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.
Extracting accurate materials data from research papers with conversa- tional language models and prompt engineering.Nature Communications, 15(1):1569
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.QM 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.