skills.rest
ZardLi1115
ZardLi1115COMMUNITY
Explore all skills by this author →
GitHub

drug-discovery

Retrieve bioactivity and molecule property data from public biomedical databases.

4|Updated May 18, 2026
Search Tags:#drug discovery#ChEMBL#medicinal chemistry#cheminformatics#ADMET#PubChem#OpenFDA
One-click install
npx skills add https://github.com/ZardLi1115/zedclaw --skill drug-discovery-zardli1115
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/ZardLi1115/zedclaw/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill drug-discovery-zardli1115

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Drug-discovery research often stalls on slow, repetitive gathering of basic molecule properties, target-linked bioactivity, and early interaction/safety signals from public biomedical databases.

Core Features & Use Cases

  • Bioactive compound and target search (ChEMBL): Find targets and retrieve top bioactivity records to support hit/lead exploration and literature-style evidence gathering.
  • Drug-likeness scoring (Lipinski Ro5 + Veber): Quickly assess oral-likeness using physicochemical proxies like MW, LogP, HBD/HBA, TPSA, and rotatable bonds.
  • Safety and interaction signals (OpenFDA): Look up reported drug-drug interaction text and adverse event terms to inform risk-aware iteration.
  • ADMET-style reasoning support with references: Provides an ADMET guide (CYP450 metabolism, hERG risk heuristics, and mitigation ideas) to structure interpretation and follow-up questions.

Quick Start

Use the drug-discovery skill to evaluate a candidate by first retrieving its ChEMBL identity/properties, then checking Ro5 and Veber drug-likeness, and finally summarizing OpenFDA interaction/adverse-event snippets relevant to the molecule name you provide.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I retrieve compound bioactivity data from ChEMBL for drug discovery?▼

To retrieve compound bioactivity data, the drug discovery process queries ChEMBL by specified targets to extract top bioactivity records, supporting hit and lead exploration with structured literature-style evidence.

How do I check drug-likeness using Lipinski Ro5 and Veber rules?▼

You can check drug-likeness by computing physicochemical proxies including MW, LogP, HBD/HBA, TPSA, and rotatable bonds against Lipinski Ro5 and Veber thresholds to quickly assess oral-likeness for candidate molecules.

Can I use OpenFDA to look up adverse event terms and drug-drug interactions?▼

Yes, you can use OpenFDA to look up reported drug-drug interaction text and adverse event terms, allowing you to gather early safety signals and inform risk-aware iteration during lead optimization.

What is ADMET-style analysis and how do CYP450 and hERG heuristics guide it?▼

ADMET-style analysis interprets absorption, distribution, metabolism, excretion, and toxicity risks using CYP450 metabolism and hERG risk heuristics, structuring safety interpretation and mitigation ideas for medicinal chemistry.

Does this drug discovery workflow require any specialized software dependencies?▼

No specialized software dependencies are required; the workflow applies drug-likeness rule filters and interprets safety information using public endpoints and computed physicochemical thresholds guided by included reference notes.

What is the best way to structure early drug discovery decisions using public biomedical databases?▼

The best way to structure early drug discovery decisions is retrieving ChEMBL identities, checking Ro5 and Veber drug-likeness, and summarizing OpenFDA interaction snippets to iterate on lead optimization ideation.

Related Skills

Explore More Education & Research Skills→
royhenengelroyhenengel

notion-create-database-row

Insert rows into Notion databases using natural-language property values.

Community
Intermediate
jackspacejackspace
16

medchem

Apply Lipinski, Veber, CNS, leadlike, PAINS filters to prioritize molecular libraries.

Community
Advanced
Runchuan-BURunchuan-BU
401

query-opentarget

Queries OpenTargets Platform for drug-target associations and disease-gene evidence via structured GraphQL responses.

Community
Intermediate
InternScienceInternScience
28

molclaw-quickvina-docking

Performs GPU-accelerated molecular docking and generates pose files with affinity values.

Official
Advanced