tox-paper-extractor
CommunityEnd-to-end OA toxicity data extraction pipeline.
Authorcihebi2
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates an end-to-end open-access (OA) literature workflow for toxicity/peptide data, from candidate discovery to downloaded OA full texts and auditable extractions, enabling faster, repeatable data gathering for training and analysis.
Core Features & Use Cases
- End-to-end OA literature pipeline: discovery via Europe PMC, OA downloads (PDF/XML and supplements), and audit-ready extraction of raw records and tables.
- Training-readiness screening: flags for sequences, units, censoring, and structured readiness (train_ready_strict/relaxed) to support model development.
- Monitoring and reproducibility: generates monitoring reports, per-paper provenance, and audit-friendly outputs (raw_extractions.csv, raw_experimental_records.csv, extracted_tables).
Quick Start
Run the tox-paper-extractor on a set of publications using the provided pipeline script, for example:
- python scripts/run_tox_paper_pipeline.py --query '<your query>' --max-results 50 --min-score 5 --out-root runs
Dependency Matrix
Required Modules
pandasrequestsPyMuPDF
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: tox-paper-extractor Download link: https://github.com/cihebi2/codex_skills/archive/main.zip#tox-paper-extractor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.