DDI Corpus 2013

Query DDI Corpus 2013 for annotated drug–drug interactions with JSON output.

130|4|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/QSong-github/DrugClaw --skill ddi-corpus-2013
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: DDI Corpus 2013
Source: https://github.com/QSong-github/DrugClaw/tree/main/skills/drug_nlp/ddi_corpus
Command: npx skills add https://github.com/QSong-github/DrugClaw --skill ddi-corpus-2013

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly retrieve annotated drug–drug interaction information from the DDI Corpus 2013, enabling researchers to study interaction patterns without manually parsing XML data.

Core Features & Use Cases

  • Entity-level lookup: query drugs and obtain partner interactions, ddi_type, and source sentences.
  • Structured results: returns JSON with fields like canonical_names, entity_types, interactions, and example_sentences.
  • Use Case: evaluate potential interactions for a list of drugs and compare interaction types across sources (DrugBank, MedLine).

Quick Start

Query one or more drug names to retrieve their annotated DDI interactions from the corpus.

Frequently Asked Questions about DDI Corpus 2013

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

FAQPage Schema
How do I retrieve annotated drug-drug interactions from the DDI Corpus 2013?

To retrieve drug-drug interactions from the DDI Corpus 2013, query one or more drug names to obtain partner interactions, ddi_type, and source sentences parsed directly from XML-annotated data.

How do I extract drug interaction types and partner entities from biomedical XML corpora?

Extracting drug interaction types and partner entities from biomedical XML corpora involves querying annotated drug names to return structured JSON fields containing ddi_type, partner interactions, and source labels.

Can I compare drug interactions across DrugBank and MedLine sources in the DDI Corpus?

Yes, you can compare drug interactions across DrugBank and MedLine sources, as querying the DDI Corpus returns structured JSON results that include source labels for each annotated interaction.

What is the best way to query biomedical NLP corpora for drug-drug interactions without manual XML parsing?

The best way to query biomedical NLP corpora for drug-drug interactions without manual XML parsing is using an index-based retrieval skill that returns JSON-formatted outputs with interaction details and example sentences.

How do I limit the number of returned interactions and sentences when querying the DDI Corpus?

You can limit the number of returned interactions and sentences when querying the DDI Corpus by applying configurable maximum limits during the local index-based retrieval process.

Does the DDI Corpus 2013 skill return structured JSON output for entity-level drug interactions?

Yes, the DDI Corpus 2013 skill returns structured JSON output for entity-level drug interactions, providing fields like canonical_names, entity_types, interactions, and example_sentences.