drug-discovery

Search ChEMBL and PubChem for bioactivity and molecular property data.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/big4council-prog/b4c-agent --skill drug-discovery-big4council-prog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/big4council-prog/b4c-agent/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/big4council-prog/b4c-agent --skill drug-discovery-big4council-prog

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

It helps researchers quickly search for relevant bioactive compounds, estimate drug-likeness properties, and gather interaction/adverse-event signals without manually stitching together multiple resources.

Core Features & Use Cases

  • Bioactive compound discovery (ChEMBL): Find targets and retrieve top active molecules and activity snapshots to support lead-hunting and hypothesis generation.
  • Drug-likeness screening (Lipinski Ro5 + Veber): Compute key oral-bioavailability-related properties (e.g., MW, LogP, HBD/HBA, TPSA, rotatable bonds) and flag likely rule violations.
  • Interaction & safety signals (OpenFDA): Look up reported drug-drug interaction snippets and adverse event frequencies to inform de-risking.
  • Target/disease association (OpenTargets): Identify gene/target associations with diseases to connect mechanistic targets to clinical relevance.
  • Use case: Given a target (e.g., EGFR), a candidate molecule name or identifier, and a proposed drug name, screen bioactivity, evaluate oral-likeness, and pull interaction/adverse-event signals to prioritize next experiments.

Quick Start

Ask the skill to screen the candidate molecule for Lipinski Ro5 and Veber and summarize the rule outcomes using public property data.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I screen molecules for Lipinski Ro5 and Veber drug-likeness properties?

To screen molecules for Lipinski Ro5 and Veber drug-likeness, this Skill computes oral-bioavailability properties like MW, LogP, HBD/HBA, TPSA, and rotatable bonds using public data to flag rule violations.

What is the best way to find bioactive compounds for a specific target like EGFR?

Finding bioactive compounds for a specific target involves searching ChEMBL to retrieve top active molecules and activity snapshots, supporting lead-hunting and hypothesis generation for drug discovery decision-making.

Can I look up drug-drug interaction and adverse event signals using OpenFDA data?

Yes, you can look up drug-drug interaction and adverse event signals using OpenFDA data to retrieve reported interaction snippets and event frequencies, which informs safety de-risking during compound evaluation.

Do I need API keys to access ChEMBL, PubChem, and OpenTargets for compound discovery?

No, you do not need API keys for compound discovery because this Skill operates with public, no-auth API access to ChEMBL, PubChem, OpenFDA, and OpenTargets for deterministic retrieval and parsing.

How do I connect mechanistic targets to clinical relevance during drug discovery?

To connect mechanistic targets to clinical relevance during drug discovery, identify gene and target associations with diseases using OpenTargets to link target mechanisms to clinical outcomes.

What are the limitations of using public APIs for drug-likeness screening?

Limitations of using public APIs for drug-likeness screening include relying on unauthenticated endpoints for deterministic retrieval, which may constrain batch sizes, parsing speed, and real-time safety signal coverage.