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

Reinvent: Generative

1
0
Drug Design
    More
Step 1: Upload your data

Upload Pre-processed SMILES File

Drag your file(s) or upload
  • Your file can be in the following formats:csv
    • SMILES strings should be in the first column of the .csv file without a header. If you used the Reinvent: Data Preparation Module, you can directly upload its output file here. Example: Cc1cc(S(=O)(=O)NC(C)c2nnc3ccccn23)ccc1Br Cc1cc(=NC(=O)c2ccc3c(-c4nc5ccccc5[nH]4)[nH]nc3c2)[nH][nH]1 O=C1CC(c2ccc(Br)cc2)Nc2c(Br)cc(Br)cc21
or
Don’t have a file?
Use our demo data to run
Use Demo Data
View example data

Upload Empty Model File

Drag your file(s) or upload
  • Your file can be in the following formats:ckpt
    • The checkpoint file (.ckpt) contains all available tokens that are in the training set. So it acts as a vocabulary. In order to create a suitable .ckpt file, (Reinvent: Create Initial prior/agent Generative Model) app needs to be used.
or
Don’t have a file?
Use our demo data to run
Use Demo Data
Step 2: Set Parameters
1
3
1000

This app was originally created based on notebook (Transfer Learning Mode) from the ReinventCommunity repo. The purpose of this app is to train an empty model created from the previous Reinvent: Create Initial prior/agent Generative Model. In this scenario, inputs are an empty model (.ckpt file) and a processed dataset (.csv file) generated by Reinvent: Data Preparation Module. The output will be the Prior that can be used afterward for other apps of Reinvent such as reinforcement learning. For more information, please see the tutorial page of Reinvent Apps.

Example Use Case: Train generative model with Transfer Learning

Limitations: Some of the parameters are kept the same as in the original notebook.

Technology: Transfer Learning (TL)

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 This content is a preprint and has not been peer-reviewed.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-11-2022
Previous Job Parameters
Your previous job parameters will show up here
so you can keep track of your jobs
Results
Parameters