Percepta® Suite

Physicochemical, ADME and Toxicity Predictions

Accelerate drug discovery and lead optimization with structure-based predictions that provide insights into molecular behavior, pharmacokinetics, and safety.

Trusted By Companies Worldwide

Explore

Predict physicochemical, ADME, and toxicity properties from chemical structure.

Evaluate and visualize predicted results using sorting and plotting tools.

Assess the reliability of predicted property values to support confident decision-making.

Train prediction models with proprietary experimental data to improve predictions for novel chemical space.

Predict with Confidence Across Key Property Domains

Explore Structure-Property Relationships

Predict physicochemical properties from chemical structure to support compound design and optimization.
Evaluate and interpret structure–property relationships influencing solubility, lipophilicity, ionization, and developability.
Investigate molecular property profiles to guide lead optimization and compound selection.

Evaluate Pharmacokinetic Behavior

Predict pharmacokinetic properties from chemical structure to evaluate absorption, distribution, metabolism, and excretion behavior.
Assess exposure, bioavailability, metabolic stability, and more to support candidate selection and optimization.
Leverage PK predictions to identify compounds with favorable in vivo performance earlier in discovery.

Assess Toxicity Risks Earlier

Predict toxicity endpoints and safety liabilities from chemical structure to support early risk assessment.
Evaluate potential adverse effects to prioritize safer compounds and reduce late-stage attrition.
Leverage predictive safety data to guide compound selection and optimization decisions.

Predictive Modules in Percepta Suite

PhysChem

Physicochemical properties:

Aqueous Solubility*
Boiling Point/Vapor Pressure
LogD
LogP*
pK_a
Sigma

Molecular Descriptors:

Density
Freely Rotatable Bonds
H-Bond Donors and Acceptors
Index of Refraction
Molar Refractivity
Molar Volume
Molecular Weight
Parachor
Polar Surface Area
Polarizability
Rule-of-5
Surface Tension

ADME

Blood Brain Barrier Permeation
Cytochrome P450 Inhibitors*
Cytochrome P450 Substrates*
Distribution*
Maximum Recommended Daily Dose
Oral Bioavailability
Passive Absorption
P-gp Specificity*
PK Explorer
Regioselectivity of Metabolism

Toxicity

Acute Toxicity*
Aquatic Toxicity*
Endocrine System Disruption
Mutagenicity*
Health Effects
hERG Inhibition*
Irritation

*Trainable with your own experimental data

Benefits

Accelerate Decision-Making with Predictive Insight

Fast, Accurate, Reliable Results

Calculate properties for single compounds or large compound libraries using curated experimental data.

Evaluate prediction confidence using a reliability index, similar structures, and literature references.

Convenient Visualization

Visualize substructure and atomic contributions to predicted property values with color mapping (select models).

Quickly identify favorable and unfavorable compounds in libraries using user-defined color coding.

Improve Predictions with Machine Learning

Train prediction models using your own experimental data to extend prediction accuracy to proprietary chemical space and build project-specific training sets for fine-tuned prediction accuracy.

Easy to Use

Draw or import a chemical structure to generate molecular property predictions and train models with your own experimental data through an intuitive interface designed for chemists, not programmers.

Gain Deeper Insights

Identify trends, prioritize compounds, and evaluate complete molecular property profiles using interactive scatter plots, filtering, sorting, and ranking tools to support confident decision-making.

Augment Structured Data for AI/ML

Annotate large structured datasets with physicochemical, ADME and toxicity property predictions to provide additional context before feeding them into machine learning (ML) and artificial intelligence (AI) models.

Request a Demo

Insights for Modern Drug Discovery

Blog

Navigating Drug Design in ‘Beyond the Rule of 5’ Landscape

As drug discovery expands beyond traditional boundaries, complex small molecules like PROTACs challenge old rules. Discover how our predictive platforms help scientists design bioavailable, scalable drugs in the evolving ‘bRo5’ space with precision and confidence.

Read Blog

Blog

The Importance of Ionization in Pharmaceutical R&D

Discover why ionization is critical throughout pharmaceutical R&D, from lead optimization and formulation to ADME prediction and chromatography.

Read Blog

How it Works

Predict in Seconds with
Percepta Suite

Draw/import your structure
Select the property of interest
Review results and make decisions
Report to PDF or copy/paste

Request a Demo

Features of Percepta Suite

Physiochemical

General Features

Calculate physicochemical properties for organic molecules ranging from traditional drug-like structures to higher molecular weight compounds up to a recommended MW limit of ≤2000 Daltons (e.g. peptides, proteins, polymeric units, and other bRo5 compounds).
Start with a 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.
Several algorithms available for many predictions—see individual module for more details.
Automatic detection of tautomeric forms (for applicable prediction modules).
- Select the canonical or major form
Evaluate results.
- Structure highlighting for sub-structure/atomic contributions
- Calculation protocols
Calculate physicochemical 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
See results for previously calculated values via your activity history.
Estimates of prediction accuracy to assess reliability of predicted values (information provided differs by module and calculation algorithm).
- 95% confidence intervals
- Interactive calculation protocols
- Reliability Index and display of 5 most similar structures in the training library with experimental values and literature references
Report results to PDF or copy to your application of choice
Download QPRF and QMRF documents for LogP module (GALAS model) and LogS_{0 module}
Train algorithms with experimental data in select modules—logP, pK_a, logD
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 (not available in batch deployment)

Property-Based Structure Modification and Lead Optimization

Gain insights into structure-property relationships.
Understand and modify the pharmacokinetic profile of lead compounds.
- Good/bad indicators for Lipinksi’s rule-of-5 and lead-likeness.
Identify structural fragments responsible for toxicity.
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.

Aqueous Solubility

Calculate quantitative solubility in pure (unbuffered) water at 25°C.
Predict qualitative solubility at pH 7.4—compounds categorized from highly soluble to insoluble.
- GALAS (Global, Adjusted Locally According to Similarity) algorithm.
- Display of 5 most similar structures from the training set with experimental values.
Estimate intrinsic solubility—logS_0.
- Predictions based on a training set of >6800 compounds and a GALAS algorithm.
- Reliability value and up to 5 most similar structures from the training set provided with experimental data.
Predict pH-dependent aqueous solubility—logS.
- Solubility at physiological pH values of interest (pH 1.7, 4.6, 6.5, 7.4, 8.0).
- Plot of predicted pH versus solubility.
Train the model with experimental values.

Boiling Point/Vapor Pressure

Estimate the boiling point of organic compounds as a function of pressure.
Predict the vapor pressure as a function of temperature.
Estimate the enthalpy of vaporization at the boiling point.
Estimate flash point at the temperature unit of your choice.
View results in a table or graphical plot.

LogP

Predict logP—choose from three prediction algorithms:
- Classic
- GALAS (Global, Adjusted Locally According to Similarity).
- Consensus logP based on the other two models.
Detailed calculation protocol lists all contributing functional groups, carbon atoms, and interactions through aliphatic, aromatic, and vinylic systems (Classic).
- Click protocol entry to highlight the corresponding entity on the structure.
Color highlighting of the molecule to highlight hydrophilic/lipophilic substructures (GALAS).
Train the model with experimental values to improve predictions for proprietary chemical space.
- Create and select different training libraries for calculations, or switch to the built-in algorithm.

Learn more about our LogP calculator

LogD

LogD predictions are based on the logP and pK_a models of PhysChem Suite

Select from a variety of logP and pK_a algorithms (default: logP Consensus, pK_a Classic).
View logD calculation results by pH.
- Physiologically relevant values (1.7, 4.6, 6.5, 7.4, 8.0).
- Click and drag across the plot (logD vs pH) for logD at a pH value of interest.
- Add/remove predictions at a specific pH value.
Train the model with experimental values of logP and pK_a to improve predictions for proprietary chemical space.
- Create and select different training libraries for calculations, or switch to the built-in algorithm.

Learn more about our LogD module

pKa

Calculate the acid dissociation constant (pK_a) under standard conditions (25°C, zero ionic strength) in aqueous solution for every ionizable group.
Choose from two different algorithms: pK_a Classic (default calculator) and GALAS
Information about each ionization process (dissociation reaction) for all stages of ionization.
Color-coding of ionizable groups: red = acidic, blue = basic, purple = amphoteric ionization centers; color intensity indicates acid/base strength.
Calculation of the strongest acid and base dissociation constants.
Reliability range (in ±log units) for calculated pK_a values.
Detailed calculation protocol for each predicted ionization (referred to as dissociation stage).
- Hover on a dissociation stage to see the related ionizable center highlighted on the structure.
- Click structure fragment to see it highlighted on the structure.
Train the algorithm with experimental data.

Learn more about our pK_a calculator

Additional pKa GALAS Model Features

Display of the percentage contribution of individual ionization microstages to the final pK_a.
View calculated pK_a values as a function of pH in interactive plots (pH 0-14) and tables (select pH values including the physiologically relevant values 1.7, 4.6, 6.5, 7.4).
- Net charge vs. pH.
- Click and drag slider on the plot to see the ionic forms present at the pH of interest.
- See the fraction of all ionic forms present at a pH of interest.
- Protonation state vs. pH.
- Click on the protonation state label to display/hide its curve on the plot.
- Ionogenic group state vs. pH.

Sigma

Calculate substituent-specific parameters for selected fragments of the molecule in aqueous solution, at zero ionic strength and 25°C.
- Electronic substituent constant (Hammett)
- Steric constants (molar volume, molar refractivity)
- Hydrophobic constant (Hansch Pi)
High accuracy—typical calculation accuracy of ±0.05.
Internal database contains >850 substituents and >3000 carefully derived experimental electronic constants.

Other Molecular Descriptors

Density
Freely Rotatable Bonds
H-Bond Donors and Acceptors
Index of Refraction
Molar Refractivity
Molar Volume
Molecular Weight
Parachor
Polar Surface Area
Polarizability
Rule-of-5
Surface Tension

ADME

General 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, pK_a, 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)

Property-Based Structure Modification and Lead Optimization

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

Blood-Brain Barrier Permeability

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, pK_a, 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

Cytochrome P450 Inhibitors

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

Cytochrome P450 Substrates

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

Distribution

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

Maximum Recommended Daily Dose

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

Oral Bioavailability

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

Passive Absorption

Absorption

Predict passive permeability across jejunal epithelium based on logP and pK_a
- Enter experimentally measured values to improve prediction
- Alter logP and pK_a 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 pK_a values, or logD at specific pH
- Adjust pH and stir rate
- Alter logD, or logP and pK_a 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 Specificity

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

PK Explorer

Explore the dependency of various pharmacokinetic parameters on physicochemical properties

Visualize the dependence of the following parameters on dose, logP, and pK_a (results provided as graphical plots. Use predicted values or enter experimentally derived values for logP and pK_a):
- %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 (k_a), total body clearance (k_e), solubility in the gastrointestinal tract (Sol_GI), volume of distribution (V_d), 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)

Regioselectivity of Metabolism

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)

Toxicity

General Features

Calculate toxicity endpoints 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
Structure highlighting to indicate sub-structure/atomic contributions (present in some modules)
Calculate toxicity endpoints 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
Download QMRF and QMRF documents for the Mutagenicity (Ames Test) module
Train algorithms with experimental data in select modules—acute toxicity, aquatic toxicity, mutagenicity, hERG inhibition, logP, logD, and pK_a
Add custom models/algorithms and in-house prediction algorithms by connecting to an existing web service using an XML protocol, or with a DLL (available in thin client deployments only)

Property-Based Structure Modification and Lead Optimization

Gain insights into structure-property relationships
Understand and modify the pharmacokinetic profile of lead compounds
- Good/bad indicators for Lipinksi’s rule-of-5, lead-likeness, and toxicity endpoints
Identify structural fragments responsible for hazardous activity—hERG inhibition and mutagenicity
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

Acute Toxicity

LD₅₀

Calculate LD₅₀ (mg/kg) for mice under oral, intraperitoneal, intravenous, and subcutaneous administration; and for rats under oral and intraperitoneal administration
Estimate of prediction accuracy
- Reliability of prediction and display of 5 most similar structures in the internal library with experimental LD₅₀ values
Train the model with experimental data

Acute Toxicity Categories

Predict the probabilities that LD₅₀ will demonstrate various levels of acute toxicity following oral administration (based on rodent data)
Categorize compounds for “Oral Acute Toxicity Hazard” as defined by the OECD (Organization for Economic Cooperation and Development)
- Hover over the label for details
Estimate of prediction accuracy
- Display of 5 most similar structures in the internal library with experimental values

Hazards

Identify fragments that may be responsible for high acute toxicity
- Color-map on the structure
- Tabbed results provide detailed information for each fragment
Learn how different routes of administration impact toxicity—intravenous, oral, and intraperitoneal
Distribution density plot illustrating :
- The frequency of compounds with different LD₅₀ ranges in the training set
- Compounds that contain the highlighted fragment
- T-Test results demonstrating whether the presence of a highlighted fragment leads to a statistically significant increase in toxicity
Box and whisker plot of compounds that contain the hazardous fragment compared with the full training set
- Display of the 5 most similar structures in the internal library with the selected hazardous fragment with experimental values

Aquatic Toxicity

Predict LC₅₀ values (mg/L) for Fathead minnow (Pimephales promelas) and Water flea (Daphnia magna)
Predict IGC₅₀ values (mg/L) for Ciliate protozoa (Tetrahymena pyriformis)
Estimate of prediction accuracy
- Reliability of prediction and display of 5 most similar structures in the internal library with experimental values
Train the model with experimental data

Endocrine System Disruption

Predict the probabilities of estrogen receptor binding affinity exceeding two different thresholds
- Classify the compounds by their relative binding affinity for the estrogen receptor compared to estradiol-based on LogRBA
Estimate of prediction accuracy
- Reliability of prediction and display of 5 most similar structures in the internal library with experimental LogRBA values and literature references

Mutagenicity

Predict the probability of a positive Ames test
- Color-map of atoms/functional groups in the structure that contribute to mutagenicity potential
Estimate of prediction accuracy
- Reliability of prediction and display of 5 most similar structures in the internal library with overall experimental Ames test result
Browse the mutagenicity database for:
- Information about studies conducted with each compound
- Tested bacterial strains
- The presence or absence of metabolic activation, and other experimental conditions
Train the model with experimental data

Health Effects

Estimate the probability of adverse effects (at the therapeutic dose) for blood, cardiovascular system, gastrointestinal system, kidney, liver, and lungs
Color-map of structural fragments that contribute to adverse effects
Estimate of prediction accuracy
- Display of 5 most similar structures in the internal library with route, species, and a listing of clinically observed toxic effects.

hERG Inhibition

Predict the probability of human ether-a-go-go related gene (hERG) channel inhibition at clinically relevant concentrations (K_i < 10 μM)) using two different models—one based on structural descriptors, and one based on physicochemical properties
- Simulate how different experimental assays (e.g., conventional or automated patch-clamp, ligand replacement, etc.) impact the measured value of hERG inhibition potential
- Explore the influence of physicochemical and molecular properties on hERG inhibition potential
Explore how physicochemical properties (acid/base pK_a, logP) and molecular weight impact hERG inhibition
- Color “heat map” displays interdependence of hERG inhibition, pK_a, and logP
Estimate of prediction accuracy
- Reliability of prediction and display of 5 most similar structures in the internal library with experimental results (inhibitor, non-inhibitor) and literature references
Train the model with experimental data

Irritation

Eye Irritation

Calculate the probability of eye irritation in a standard Draize (rabbit) at 100mg and 500mg
- Statement of applicable rules and description of functional groups that contribute to eye irritation
- Highlighted contributing structural fragments
Estimate of prediction accuracy
- Display of up to 5 most similar structures in the internal library with experimental values and literature references

Skin Irritation

Calculate the probability of skin irritation in a standard Draize (rabbit) at 100mg and 500mg
- Statement of applicable rules and description of functional groups that contribute to skin irritation
- Highlighted contributing structural fragments
Estimate of prediction accuracy
- Display of up to 5 most similar structures in the internal library with experimental values and literature references

Percepta Suite

Other vendors

Percepta Suite Trusted PhysChem predictions built on decades of scientific research.

Other vendors Prediction quality and scientific depth vary by platform.

Percepta Suite Comprehensive ADME and toxicity assessments in one platform.

Other vendors ADMET coverage varies, with some solutions emphasizing specific discovery stages or scientific domains.

Percepta Suite Easily and quickly retrain supported models using your own experimental data.

Other vendors Model customization may require specialist expertise or external support.

Percepta Suite Interactive tools reveal structure-property relationships and molecular drivers behind predicted properties.

Other vendors Insight tools vary by platform and may focus on specific workflows or endpoints.

Percepta Suite Confidence metrics, applicability domains, rich prediction metadata, and model documentation built in.

Other vendors Limited visibility into prediction reliability or model methodology.

Percepta Suite Built-in QMRF and QPRF reporting for regulatory support for select models.

Other vendors Regulatory documentation may require additional effort or external tools.

What Our Customers Say About Percepta Suite

What is the difference between Percepta Suite and PhysChem Suite?

PhysChem Suite is focused specifically on physicochemical property prediction, including logP, logD, pK_a, aqueous solubility, and related molecular descriptors.

Percepta Suite combines PhysChem Suite with ADME and toxicity prediction capabilities in a single platform, bringing together physicochemical, pharmacokinetic, and toxicological property prediction to support broader drug discovery, molecular design, and lead optimization workflows.

Is Percepta Suite the same as ACD/Labs Percepta?

What physicochemical/ADME properties and toxicity endpoints can be predicted in Percepta Suite?

Percepta Suite predicts a broad range of physicochemical properties, ADME properties, and toxicity endpoints from chemical structure. These include properties such as pK_a, logP, logD, and aqueous solubility; ADME endpoints such as absorption, distribution, cytochrome P450 activity, and P-glycoprotein specificity; and toxicity endpoints including mutagenicity, hERG inhibition, acute and aquatic toxicity, and adverse effects on organs.

Read the complete list of available prediction modules.

Why are physicochemical properties important for ADME and toxicity prediction?

Physicochemical properties influence how a compound behaves in biological systems, including absorption, distribution, membrane permeability, and interactions with biological targets. Because ADME and toxicity endpoints are closely linked to molecular features such as ionization state and lipophilicity, accurate physicochemical data helps improve the reliability of ADME and toxicity predictions and supports better decision-making earlier in drug discovery.

Can Percepta Suite be trained with proprietary experimental data?

Yes. Select models within Percepta Suite can be trained using proprietary experimental data to improve prediction accuracy and better reflect an organization’s specific chemical space.

Directly trainable endpoints include:

LogP
pK_a
Distribution
P-glycoprotein specificity
Cytochrome P450 substrate and inhibition models
Aqueous solubility
Acute toxicity
Aquatic toxicity
Mutagenicity
hERG inhibition

Why is it important to train predictors?

Training prediction models with reliable in-house experimental data can improve prediction accuracy for proprietary and novel chemical space. Commercial prediction models are typically built using publicly available datasets and may not fully represent the compounds being investigated in a specific research program. Training helps expand the model applicability domain, reduce prediction error for relevant chemistries, and can save time compared to building and validating entirely new models from scratch.

What deployment options are available for Percepta Suite?

Can Percepta Suite be integrated into third-party or in-house models and workflows?

Yes. Percepta Suite supports integration of third-party and in-house models within computational workflows via a number of programmatic APIs such as RESTful webservice, including integration through platforms such as KNIME. This enables predictive molecular property data to be incorporated into existing modelling, automation, and AI/ML pipelines.

Ready to take the next step?

Take a Tour

See how Percepta Suite can help you with predicting key physicochemical properties and achieving your lead optimization goals.

Request a Demo

Talk to Our Team

Schedule a consultation with our scientific solutions experts to discuss your specific research workflows, requirements, and implementation needs.

Stay up to date

Stay up-to-date on all the latest insights, research and product news from Revvity Signals.

Stay up to date

Signals AI

Signals AI

Signals AI

Your Notifications (0)

Percepta® Suite

Physicochemical, ADME and Toxicity Predictions

Trusted By Companies Worldwide

Property Predictions to Support Drug Design and Discovery

Explore Structure-Property Relationships

Evaluate Pharmacokinetic Behavior

Assess Toxicity Risks Earlier

PhysChem

ADME

Toxicity

Fast, Accurate, Reliable Results

Convenient Visualization

Improve Predictions with Machine Learning

Easy to Use

Gain Deeper Insights

Augment Structured Data for AI/ML

Navigating Drug Design in ‘Beyond the Rule of 5’ Landscape

The Importance of Ionization in Pharmaceutical R&D

How it Works

Predict in Seconds with
Percepta Suite

Features of Percepta Suite

Product Comparison

What Our Customers Say About Percepta Suite

Percepta Suite FAQs

Ready to take the next step?

Take a Tour

Talk to Our Team

Stay up to date

Revvity Signals Login

Percepta® Suite

Physicochemical, ADME and Toxicity Predictions

Trusted By Companies Worldwide

Explore

Property Predictions to Support Drug Design and Discovery

Predict with Confidence Across Key Property Domains

Explore Structure-Property Relationships

Evaluate Pharmacokinetic Behavior

Assess Toxicity Risks Earlier

Predictive Modules in Percepta Suite

PhysChem

ADME

Toxicity

Benefits

Accelerate Decision-Making with Predictive Insight

Fast, Accurate, Reliable Results

Convenient Visualization

Improve Predictions with Machine Learning

Easy to Use

Gain Deeper Insights

Augment Structured Data for AI/ML

Insights for Modern Drug Discovery

Navigating Drug Design in ‘Beyond the Rule of 5’ Landscape

The Importance of Ionization in Pharmaceutical R&D

How it Works

Predict in Seconds withPercepta Suite

Features of Percepta Suite

What Our Customers Say About Percepta Suite

Quote from Bill Simmons

Quote from Tim Tam

Quote from Regis Leung-Toung

Subscribe to receive more information about property predictons

Percepta Suite FAQs

Ready to take the next step?

Take a Tour

Talk to Our Team

Stay up to date

Predict in Seconds with
Percepta Suite