SemKraph KG: Pipeline Input Datasets

SemKraph KG: Pipeline Input Datasets SemKraph KG (normalized SemMedDB + iKraph) and the SemKraph CM Subgraph (Complementary Medicine seeds + 1-hop neighborhood) using the semkraphkg-pipeline. These KGs are intended to provide comprehensive literature-mined knowledge for general medicine and complementary medicine, respectively. About the Project COMBINI (Connecting Complementary Medicine and Biological Knowledge to support Integrative Health) is a multi-institutional project (University of Illinois/NCSA, University of Minnesota, Mayo Clinic) funded by the NIH/NCCIH. The objective of the project is to develop informatics methods and resources that consolidate evidence on complementary medicine, integrate it with conventional medicine in an AI-ready format, and enable knowledge management and scientific discovery in complementary and integrative health. Knowledge Graph Sources: SemMedDB: NLM repository of semantic predications from PubMed citations. iKraph: Specialized biomedical relation and entity graph. COMBO Ontology: SKOS-enriched ontology of complementary medicine concepts and mapping links. Files Included Component File Description SemMedDB concept.csv UMLS concept metadata predication.csv.gz Gzipped semantic triples from literature iKraph DBRelations.json Relationship records NER_ID_dict_cap_final.json Name-to-ID lookup dictionary PubMedList.json Citation mapping list RelTypeInt.json Relation type indices COMBO COMBO_20260115_with_skos.owl OWL ontology with SKOS annotations & UMLS mapping anchors Mapping ikraph_reltype_to_biolink_mapping_review.xlsx Excel sheet mapping iKraph relations to Biolink predicates How to Use Run the automatic download utility from the pipeline repository root: pip install -r requirements.txt python3 cli.py download \ --semmed-dir data/semmed \ --ikraph-dir data/ikraph \ --combo-dir data/combo \ --reltype-xlsx ikraph_reltype_to_biolink_mapping_review.xlsx (Alternatively, place the files manually in the corresponding directories above.)