Fig. 1

The overall flowchart demonstrates the process steps involved in the study, which are divided into five key stages. The first phase is data sourcing and preprocessing, which utilizes datasets such as NCBI-Disease, BC5CDR, and BC4CHEMD and employs tools such as NLTK to perform data preprocessing tasks. The second phase is data modeling, which focuses on the representation of entities such as proteins, diseases, genes and drugs. The third phase is knowledge extraction, in which relevant entities are extracted using BioPLBC model and further relationship extraction is performed based on these entities to capture the relationships between the entities. The fourth stage is to store the extracted data into Neo4j graph database. The fifth stage uses the ALEQ algorithm to perform advanced semantic query to retrieve the relevant knowledge. The flowchart systematically outlines the complete approach from data collection, processing to knowledge querying.