Agentic Literature Extraction Augments Targeted Protein Degradation Databases
Abstract
Predictive models in medicinal chemistry depend on structured assay data locked in primary publications. This bottleneck is acute in targeted protein degradation (TPD), where each assay record must combine compound identity, degradation target, recruiter, assay context, and endpoint values reported across sections, tables, and supplementary files. Existing TPD databases are manually curated and often lack assay context. We present an expert-in-the-loop large language model workflow in which a cross-validated prompt-refinement module adapts extraction instructions from scarce expert annotations. With only seven annotated molecular glue publications, the workflow achieved record-level F1 = 0.98 and transferred to proteolysis-targeting chimeras (PROTACs) by terminology substitution alone (F1 ≥ 0.93). The resulting database, AutoTPD, contained 81% and 92% more molecular glue and PROTAC records than standardized reference datasets; expert audits found 92/100 and 33/40 new records to be correct. Applying the workflow to eligible PubMed Central open-access literature added 4,483 records from 598 publications, yielding AutoTPD+, a public, versioned database of 7,622 TPD records, including degradation assay measurements, designed for monthly updates. In a controlled surrogate model comparison, PROTAC degradation activity models trained on AutoTPD+ saw a 8.9-18.2% error reduction relative to models trained on the original PROTAC-DB data.
Related
- ELiAH2: update of the atlas of E3 ligases in human tissues by integrating tissue-specificity and docking properties of ligands for targeted protein degradation
- Hepatitis C Virus NS2 Protein Is Phosphorylated by the Protein Kinase CK2 and Targeted for Degradation to the Proteasome
- Dynamic Modulation of Neural Cell Identity Maintenance via Lysine Acetyltransferase Type 3 Protein Targeted Degradation
- Targeted RNA degradation of HIV-1 TAR element at 5'UTR by CRISPR-Cas13X blocks HIV-1 lytic reactivation
- Reliable extraction of clinical-trial evidence with provenance, verification, and targeted review
BibTeX
@misc{rao2026agentic,
title = {{Agentic Literature Extraction Augments Targeted Protein Degradation Databases}},
author = {Yaochen Rao and Farzaneh Jalalypour and N. M. Anoop Krishnan and Rocío Mercado},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2605.11221},
eprint = {2605.11221},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.11221},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Agentic Literature Extraction Augments Targeted Protein Degradation Databases
AU - Yaochen Rao
AU - Farzaneh Jalalypour
AU - N. M. Anoop Krishnan
AU - Rocío Mercado
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2605.11221
UR - https://arxiv.org/abs/2605.11221
AB - Predictive models in medicinal chemistry depend on structured assay data locked in primary publications. This bottleneck is acute in targeted protein degradation (TPD), where each assay record must combine compound identity, degradation target, recruiter, assay context, and endpoint values reported across sections, tables, and supplementary files. Existing TPD databases are manually curated and often lack assay context. We present an expert-in-the-loop large language model workflow in which a cross-validated prompt-refinement module adapts extraction instructions from scarce expert annotations. With only seven annotated molecular glue publications, the workflow achieved record-level F_1 = 0.98 and transferred to proteolysis-targeting chimeras (PROTACs) by terminology substitution alone (F_1 ≥ 0.93). The resulting database, AutoTPD, contained 81% and 92% more molecular glue and PROTAC records than standardized reference datasets; expert audits found 92/100 and 33/40 new records to be correct. Applying the workflow to eligible PubMed Central open-access literature added 4,483 records from 598 publications, yielding AutoTPD+, a public, versioned database of 7,622 TPD records, including degradation assay measurements, designed for monthly updates. In a controlled surrogate model comparison, PROTAC degradation activity models trained on AutoTPD+ saw a 8.9-18.2% error reduction relative to models trained on the original PROTAC-DB data.
ER -