AI agents are everywhere accomplishing activities. Drug Discovery agents have been coming on fast and the scale at which these agents approach drug discovery is phenomenal.
There is a great example of a AWS agent that was SPECification built using Kiro from scratch in 3 weeks that delivers drug targets. Amazing to see that it is able to discover new targets using standard BIO databases that they listed:
Literature & Clinical: PubMed, ClinicalTrials.gov, OpenFDA
Drug Discovery: ChEMBL, PubChem, ZINC, GToPdb
Proteins & Genomics: UniProt, STRING, Ensembl, InterPro
Gene Expression: GEO, GTEx, gnomAD, ClinVar, dbSNP
Pathways: Reactome, KEGG, WikiPathways
Structural Biology: PDB, EMDB, AlphaFold
Disease Data: Open Targets, Monarch, GWAS Catalog
Patents: USPTO Patent Search
Specialized: cBioPortal, PRIDE, JASPAR, ReMap, UCSC, and more
Read more about this on the amazon page:
And then try this out in AWS.
https://github.com/aws-samples/sample-target-identification-agent-using-kiro