Antibody engineering workflows
Engineer antibodies,from design to screening.
Number variable regions, review humanness and developability, predict structures, model antibody-antigen complexes, and keep every output tied to the sequence it supports.
Result generated with Boltz-2
Capabilities
Antibody engineering models
RFantibody
Structure-based de novo antibody and nanobody design pipeline combining antibody-tuned RFdiffusion, ProteinMPNN sequence design, and antibody-tuned RoseTTAFold2 filtering.
IgGM
IgGM is a generative foundation model for antibody and nanobody design against a target antigen. Supports CDR design, affinity maturation, inverse design, and framework design. Requires an antigen structure (PDB) and antibody sequences with "X" marking positions to design.
IgDesign
Design antibody CDR sequences via inverse folding. Generates complementarity-determining region (CDR) sequences for antibodies targeting therapeutic antigens using deep learning. Optimizes CDR loops (HCDR1, HCDR2, HCDR3) based on antibody-antigen complex structures.
BioPhi
Antibody humanization and humanness evaluation platform from Merck. Sapiens mode uses deep learning trained on the Observed Antibody Space (OAS) to humanize antibody sequences, while OASis mode evaluates humanness using 9-mer peptide search against human antibody databases.
Humatch
Humatch is an antibody humanization tool that transforms non-human antibody sequences into humanized variants. Uses three lightweight CNNs to identify optimal human V-genes and generate paired heavy and light chain sequences with minimal edits while maintaining functionality.
AntiFold
Inverse folding for antibody variable domains and nanobodies. Predicts amino acid sequences compatible with antibody structures using IMGT numbering while preserving native AntiFold chain handling and structural constraints.
Read to research?
Free
Per user/month, billed annually
For trying ProteinIQ
- 1,200 credits/year
- Daily lightweight analysis
- Core sequence and format tools
Lite
Per user/month, billed annually
For regular individual research
- 6,000 credits/year
- No daily job limit
- API, assistant, and workflows
Plus
Per user/month, billed annually
For high-throughput workflows
- 24,000 credits/year
- More concurrent jobs
- Batch workflow runs
Pro
Per user/month, billed annually
For commercial research
- 96,000 credits/year
- Commercial license
- Highest self-serve limits
Questions & answers
ProteinIQ supports antibody engineering workflows for numbering, germline context, humanness review, humanization triage, developability screening, antibody structure prediction, nanobody modeling, antibody-antigen docking, and design review. Each workflow keeps upstream scores, files, and tool conventions visible for scientific inspection.
ProteinIQ antibody tools can accept FASTA sequences, paired heavy and light chains, single-domain or nanobody sequences, PDB structures, and antigen structures depending on the upstream model. The platform keeps each accepted input format tied to the tool that produced the downstream annotation, model, or score.
Yes. ProteinIQ can run antibody humanization and humanness review workflows using tools such as BioPhi, AbLang-style language model review, and humanization comparison steps. The answers are presented as sequence-level evidence for review, not as a hidden replacement for expert antibody engineering judgment.
Yes. ProteinIQ includes antibody and nanobody structure workflows that can turn variable-region sequences into modeled structures when the selected upstream tool supports that input. The generated PDB or related structure files, confidence values, and logs remain available for inspection and export.
Yes. ProteinIQ supports antibody-antigen docking and exploratory complex modeling workflows that can combine antibody chains or modeled antibody structures with an antigen structure. Docking outputs are useful for hypothesis generation and triage, while binding, specificity, and epitope claims still need experimental evidence.
ProteinIQ keeps antibody numbering, germline calls, humanness scores, developability tables, modeled structures, docking files, and logs associated with the input sequence or structure that produced them. This helps reviewers avoid separating heavy chains, light chains, residue annotations, and downstream models during triage.
Yes. ProteinIQ workflows are useful when you want connected antibody annotation, humanization, structure, and docking steps, but individual tools such as ANARCI, BioPhi, ImmuneBuilder, RFantibody, ParaSurf, and HADDOCK3 can also be opened directly for focused analysis.
ProteinIQ antibody workflows can export numbered sequence tables, humanness and developability CSV files, predicted structures, designed sequences, docking models, logs, and upstream result files depending on the tool. Exported outputs preserve the upstream labels and formats needed for review outside the platform.
No. ProteinIQ organizes computational antibody engineering evidence for prioritization and review. Expression, binding, specificity, immunogenicity, developability, and manufacturability experiments are still required before making biological, therapeutic, or clinical claims.