Ref D2
Computational Service
Confidence Reported
Scoped After Feasibility Review
Service Overview
A compound that cannot reach its target is not a drug, whatever its affinity. We predict the absorption and permeability profile — passive permeability, efflux liability, intestinal absorption, oral bioavailability and blood–brain barrier penetration — and, where a compound fails, identify whether the cause is size, polarity, ionisation, hydrogen-bonding or transporter recognition. For CNS programmes we add the multiparameter optimisation scoring that governs brain-penetrant design.
Key Features & Advantages
Cause Diagnosed, Not Only Predicted
A low permeability prediction is accompanied by the property driving it, because a compound failing on polar surface area requires a different fix from one failing on efflux.
Efflux Treated Separately
P-glycoprotein and related transporter liability is predicted independently of passive permeability, which is essential for CNS and oncology programmes where efflux is the usual failure mode.
CNS MPO Scoring
Brain-penetrant programmes receive full multiparameter optimisation scoring with per-property contributions, showing precisely which parameter is holding the score down.
Series Trends Made Visible
Permeability is reported across the series against structural change, so the chemistry team can see which modifications cost absorption and which do not.
Where This Service Is Used
1Deciding which hits from a screen are worth progressing to cell-based assays
2Diagnosing a disconnect between biochemical potency and cellular activity
3Designing CNS-penetrant compounds and predicting brain exposure risk
4Assessing oral bioavailability risk before in vivo pharmacokinetic studies
5Guiding prodrug or formulation strategy for compounds with intrinsically poor absorption
Methods and Techniques Applied
1Passive permeability prediction benchmarked against Caco-2 and PAMPA style endpoints
2P-glycoprotein substrate and inhibitor prediction, with other efflux transporters where models permit
3Human intestinal absorption and oral bioavailability prediction with applicability-domain checking
4Blood–brain barrier penetration prediction and CNS multiparameter optimisation scoring
5Property-based diagnosis linking each failure to polarity, ionisation, size or hydrogen-bond count
6Comparison against reference compounds with known behaviour to place predictions in context
What We Need From You
1Compounds as SMILES or SDF with stereochemistry specified
2Intended route of administration and target tissue, including whether CNS exposure is required
3Any measured permeability, efflux ratio or pharmacokinetic data for calibration
4Known cellular activity data, which often explains whether permeability is the limiting factor
What You Receive
1Absorption and permeability table with predicted values and confidence indicators
2Efflux liability assessment per compound
3CNS MPO scores with per-property breakdown for neuroscience programmes
4Diagnostic commentary attributing each failure to a specific property
5Recommendation of which compounds to progress and which assay would settle the remaining uncertainty
What We Compute and Report
1Predicted passive permeability benchmarked against standard cell-monolayer and artificial-membrane endpoints
2Efflux transporter substrate and inhibitor likelihood, reported independently of passive permeability
3Human intestinal absorption and oral bioavailability estimates with applicability-domain flags
4Blood–brain barrier penetration estimate and CNS multiparameter score with per-property contributions
5Attribution of each predicted failure to the property driving it
Questions We Are Asked Before Scoping
How well do these models predict human absorption?
▸They rank compounds usefully and identify clear failures, but absolute human bioavailability prediction remains unreliable because it also depends on first-pass metabolism, solubility and dissolution rate in vivo.
Is a positive BBB prediction enough for a CNS programme?
▸No. Predicted penetration does not establish free brain concentration at the target, which requires measured unbound brain-to-plasma ratios. The prediction decides what is worth measuring.
Can you model transporter-mediated uptake?
▸Efflux prediction is reasonably mature; active uptake transporter models are substantially weaker and are reported with that caveat rather than presented as equivalent.
Interpretation and Limitations
Computational predictions prioritise hypotheses; they do not independently establish binding, biological activity, therapeutic efficacy, safety or clinical validity. Performance depends on input quality, target class, the structural evidence available and the applicability domain of the selected methods. Scores used for ranking are comparative devices and should not be read as measured quantities. All deliverables are for research use only and are not intended for diagnostic or therapeutic use.
Is This the Right Service for You?
Choose this when
Biochemical potency is not translating into cellular activity
A CNS programme needs brain exposure risk assessed before in vivo work
Oral bioavailability risk must be understood before pharmacokinetic studies are commissioned
Consider another service when
Clearance rather than absorption is the suspected problem
Metabolic Stability & CYP Prediction The molecule sits far outside conventional property space
Macrocycle Design What Goes Wrong, and How We Handle It
These are the failure modes that produce confident-looking results which do not survive the next experiment. Each one is designed against rather than discovered afterwards.
Low permeability assumed to be a passive problem when efflux is the cause
Transporter liability is predicted independently of passive permeability, because the two require different fixes.
Predicted blood–brain barrier penetration read as free brain exposure
The prediction is reported as a triage signal; unbound brain-to-plasma measurement is named as the confirmatory experiment.
Absolute bioavailability quoted from a model
We report relative risk and the property driving it, and state that absolute human values are not reliably predictable.
A Worked Example
A potent series with no cellular activity
The situation
Enzyme IC50 values were in the low nanomolar range while the cell assay showed nothing at ten micromolar.
What the work involved
Passive permeability, efflux liability and ionisation were predicted across the series, and the results were correlated against the structural changes the chemists had made.
What came back
A basic amine introduced three rounds earlier was driving efflux across the whole series. Two neutral replacements were proposed, and the property-versus-potency trade-off was quantified for each.
Illustrative of the shape this work takes. Details are generalised, no client or target is identified, and scope and outcome vary with the system in question.
What Published Work Reports
The results below were published by independent groups and are cited to show what these computational approaches have achieved in the literature. They are not ICDMO project results, and outcomes vary substantially between targets, datasets and programmes. We do not promise comparable results for any particular project.
Property prediction is accurate enough to triage, not to replace measurement
Across the published literature, lipophilicity and surface-property predictions are generally reliable, while aqueous solubility models typically carry errors around one log unit and absolute human pharmacokinetic prediction remains weak. We therefore report predictions with their expected error and applicability-domain status, and recommend measurement at the point where a decision turns on the number rather than the rank order.
Method comparison literature, ongoing ↗Service Workflow
1
Scientific Consultation
We discuss the objective, the decision it supports and the data you hold. Nothing is quoted before we understand what the result has to answer.
2
Feasibility Review
We check that the data, target class and available structural evidence can support the proposed approach, and say plainly where they cannot.
3
Technical Proposal
Scope, methods, deliverables, timeline and price are confirmed in writing, together with the limitations we expect to report.
4
Computation and QC
The analysis runs on pinned tool versions in a containerised environment, with quality checkpoints and method comparison where that is informative.
5
Report and Follow-Up
You receive the ranked results, the documented methods, the limitations and a proposed validation plan, plus support in interpreting them.
Service Process
1
Online Consultation
›
2
Solution Matching
›
3
Service Contract
›
4
Project Execution
›
5
Data Delivery
Specifications & Turnaround
Note: ICDMO delivers computational (in silico) services. Results prioritise hypotheses for testing; they do not by themselves establish binding, biological activity, efficacy or safety. All deliverables are for research use only and are not intended for diagnostic or therapeutic use. Downstream experimental work is scoped separately and executed through qualified partners.
Get a Custom Quote
Our scientific team responds within 24 hours with a detailed technical proposal and pricing tailored to your project.
Contact Us Online ConsultationStandard Deliverables
✓Sequence-verified final product
✓Full QC documentation
✓Certificate of Analysis (CoA)
✓Electronic data files
✓Project completion report
Why ICDMO?
Computational CDMO Focus
Reproducible, Versioned Pipelines
Confidence & Limitations Reported
Experiment-Aware Recommendations
Response Within One Business Day