Data

Tools

Indexes

Applications

Experiments

Open Source Science

deep_active_learning_biore

Framework to study the use of deep active learning for biomedical relation extraction

https://github.com/oligogenic/deep_active_learning_biore

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 4 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: plos.org, zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.0%) to scientific vocabulary

Keywords

active-learning active-learning-in-nlp annotation biomedical biomedical-text-mining relation-extraction
Last synced: 6 months ago · JSON representation ·

Repository

Framework to study the use of deep active learning for biomedical relation extraction

Basic Info
  • Host: GitHub
  • Owner: oligogenic
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 7.97 MB
Statistics
  • Stars: 2
  • Watchers: 3
  • Forks: 0
  • Open Issues: 0
  • Releases: 2
Topics
active-learning active-learning-in-nlp annotation biomedical biomedical-text-mining relation-extraction
Created almost 3 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

Deep active learning for biomedical relation extraction DOI

Code and data to study deep active learning for biomedical relation extraction (bioRE), article can be found here.

Data sets can be found in the data folder.

Scripts to reproduce the results of the article can be found in the launchers folder.

The experiments were conducted on a server with Ubuntu Desktop 20.04.5 LTS (GNU/Linux 5.15.0-56-generic x8664) operating system, Nvidia driver 470.161.03, CUDA version 11.4, with 32GB RAM on 2 Asus GTX 1080 TI GPUs. You may want to modify the `configaccelerate.yaml` file to fit your hardware.

An environment to run the experiments can be built with the environment_pytorch.yaml file using conda : conda env create -f environment_pytorch.yaml and then activated with : conda activate pytorch

Acknowledgements

This project was realised at the Interuniversity Institute of Bioinformatics in Brussels (IB2), a collaborative bioinformatics research initiative between Université Libre de Bruxelles (ULB) and Vrije Universiteit Brussel (VUB). This work was supported by the Service Public de Wallonie Recherche by DIGITALWALLONIA4.AI [2010235—ARIAC]; the European Regional Development Fund (ERDF) and the Brussels-Capital Region-Innoviris within the framework of the Operational Programme 2014-2020 through the ERDF-2020 project ICITY-RDI.BRU [27.002.53.01.4524]; an F.N.R.S-F.R.S PDR project [35276964]; Innoviris Joint R&D project Genome4Brussels [2020 RDIR 55b]; and the Research Foundation-Flanders (F.W.O.) Infrastructure project associated with ELIXIR Belgium [I002819N].

License

This work is under a MIT license.

Cite us

See above by clicking on "Cite this repository"

Owner

  • Name: oligogenic
  • Login: oligogenic
  • Kind: organization

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Nachtegael"
  given-names: "Charlotte"
  orcid: "https://orcid.org/0000-0002-5034-8975"
- family-names: "De Stefani"
  given-names: "Jacopo"
  orcid: "https://orcid.org/0000-0003-0257-4537"
- family-names: "Lenaerts"
  given-names: "Tom"
  orcid: "https://orcid.org/0000-0003-3645-1455"
title: "A study of deep active learning methods to reduce labelling efforts in biomedical relation extraction"
version: 1.1.0
doi: 10.5281/zenodo.10454561
date-released: 2023-04-17
url: "https://github.com/oligogenic/Deep_active_learning_bioRE"
preferred-citation:
  type: article
  authors:
  - family-names: "Nachtegael"
    given-names: "Charlotte"
    orcid: "https://orcid.org/0000-0002-5034-8975"
  - family-names: "De Stefani"
    given-names: "Jacopo"
    orcid: "https://orcid.org/0000-0003-0257-4537"
  - family-names: "Lenaerts"
    given-names: "Tom"
    orcid: "https://orcid.org/0000-0003-3645-1455"
  doi: "10.1371/journal.pone.0292356"
  journal: "PLOS ONE"
  publisher: "Public Library of Science"
  title: "A study of deep active learning methods to reduce labelling efforts in biomedical relation extraction"
  year: 2023
  month: 12
  volume: 18
  url: "https://doi.org/10.1371/journal.pone.0292356"
  start: 1
  end: 23
  issue: 12

GitHub Events

Total
Last Year