Ref I2
Computational Service
Confidence Reported
Scoped After Feasibility Review
Service Overview
Single-domain antibodies have properties that make them worth the engineering effort — small size, high stability, access to cryptic epitopes and simple single-chain production — and a distinctive set of design problems. We model VHH structures with attention to the long CDR3 loop and the hallmark framework-2 residues, engineer that loop for affinity or specificity, humanise the camelid framework without losing stability, and screen for the aggregation and liability risks that single domains carry.
Key Features & Advantages
CDR3 Modelled Properly
The long, structurally variable CDR3 that dominates VHH binding is treated with dedicated loop modelling and ensemble generation rather than a single predicted conformation.
Framework-2 Handled With Care
The hallmark hydrophilic residues that replace the VL interface are critical to solubility, and humanisation designs preserve or compensate for them explicitly.
Stability As A Design Objective
Thermal and chemical stability, the main commercial advantage of the format, are modelled and protected through the engineering rather than sacrificed for affinity.
Epitope-Directed Design
Where the epitope is known, complex modelling directs loop engineering toward the intended surface, including the concave and cryptic sites VHHs reach.
Where This Service Is Used
1Optimising a VHH obtained from immunisation or library selection
2Humanising a camelid framework while preserving stability and solubility
3Engineering CDR3 for improved affinity or altered specificity
4Designing multivalent or bispecific constructs built from VHH modules
5Assessing and mitigating aggregation risk before scale-up
Methods and Techniques Applied
1VHH structure prediction with dedicated CDR3 loop modelling and conformational ensemble generation
2Framework analysis against camelid and human germlines, with hallmark residue assessment
3Antigen complex modelling and epitope-directed loop design where the target site is known
4Loop redesign and sequence optimisation with stability and solubility constraints applied jointly
5Humanisation design with back-mutation analysis focused on stability-critical positions
6Developability screening: aggregation propensity, charge distribution, chemical liability motifs
What We Need From You
1VHH sequence or sequences, with any measured affinity, stability or expression data
2Antigen sequence or structure and epitope information if mapping has been done
3The design objective: affinity, specificity, stability, humanisation or format conversion
4Intended application, since diagnostic, imaging and therapeutic uses impose different constraints
What You Receive
1Designed VHH sequences ranked with the rationale for each modification
2Structural models including CDR3 ensembles and, where applicable, antigen complexes
3Humanness and humanisation assessment with back-mutation recommendations
4Developability report covering aggregation, solubility and chemical liabilities
5Prioritised construction and testing plan for the designed panel
What We Compute and Report
1Designed single-domain sequences with the modification rationale per position
2CDR3 conformational ensembles with the population of each modelled state
3Humanness scores and framework hallmark analysis
4Aggregation-prone region mapping on the modelled surface
5Predicted stability change for every proposed substitution
Questions We Are Asked Before Scoping
Can you design a VHH against a new antigen from scratch?
▸De novo binder design is possible but low-yield and best treated as exploratory. Where you already have a binder from immunisation or display, engineering it is far more likely to succeed.
Will humanisation reduce affinity or stability?
▸It can, particularly when hallmark framework-2 positions are changed. Designs are delivered as a graded series so the affinity-versus-humanness trade-off can be measured rather than guessed.
How accurate is CDR3 modelling?
▸Long CDR3 loops remain among the harder modelling problems. We deliver ensembles rather than a single pose, and design decisions are checked for robustness across that ensemble.
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 single-domain binder needs optimising for affinity, stability or specificity
Camelid framework immunogenicity must be reduced without losing solubility
Sequencing output from a selection campaign needs triaging before expression
Consider another service when
A conventional two-domain antibody is the format
Full-Length IgG Antibody Design The construct must engage two targets at once
Bispecific & Multispecific Antibody 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.
A single predicted CDR3 conformation driving the whole design
CDR3 is delivered as an ensemble and every design decision is checked for robustness across it.
Germlining the framework-2 hallmark positions and losing solubility
Those positions are treated explicitly, with compensating substitutions designed where they are changed.
Selection enrichment mistaken for quality
Candidates are ranked on developability and modelled behaviour, not only on how often they appeared in the final panning round.
A Worked Example
Triaging 400 sequences from a display campaign
The situation
Panning produced several hundred unique sequences and the team could express twenty.
What the work involved
Sequences were clustered by CDR3, germlines assigned, framework anomalies from PCR flagged, leading clones modelled, and surfaces screened for aggregation-prone regions and chemical liabilities.
What came back
Nine genuine families rather than the apparent hundreds, four of which carried unpaired cysteines or strong aggregation patches. Twenty constructs were chosen across the five clean families.
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.
10- to 140-fold affinity improvements from computational design
Computational interface redesign produced a tenfold affinity improvement in cetuximab, reaching 52 pM, and a 140-fold improvement to 30 pM for an anti-lysozyme model antibody — improvements achieved by designing a small number of interface substitutions rather than by library selection.
Lippow, Wittrup & Tidor, Nature Biotechnology, 2007 ↗Interface models predict which substitutions help, with measurable accuracy
A 2024 study combining structural interface analysis with sequence-derived evolutionary information reported a predictive model for antibody–antigen interaction with an area under the curve of 0.83 and precision of 0.89 on held-out data, and experimentally confirmed a designed point mutation that improved affinity 2.5-fold to 2 nM. Typical computational maturation gains are modest per mutation, which is why a designed panel is measured rather than a single variant.
Experimental validation study, 2024 ↗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