Screening Compound Database

The data sources for small-molecule virtual screening are rich and diverse, with scales ranging from millions to tens of billions. However, data quality, structural coverage, standardization, and procurement costs remain core industry bottlenecks that directly impact the efficiency and hit rate of virtual screening. To address these challenges, AnyMol has meticulously curated a premier Screening Compound Database. By aggregating novel drug-like molecules from nearly 1,000 specialized laboratories across dozens of countries, we provide a stable, reliable, and high-quality foundation of tens of millions of compounds. Our database underwent deep data cleaning and standardization—utilizing the SDF standard format and eliminating structural errors—while maintaining dynamic updates on stock availability. Currently, the database features approximately 26 million compounds and over 50,000 novel scaffolds, offering comprehensive coverage across diverse structural types including FDA-approved and clinical-stage drugs, natural products and derivatives, active inhibitors, molecular glues, covalent inhibitors, and drug-like screening sets. To meet specific research needs regarding screening scale and structural richness, the database is further categorized into Core, Curated, and Extended Libraries, allowing it to adapt flexibly to various virtual screening scenarios and effectively accelerate drug discovery.