ASAP Discovery x OpenADMET CompetitionTake part in the first prospective benchmark on Polaris.

Benchmark

tdcommons/caco2-wang
Created on: July 22, 2024Train size: 728Test size: 182
Public
Single Task
Regression

Participants

Tags

ADMET
singletask

Related dataset

Leaderboard

Test set
Task
#
NameContributors
mean_absolute_error
References
1

1B_MPNN_MolGPS-ens_LargeMix-and-Phenomics

0.282
2

3B_e50_MPNN_LargeMix-and-Phenomics

0.316
3

1B_MPNN_LargeMix-and-Phenomics

0.319

Details

README

Background

The human colon epithelial cancer cell line, Caco-2, is used as an in vitro model to simulate the human intestinal tissue. The experimental result on the rate of drug passing through the Caco-2 cells can approximate the rate at which the drug permeates through the human intestinal tissue.

Description of readout

Task Description: Regression. Given a drug SMILES string, predict the Caco-2 cell effective permeability.

Data resource

Reference: Wang, NN et al, ADME Properties Evaluation in Drug Discovery: Prediction of Caco-2 Cell Permeability Using a Combination of NSGA-II and Boosting, Journal of Chemical Information and Modeling 2016 56 (4), 763-773