Supported molecular properties

ClinTox

A ToxSmi model trained on ClinTox dataset which has two endpoints: Probability of FDA approval and Probability of failure in clinical trials. When using this model, please cite Born et al. (2023) (citation below).

SIDER

A ToxSmi model trained on the SIDER dataset for 27 different types of side effects of drugs. When using this model, please cite Born et al. (2023) (citation below).

Tox21

A ToxSmi model trained on the Tox21 dataset with 12 different types of environmental toxicities. When using this model, please cite Born et al. (2023) (citation below).

SCScore

Predict the synthetic complexity score (SCScore) as presented in Coley et al. (J. Chem. Inf. Model.; 2018).

SAS

Estimate the synthetic accessibility score (SAS) as presented in Ertl et al. (Journal of Chemoinformatics; 2009).

Lipinski

Measure whether a molecule confirms to the Lipinski-rule-of-five as presented in Lipinski et al. (Advanced Drug Delivery Reviews; 2001).

Penalized logP

Measure the penalized logP (partition coefficient) score as presented in Gomez-Bombarelli et al. (ACS Central Science; 2018). This is the logP minus the number of rings with > 6 atoms minus the SAS.

QED

Measure the drug-likeness as presented in Bickerton et al. (Nature Chemistry; 2012).

LogP

Measure the logP (partition coefficient) of a molecule as presented in Wildman et al. (J. Chem. Inf. Comput. Sci.; 1999).

Bertz

Calculate the total polar surface area of a molecule as presented in Ertl et al. (Journal of Medicinal Chemistry; 2000).

TPSA

Calculate the first general index of molecular complexity Bertz (Journal of the American Chemical Society; 1981).

Is-Scaffold

Whether the molecule is identical to its Murcko scaffold.

Number-Of-X

Calculated with RDKit.

Molecular Weight

Calculated with RDKit.

ToxSmi citation

@article{born2023chemical,
  title={Chemical representation learning for toxicity prediction},
  author={Born, Jannis and Markert, Greta and Janakarajan, Nikita and Kimber, Talia B. and Volkamer, Andrea and Rodriguez Martinez, Maria and Manica, Matteo},
  journal={Under review at Digital Discovery},
  year={2023}
}

Unsupported properties

The following molecular properties are available via the GT4SD API but not in this UI:

MoleculeOne endpoint for retrosynthesis
ASKCOS endpoint for retrosynthesis
TDC-Docking endpoint for docking against a user-provided target
TDC-Docking endpoint for docking against 3pbl.
Protein-ligand binding against one of the targets drd2, gsk3b, jnk3, fpscores, cyp3a4_veith, drd2_current, gsk3b_current or jnk3_current.
Tanimoto similarity to a seed molecule.

Moreover, GT4SD also includes properties on other entities such as proteins and crystals.