A prompt-refined LLM workflow extracts TPD assay records with F1 scores above 0.93 from few expert examples, expanding molecular glue and PROTAC databases by 81% and 92% with over 82% expert-validated accuracy.
Chemical name to structure: OPSIN, an open source solution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.QM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows
A prompt-refined LLM workflow extracts TPD assay records with F1 scores above 0.93 from few expert examples, expanding molecular glue and PROTAC databases by 81% and 92% with over 82% expert-validated accuracy.