PMC Tables

Extract relational tables from PubMed Central.

Features

• Download articles and supplemental material from NCBI PubMed Central and EuroPMC.
• Extract tables from articles and supplemental material and save then in HDF5 files.

Notebooks

This repository contains the pipeline for extracting and processing tables from PubMed Central and Europe PMC.

graph TD;
  statistics.ipynb --> download.ipynb;
  to_download.ipynb --> download.ipynb;
  download.ipynb --> archive_to_hdf5.ipynb;
  archive_to_hdf5.ipynb --> query_mutation_tables.ipynb;
  presentation.ipynb;
  project_report.ipynb;

Loading

Additional resources

• Data package - Repository of Jupyter notebooks showing how to run the entire PMC tables pipeline.
• Project report - Project report in which I describe PMC tables.
• Project presentation - Slides for a course presentation in which I describe PMC tables.