Overview
What this category covers
Antibody work divides into modelling, engineering and triage, and this category covers all three in silico. Full-length IgG design, single-domain engineering, bispecific format selection and assembly, computational affinity maturation and humanisation each rest on the same foundation: structural models of the variable domains and, where possible, of the antigen complex, combined with developability screening across the entire sequence.
What we deliver
▸Full-length IgG design including framework selection and Fc engineering
▸VHH and nanobody engineering with dedicated CDR3 modelling
▸Bispecific format selection, chain pairing design and geometry modelling
▸In silico affinity maturation with binding and stability scored together
▸Humanisation with structure-guided back-mutation and immunogenicity assessment
Who this is for
▸Teams that have obtained a binder and need it made developable
▸Programmes converting binders into bispecific or multispecific formats
▸Groups humanising murine or camelid antibodies for therapeutic development
▸Projects needing developability triage before committing to expression
How engagements in this category are run
Antibody engagements are built around a designed panel rather than a single construct, because expression and binding outcomes cannot be predicted reliably enough to justify betting on one sequence. We model first, design a panel that tests distinct hypotheses, screen it computationally for developability liabilities, and recommend the order in which constructs should be made. Your expression and binding results then feed back into the next design round.
Services
5 computational services in this category
I1
Full-Length IgG Antibody Design
AI-driven design of full-length IgG antibodies against target antigens. CDR loop grafting, framework selection, humanization scoring, and Fc engineering for effector function.
Learn MoreI2
VHH / Nanobody Design
Computational design and optimization of single-domain antibodies (VHH/nanobodies). CDR3 loop engineering, camelid framework humanization, epitope-specific design, and stability optimization…
Learn MoreI3
Bispecific & Multispecific Antibody Design
Computational design of BsAbs and multispecific formats (CrossMab, DuoBody, scFv fusions, DVD-Ig). Ternary complex modeling, linker optimization, chain mispairing risk assessment.
Learn MoreI4
CDR Affinity Maturation (In Silico)
Computational affinity maturation of antibody CDR loops. Saturation mutagenesis scanning, ML fitness landscape, energy-guided CDR optimization, and variant prioritization for experimental va…
Learn MoreI5
Antibody Humanization
Computational humanisation of murine or camelid antibodies: framework grafting, structure-guided back-mutation analysis, human germline content scoring and predicted T-cell epitope assessmen…
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.
Making a hybridoma or display binder developable
The situation
A binder exists and works, but has liabilities that would cause problems in development.
What we do
Sequence numbering and germline assignment, variable domain and complex modelling, whole-sequence liability mapping, surface patch analysis, and design of variants that remove the problems without touching the paratope.
What you receive
A designed panel with per-variant rationale, structural models, a developability report by position, and a recommended expression order.
Typical timeline: 3–5 weeks
Humanising with the affinity cliff located empirically
The situation
A murine or camelid antibody needs humanising and the team cannot afford several sequential rounds of trial and error.
What we do
Framework selection on canonical compatibility rather than identity alone, structure-guided back-mutation design, and construction of a graded series from conservative to fully germline-matched.
What you receive
Six to twenty variants spanning the humanness axis, with humanness and predicted epitope content per variant, so one expression round locates where affinity falls off.
Typical timeline: 2–4 weeks
Choosing and engineering a bispecific format
The situation
Two validated binders exist and the team must pick an architecture before committing to construction.
What we do
Format comparison against the required mechanism and geometry, assembly and antigen complex modelling, chain pairing engineering, linker sampling for span and reach, and developability assessment per format.
What you receive
A format recommendation with the trade-offs stated, complete construct sequences, pairing risk assessment, and a small panel to build rather than a single bet.
Typical timeline: 4–8 weeks
Questions
Asked before we scope this work
Can you design a binder against a new antigen from scratch?
De novo binder design is possible but low-yield and is scoped as exploratory. Engineering a binder you already have is far more dependable, and we will say which situation you are in.
How many constructs should we express?
Ten to thirty for most engineering campaigns. Binding and expression outcomes are not predictable enough to justify a single construct, so panels are designed to test separable hypotheses.
Do you predict affinity numbers?
We rank variants and flag mutations likely to be harmful. Predicted affinity values are not reliable enough to act on without measurement, and we do not present them as if they were.
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 ↗More
Other service categories
Target Identification & Validation5Virtual Screening (Small Molecule)3Small Molecule Design & Optimization2ADMET & Drug-Likeness Prediction4Molecular Dynamics & Simulation3AIDD — Small Molecule Platform2Structure-Based Drug Design (SBDD)3Bioinformatics & Multi-Omics Analysis11Peptide & 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