MMP-Cliffs, SAR Transfer Series, and RECAP-MMPs: ChEMBL-Derived Molecular Data

Ye Hu from the University of Bonn presents three MMP-based data sets derived from the latest release of the ChEMBL database. The data sets include activity cliffs, structure-activity relationship (SAR) transfer series, and second generation MMPs based on retrosynthetic rules. Structural data and information are provided in eight different files comprising the three data sets, with compounds represented in canonical SMILES on a per-target basis for Ki and IC50 subsets.

Use Cases

• Predicting molecular activity cliffs based on structural similarity and potency data.
• Analyzing structure-activity relationship transfer series for drug discovery.
• Training models for retrosynthetic analysis using RECAP-MMP rules.
• Benchmarking algorithms for molecular property prediction using ChEMBL-derived data.

Strengths

• Data is derived from the latest release of the authoritative ChEMBL database.
• Data is organized into three distinct, clearly designated sets: MMP-cliffs, SAR transfer series, and RECAP-MMPs.
• Compounds are provided in canonical SMILES representation, a standard format for molecular structure.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

University of Bonn, derived from ChEMBL.

Collection Method

Derived from compounds in the ChEMBL database, processed into activity cliffs, SAR transfer series, and RECAP-MMPs.