Amass connects your assistant to six curated biomedical corpora: BioMedCore (43M+ records: peer-reviewed publications from PubMed/PMC and conference abstracts from society meetings), TrialCore (1.2M+ clinical trials from ClinicalTrials.gov and the WHO ICTRP), DrugCore (22K+ harmonized drugs/molecules covering modality, clinical stage, structure, synonyms, and the gene targets each drug acts on; ChEMBL-linked), RegulatoryCore (7K+ unified FDA + EMA marketing authorizations with source documents such as labels, reviews, SmPCs, and EPARs), GeneCore (43K+ harmonized human genes with a target-intelligence layer covering druggability, DepMap essentiality, ChEMBL target class, clinical-precedent tractability, curated safety liabilities, and gnomAD constraint), and PatentCore (preview, life-science patents with full-text search, CPC/IPC classifications, assignees/inventors, and patent families). Users can search and retrieve full records with filters that beat open-web retrieval, and follow cross-links across corpora back to each underlying source.
How to use
- 1Add it in ChatGPT
Open Amass in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.
- 2Use it in a chat
Type @ in the composer and pick Amass, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.
Things to ask
- “Map the current landscape for oral GLP-1 agonists in obesity — what's approved, what's in trials, and who holds patents.”
- “Make the case for and against KRAS G12D as a drug target: biology, what's been tried clinically, and failures.”
- “What happened to semaglutide since first approval — indication expansions, label changes, safety signals, and literature.”
Disconnect
- 1Disconnect it in ChatGPT
Open Settings, then Apps or Plugins (the label depends on your rollout), select Amass and choose Disconnect. ChatGPT stops acting through your account; past conversations aren't deleted.