# Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows

arXiv: https://arxiv.org/abs/2605.11221 · HTML: https://mlsanity.com/paper/2605.11221/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 6 of its 32 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 6 of 6)

- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering](https://mlsanity.com/paper/2303.05352/) (2023)
- [MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction](https://mlsanity.com/paper/2109.15290/) (2021)
- [LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature](https://mlsanity.com/paper/2510.26824/) (2025)
- [An autonomous living database for perovskite photovoltaics](https://mlsanity.com/paper/2601.17807/) (2026)
- [A Comprehensive Review of Emerging Approaches in Machine Learning for De Novo PROTAC Design](https://mlsanity.com/paper/2406.16681/) (2024)

## Abstract (arXiv)

Predictive models in biomedicine depend on structured assay data locked in the text, tables, and supplements of primary publications. This bottleneck is especially 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. Inconsistent compound identifiers and incomplete or implicit assay context further demand domain-specific logic that generic LLM pipelines do not provide. Existing molecular glue and PROTAC databases are manually curated and often lack the experimental context required for downstream modeling. We formulate TPD database extraction as a domain-specific curation task and present an expert-in-the-loop LLM workflow, evaluated through a triangular comparison among LLM predictions, standardized baseline records, and expert-annotated ground truth. A lightweight 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 PROTACs by terminology substitution alone, maintaining record-level F1 > 0.93. Applied at scale, it expanded molecular glue and PROTAC databases by 81% and 92% records, respectively, with 92% and 82.5% of newly recovered records validated as correct upon expert review. The workflow also recovered kinetic and assay-context information essential for cross-study potency comparison and condition-aware degradation modeling. We release the workflow, prompts, evaluation code, and extracted datasets as resources for TPD data curation and AI-assisted scientific curation more broadly.