Case Study
Solubility and Permeability Prediction Service

Inquiry
Solubility and Permeability Prediction Service - CD ComputaBio
AI for Drug Absorption

Solubility and Permeability Prediction Service

CD ComputaBio helps you evaluate aqueous solubility and membrane permeability together to identify absorption bottlenecks, formulation risk, and the analogs most likely to improve oral exposure.

Balance
Context
Act
Decide
Our Services

Solubility and Permeability Prediction Services

Each service can be used independently or combined into a staged workflow that moves from broad candidate screening to detailed absorption and formulation analysis.

Service-first project design

The workflow begins with the absorption or formulation decision, not with a predefined simulation package.

01
Candidate Discovery

Solubility Risk Prediction

Rank compounds by aqueous solubility risk, considering intrinsic versus apparent behavior, pH sensitivity, solid-state factors, and formulation constraints.

02
Absorption Assessment

Permeability Prediction

Estimate passive or Caco-2-oriented permeability with endpoint-specific models, applicability-domain review, and transport-mechanism interpretation.

03
Trade-Off Analysis

Solubility–Permeability Balance

Compare analogs across ionization, lipophilicity, polarity, and size to avoid optimizing one property at the expense of the other.

04
pH & Ionization

pH-Dependent Behavior Modeling

Analyze how ionization state, pKa, and logD influence solubility and permeability across the physiological pH range.

05
Series Optimization

Analog-Series Design

Use matched molecular pairs and structure–property relationships to guide analog design that improves the overall absorption profile.

06
Formulation Strategy

Formulation and Assay Prioritization

Determine which experiments—kinetic or thermodynamic solubility, PAMPA, Caco-2, or solid-form analysis—will best resolve the dominant bottleneck.

07
Regulatory Context

BCS-Oriented Risk Interpretation

Provide Biopharmaceutics Classification System (BCS) –oriented guidance without claiming formal classification from prediction alone.

The Absorption Balance

Every gain has a counterweight

More polarity may improve dissolution while weakening membrane passage; more lipophilicity can reverse that trade-off. We model these shifts together instead of optimizing isolated endpoints.

The result is a property-balance brief that identifies the limiting step, the safest design margin, and the measurement most likely to resolve uncertainty.

Balance map
Dissolution reserve

How much aqueous availability remains across the relevant pH range?

Membrane passage

Can the neutral fraction cross efficiently without excessive efflux exposure?

Charge-state shift

Where does ionization change the dominant absorption mechanism?

Developability margin

Which risks belong to molecular design, and which can formulation realistically absorb?

Failure-Driven Design

Translate absorption failure into a molecular design question

Compound optimization becomes more efficient when the observed performance loss is connected to a specific solubility, permeability, or formulation mechanism.

Common absorption observations

01
Low or variable oral exposure

May indicate poor solubility, inadequate permeability, or a combination of both.

02
Food effect or pH-dependent exposure

May reflect ionization-related solubility changes or formulation sensitivity.

03
High in-vitro activity but low in-vivo response

May arise from poor dissolution, efflux, or metabolic instability.

04
Inconsistent Caco-2 results

May involve assay conditions, transporter interplay, or compound-specific artifacts.

05
Poor developability for oral formulation

May reflect low solubility, high lipophilicity, or solid-form instability.

Possible computational responses

The modeling strategy is selected according to the suspected failure mechanism and the evidence needed to choose a new compound or formulation.

Solubility limitation Intrinsic/apparent solubility prediction, pH profiling, solid-state risk assessment
Permeability limitation Passive permeability estimation, Caco-2-oriented QSPR, efflux risk flags
pH-dependent behavior pKa, logD, charge-state analysis, and solubility–pH profiles
Formulation uncertainty Solubility method selection, excipient compatibility, and developability scoring
Analog optimization Matched-pair analysis, structure–property relationships, and trade-off ranking
Ionization Lanes

Read absorption behavior through charge state

Each ionization class creates a different balance of dissolution, passive transport, assay sensitivity, and formulation opportunity.

01

Neutral lane

Benchmark non-ionizable compounds and establish baseline absorption expectations.

Watch: lipophilicity and solid state
02

Acidic lane

Evaluate pH-dependent solubility and permeability for carboxylic acids, sulfonamides, and phenols.

Watch: intestinal pH transition
03

Basic lane

Assess ionization behavior, solubility at gastric pH, and permeability in the intestine.

Watch: gastric-to-intestinal shift
04

Zwitterionic lane

Analyze complex charge-state behavior and its impact on absorption and formulation.

Watch: low passive diffusion
05

Multi-pKa lane

Optimize solubility, permeability, and developability within a single chemical series.

Watch: shifting microstates
Computational Platform

Connect molecular properties to absorption-level decisions

Solubility and permeability behavior spans several length and time scales. QSPR models can provide rapid estimates, machine learning can capture nonlinear relationships, and pH-dependent analysis can clarify ionization effects.

Higher-resolution approaches can then examine transport mechanisms, formulation interactions, and developability for selected candidates.

Staged modeling reduces unnecessary calculation

Broad AI and QSPR screening can narrow the candidate space before more detailed experimental or simulation work is performed.

01
QSPR Modeling

Interpretable structure–property relationships for solubility, permeability, and ionization.

02
Machine Learning

Nonlinear models for complex property relationships, with applicability-domain assessment.

03
pH-Dependent Analysis

pKa, logD, charge-state profiling, and solubility–pH curve generation.

04
Caco-2 & PAMPA Modeling

Endpoint-specific permeability predictions with validation and interpretation.

05
Formulation & Developability

Integration of property predictions with formulation risk and experimental follow-up planning.

Representative Project Questions

Different absorption problems require different compound strategies

These examples illustrate how a project can be structured around a specific experimental bottleneck.

Oral Lead Ranking

Which compound has the best balance of solubility and permeability?

Compare solubility, permeability, ionization, and lipophilicity to identify the lead with the lowest absorption risk.

Output: prioritized compounds with trade-off maps and experimental follow-up recommendations.
Analog Optimization

How can polarity be increased without losing permeability?

Use matched molecular pairs to identify structural changes that improve solubility while maintaining or enhancing permeability.

Output: design hypotheses with predicted property profiles and risk assessments.
Formulation Handoff

Which formulation approach is most likely to succeed?

Evaluate solubility, solid-state risk, and developability to prioritize formulation strategies and experiments.

Output: formulation recommendations and a prioritized assay plan.
BCS Assessment

Is the compound likely to be BCS Class 2 or Class 4?

Provide a BCS-oriented risk interpretation based on predicted solubility and permeability, with clear uncertainty and follow-up advice.

Output: BCS risk assessment and recommended confirmatory experiments.
Project Workflow

From absorption failure to a compound ready for experimental testing

The workflow is customized around the compound series, available data, and the specific decision the client needs to make.

01

Define the Absorption Problem

Identify solubility limitation, permeability barrier, pH sensitivity, or formulation risk.

02

Build the Compound Space

Curate structures, properties, measured data, and experimental context.

03

Model Critical Properties

Apply QSPR, machine learning, or pH-dependent analysis according to the key uncertainty.

04

Compare Trade-Offs

Rank solubility, permeability, ionization, and developability together.

05

Plan Validation

Deliver prioritized compounds or formulations with recommended controls, measurements, and next-step criteria.

Project Deliverables

Results designed for compound selection and formulation decisions

The final package can combine candidate rankings, molecular interpretation, calculated datasets, property profiles, and a targeted validation plan.

01 Compound Ranking

Prioritized compounds with solubility, permeability, and ionization scores.

02 Property Profiles

pH-solubility curves, permeability estimates, pKa, logD, and charge-state analysis.

03 Trade-Off Maps

Visual comparisons of solubility vs. permeability for analog series.

04 Technical Data Package

Structures, descriptors, model outputs, plots, and documentation.

05 Mechanistic Interpretation

Explanation of the molecular features driving favorable or unfavorable absorption behavior.

06 Validation Recommendations

Suggested assays, controls, and experimental follow-up to confirm predictions.

Frequently Asked Questions

Planning a solubility and permeability prediction project

Can intrinsic and apparent solubility be modeled together?

They must be distinguished. Apparent solubility can reflect ionization, salts, supersaturation, aggregation, or protocol effects, whereas intrinsic solubility refers to the neutral form under defined conditions.

Does high Caco-2 permeability guarantee good oral absorption?

No. Dissolution, solubility, efflux, metabolism, transporters, dose, formulation, and intestinal conditions also influence exposure.

Can a predicted BCS class be provided?

We can provide BCS-oriented risk interpretation, but formal classification depends on defined experimental solubility, permeability, dose, and regulatory criteria.

Can pH-dependent behavior be considered?

Yes, when pKa, charge state, logD, and relevant pH conditions are available or can be estimated, with uncertainty clearly noted.

How do you choose between PAMPA and Caco-2 follow-up?

PAMPA emphasizes passive diffusion, while Caco-2 can reflect cellular barriers and transporter effects. The choice depends on the mechanism and decision the experiment must resolve.

What information is needed to start a solubility and permeability project?

Helpful inputs include compound structures, desired endpoint definitions, pH range, assay context, measured data when available, dose and route context, and the decision the computational study should support.

Which compound can deliver the right balance of solubility and permeability for your target?

Share your compound series, available data, observed absorption issues, and performance targets. CD ComputaBio can develop a customized solubility and permeability prediction workflow.

Start Your Project

Online Inquiry

Submit your project details below, and our team will respond within 24 hours.

x
Need help getting the data you need?

Talk to our technical team about your project!

I Want To Talk