Ref D1
Computational Service
Confidence Reported
Scoped After Feasibility Review
Service Overview
Physicochemical properties determine whether a potent molecule can ever become a drug, and they are the cheapest thing to get right early. We compute the full property profile — molecular weight, lipophilicity, ionisation, solubility, polar surface area, three-dimensional character and shape descriptors — apply the standard drug-likeness and developability filters, and explain which specific substructure is responsible when a compound fails. The purpose is to redirect chemistry, not to produce another column in a spreadsheet.
Key Features & Advantages
Ionisation Handled Properly
pKa prediction and pH-dependent logD are computed rather than inferred from logP, since most drug molecules are ionisable and their behaviour at gut and plasma pH differs from the neutral form.
Filters Interpreted, Not Just Applied
Rule of five, Veber, Pfizer 3/75 and GSK 4/400 violations are reported with the offending property and the structural cause, so the result points to a modification.
Series-Level Reading
For a compound series we report property trends across the SAR, which reveals where the chemistry is drifting toward a developability cliff before it arrives.
Calibrated Where Data Exists
When you supply measured solubility or logD for part of the series, predictions are benchmarked against it and the observed error is reported alongside the numbers.
Where This Service Is Used
1Triaging a hit list before committing assay capacity
2Property profiling of a lead series to identify developability drift
3Diagnosing which property is responsible for poor exposure in an in vivo study
4Setting property criteria for a library design or virtual screening filter
5Comparing a candidate against competitor compounds on a common property basis
Methods and Techniques Applied
1Structure standardisation: salt stripping, tautomer canonicalisation and stereochemistry handling
2Prediction of logP, logD at relevant pH, pKa for all ionisable centres and aqueous solubility
3Calculation of polar surface area, hydrogen-bond counts, rotatable bonds, Fsp3 and shape descriptors
4Application of drug-likeness and developability rule sets with violation attribution
5Aggregation, PAINS and reactive-group flagging with the matching substructure highlighted
6Benchmarking against measured data where supplied, with the resulting error range reported
What We Need From You
1Compounds as SMILES or SDF with defined stereochemistry and salt form
2The intended route of administration and target tissue, which set the relevant property windows
3Any measured properties available for calibration
4Internal property criteria, if your organisation applies its own thresholds
What You Receive
1Property table covering all computed descriptors, one row per compound
2Rule-set compliance summary with violations attributed to specific properties and substructures
3Visual property-space plots showing where the series sits relative to drug-like space
4Flagged liabilities with the structural cause identified for each
5Written commentary on which compounds are developable and what modification each problem suggests
What We Compute and Report
1Lipophilicity as logP and pH-dependent logD, with pKa for every ionisable centre
2Aqueous solubility estimate with the expected error range stated
3Polar surface area, hydrogen-bond donor and acceptor counts, rotatable bonds and three-dimensional character
4Rule-set compliance with each violation attributed to a specific property and substructure
5Series-level property trends across your structure–activity relationship
Questions We Are Asked Before Scoping
How accurate are these predictions?
▸Lipophilicity and polar surface area are generally reliable; aqueous solubility and pKa carry wider error, often around one log unit for solubility. We report expected error rather than bare values.
Can predictions replace measurement?
▸For triage across hundreds of compounds, yes. For a development candidate, no — measured solubility, logD and stability are required, and prediction serves to decide what is worth measuring.
What about compounds outside rule-of-five space?
▸Macrocycles, peptides and degraders sit outside the applicability domain of many standard models. We flag this explicitly and apply models suited to that space where they exist.
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
A hit list must be triaged before assay slots are committed
A series needs monitoring for developability drift as the chemistry evolves
Property criteria are being set for a library design or a screening filter
Consider another service when
The specific question is whether the compound will cross a membrane
Absorption & Permeability Prediction Safety liabilities are the deciding factor
Toxicity & Safety Profiling 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.
logP quoted for an ionisable compound as though it were logD at physiological pH
pKa is predicted for every ionisable centre and logD is reported at the pH values that matter.
Solubility predictions used as measurements
Expected error is reported with the value, and measurement is recommended at the point where a decision turns on the number.
Rule violations reported without the cause
Every violation names the offending property and the substructure responsible, so it points to a modification.
A Worked Example
Property triage across a 900-compound hit list
The situation
A screening campaign returned more actives than the team could progress, with no property filter applied.
What the work involved
Structures were standardised, ionisation and logD computed at gut and plasma pH, solubility estimated with error ranges, and drug-likeness and interference filters applied with violations attributed.
What came back
Two hundred and ten compounds inside the agreed property window, with forty flagged as likely aggregators and excluded — a filter that removed a full assay plate of probable artefacts.
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