- Home
- Industry Solutions
- Services
- Support
- About Us
Generally, the structural information of protein is more valuable than sequence alone for determining its function. Through the three-dimensional (3D) structure of a protein, researchers can understand its biochemical function and interaction properties in molecular detail. Protein modeling shares the long-term aspiration of providing 3D atomic-level information for most proteins based on their amino acid sequences. Homology modeling has become a useful tool for the prediction of protein structure when the model protein is related to at least one other protein with both a known sequence and a known structure. At Creative Biolabs, our advanced AI-assisted platform can offer homology modeling, protein threading or fold recognition, and Ab initio quantum chemistry methods for predicting the 3D structures of proteins.
Fig.1 The four main steps of comparative protein structure modeling. (Bordoli, et al., 2008)
G protein-coupled receptors (GPCRs) are a large superfamily of integral membrane proteins involved in the regulation of a wide range of physiological functions. They are important pharmacological targets because of the breadth and importance of the physiological roles undertaken by the GPCR family. For the design of new drugs, the native structure of proteins can provide important insight into understanding their function. However, due to the paucity of crystal structures, the experimental determination of the 3D structure of GPCR membrane proteins has proved to be very difficult. Today, our AI-assisted homology modeling platform can be used for the construction of GPCR models, the study of their structure-function relationships, and the identification of lead ligands.
Antibodies are protective proteins that are produced by the immune system and play a critical role in our immune system recognizing various antigens. They have been widely used in many medical, diagnostic, and biotechnological applications. The ability to predict their high-quality 3D structures is an important component of the antibody engineering process. However, experimental determination of antibody structures is laborious and the structures of only a few hundred antibodies have been solved by X-ray crystallography. Taking advantage of the AI-assisted modeling method, we can help our customers to predict the 3D structure of antibodies of interest. Meanwhile, the quality of the resultant antibody model will be verified for better use in the design of the novel antibody.
Protein kinases are part of a huge superfamily and the key regulators of cell function. There exist many kinases and isoforms, such as PKA, PKG, and PKC32 as well as tyrosyl protein kinases. Understanding the 3D structures of protein kinases could be of great help in the rational design of specific ligands. However, there are a few crystal structures of protein kinases that have been experimentally defined. Homology modeling is the classical approach to predicting the protein kinase structures and has been widely diffused. Our AI-assisted modeling platform can build high-quality antibody homology models for the protein kinases and several methods for homology model analysis.
Fig.2 General secondary structure of kinases complexed with ATP. (Tuccinardi & Martinelli, 2011)
A protein complex is a group of two or more associated polypeptide chains and proteins are linked by non-covalent Protein-protein interactions (PPI) in the protein complex. The majority of proteins in the Protein Data Bank are homomultimeric, including many soluble and membrane proteins, which may mediate and regulate gene expression, activity of enzymes, receptors, ion channels, and cell adhesion processes. Protein-protein interactions are important for many biological processes and knowledge of the 3D structure of the multimeric protein will help to understand the underlying mechanism of protein-protein interactions and explore their function. In the past few decades, an increasing number of multi-chain protein complex structures have been determined. Creative Biolabs can use the AI-assisted platform to predict the protein interaction sites and interface residue pairs. Meanwhile, we can also help our clients to predict the protein complex structure by template-based and template-free methods, and machine/deep learning models.
References