chembl-bioactivity

Retrieve ChEMBL bioactivity data and generate standardized SAR-ready tables.

33|6|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill chembl-bioactivity
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chembl-bioactivity
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/02-chemistry/chembl-bioactivity
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill chembl-bioactivity

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chembl-webresource-client, pandas, matplotlib, numpy, rdkit, seaborn.

What problem does it solve?

It helps you retrieve and analyze ChEMBL bioactivity measurements (such as IC50, Ki, and pChEMBL) so you can build clean SAR datasets and interpret structure–activity relationships without manual scraping.

Core Features & Use Cases

  • Target lookup & selection: Find ChEMBL targets by keyword (e.g., a gene/protein synonym) and filter to a relevant organism/target type.
  • Bioactivity retrieval: Pull activity records for a chosen target, focusing on standard types (IC50/Ki/Kd) and optionally filtering by minimum pChEMBL.
  • SAR analysis & visualization: Compute activity distributions and generate quick SAR-ready tables (including RDKit descriptors) and correlation plots; also supports activity-cliff detection using structural similarity plus potency gaps.

Quick Start

Use this Skill to query ChEMBL for EGFR (CHEMBL203) IC50 and Ki bioactivity, standardize values to pChEMBL, and output a dataset plus an SAR summary table for downstream QSAR modeling.

Frequently Asked Questions about chembl-bioactivity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retrieve ChEMBL bioactivity data and prepare it for SAR analysis?

You retrieve ChEMBL bioactivity records for a specific target via the ChEMBL REST API, extract standard activity fields like IC50 and Ki, and normalize them to pChEMBL to produce SAR-ready tables for QSAR modeling.

What does pChEMBL normalization mean for QSAR datasets?

pChEMBL normalization converts raw IC50 and Ki measurements into a standardized logarithmic scale, enabling consistent descriptor–activity correlation analysis and accurate QSAR dataset construction across diverse bioactivity records.

Can I use RDKit to compute molecular descriptors for ChEMBL bioactivity data?

Yes, you can use RDKit to optionally compute molecular descriptors for retrieved ChEMBL bioactivity data, generating correlation plots and SAR-ready tables to support structure-activity relationship workflows.

How do I detect activity cliffs using ChEMBL bioactivity and structural similarity?

You detect activity cliffs by analyzing retrieved ChEMBL bioactivity records to identify structurally similar compounds with significant potency gaps, combining RDKit similarity calculations with pChEMBL value differences.

Does this method require the chembl-webresource-client to access the ChEMBL REST API?

Yes, accessing the ChEMBL REST API through chembl-webresource-client is required to query targets by keyword, filter by organism, and pull standard activity records for SAR dataset construction.

What is the best way to visualize structure-activity relationships from ChEMBL data?

The best way to visualize SAR from ChEMBL data is using pandas, matplotlib, and seaborn to compute activity distributions and generate correlation plots from RDKit molecular descriptors and normalized pChEMBL values.