MD Anderson Cancer Center logo Lyda Hill logo Cancer Research UK logo logo

can SAR .ai

The integrated knowledge-base that brings together multidisciplinary data across biology, chemistry, pharmacology, structural biology, cellular networks and clinical annotations, and applies machine learning approaches to provide drug-discovery useful predictions.

We are in a transition period moving to MD Anderson Cancer Center. There might be glitches while we finalize this and if you find any issues, please contact us via email

Version: 1.6.4

Chemical Search

Substructure and similarity searches against
the chemical database
Chemical Search Image
Advanced Search image
Advanced Search image

Advanced Search

  • Protein
  • Cell Lines
  • Drugs & Compounds
  • Diseases
  • 3D Structures
  • Protein Families
Advanced Search image

FUNDING is made possible through the help of:

MD Anderson Cancer Center LydaHill Philanthropies Foundation CRUK


Organizations that help with data:

DepMap PDBe DataBank ChEMBL Chemical Probes Portal


Kindly cite canSAR:

canSAR: update to the cancer translational research and drug discovery knowledgebase, Costas Mitsopoulos, Patrizio Di Micco, Eloy Villasclaras Fernandez, Daniela Dolciami, Esty Holt, Ioan L. Mica, Elizabeth A. Coker, Joseph E. Tym, James Campbell, Ka Hing Che, Bugra Ozer, Christos Kannas, Albert A. Antolin, Paul Workman, Bissan Al-Lazikani, Nucl. Acids Res. 2021 Jan 8;49(D1):D1074-D1082. doi: 10.1093/nar/gkaa1059

Latest data release for

Release date: Sep 20, 2023

3D Structures: 193,963 (added 298)
PDB bioassemblies: 1,536,221 (added 2,520)
PDB Chains: 553,580 (added 1,048)
Cavities in PDB chains: 5,928,958 (added 10,433)
Druggable Cavities: 237,405 (added 317)
Protein families: 7,369 (added 1)

Find out more