Prediction

1. Draw molecules or select a file.

Update Add to list
Title Mol SMILES Optional parameters
apKa bpKa logP

2. Select prediction parameters.

Parameter Organism/Cell Type Output Accuracy Reference Method Descriptor Updated at
Sol(pH7) Regression Value
  • MSE: 0.533±0.034
  • R2: 0.651±0.021
ChEMBL33 (n = 22,749)
  • GCN (GINConvolution)16
2025/02
The older version1 is here
Sol(pH6) Regression Value
  • MSE: 0.609±0.041
  • R2: 0.503±0.026
ChEMBL32 (n = 3,692)
  • GCN (GINConvolution)16
  • Fine tuning model based on Sol(pH7)
Sol(pH1) Regression Value
  • MSE: 0.729±0.079
  • R2: 0.464±0.063
ChEMBL32 (n = 973)
  • GCN (GINConvolution)16
  • Fine tuning model based on Sol(pH7)
fu,p Human Regression Value
  • MSE: 0.154±0.015
  • R2: 0.690±0.019
ChEMBL34 (n = 3,974)
  • GCN (GINConvolution)16
  • Multitask model with fu,p human/rat/mouse
2025/02
The older version2 is here
fu,p Rat Regression Value
  • MSE: 0.209±0.015
  • R2: 0.570±0.025
ChEMBL34 (n = 1,451)
  • GCN (GINConvolution)16
  • Multitask model with fu,p human/rat/mouse
2025/02
The older version3 is here
fu,p Mouse Regression Value
  • MSE: 0.200±0.016
  • R2: 0.645±0.028
ChEMBL34 (n = 2,528)
  • GCN (GINConvolution)16
  • Multitask model with fu,p human/rat/mouse
fu,brain Mammal Regression Value
  • MSE: 1.48
  • R2: 0.58
Watanabe et al.3 GB
  • Mordred10
  • jCompoundMapper11
2021/03
The older version4 is here
CLint Human Regression Value
  • MSE: 0.193±0.024
  • R2: 0.591±0.042
ChEMBL33 (n = 5,279)
  • GCN (GINConvolution)16
2025/02
The older version5 is here
CYP.probability7 Human Probability Value Accuracy:
  • CYP1A2: 0.617
  • CYP2C9: 0.600
  • CYP2D6: 0.712
  • CYP3A4: 0.825
RF
CYP.site7 Human Site Site Yamazoe et al.8,9
Papp(AtoB) Human/Caco-2 Regression
  • MSE: 0.370±0.036
  • R2: 0.417±0.043
ChEMBL33 (n = 6,309)
  • GCN (GINConvolution)16
2025/02
The older version1 is here
Papp(AtoB) Human/LLC-PK1 Regression Value R2 = 0.687 Linear Stacking
(LGBM, XGB, Catboost, RF, NN)
  • Mordred10
  • jCompoundMapper11
  • RDKit12
  • CDK13
P-gp NER.class Human/LLC-PK1 3 class
  • Low (1-1.4)
  • Medium (1.4-9.8)
  • High (> 9.8)
Kappa: 045 Watanabe et al.3 GB
  • Mordred10
  • jCompoundMapper11
2021/03
Fa.class Human 3 class
  • Low (0-0.2)
  • Medium (0.2-0.7)
  • High (0.7-1.0)
  • Accuracy: 0.836
  • Kappa: 0.560
Esaki et al.1 RF6
CLr Human Regression Value In higher range of CLr Human (more than 1.02 mL/min/kg), 70.5% of samples were fell in within 2-fold error Watanabe et al.6
  • RF
  • PLS
fe.class Human 2 class
  • Low (< 0.3)
  • Medium-High (> 0.3)
  • Kappa: 0.49
  • Balanced accuracy: 0.74
Watanabe et al.6 RF
CR_type.class Human 3 class
  • Reabsorption
  • Secretion
  • Intermediate
  • Kappa: 0.32
  • Balanced accuracy: 0.70, 0.58 and 0.68 in Reabsorption, Intermediate and Secretion, respectively
Watanabe et al.6 RF13
Kp,brain
Kp,uu,brain
Rat Correction method considering P-gp NER Value Kp,uu,brain
42.9% and 64.3% samples were fell within 5- and 10-fold, respectively.
Watanabe et al.3 GB
  • Mordred10
  • jCompoundMapper11
  • ChemAxon15 if the pKa values are not given by the user.

Citing the individual models

  1. Esaki, T., Ohashi, R., Watanabe, R., Natsume-Kitatani, Y., Kawashima, H., Nagao, C., Komura, H., Mizuguchi, K., Constructing an in silico three-class predictor of human intestinal absorption with Caco-2 permeability and dried-DMSO solubility. J. Pharm. Sci. 2019; 108(11):3630-3639.
  2. Watanabe, R., Esaki, T., Kawashima, H., Natsume-Kitatani, Y., Nagao, C., Ohashi, R., Mizuguchi, K., Predicting fraction unbound in human plasma from chemical structure: improved accuracy in the low value ranges. Mol. Pharm. 2018; 15(11):5302-5311.
  3. Watanabe, R., Esaki, T., Ohashi, R., Kuroda, M., Kawashima, H., Komura, H., Natsume-Kitatani, Y., Mizuguchi, K. Development of an in silico prediction model for P-glycoprotein efflux potential in brain capillary endothelial cells towards the prediction of brain penetration. J. Med. Chem. 2021; 64(5):2725-2738.
  4. Esaki, T., Ohashi, R., Watanabe, R., Natsume-Kitatani, Y., Kawashima, H., Nagao, C., Mizuguchi, K., Computational model to predict the fraction of unbound drug in the brain. J. Chem. Inf. Model. 2019; 59(7):3251-3261.
  5. Esaki, T., Watanabe, R., Kawashima, H., Ohashi, R., Natsume-Kitatani, Y., Nagao, C., Mizuguchi, K., Data curation can improve the prediction accuracy of metabolic intrinsic clearance. Mol. Inform. 2019; 38(1-2):e1800086.
  6. Watanabe, R., Ohashi, R., Esaki, T., Kawashima, H., Natsume-Kitatani, Y., Nagao, C., Mizuguchi, K., Development of an in silico prediction system of human renal excretion and clearance from chemical structure information incorporating fraction unbound in plasma as a descriptor. Sci. Rep. 2019; 9(1):18782.
  7. These prediction models were developed and donated by Fujitsu, Ltd. (Tokyo, Japan).
  8. Yamazoe, Y., Yoshinari, K., Prediction of regioselectivity and preferred order of metabolisms on CYP1A2-mediated reactions. Part 3. Difference in substrate specificity of human and rodent CYP1A2 and the refinement of predicting system. Drug Metab Pharmacokinet. 2019; 34(4):217-232.
  9. Yamazoe, Y., Goto, T., Tohkin, M., Reconstitution of CYP3A4 active site through assembly of ligand interactions as a grid-template: solving the modes of the metabolism and inhibition. Drug. Metab. Pharmacokinet. 2019; 34(2):113-125.

Other references

  1. Moriwaki, H., Tian, Y. S., Kawashita, N., Takagi, T., Mordred: a molecular descriptor calculator. J. Cheminform. 2018; 10(1):4.
  2. Hinselmann, G., Rosenbaum, L., Jahn, A., Fechner, N., Zell, A., jCompoundMapper: an open source Java library and command-line tool for chemical fingerprints. J. Cheminform. 2011; 3(1):3.
  3. RDKit: Open-source cheminformatics; https://www.rdkit.org
  4. Steinbeck, C., Han, Y., Kuhn, S., Horlacher, O., Luttmann, E., Willighagen, E., The Chemistry Development Kit (CDK): an open-source Java library for chemo- and bioinformatics. J. Chem. Inf. Comput. Sci. 2003; 43(2):493-500.
  5. Yap, C. W., PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J. Comput. Chem. 2011; 32(7):1466-1474.
  6. Breiman, L., Random Forest. Machine Learn. 2001; 45(1):5-32.
  7. Protonation calculator was used for the Kp,brain and Kp,uu,brain predictions, Marvin 21.3.0, ChemAxon (https://www.chemaxon.com)
    powered by ChemAxon
  8. kMoL (Machine Learning library for Molecular systems) was used as a framework (https://github.com/elix-tech/kmol)