Name: Gully Burns
Type: User
Company: @chanzuckerberg
Bio: Research Scientist at CZI. Building 'Scientific Knowledge Engineering' tools and systems for the CZI Science Projects.
Twitter: sciknowengine
Location: Redwood City, CA
Blog: https://gullys.website
Gully Burns's Projects
Some simple scripts to work with MONDO data
Tools for curating biomedical training data for large-scale language modeling
Fork of chat-langchain with minimal edits for reuse on open-source tools.
Template for nbdev projects
Extracting scientific claims from biomedical abstracts (powered by AllenNLP), demo:
Open source text annotation tool for machine learning practitioner.
Dockerfile base designed to provide a sharable, stable set of libraries for data science work. Thanks to the awesome Florian Geigl (@floriangeigl) for making his implementation available.
Source to www.draw.io
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
GPT based autonomous agent that does online comprehensive research on any given topic
My professional blog: 'Scientific Knowledge Engineering Meets Data Science'.
Jupyter Widget for data annotation
Developing local LLMs for use within LangChain
Open Source Code for Extraction of Methods and Datasets from Biomedical Papers
Porting the theme to CZI
Boilerplate to start with Docker setup (Next.js included)
NLM .nxml to text format conversion
library supporting NLP and CV research on scientific papers
Copy of huridocs PDF extraction library
A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files
Research Object describing source code and data for Burns et al (2019)
Code for finding ontology term matches in Napari plugin descriptions
An interactive PDF reader.
SciGraph docker image and monarch specific configurations
WebGL Experiment
Simple interaction code to define the BioC as a UIMA type and provide support for it's use in text mining applications based on the CleartTk UIMA system.