Antibody developability assessment
Flag developability risks before ordering antibodies
Screen a set of antibody or nanobody candidates for surface patches, viscosity, polyreactivity, aggregation, solubility and humanness, then hand your team one table of flags before any gene is ordered.
Trusted by 16,500+ researchers and published in
Number and model the domains
Number the variable domains so CDRs are read the same way across candidates, and predict a structure for the checks that need one. ANARCII does the numbering, and ImmuneBuilder models antibodies and nanobodies.
Profile surface patches
TAP2 and TNP compare CDR length and surface patches with clinical-stage antibodies and nanobodies. DeepSP predicts aggregation and charge descriptors from sequence, and Aggrescan3D scores aggregation per residue on a structure.
Predict viscosity and polyreactivity
Both classifiers take a paired Fv sequence and return a low or high call. DeepViscosity predicts viscosity at 150 mg/mL and PolyXpert predicts polyreactivity. Neither replaces a measured assay.
Check solubility, humanness and liabilities
NetSolP and Protein-Sol predict solubility from sequence, BioPhi scores humanness, and the glycosylation finder lists N-linked sequons, including those in CDRs.
More antibody engineering workflows
Antibody structure prediction
Model paired variable domains and inspect CDR loops before profiling their surfaces.
Antibody design
Generate antibody and nanobody candidates against a target, then bring them here for triage.
Antibody-antigen docking
Dock a candidate to its antigen and review the interface after it passes developability screening.
Read the flags in context
Background guides on the methods, scores, and numbers behind these workflows.

Proteins · 16 min
Protein aggregation: causes, prediction and prevention
Protein aggregation is the self-association of protein molecules into amorphous clumps, soluble oligomers or ordered amyloid fibrils. Learn why proteins aggregate, how aggregates are measured, what TANGO, AGGRESCAN, CamSol, Aggrescan3D, Protein-Sol and NetSolP predict from sequence and structure, and how formulation, mutations and expression conditions prevent it, with a worked Aggrescan3D run on transthyretin.

Antibodies · 12 min
Human vs humanized vs chimeric antibodies: the origin of every FDA-approved antibody
Of 159 antibody products the FDA licensed by September 2026, 52% are humanized, 34% fully human, 9% chimeric and 5% murine, by ProteinIQ's label-by-label count. The fully human share has held near one-third since 2015. Free CSV.

Antibodies · 13 min
Antibody variable regions: VH, VL, CDRs and frameworks
VH and VL domains, the six CDRs and eight framework regions they contain, how Kabat, Chothia and IMGT draw CDR boundaries, and how V(D)J recombination and somatic hypermutation create variable-region diversity.
FAQs
Providers do not publish a fixed price for a complete developability assessment. Curia describes an entry package of in silico sequence liability and immunogenicity analysis with a one-week turnaround, and Evotec describes in silico property and structure analysis with reporting, but both ask for a quote. The wet-lab packages that add polyspecificity, stability and forced degradation testing are quoted on request.
A quote depends on the number of candidates, whether the work is computational only or includes assays, and how much expert interpretation is added.
ProteinIQ is self-service. The Free plan includes 200 credits, and paid plans start at $9 per month for Lite, with Plus at $29 and Pro at $99. A paired antibody costs 30 credits in BioPhi, a DeepViscosity job of up to 100 antibodies costs 32 credits, and an Aggrescan3D structure costs 5, all quoted before the run. Batch mode needs a paid plan, and done-for-you projects are scoped separately.
DeepSP and DeepViscosity take up to 100 antibodies in one job, PolyXpert up to 1,000 pairs on the largest plan, and TNP several nanobodies per FASTA. TAP2, BioPhi and Aggrescan3D process one antibody or structure per job, so use batch mode, which runs up to 250 jobs per batch on paid plans.
Not for most checks. DeepSP, DeepViscosity, PolyXpert, BioPhi, NetSolP and Protein-Sol start from sequence. TAP2 and TNP build a model themselves, and Aggrescan3D needs a structure you provide, such as one from ABodyBuilder3 or ImmuneBuilder.
None of them on its own. Disagreement usually means the tools measure different properties, for example a clean TAP2 profile with a high polyreactivity call. Read it as a reason to measure that property first, and use the residue-level tables to see which region drives each flag.
TNP profiles single-domain VHH against clinical-stage nanobodies, and BioPhi accepts a heavy chain alone when VHH input is enabled, with a warning to validate solubility separately. TAP2, DeepSP, DeepViscosity and PolyXpert expect a paired VH and VL.
Each job stores its inputs, settings and result files in your job history, and tables can be downloaded as CSV. Do not submit sequences that must never be stored outside your own systems.
AI answers from our docs. No sign-in needed.
Focus on research, not infrastructure
Start free with 200 credits a month and no installs. Upgrade when your project needs more compute.