Overview
What this category covers
Virtual screening exists to spend assay capacity well. This category narrows compound sets — from a curated catalogue of thousands to make-on-demand spaces of billions — down to a shortlist that has been filtered for developability, docked with a validated protocol and inspected pose by pose. We are explicit about what screening does: it enriches, it does not confirm, and the shortlist is a set of hypotheses for your assay.
What we deliver
▸Staged screening cascades from property filtering through to precision docking
▸AI-accelerated access to billion-scale make-on-demand chemical space
▸Binding mode analysis and interaction maps for every shortlisted compound
▸Scaffold-diverse selections sized to your assay and purchasing capacity
▸Protocol validation against known actives wherever such data exists
Who this is for
▸Teams needing chemical starting points for a structurally characterised target
▸Groups with limited assay throughput that must choose compounds carefully
▸Programmes seeking novel chemotypes outside crowded IP space
▸Projects wanting to test a target before committing to high-throughput screening
How engagements in this category are run
Every screen begins with target preparation and, where known actives exist, protocol validation by retrospective enrichment. Only then is the library processed, and the cascade is sized so that the compute is concentrated on the compounds most likely to survive. Shortlists are built to your assay capacity and purchasing constraints, clustered for chemotype diversity and inspected individually before delivery. We report the expected attrition honestly: a screening shortlist is a set of testable hypotheses, and hit rates vary widely between targets.
Services
3 computational services in this category
B1
High-Throughput Virtual Screening (HTVS)
Rapid multi-stage screening of large compound libraries (10K–100M+). ADMET pre-filter → HTVS → SP → XP docking cascade.
Learn MoreB2
Molecular Docking (Rigid & Induced-Fit)
Precision docking with binding mode analysis, key interaction residue identification. IFD for flexible active sites. Covalent docking for targeted covalent inhibitors.
Learn MoreB5
AI-Powered Ultra-Large Library Screening
Machine-learning-accelerated screening of billion-scale make-on-demand chemical space. Learned scoring triages the full library; every shortlisted compound is confirmed by conventional docki…
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.
First chemical matter for a structurally characterised target
The situation
A target has a structure and a validated pocket, but no known ligands and no internal compound collection worth screening.
What we do
Receptor and library preparation, property and liability pre-filtering, a staged docking cascade from fast to precision scoring, rescoring of survivors, scaffold clustering, and individual inspection of every pose that reaches the shortlist.
What you receive
Fifty to five hundred purchasable compounds with poses, interaction analysis, diversity statistics and supplier information, sized to your assay capacity.
Typical timeline: 3–5 weeks
Escaping a crowded chemical space
The situation
A programme has hits, but they sit inside a patented series and the team needs starting points somewhere else.
What we do
Make-on-demand space is screened using machine-learned triage with conventional re-docking of survivors, then filtered for novelty against known actives and published chemotypes before selection.
What you receive
A shortlist with novelty distance reported per compound, estimated synthesis success rate and lead time, and re-docked poses for every delivered molecule.
Typical timeline: 5–8 weeks
Explaining why an earlier screen failed
The situation
A previous campaign produced nothing, and the team needs to know whether the target, the site or the method was at fault.
What we do
We reassess the site for druggability, check whether the protocol reproduces any known binding mode, examine the library for property and liability bias, and look for an alternative or cryptic site.
What you receive
A diagnosis with the evidence, and a recommendation: rerun differently, pursue another site, change modality, or stop.
Typical timeline: 2–3 weeks
Questions
Asked before we scope this work
How big a shortlist should we ask for?
Match it to assay capacity rather than to ambition. Fifty well-chosen, chemotype-diverse compounds usually teach more than five hundred selected purely by score.
Can you screen our internal collection?
Yes, and we will standardise and quality-check it first. Corporate collections frequently contain duplicates, degraded structures and liability chemotypes that have never been filtered out.
Do you help with compound purchasing?
We deliver supplier identifiers, availability and price bands so a shortlist converts directly into an order. Purchasing itself stays with you.
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 ↗More
Other service categories
Target Identification & Validation5Small Molecule Design & Optimization2ADMET & Drug-Likeness Prediction4Molecular 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