AI-assisted mining of biomedical literature
PubMiner AI is a scalable, AI-enabled workflow designed to facilitate the extraction of valuable information from extensive scientific publications. It uses the Retrieval Augmented Generation (RAG) approach, with a structured knowledge graph in the retrieval step and is hosted on the Databricks platform which provides smooth integration of processing resources on the cloud. By pulling data from interlinked sources like PubMed, SemMedDB, and Graphwise’s LinkedLifeData (LLD) Inventory datasets, PubMiner AI can focus only on the most relevant biomedical information. The system recognizes biological terms such as gene, protein, and enzymes and extracts their interactions described in the document through natural language processing. The extracted interactions are further analyzed with a set of features of each entity that were collected from the related public databases to infer more interactions from the original interactions. An inferred interaction from the interaction analysis and native interaction are provided to the user with the link of literature sources
