OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Dgl Lifesci

Dgl Lifesci is an open-source Python library built on DGL for graph neural network work in chemistry and biology, providing graph construction and featurization, evaluation methods, model architectures, training scripts, pretrained models, and command-line examples.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dgl Lifesci — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Dgl Lifesci when you need a Python toolkit for developing graph neural network workflows on molecular or biological data, rather than a hosted prediction service.

Who it is for

  • Life-science researchers preparing molecular or biological graph data for machine-learning experiments.
  • Python developers building graph neural network models for molecular properties or reaction prediction.

Documented uses

  • Construct and featurize graphs from life-science data.
  • Train graph neural network models for molecular-property prediction.
  • Explore reaction-prediction workflows through repository examples and CLI tools.
  • Adapt included architectures, training scripts, and pretrained models for graph-learning experiments.
Before you choose

Requirements & limits

The project is open source under the Apache-2.0 license. The README documents package installation with pip and installation from the repository.

  • The documented stack requires Python 3.6+, DGL 0.7.0+, PyTorch 1.5.0+, and RDKit.
  • The README lists Linux distributions from Ubuntu 16.04 onward, macOS, and Windows 10.
  • The CLI workflows require cloning the repository; the README links to molecular-property and reaction-prediction examples.
  • The JTVAE example specifies RDKit 2018.09.3.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install DGL-LifeSci with pip

Install the Python package after preparing its documented dependencies.

Before you start

  • Python 3.6 or later
  • DGL 0.7.0 or later
  • PyTorch 1.5.0 or later
  • RDKit

Steps

  1. Install PyTorch and DGL following their respective installation instructions.

  2. Install RDKit; the README gives the command below as one option.

    Documented command
    pip install rdkit

  3. Install DGL-LifeSci with the command below.

    Documented command
    pip install dgllife

  4. Check the installation by importing dgllife and printing dgllife.__version__.

Expected outcome

The package is installed and its version can be queried from Python.

Guide limitations

  • The README's JTVAE example requires RDKit 2018.09.3.
  • This setup sequence does not cover running a particular prediction workflow.
Documentation 1 ↗
Source-based practical guide

Prepare access to the CLI prediction examples

Clone the repository to access its molecular-property and reaction-prediction CLI examples.

Before you start

  • Git
  • A local environment with DGL-LifeSci's documented Python dependencies installed

Steps

  1. Clone the repository with the command below.

    Documented command
    git clone https://github.com/awslabs/dgl-lifesci.git

  2. Open the repository's examples/property_prediction/csv_data_configuration/ directory for the molecular-property example.

  3. Open examples/reaction_prediction/rexgen_direct/ for the reaction-prediction example.

Expected outcome

The repository and the two documented CLI example locations are available for inspection.

Guide limitations

  • The README points to example directories but does not provide the commands or configuration details needed to execute either workflow.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
6 November 2026
Original website title
awslabs/dgl-lifesci · Official homepage title · retained in its source language
How we review sourcesSuggest a correction