Skip To Content
ADME Suite

Predict Pharmacokinetic Properties

Request a Consultation or Demo

ADME Suite Overview

Calculators & Predictors for ADME Properties

In silico prediction of absorption, distribution, metabolism, and excretion (ADME) properties supports high-throughput screening of libraries, provide insights into pharmacological effects, and can help assure that products are safe for human use.

ACD/ADME Suite is a collection of prediction modules that provide high-quality, structure-based calculations of pharmacokinetic properties.

  • Predict from structure:
    • Blood-brain barrier penetration
    • Cytochrome P450* inhibition and substrate specificity
    • Distribution*
    • Maximum recommended daily dose for human clinical trials
    • Oral bioavailability—its dependence on logP and bioavailability-dose dependence
    • Passive absorption
    • P-glycoprotein specificity*
    • Physicochemical properties—logP,* logD,* pKa,* aqueous solubility,* etc.
    • Sites of metabolism
  • Assess the reliability of predicted values
  • Search the internal library of experimental data for select models
  • Train prediction models with experimental data to better reflect novel chemical space
  • Include custom models and in-house prediction algorithms

*Train these modules with your own data

 

Benefits

Everything You Need in an ADME Property Calculator

Easy to Use

  • Simply draw your structure for predictions—easy enough to use for medicinal, synthetic, and research chemists
  • You don’t need to be a software engineer, programmer, or computational chemist to train the models

Fast, Accurate, Reliable Results

  • Quickly calculate properties for single compounds or tens of thousands
  • Predictions are based on carefully curated databases of experimental data
  • Easily gauge result quality with a reliability index, a display of similar structures in the database, and literature references for the original experimental data

Convenient Visualization

  • Visualize the substructure/atomic contributions to a property value with color-mapping on the structure (select modules)
  • Quickly identify favorable and unfavorable compounds in a library with user-defined color-coding of results in the spreadsheet

Deeper Insights

  • Identify trends and prioritize compounds easily with tools to create scatter plots, browse, filter, sort, and rank libraries
  • Make decisions confidently with a complete property profile of each molecule in one place

Customizable with In-House Data

  • Get the accuracy of in-house models from a commercial product. Use your own experimental data to expand the applicability domain of trainable modules.

Expandable to Third-Party Models

  • Create a single environment for predicted data by including third-party and in-house models

Screen tens or hundreds of compounds for their ADME profile. Color-code results. Sort, rank and filter.

Predict ADME properties—Cytochrome P450 substrates module seen here. See similar structures, literature references and assess reliability.

Investigate structure/lead modification to reach a target property profile

How it Works

Predictions in Seconds with ADME Suite

Request a Consultation or Demo

  • 1 Draw/import your structure
  • 2 Select the property of interest
  • 3 Review results and make decisions
  • 4 Conveniently report to PDF or copy/paste
Customer Reviews
“ACD/Labs' physicochemical and ADMET prediction software provides...a surprising wealth of information on compound drug-likeness in a simple to use, intuitive format with excellent output graphics.”

Bill Simmons
Loyola University

“PhysChem, ADME, Tox in one sleek interface that's very user-friendly.”

Regis Leung-Toung
Apotex

“[Our] main reasons for choosing Percepta were its ease of use, configurability, and ability to use existing in-house algorithms.”


Merck KGaA

Product Features

ADME Property Calculator Features

  • Calculate ADME properties for organic molecules from structure (draw in-app, or copy/paste from third-party drawing packages); SMILES string; InChI code; imported MOL, SK2, SKC, or CDX files; or search by name in the built-in dictionary
  • Automatic detection of tautomeric forms (for applicable prediction modules)
    • Select the canonical or major form
  • Structure highlighting to indicate sub-structure/atomic contributions (select modules)
  • Calculate properties for groups or libraries of compounds and use built-in tools to sort, filter, plot, and rank results
    • Set user-defined label colors
    • Filter results numerically
    • Sort results by ascending/descending values
  • Retrieve results of previously calculated values in your activity history
  • Report results to PDF or copy/paste to your application of choice
  • Train algorithms with experimental data in select modules—CYP450 Inhibition, Distribution, LogP, LogD, pKa, and P-gp Specificity
  • Add custom models/algorithms and in-house prediction algorithms by connecting to an existing web service using an XML protocol, or in the form of a DLL (available in thin client deployments only)
  • Gain insights into structure-property relationships
  • Understand and modify the pharmacokinetic profile of lead compounds
    • Good/bad indicators for Lipinski’s rule-of-5, lead-likeness, cell permeability, plasma protein binding, CNS penetration, metabolic stability, and CYP inhibition
  • Modify sets of structures with the interactive optimization tool
    • Generate libraries of analogs with substituent modifications based on an optimal property profile
    • Sort, filter, and prioritize hundreds of structural analogs according to your desired property profile
    • Create and use custom fragment libraries
    • Target synthetically accessible fragments with the built-in retrosynthesis tool
  • Quantitatively predict blood-brain barrier (BBB) permeability.
    • Rate of brain penetration (logPS)
    • Extent of brain penetration (logBB)
    • Brain/plasma equilibration rate (log(PS * fu, brain))
  • Alter values for underlying physicochemical properties—logP, pKa, unbound fraction in plasma—to investigate the effect on BBB permeability
  • Visualize results
    • “Traffic light” indicators of permeability
    • Plot of the BBB penetration of compound under investigation with well-known CNS-active and peripherally-active drugs
  • Alerts for compounds that undergo facilitated diffusion or active efflux across the BBB
  • Submodules for LogPS and LogBB provide detailed prediction results
    • Up to 3 most similar structures in the internal library provided, with experimental values and literature references
  • Calculate the probability of a compound exhibiting “general” (IC50 < 50 μM) or “effective” (IC50 < 10 μM) inhibition of 5 major human cytochrome P450 isoforms: 3A4, 2D6, 2C9, 2C19, 1A2
    • Results displayed as a bar plot with confidence intervals
  • Estimates of prediction accuracy for each result
    • Reliability index and display of 5 most similar structures in the internal library with experimental values and literature references
  • Train the algorithm with experimental data
  • Calculate the probability that a compound will be metabolized by the cytochrome P450 (isoforms 3A4, 2D6, 2C9, 2C19, 1A2)
    • Results displayed as a bar plot with confidence intervals
  • Estimates of prediction accuracy for each result
    • Reliability index and display of 5 most similar structures in the internal library with experimental values and literature references
  • Train the algorithm with experimental data

Plasma Protein Binding

  • Predict plasma-protein binding (PPB)
    • Percentage bound to human plasma proteins (% PPB)
    • Affinity constant to serum albumin (logKaHSA)
  • List of plasma proteins contributing to binding
  • Estimate of prediction accuracy
    • Reliability index and display of 5 most similar structures in the internal library with experimental values and literature references
  • Train with experimental data

Volume of Distribution

  • Calculate the extent of tissue binding and Volume of Distribution (Vd) based on a physiological Øie-Tozer model
  • Alter values for key underlying properties—logP, and unbound fraction in plasma—to investigate the effect on distribution into the tissues
  • Estimate of prediction accuracy
    • Display of 5 most similar structures in the internal library with experimental values and literature references
  • Calculate the maximum recommended daily dose in humans (mg/kg/day)—for oral administration
  • Estimate of prediction accuracy
    • Reliability index and display of 5 most similar drugs in the internal library with experimental values and literature references
  • Indication of adverse effects on organs
  • Indication of toxicity in mouse (for oral and intravenous administration)
  • Alert for unreliable predictions

Active Transport

  • Predict whether or not a compound is a likely substrate for oligopeptide transporter (PepT1), or bile acid transporter (ASBT)
  • Predict carrier-mediated transport by other systems: monocarboxylic acid transporter MCT1, amino acid carriers, etc.
  • Reference data for similar structures

Bioavailability

  • Predict the percentage of drug that will reach systemic circulation after oral administration (%F)
  • Explore dose-dependence
  • See the contribution of endpoints that affect oral bioavailability: solubility, stability (pH <2), passive absorption, first-pass metabolism, P-gp efflux, active transport
    • Results displayed with color-coding to indicate good or poor bioavailability
  • Estimate of prediction accuracy
    • Display of up to 5 similar structures in the internal library with experimental values and literature references

Absorption

  • Predict passive permeability across jejunal epithelium based on logP and pKa
    • Enter experimentally measured values to improve prediction
    • Alter logP and pKa values to model the limiting effect of lipophilicity and ionization on intestinal permeation rate
  • Calculate the extent of oral absorption (%HIA)
  • Estimate relative contributions of transcellular and paracellular routes to overall %HIA
  • Provides access to Absorption DB—a fully browsable and searchable database containing experimental data that was used for the development of the HIA model together with corresponding literature references
  • Experimental values of the relevant properties for up to 3 similar structures from the internal set

Caco-2

  • Calculate passive permeability across Caco-2 cell monolayers at specified pH and stirring conditions based on logP and pKa values, or logD at specific pH
    • Adjust pH and stir rate
    • Alter logD, or logP and pKa values to model the limiting effect of lipophilicity and ionization on Caco-2 permeation rate
  • Information about the relative contributions of transcellular and paracellular routes to overall Caco-2 permeability
  • Estimate of prediction accuracy
    • Display of up to 3 similar structures in the internal library with experimental information and literature references

P-gp Inhibitors

  • Estimate the probability that a compound inhibits P-glycoprotein and that it is a potent inhibitor
  • Classify a compound as an inhibitor or non-inhibitor of P-glycoprotein based on structural features and physicochemical properties
  • Estimate of prediction accuracy
    • Reliability of prediction and display of 5 most similar structures in the internal library with experimental values and literature references
  • Train with experimental data

P-gp Substrates

  • Estimate the probability that a compound is a P-glycoprotein substrate and that it is a high-affinity substrate
  • Classify a compound as a substrate or non-substrate of P-glycoprotein based on ionization, molecular size and compound class (peptide, alkaloid, anthracycline, etc.)
  • Estimate of prediction accuracy
    • Reliability of prediction and display of 5 most similar structures in the internal library with experimental values and literature references
  • Train with experimental data

Explore the dependency of various pharmacokinetic parameters on physicochemical properties

  • Visualize the dependence of the following parameters on dose, logP, and pKa (results provided as graphical plots. Use predicted values or enter experimentally derived values for logP and pKa):
    • %F–LogP (the dependence of oral bioavailability on logP at a defined dose)
    • Cp(Max)–LogP (the dependence of maximum achievable drug concentration on logP at a defined dose)
    • %F–Dose (bioavailability–dose relationship)
    • Cp(Max)–Dose (maximum achievable drug plasma levels at different doses)
    • Cp–Time (simulation of plasma concentration-time curves for oral and intravenous administration)
  • Estimate absorption (ka), total body clearance (ke), solubility in the gastrointestinal tract (SolGI), volume of distribution (Vd), and presystemic metabolism in the gut and liver (first-pass clearance) based on entered physicochemical property values
    • Alter any of these values to recalculate
    • Choose to ignore first-pass clearance
  • Calculate maximum achievable plasma level (Cp(Max)) and the corresponding time (Tmax), area under the concentration-time curve (AUC) after oral and intravenous administration, and oral bioavailability (%F)
  • Predict metabolic soft spots for metabolism by human liver microsomes (HLM) and the five major cytochrome P450 enzymes (1A2, 2C19, 2C9, 2D6, 3A4) to help:
    • Identify metabolic sites on new chemical entities
    • Guide synthesis of compounds with improved metabolic properties
    • Identify and elucidate likely metabolite structures
  • Color mapping on structure indicates the probability of metabolism at each atom
  • Probability score (0–1) for each atom as a likely site of metabolism
  • View the expected metabolic reaction type at every atom: aliphatic or aromatic hydroxylation, N-dealkylation, O-dealkylation, or S-oxidation
  • Estimate of prediction accuracy
    • Reliability of prediction and display of 5 most similar structures in the internal library. Indication of similarity of the metabolic site and experimental result (Metabolized, or Not Metabolized)
Deployment/Integration Options

Choose the Deployment Option That Works for You

Desktop/Thick Client

Install ACD/ADME Suite on individual computers to use the full graphical user interface and to train the trainable modules with your own data.

Batch

Calculate ADME properties for tens of thousands of compounds with minimal user intervention. Batch deployment is compatible with Microsoft Windows and Linux operating systems. Plug in to corporate intranets or workflow tools such as Pipeline Pilot.

Percepta Portal/Thin Client

Use a browser-based application to predict ADME properties. KNIME integration components are available. Host on your corporate intranet or the cloud. Available for Linux and Windows OS.

More Reasons to Use ADME Suite

Train the Models with Your Own Data for Better Accuracy

Request a Consultation or Demo

Quite often R&D organizations build their own ADME property prediction models with experimental data collected in-house. While these models offer excellent accuracy because they represent the chemical space of interest, updating and supporting in-house models is time-consuming.

ADME Suite allows you to use curated experimental data to expand the training database and the applicability domain of trainable models. So, you get the accuracy of an in-house model with the support and broad applicability of a commercial product. And because the training is easy to do, you won’t need a computational chemist or software engineer.

Request a Consultation or Demo

What's New!

What's New in ADME Suite v2021

  • Add Similarity Index (SI) and the Data-Model Consistency Index (DMCI) values for predicted results, in the Spreadsheet Workspace, for a better understanding of their reliability
  • Calculate the pH value at which a molecule has zero net charge (the isoelectric point)
  • Activate/deactivate extended tool tips from the Expert Panel

PhysChem Suite

Many of the ADME characteristics of a molecule are directly impacted by its physicochemical properties. That is why we include PhysChem Suite with your purchase of ADME Suite.