Open Targets Querying with NLP

Soylemez

Query the Open Targets Platform using natural language. The Open Targets Platform (platform.opentargets.org) integrates evidence from genetics, genomics, transcriptomics, drugs, animal models, and scientific literature to score and rank target-disease associations for drug-target identification. The model accepts queries in the form of " What are the top [k] diseases associated with [GENE NAME]?" and " What are the top [k] genes related to [DISEASE NAME]?" Alternatively, for improved precision, you can use the ENSG of the gene or the EFO id for the diseases.

Example use case: Querying Open Targets Platform with Natural Language. If you want to know the top 8 diseases associated with the APOE gene: "What are the top 8 diseases associated with APOE?" or the top 3 genes associated with Alzheimer's disease: "Find the top 3 genes related to Alzheimer disease."

Technology: Open Targets Platform and GPT3

Limitations: It does not produce any novelty or new-knowledge that is not available in the Open Targets Platform. We are currently improving the types of queries it accepts.

Citation:
https://github.com/cx0/chatGPT-for-genetics, Ochoa, D. et al. (2023). The next-generation Open Targets Platform: reimagined, redesigned, rebuilt. Nucleic Acids Research.
Released: Mar-14-2023
v1.0
Biomedical Language Models
GPT
586
7
share
View Source