A Method to Learn Embedding of a Probabilistic Medical Knowledge Graph: Algorithm Development (Preprint)

Abstract

BACKGROUND Knowledge graph embedding is an effective semantic representation method for entities and relations in knowledge graphs. Several translation-based algorithms, including TransE, TransH, TransR, TransD, and TranSparse, have been proposed to learn effective embedding vectors from typical knowledge graphs in which the relations between head and tail entities are deterministic. However, in medical knowledge graphs, the relations between head and tail entities are inherently probabilistic. This difference introduces a challenge in embedding medical knowledge graphs. OBJECTIVE We aimed to address the challenge of how to learn the probability values of triplets into representation vectors by making enhancements to existing TransX (where X is E, H, R, D, or Sparse) algorithms, including the following: (1) constructing a mapping function between the score value and the probability, and (2) introducing probability-based loss of triplets into the original margin-based loss function. METHODS We performed the proposed PrTransX algorithm on a medical knowledge graph that we built from large-scale real-world electronic medical records data. We evaluated the embeddings using link prediction task. RESULTS Compared with the corresponding TransX algorithms, the proposed PrTransX performed better than the TransX model in all evaluation indicators, achieving a higher proportion of corrected entities ranked in the top 10 and normalized discounted cumulative gain of the top 10 predicted tail entities, and lower mean rank. CONCLUSIONS The proposed PrTransX successfully incorporated the uncertainty of the knowledge triplets into the embedding vectors.

Knowledge-Based Biomedical Data Science

“…In more basic research applications, broad themes included the use of KGs to produce vector embeddings for prediction or visualization in low dimensional spaces (17,40,48); the use of link prediction methods over KGs to hypothesize previously unobserved relationships (38,40,42,(49)(50)(51)(52)(53)(54)(55)(56)(57)(58); and the use of KGs to generate complex mechanistic accounts of experimental data . Several efforts combined these themes, particularly the use of edge embeddings to improve link prediction (37,50,55,59,60).…”