EXSCLAIM2.0: LLM-powered Automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific figures

🤔 Consider Collaboration

If you find this tool or any of its derived capabilities useful, please consider registering as a user of Center for Nanoscale Materials. We will keep you posted of latest developments, as well as opportunities for computational resources, relevant data, and collaboration. Please contact Maria Chan (mchan@anl.gov) for details.

Introduction to EXSCLAIM2.0

EXSCLAIM2.0 is a Python package combining EXSCLAIM! code with Large Language models (LLMs) that can be used for the automatic generation of datasets of labeled images from published papers. There are four main steps:

1. JournalScraper: scrape journal websites, acquiring figures, captions, and metadata
2. CaptionDistributor: separate figure captions into the component chunks that refer to the figure's subfigures using LLMs and prompt engineering
3. FigureSeparator: separate figures into subfigures, detect scale information, label, and type of image
4. PDFScraper: scrape journal articles in PDF form, acquiring figures, captions and metadata.

Installation

The guides to install EXSCLAIM through Pip, Git and Docker can be found within the wiki. The guides include installing pre-compiled versions as well as building from the source code and then installing.

Using Exsclaim 2.0

from exsclaim import Pipeline
search_query = {
		...
}
results = Pipeline(search_query)

where search_query is either a dictionary representing a valid JSON object, or a Pathlike string pointing towards a valid JSON file, or

python -m exsclaim query {path to json file holding search query}

More extensive guides can be found within the wiki.

Using Docker Compose

To use Docker Compose to host the service, run the following commands in the base directory:

docker compose up --build python

Upgrading the Database

Starting with version 2.5.3, EXSCLAIM will be using Alembic to easily upgrade the schema of the database. If you have a version of the database existing before this change, you can run

alembic stamp 751d7ac35cd2

to have alembic recognize that the database already has a history, then run

alembic upgrade head

to update the database. With future versions, you can then run

alembic upgrade head

to update to the proper schema.

Acknowledgements

This material is based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357

This work was performed at the Center for Nanoscale Materials, a U.S. Department of Energy Office of Science User Facility, and supported by the U.S. Department of Energy, Office of Science, under Contract No. DE-AC02-06CH11357.

We gratefully acknowledge the computing resources provided on Bebop, a high-performance computing cluster operated by the Laboratory Computing Resource Center at Argonne National Laboratory.

Citation

If you find EXSCLAIM! useful, please encourage its development by citing the following paper in your research:

Schwenker, E., Jiang, W. Spreadbury, T., Ferrier N., Cossairt, O., Chan M.K.Y., EXSCLAIM! - An automated pipeline for the construction and
labeling of materials imaging datasets from scientific literature. arXiv e-prints (2021): arXiv-2103

Bibtex

@article{schwenker2021exsclaim,
  title={EXSCLAIM! - An automated pipeline for the construction of labeled materials imaging datasets from literature},
  author={Schwenker, Eric and Jiang, Weixin and Spreadbury, Trevor and Ferrier, Nicola and Cossairt, Oliver and Chan, Maria KY},
  journal={arXiv e-prints},
  pages={arXiv--2103},
  year={2021}
}