Overview
What this category covers
Most compounds fail for reasons that have nothing to do with potency. This category predicts the properties that decide developability — physicochemical behaviour, absorption and permeability, metabolic fate and safety liabilities — early enough for the chemistry to respond. Every flag is delivered with the substructure and the mechanism behind it, because an alert that cannot be acted on is only a delay.
What we deliver
▸Full physicochemical and drug-likeness profiling with violations attributed to structure
▸Permeability, efflux, absorption and blood–brain barrier assessment with CNS MPO scoring
▸Metabolic stability prediction with atom-level soft-spot mapping and CYP profiling
▸Safety profiling across cardiac, genotoxic, hepatic and sensitisation endpoints
▸Assay interference screening to keep artefacts out of your hit list
Who this is for
▸Teams triaging screening hits before committing assay resource
▸Lead optimisation programmes monitoring developability drift across a series
▸Groups diagnosing poor exposure, rapid clearance or unexpected toxicity
▸Projects preparing a candidate selection package
How engagements in this category are run
Property work is fastest to deliver and most useful when it arrives before decisions are made, so these services are often run as a standing filter across a programme rather than as a one-off study. We agree the endpoint set and the thresholds that matter for your route of administration, calibrate against any measured data you hold, and report failures with the substructure responsible. Where a prediction sits outside its applicability domain, we say so instead of returning a number that looks confident.
Services
4 computational services in this category
D1
Physicochemical Property Prediction
MW, logP, logD, pKa, solubility, PSA, Fsp3, drug-likeness filters (Ro5, Veber, Pfizer 3/75, GSK 4/400).
Learn MoreD2
Absorption & Permeability Prediction
Caco-2, PAMPA, P-gp, BBB, oral bioavailability, HIA prediction. CNS MPO scoring.
Learn MoreD3
Metabolic Stability & CYP Prediction
Microsomal/hepatocyte metabolic stability (t½, CLint), CYP inhibition (1A2/2C9/2C19/2D6/3A4), soft spot identification, reactive metabolite flagging.
Learn MoreD4
Toxicity & Safety Profiling
hERG cardiotoxicity, Ames mutagenicity, drug-induced liver injury, skin sensitisation and genotoxicity risk, assay interference and aggregation flags, and expert structural alerts with the r…
Learn MoreIn Practice
What a project in this category looks like
Three shapes we are asked for most often. Scope is always set after a feasibility review, so timelines below are typical rather than quoted.
Triaging a hit list before assay commitment
The situation
Screening produced several hundred candidates and the team must decide which to buy and test first.
What we do
Full property profiling, drug-likeness and developability rule assessment, permeability and efflux prediction, metabolic soft-spot mapping, and assay interference screening, with every flag attributed to the substructure responsible.
What you receive
A ranked table with the liabilities per compound, the property driving each failure, and a recommendation of which compounds justify assay slots.
Typical timeline: 3–7 working days
Diagnosing rapid clearance in a lead series
The situation
The series is potent but disappears in microsomal incubations, and the chemistry team does not know where to block.
What we do
Atom-level site-of-metabolism prediction across the series, clearance and half-life estimates by species, metabolite structure proposals, and analysis of how the observed stability tracks the structural changes already made.
What you receive
Soft-spot maps on each structure, ranked positions to block, proposed metabolites for the analytical team, and the likely consequence of blocking each site.
Typical timeline: 1–2 weeks
Safety profiling ahead of candidate selection
The situation
Two or three compounds are in contention and the team needs a documented computational safety assessment for the selection meeting.
What we do
Cardiac, genotoxic, hepatic and sensitisation endpoints are predicted, structural alerts are interpreted with their mechanism, and interference behaviour is separated from genuine liability.
What you receive
A consolidated risk profile per candidate with alerts ranked by severity and confidence, plus mitigation suggestions where a liability is structurally addressable.
Typical timeline: 1–2 weeks
Questions
Asked before we scope this work
How accurate are these predictions?
Lipophilicity and surface properties are generally reliable; solubility typically carries around one log unit of error; absolute human pharmacokinetics is not reliably predictable. We report expected error rather than bare numbers.
Can predictions replace measurement?
For triage across hundreds of compounds, yes. For a development candidate, no — measured solubility, stability and safety data are required, and prediction decides what is worth measuring.
What about degraders and macrocycles?
They sit outside the applicability domain of many standard models. We flag that explicitly and use models built for that space where they exist rather than quoting a confident-looking number.
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 ↗More
Other service categories
Target Identification & Validation5Virtual Screening (Small Molecule)3Small Molecule Design & Optimization2Molecular Dynamics & Simulation3AIDD — Small Molecule Platform2Structure-Based Drug Design (SBDD)3Bioinformatics & Multi-Omics Analysis11Antibody Design & Engineering (AI)5Peptide & Cyclic Peptide Drug Design4Protein Design & Engineering (AI)4ADC & Bioconjugate Design2Compound & Biological Library Design3
Bring us the scientific question, not a service code
Share your target, dataset, sequences or objective. We will recommend a scoped computational plan, the expected deliverables, a timeline and the validation options.
Request a Feasibility Review