Sign in to view source links and access this dataset
Description
13,886 sdMMP-cliffs and 8,140 sdRMMP-cliffs across 93 and 73 biological target sets, respectively, are provided. The data, compiled by Huabin Hu at the University of Bonn, includes ChEMBL IDs, target names, PubChem assay IDs, and SMILES representations for active and inactive compounds forming activity cliffs.
Use Cases
Predicting molecular potency cliffs based on structural similarity and target set context.
Analyzing the distribution of activity cliffs across specific biological targets mentioned in the description.
Training models to identify isdMMP-cliffs and isdRMMP-cliffs from compound structures and assay data.
Strengths
Provides a substantial collection of 13,886 sdMMP-cliffs and 8,140 sdRMMP-cliffs.
Covers a wide range of 93 and 73 distinct biological target sets.
Includes specific identifiers (ChEMBL ID, PubChem AID/CID) and structural representations (SMILES) for each compound.
Limitations
Column-level documentation is absent; field semantics must be inferred after download.
Row count for the full dataset is unknown, which may limit suitability assessment.
Last update date is unknown; freshness unverified.