Structured Dataset of Traditional Efficacies for Chinese Herbal Medicines

This dataset provides a structured table of traditional therapeutic effects (efficacies) for Traditional Chinese Medicine (TCM) herbs. It addresses the issue of semantic ambiguity in natural language efficacy descriptions by converting them into standardized, computable formats. Dataset Content: The dataset consists of standardized entries linking herbs to their therapeutic effects, categorized into two types: Explicit Efficacy Nodes: Core therapeutic effects structured directly from authoritative TCM textbooks (e.g., Chinese Materia Medica). Expanded Efficacy Nodes (Inferred): Implicit therapeutic effects generated through rule-based semantic reasoning mechanisms (Rules A, B, C, D) based on a TCM knowledge graph. These nodes explicitly link herbs to specific symptoms or sub-patterns that are logically implied by their core functions. Data Structure: The data is provided in .csv format (UTF-8 encoded) with the following fields: Chinese Herb Code & Name Efficacy ID & Name (Standardized) Node Type (Classifies the source: Explicit vs. Expanded Rules) Potential Applications: This resource is intended for researchers in TCM informatics, biomedical knowledge graphs, and AI-based prescription analysis. It supports tasks such as formula efficacy prediction, symptom-herb association mining, and computational reasoning. ContactFor questions, please contact:LI Yuanbai:[e-mail]