ACD/Percepta physicochemical and adme tox prediction software

ACD/Oral Bioavailability

Predict endpoints affecting bioavailability including solubility, P-gp efflux, acid stability, and first pass metabolism from structure

ACD/Oral Bioavailability: Active Transport
Click to view the image series

The oral bioavailability module uses a combination of probabilistic and mechanistic models to predict oral bioavailability from structure, and relies on a number of ACD/Percepta prediction algorithms and experimental data sets. Results are provided as a quantitative prediction of bioavailability after oral administration (%F) with traffic-lights (green=good, red=problematic) for easy interpretation of the contributions of underlying properties. Additional details are available from other relevant modules—Aqueous Solubility, P-gp Specificity, and Passive Absorption.

  • Predict a number of endpoints that affect oral bioavailability:
    • Solubility (dose/solubility ratio)
    • Stability in acidic media
    • Intestinal membrane permeability by passive or active transport (with a summary of transporters where relevant)
    • P-gp efflux
    • First pass metabolism in the liver
  • Simulate dose dependence of bioavailability – explore how the predicted %F changes when different oral doses are entered
  • View up to 5 of the most similar structures from the internal training set, with experimental results and literature references

About the Model

Data Sources—various peer-reviewed scientific journals, and reference books:

  • Therapeutic Drugs, Dollery, C., Ed. 2nd Edition, Churchill Livingstone, New York, NY, 1999
  • Clarke’s Isolation and Identification of Drugs, Moffat, A. C., Jackson, J.V., Moss, M.S., Widdop, B., Eds. 2nd Edition, The Pharmaceutical Press, London, 1986

Training set size: 788

Model Performance

Classification performance of the lower threshold (%F [oral] >30%) probabilistic bioavailability model on training set compounds.

Subset Observed Calculated Probability (p)
>0.5 <0.5
Entire training set
N = 788		 True


False		 415
(52.7%)

81
(10.3%)		 114
(14.5%)

178
(22.6%)
Accuracy 75.2%
Sensitivity 78.4%
Specificity 68.7%

Classification performance of the upper threshold (%F [oral] >70%) probabilistic bioavailability model on training set compounds.

Subset Observed Calculated Probability (p)
>0.5 <0.5
Entire training set
N = 788		 True


False		 172
(21.8%)

44
(5.6%)		 126
(16.0%)

446
(56.6%)
Accuracy 78.4%
Sensitivity 57.7%
Specificity 91.0%

ACD/Labs Product Suites

The Percepta prediction modules are available as bundles to offer cost savings for multiple modules, and provide related modules as a package. Contact us for more information on the product suite that is right for you.