I am new to AmpliGraph Embedding. I want to know, will AmpliGraph Embedding accurately generate embedding of a protein sequence? I was exploring the ScoringBasedEmbeddingModel used in Ampligraph Embedding and uses the TransE scoring method. TransE is developed on the text-based knowledge base. So the question arises, how any text based embedding model can generate embedding accurately for a protein or kinase enzyme in the knowledge graph data like ?
Hi
I am new to AmpliGraph Embedding. I want to know, will AmpliGraph Embedding accurately generate embedding of a protein sequence? I was exploring the ScoringBasedEmbeddingModel used in Ampligraph Embedding and uses the TransE scoring method. TransE is developed on the text-based knowledge base. So the question arises, how any text based embedding model can generate embedding accurately for a protein or kinase enzyme in the knowledge graph data like ?
I was trying to get the embedding of the protein sequences of Protein Knowledge graph data https://www.zjukg.org/project/ProteinKG25/