There is a newer version of the record available.

Published February 6, 2023 | Version v1.2.1 (code and data)
Software Open

Optimization of binding affinities in chemical space with generative pre-trained transformer and deep reinforcement learning -- source code and data

Creators

  • 1. KAUST
  • 2. Syneron Technology, China

Description

This repository contains the code and data for SGPT-RL, a tool for chemical design using transformer and deep reinforcement learning. Through employing GPT model as the policy network, SGPT-RL can learn scaffold patterns in exploring the chemical space.

  • Publication: TBA
  • Files included in this release:
    • sgpt-rl.png: the workflow of SGPT-RL.
    • sgpt-rl-v1.2.zip: the source code of SGPT-RL.
    • data.zip: raw datasets and pretrained models. 
  • Source code repository: https://github.com/charlesxu90/sgpt

Files

data.zip

Files (140.1 MB)

Name Size Download all
md5:8be63b08c3e85a7de7108020ea0ff3a4
95.4 MB Preview Download
md5:334acbe54a213a6a9c9ccacd8d7b3e75
44.6 MB Preview Download
md5:8cb56848cc5be61a8fd14edcaad16d42
95.4 kB Preview Download

Additional details

Related works

Is supplement to
https://github.com/charlesxu90/sgpt/tree/v1.2 (URL)