Ref B1
Computational Service
Confidence Reported
Scoped After Feasibility Review
Service Overview
High-throughput virtual screening reduces a library of tens of thousands to hundreds of millions of compounds down to a shortlist small enough to buy and test. We run it as a funnel rather than a single docking job: property and ADMET pre-filters remove compounds that would fail later anyway, fast docking removes the bulk, and progressively more expensive scoring is applied only to survivors. The compounds that reach your shortlist have been examined individually for binding mode plausibility, not merely sorted by score.
Key Features & Advantages
Cascade, Not One Docking Run
Sequential filtering with increasing accuracy keeps compute focused where it matters, so a hundred-million-compound library can be screened without the cost of treating every molecule rigorously.
Pre-Filtered For Developability
Physicochemical rules, PAINS and aggregator filters and early ADMET flags are applied before docking, so the shortlist is not dominated by molecules that will never progress.
Chemotype Diversity Enforced
Final selections are clustered so you receive several distinct scaffolds rather than fifty analogues of one hit — important when the screen is your only shot at chemical starting points.
Every Shortlisted Pose Inspected
Top-ranked compounds are reviewed by a scientist for interaction quality, strain and pose stability, with those failing inspection removed and the reason noted.
Where This Service Is Used
1Finding initial chemical starting points for a target with no known ligands
2Screening commercial catalogues to identify compounds purchasable for immediate testing
3Screening an internal corporate collection before committing to an HTS campaign
4Repurposing screens against approved and clinical-stage drug sets
5Enriching a set for a focused biochemical assay where assay capacity is the limiting factor
Methods and Techniques Applied
1Receptor preparation: protonation, tautomer and flip assignment, water handling and site definition
2Ligand preparation: ionisation states at assay pH, tautomers, stereoisomer enumeration and 3D conformer generation
3Property, drug-likeness, PAINS and aggregator pre-filtering with thresholds agreed in advance
4Staged docking from fast scoring to extra-precision scoring on the surviving fraction
5Pharmacophore or interaction constraints derived from known actives or hot-spot analysis
6Clustering by scaffold, visual pose inspection, and optional rescoring by MM/GBSA for the final set
What We Need From You
1Target structure (experimental or modelled) and the binding site to be screened
2The library to screen, or a request that we select and prepare a commercial library
3Any known actives or inactives, which allow the workflow to be validated by enrichment before the real screen
4Selection constraints: purchasability, price band, supplier, novelty requirements, chemistry you wish to avoid
What You Receive
1Ranked hit list with scores, predicted properties, supplier and catalogue identifiers where applicable
2Docked poses for the shortlist in SDF, plus a viewer session for inspection
3Interaction analysis per shortlisted compound: hydrogen bonds, hydrophobic contacts, unfavourable features
4Scaffold clustering and diversity summary showing what chemotypes the shortlist covers
5Full screening report with protocol, filter thresholds, enrichment validation and hit rate expectations
What We Compute and Report
1Docking score and predicted binding pose for every compound surviving each filter stage
2Attrition counts at each stage, so the funnel from library to shortlist is fully traceable
3Predicted physicochemical and early ADMET properties for every shortlisted compound
4Interaction fingerprint per pose: hydrogen bonds, hydrophobic contacts, pi systems and unsatisfied groups
5Scaffold cluster assignment and chemotype coverage statistics across the delivered shortlist
6Retrospective enrichment metrics on your known actives, where such compounds exist
Questions We Are Asked Before Scoping
What hit rate should we expect?
▸Published campaigns commonly report a few percent for well-prepared systems, but the range is wide and target-dependent. We do not promise a rate; we do report the enrichment achieved on your known actives when you have them.
Can you screen without a known active?
▸Yes, and it is common. Known actives improve validation and constraint setting, so where none exist we lean more heavily on structural hot-spot analysis and report the added uncertainty.
Do docking scores predict affinity?
▸No. They are ranking devices with limited correlation to measured affinity. Compounds close in score should be treated as indistinguishable, which is why diversity selection matters more than the top of the list.
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
The target has a usable structure and a defined site, and you need chemical starting points
Assay capacity is limited and compounds must be chosen carefully rather than broadly
A purchasable shortlist is wanted so testing can start within weeks
Consider another service when
You need chemotypes outside any catalogue, at billion scale
AI-Powered Ultra-Large Library Screening Compounds already exist and the question is how they bind
Molecular Docking 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.
Shortlists dominated by a single scaffold because score alone drove selection
Selections are clustered by scaffold so several independent chemotypes reach the assay.
Promiscuous or assay-interfering compounds scoring well
Aggregators, reactive groups and interference substructures are filtered before docking, not diagnosed after a failed assay.
A protocol that cannot reproduce a known binding mode
Where a reference ligand exists, the protocol is validated by redocking and enrichment before the library is processed.
A Worked Example
Screening a commercial catalogue against a kinase allosteric site
The situation
The orthosteric site was crowded with competitor chemistry, and the team wanted starting points at an allosteric pocket instead.
What the work involved
Five million purchasable compounds were property- and liability-filtered, docked through a staged cascade, rescored, clustered by scaffold, and every surviving pose was inspected individually.
What came back
Two hundred compounds across eleven scaffold families, delivered with supplier codes, poses and the interactions each was expected to make.
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.
A 22% confirmed hit rate from docking 138 million compounds
In a landmark 2019 study, ~138 million make-on-demand compounds were docked against the dopamine D4 receptor. Of 549 compounds selected and tested, 122 were confirmed active — a 22% hit rate — including ligands in the sub-nanomolar range. The same work screened ~99 million compounds against AmpC β-lactamase, where 5 of 44 tested compounds were confirmed (11%), one of which was among the most potent non-covalent AmpC inhibitors reported at the time.
Lyu et al., Nature, 2019 ↗Hit rate rises with rank, which is why library scale matters
The same body of work showed that the probability of a compound being confirmed active increases as its docking rank improves, and that larger libraries push better-scoring molecules into the selected set. This is the practical argument for screening make-on-demand space rather than a physical catalogue — and also the reason scoring accuracy, not library size alone, remains the limiting factor.
Lyu et al., Nature, 2019 ↗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