Abstract: An endoplasmic reticulum-based chimeric protein construct for targeted protein degradation and the use thereof, wherein the chimeric protein construct is used for treating cancers, viral infection diseases, autoimmune diseases, neurodegenerative diseases, etc. The chimeric protein construct includes a protein binding domain based on an endoplasmic reticulum-associated degradation mechanism and a targeting domain. The protein binding domain of the chimeric protein construct based on the ERAD mechanism can be the transmembrane domain of the endoplasmic reticulum resident protein of a virus or a functional variant thereof and an endoplasmic reticulum resident domain or a functional variant thereof. The targeting domain of the chimeric protein construct can target any target proteins of interest, and can be the natural ligand of the target protein, an antibody that specifically recognizes the target protein, or an antigen-binding fragment thereof.

Abstract: A method includes generating, by a large language model (LLM), a multitude of search queries from a user input term obtained from a user application. The method further includes, executing, by the LLM, the multitude of search queries to obtain a multitude of verified search results regarding a multitude of candidates. A multitude of web presence schemas corresponding to the multitude of candidates from the multitude of verified search results is generated. The method further includes web-scraping a multitude of websites of a subset of candidates selected from the multitude of candidates to obtain a set of corresponding web-scraping payloads. The method further includes merging the corresponding web-scraping payloads with corresponding web presence schemas of the subset of candidates to obtain a multitude of updated web presence schemas. The method further includes presenting the multitude of updated web presence schemas of the subset of candidates in the user application.