Combinatorial Chemistry-based Small Molecule Database (CCSMD)
name：Combinatorial Chemistry-based Small Molecule Database (CCSMD)
The small molecule database is an important cornerstone for the development of new drugs. This database uses the core structures of dozens of mature drugs on the market, thousands of unique small molecules building blocks, and commercialized molecular building blocks, using machine learning models and mature Simple chemical reaction for intelligent splicing and combination to obtain a new combination of small molecules. At the same time, the RDKIT package in Python was used to predict and aggregate the new combination of small molecules to establish a combined chemical small molecule database (CCSMD) with a compound capacity of hundreds of thousands. The CCSMD database system is used to store combined data sets and analyze web portals, including functional modules such as storage, retrieval, and analysis annotations. The magnitude of the database has reached hundreds of thousands, and with the increase of its own small molecule data fragments, it will continue to update and expand the magnitude of the database. The final volume of the small molecule database will reach more than one million. CCSMD provides the physical and chemical properties of all small molecules, which can be selected through the Lipinskis Rules of Five or by using different search conditions to obtain a collection of a large number of combined molecules. The collection of data can be obtained from the PDB protein structure database to obtain the target protein structure Virtual screening based on protein structure is performed on the active sites, and the molecules with the highest comprehensive scores are screened out. For the selected high-ranking molecules, contact the background to obtain the synthesis path of the molecule, assemble the target molecule according to the combined synthesis path, and then conduct the biological activity evaluation. This database system provides a data cornerstone and compound source for discovering new active small molecule lead compounds.