Chemical Drug Design Service

Drug design is based on computer chemistry, through computer simulation, calculation and budgeting of the relationship between drugs and receptor biomacromolecules, the method of designing and optimizing lead compounds. Computer-aided drug design is actually the optimization and design of lead compounds by simulating and calculating the interaction between receptors and ligands. Computer-aided drug design generally includes active site analysis, database search, and new drug design.

Figure 1. Computer-aided drug design.

Principle

The general principle of drug design is to first obtain the structure of the receptor macromolecule binding site through X-single crystal diffraction technology and other techniques, and use molecular simulation software to analyze the structural properties of the binding site, such as electrostatic field, hydrophobic field, and hydrogen bonding site. Point distribution and other information. Then use database search or new drug molecular design technology to identify molecules whose molecular shape and physical and chemical properties match the receptor site, synthesize and test the biological activity of these molecules. After several rounds of cycles, new lead compounds can be discovered . Therefore, computer-aided drug design generally includes active site analysis, database search, and new drug design.

Overall solutions

Traditional drug design method

• De Novo design
  De Novo design is one of the most widely used drug design methods to discover new potentially active compounds, which can save researchers a lot of time. This powerful design tool allows users to simulate screening before experimental analysis, and modification of existing compounds. It contains a drug-like fragment library, and also allows users to add their own molecular fragments to the fragment library.
• Fragment-based Drug Design
  Compared with the screening of macromolecules, fragment-based drug design has a high screening hit rate that can achieve the treatment of complex targets, especially those involving protein-protein interaction targets. In addition, these fragments are small in size and highly soluble, and generally have better pharmaceutical properties.
• Structure-based Drug Design
  Structure-based drug design (or direct drug design) relies on knowledge of the three dimensional structure of the biological target obtained through methods such as x-ray crystallography or NMR spectroscopy.
• Multi-target drug design
  The advantage of multi-target drug design technology is to provide new ideas for the development of new drugs, make full use of the structural information of known compounds, and to a certain extent avoid the waste of research and development resources, and speed up the development of new drugs. Drug development. It has strong feasibility and broad development prospects, and may become an important tool for new drug research and development.

AI-based Algorithm

Artificial intelligence (AI) technologies, especially new methods such as deep generative models, have shown bright prospects in the de novo molecular design of new drug development, and also in other difficult issues such as hit-to-lead structural modification and compound drug-making optimization. Will play an increasingly important role. Through the use of statistical language models and transfer learning ideas in natural language processing, the docking is processed. In the construction of AI model, CD ComputaBio uses the long and short-term memory (LSTM) neural network model that is commonly used in natural language processing problems in current generative models. We can build an LSTM neural network composed of an LSTM layer, a Dropout layer, a TimeDistributed layer and a Softmax layer. As a typical Recurrent Neural Network (RNN) model, LSTM is suitable for dealing with the problem of using standard SMILES format to describe molecular structure generation, and its gated structure can also learn the characteristic properties of molecules when the SMILES formula is longer.

CD ComputaBio have cooperated with many universities or research institutions and can consult industry experts for their opinions and suggestions on some complex issues. Our drug design team is a highly professional, efficient and well-established R&D team.