drug-discovery

Query ChEMBL and PubChem to analyze drug-like compounds and rank candidates by Lipinski Ro5 and Veber rules.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/zulumonkeymetallic/bob --skill drug-discovery-zulumonkeymetallic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/zulumonkeymetallic/bob/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/zulumonkeymetallic/bob --skill drug-discovery-zulumonkeymetallic

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Pharmaceutical researchers often spend excessive time collecting public bioactivity data and evaluating drug-likeness for candidate molecules. This Skill centralizes data retrieval, property calculation, and safety context to accelerate lead identification and decision-making.

Core Features & Use Cases

  • Bioactivity data retrieval: query ChEMBL and PubChem for target-associated activity and compound properties to prioritize bioactive candidates.
  • Property-based screening: compute and present molecular weight, LogP, HBD/HBA, and TPSA to assess drug-likeness using Ro5 and Veber criteria.
  • ADMET & safety context: surface OpenFDA safety signals and OpenTargets disease associations to inform risk-aware lead selection.
  • Use Case: a medicinal chemistry team can quickly screen a list of molecules, rank by Ro5/Veber compliance, and surface safety constraints for progression decisions.

Quick Start

Evaluate a list of candidate molecules for Ro5/Veber compliance and OpenFDA/OpenTargets safety insights.

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 drug-likeness using Lipinski Ro5 and Veber rules?

Drug-likeness screening applies Lipinski Ro5 and Veber rules to evaluate molecular weight, LogP, HBD/HBA, and TPSA. This assesses candidate molecules for oral bioavailability and identifies optimization opportunities in medicinal chemistry.

How do I retrieve bioactivity data from ChEMBL and PubChem for target-associated compounds?

Bioactivity data retrieval queries ChEMBL and PubChem databases to extract target-associated activity and compound properties. This prioritizes bioactive candidates by centralizing public bioactivity data for pharmaceutical research.

Can I integrate OpenFDA safety signals into lead selection and risk assessment?

OpenFDA safety signals integrate into lead selection by surfacing safety constraints and risk assessment data. This informs risk-aware decisions during the progression of drug-like compounds in medicinal chemistry tasks.

What is the best way to rank drug candidates using ADMET considerations and disease associations?

Ranking drug candidates uses ADMET considerations and OpenTargets disease associations to inform lead selection. This surfaces optimization opportunities by evaluating bioactivity, safety context, and disease links for candidate molecules.

How do I assess drug-like compounds when bioactivity data collection takes too much time?

Assessing drug-like compounds accelerates by centralizing data retrieval, property calculation, and safety context. This evaluates bioactivity from ChEMBL and PubChem alongside Ro5 compliance to speed up lead identification decisions.