ProteinKG65

ProteinKG65 is a large-scale knowledge graph dataset for protein science. It aligns protein sequences with functional and ontological knowledge (from Gene Ontology, GO) and is compatible with structured knowledge, sequences, and textual descriptions. It aims to provide an integrated knowledge foundation—combining structured biological knowledge with sequence annotations—for tasks such as protein structure prediction, function prediction, protein–protein and protein–drug interaction analysis, and protein-related semantic question answering. The dataset contains more than 5.6 million entries.