Try Boost
Accelerate your research with up to 20 hours of computing
Contact Us
AstraZeneca |

Reinvent: Sampling Module

0
Drug Design
    More
Step 1: Upload your data

Upload Prior/Trained Agent File

Drag your file(s) or upload
  • Your file can be in the following formats:prior, new, agent
    • Please provide prior/trained agent file. Trained agent file can be obtained from Reinforcement Learning module.
or
Don’t have a file?
Use our demo data to run
Use Demo Data
Step 2: Set Parameters
False
Min: 100
Max: 5000000

This app is based on "Sampling_Demo.ipynb" from the ReinventCommunity notebook. The purpose of the notebook is to show how to sample further compounds from a given model state (agent). During the RL process, each iteration of the agent produces an output of a number of molecules and stores it inside. If more ideas are necessary for the project afterward, this can be achieved through this module. The sampling module enables you to extract molecules from the trained agent (given model state) to use for more investigation. For more information, please see the tutorial page of Reinvent Apps.

Example Use Case: A sampling of SMILES from the generative trained agent

Limitation:
- Job only can be submitted in CPU version
- Currently, maximum 5 million SMILES can be sampled

Citation:
Blaschke T, Arús-Pous J, Chen H, Margreitter C, Tyrchan C, Engkvist O, et al. REINVENT 2.0 – an AI Tool for De Novo Drug Design. ChemRxiv 2020. doi:10.26434/chemrxiv.12058026.v3. This content is a preprint and has not been peer-reviewed.
Released:
Nov-21-2022
Previous Job Parameters
Your previous job parameters will show up here
so you can keep track of your jobs