 - genetics; Glycogen Synthase Kinase 3 beta; HEK293 Cells; Humans; Interactions. Associations; Intermolecular phenomena; Ligands; Medical sciences; Models, Chemical; Molecular biophysics; Molecules; p38 Mitogen-Activated Protein Kinases - antagonists & inhibitors; p38 Mitogen-Activated Protein Kinases - chemistry; p38 Mitogen-Activated Protein Kinases - genetics; Pharmaceutical technology. Pharmaceutical industry; Pharmacology. Drug treatments; Protein Binding; Proteins; R&D; Receptors, G-Protein-Coupled - antagonists & inhibitors; Receptors, G-Protein-Coupled - chemistry; Receptors, G-Protein-Coupled - genetics; Recombinant Proteins - antagonists & inhibitors; Recombinant Proteins - chemistry; Recombinant Proteins - genetics; Research & development; Sirtuin 1 - antagonists & inhibitors; Sirtuin 1 - chemistry; Sirtuin 1 - genetics; Small Molecule Libraries - chemistry; Small Molecule Libraries - metabolism; Small Molecule Libraries - pharmacology; Structure in molecular biology; Support Vector Machine; Transfection; Transformation, Bacterial; Tridimensional structure; Validation; Ligand binding; Ligand; Virtual screening; Molecular interaction; Medical screening; Experimental study; Modeling; Computational chemistry; Binding protein; Biopolymer; Vector support machine; Pharmaceutical industry; Bioinformatics
• ISSN: 1549-9596; 1549-960X
• DOI: 10.1021/ci200264h

The three-dimensional (3D) structures of most protein targets have not been determined so far, with many of them not even having a known ligand, a truly general method to predict ligand–protein interactions in the absence of three-dimensional information would be of great potential value in drug discovery. Using the support vector machine (SVM) approach, we constructed a model for predicting ligand–protein interaction based only on the primary sequence of proteins and the structural features of small molecules. The model, trained by using 15 000 ligand–protein interactions between 626 proteins and over 10 000 active compounds, was successfully used in discovering nine novel active compounds for four pharmacologically important targets (i.e., GPR40, SIRT1, p38, and GSK-3β). To our knowledge, this is the first example of a successful sequence-based virtual screening campaign, demonstrating that our approach has the potential to discover, with a single model, active ligands for any protein.