skills.rest
eddielueng
eddieluengCOMMUNITY
Explore all skills by this author →
GitHub

drug-discovery

Search ChEMBL for targets and bioactivities, estimate drug-likeness via PubChem, and check safety signals via OpenFDA.

1|Updated Apr 14, 2026
Search Tags:#drug discovery#ChEMBL#medicinal chemistry#cheminformatics#drug-likeness#ADMET#openFDA
One-click install
npx skills add https://github.com/eddielueng/hermes-agent-zh --skill drug-discovery-eddielueng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill drug-discovery-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It helps researchers quickly gather actionable pharmaceutical research information by retrieving bioactive targets and compounds, estimating drug-likeness properties, and checking safety-leaning interaction and adverse-event signals from public biomedical datasets.

Core Features & Use Cases

  • ChEMBL bioactive search & retrieval: Find targets and pull top activities and molecule-level properties (e.g., identifiers, SMILES, molecular weight, basic physicochemical features).
  • Drug-likeness screening (Lipinski Ro5 + Veber): Evaluate oral bioavailability heuristics using Lipinski Rule of Five and Veber constraints from PubChem-derived properties.
  • Safety and interaction lookups (OpenFDA): Query reported drug-drug interaction text from FDA labels and retrieve adverse event summaries for a drug product name.
  • Additional context (OpenTargets): Identify gene/target-to-disease associations to support early hypothesis building and target validation.
  • Use Case: If you are comparing candidate molecules for early lead optimization, you can (1) locate relevant targets/actives in ChEMBL, (2) screen physicochemical liabilities with Ro5/Veber, (3) check interaction/adverse-event signals via OpenFDA, and (4) corroborate relevance with OpenTargets.

Quick Start

Ask for a molecule assessment by telling the assistant: "Screen aspirin for Lipinski Ro5 and Veber using PubChem properties, then summarize related adverse-event and interaction signals from OpenFDA labels."

Frequently Asked Questions about drug-discovery

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

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

To screen drug-likeness, this Skill retrieves molecular properties from PubChem and computes Lipinski Rule of Five and Veber constraints to estimate oral bioavailability heuristics. It evaluates physicochemical liabilities for early lead optimization candidates.

How does ChEMBL bioactive search work for finding drug targets and activities?▼

ChEMBL bioactive search works by querying public APIs to retrieve relevant biological targets and pull top bioactivities alongside molecule-level properties like SMILES and molecular weight. It helps researchers gather actionable pharmaceutical data for medicinal chemistry investigations.

Can I check adverse event signals and drug interactions using openFDA data?▼

Yes, you can check adverse event signals using openFDA data by querying reported drug-drug interaction text from FDA labels and retrieving adverse event summaries for a specific drug product. This supports early safety context building during lead optimization.

What is the best way to find gene target-to-disease associations for early hypothesis building?▼

The best way to find gene target-to-disease associations is using OpenTargets context within the drug discovery workflow. It identifies relevant biological links to support target validation and early hypothesis building across diseases.

Do I need API keys to retrieve public drug discovery knowledge from ChEMBL and PubChem?▼

No API keys are needed because the Skill operates entirely on free public APIs including ChEMBL, PubChem, OpenFDA, and OpenTargets. It retrieves bioactive targets, molecular properties, and safety signals without external dependencies or setup.

What are the limitations of using public APIs for ADMET context building in medicinal chemistry?▼

Limitations include relying only on free public datasets for ADMET context, meaning early safety signals are heuristic rather than clinically validated. The Skill provides interpretable outputs with source citations but cannot replace certified pharmacological testing.

Related Skills

Explore More Education & Research Skills→
mims-harvardmims-harvard
1.6k

tooluniverse-chemical-compound-retrieval

Retrieve and validate chemical compound data from PubChem and ChEMBL APIs.

Official
Intermediate
ZardLi1115ZardLi1115
4

drug-discovery

Retrieve bioactivity and molecule property data from public biomedical databases.

Community
Intermediate
galeepgaleep

rowan

Automate molecular modeling and medicinal chemistry workflows through a Python API.

Community
Advanced
biomaps-infrabiomaps-infra

lib-deepchem

Trains and applies DeepChem machine learning models for molecular property prediction.

Official
Advanced