dlemb

Algorithm for knowledge graph embedding (KGE) generation

https://github.com/freh-g/dlemb

Science Score: 26.0%

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

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Algorithm for knowledge graph embedding (KGE) generation

Basic Info
  • Host: GitHub
  • Owner: freh-g
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 2.31 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created about 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.md

DLemb

DLemb is an algorithm that creates node embeddings from a knowledge graph. The knowledge graph has to be fed to the algorithm in a .csv format without index and with specific headers i.e.

  • source: id of the source
  • target: id of the target
  • rel_type: type of the interaction

An example is available in data/kg_edgelist.csv. This knowledge graph is composed of 41k nodes of 4 types (functions, phenotypes, drugs and proteins) and ~60 types of relationships.

DLemb need several dependencies, an environment named DLemb can be created by running

conda env create -f DLemb.yml Then activate the environment with

conda activate DLemb

The algorithm consists of a shallow neural network implemented in Keras, it is composed by an Embedding layer and a normalized Dot layer. It works by randomly generating negative (wrong) triplets that are used to train the network: once the Dot product is computed the error is calculated trough RMSE and the weights of the embedding layer are optimized trouhg Adam optimization.

The customizable flags of DLemb can be listed by running:

./DLemb.py -h DLemb automatically runs on GPU is available. A typical call for DLemb is as follows:

./DLemb.py -i data/kg_edgelist.csv -o outputs/kg_embeddings.pickle

Owner

  • Name: Francesco Gualdi
  • Login: freh-g
  • Kind: user
  • Location: Barcelona
  • Company: Institut Hospital del Mar d'investigacions mediques (IMIM)

Bsc in biology at UNIFE, Msc in medical biotechnology at UNIVR. Currently working in medical bioinformatics group at IMIM, Barcelona doing my PhD in Biomedicine

GitHub Events

Total
Last Year