Protein engineering
Design proteins and binders, then check they fold
Generate backbones and binders, design their sequences, and fold them with independent models before you order genes.
Trusted by 16,500+ researchers and published in
Generate backbones and binders
Start from the structural constraints of your problem, such as a target surface to bind, and generate new backbones or binders that fit them.
Design and redesign sequences
Assign sequences to designed backbones, or redesign chosen residues around ligands and for solubility. Run more than one model and compare what they converge on.
Predict structures
Fold candidate sequences with several independent models and compare their confidence. A design that only one model likes deserves suspicion.
Check stability and developability
Check thermostability, solubility, aggregation and surface exposure before you pick designs, so the ones you order are the ones that can be made.
Protein engineering use cases
Pick the method that fits your question and evidence. Each one comes with a workflow you can open and edit.
De novo protein design
Generate proteins beyond known templates, then connect backbone generation, sequence assignment, refolding, and candidate review.
Protein binder design
Design compact proteins against a specified target surface, then connect sequence optimization, refolding, and interface review.
Inverse folding
Design amino-acid sequences for a fixed protein backbone, compare complementary models, and refold candidates before selection.
Protein sequence design
Generate or optimize amino-acid sequences against structural, functional, stability, and developability objectives.
Protein structure prediction
Fold a protein sequence online with AlphaFold2 or ESMFold, predict complexes with ligands or nucleic acids using Boltz-2 or Chai-1, and see which regions each model is confident about.
Protein complex structure prediction
Predict multi-chain protein assemblies and compare interface geometry, stoichiometry assumptions, confidence, and model agreement.
Protein structure search
Search large protein-structure databases with a query fold, then inspect ranked neighbors, coverage, scores, and alignments.
Multiple protein structure alignment
Compare three or more protein structures in one shared correspondence, then review conserved cores, outliers, and alignment consistency.
Guides for protein engineering
Background guides on the methods, scores, and numbers behind these workflows.

Structures · 17 min
What is pLDDT, and what counts as a good score
pLDDT is the per-residue confidence score that AlphaFold, ESMFold and Boltz attach to predicted structures. Learn what the 90, 70 and 50 cutoffs mean and why neither a high nor a low score settles whether a region is real.

Structures · 16 min
What is PAE, and how to read a PAE plot
PAE (predicted aligned error) is the pairwise confidence matrix that AlphaFold, Boltz and Chai-1 write next to a predicted structure. Learn how to read its blocks and stripes and use it for domains and interfaces.

Structures · 15 min
ipTM vs pTM: judging predicted complexes
pTM scores the whole predicted structure, while ipTM scores only how chains sit relative to each other. Learn what the 0.5, 0.6 and 0.8 cutoffs mean and why disordered tails lower ipTM.

Proteins · 18 min
What is a protein language model, and what is it used for
A protein language model is a neural network trained to predict amino acids from the rest of a sequence. Learn how ESM-2, ESM C, ESM3, ProtT5 and ProGen2 differ, what their embeddings and likelihoods are used for, how they compare with alignment-based methods like AlphaFold2, and which licences allow commercial use.

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.

Proteins · 19 min
Disulfide bonds in proteins: how they form and what they do
A disulfide bond is a covalent S-S link between the side chains of two cysteines, formed by oxidation of their thiol groups. Proteins make them in the endoplasmic reticulum and the bacterial periplasm, rarely in the cytosol. Learn the chemistry, the geometry measured in 941 high-resolution structures, why a cross-link stabilizes a protein, famous examples such as insulin, lysozyme and IgG, and how to find disulfides in a structure file or in the lab.
FAQs
ProteinIQ brings these computational checks together around each protein candidate. You can design or score sequences, predict folds, assess stability and solubility, inspect structures, and retain the output files and confidence data that explain a ranking. Start with a sequence, structure, or variant set and run a focused tool or connected workflow. ProteinIQ keeps the generated candidates, structures, tables, scores, and logs available for comparison and for planning experimental validation.
ProteinIQ supports protein engineering workflows for folding, structure prediction, protein design, variant scoring, stability review, solubility analysis, binder design, structure validation, and downstream candidate comparison. The platform keeps the upstream files, scores, confidence values, and logs available for review.
ProteinIQ protein tools can accept FASTA sequences, PDB or CIF structures, protein complexes, mutation lists, reference models, and design constraints depending on the upstream method. Each workflow preserves the relationship between the input sequence or structure and the outputs it generates.
Yes. ProteinIQ can run protein design tools that generate or redesign sequences from structural context, then route candidates into folding, stability, solubility, and validation checks. The generated variants are computational candidates for review and testing, not automatically validated proteins.
Yes. ProteinIQ can run protein structure prediction and folding tools when the sequence or structure inputs match the upstream model requirements. Outputs can include PDB or CIF files, confidence metrics, model artifacts, and logs so predicted structures can be inspected and exported.
Yes. ProteinIQ can connect protein candidates to stability, solubility, aggregation, mutation, and sequence-property tools depending on the workflow. These computational scores help prioritize variants, and ProteinIQ keeps the score tables tied to the sequence or structure being evaluated.
Yes. ProteinIQ can support binder design and protein interaction workflows when the required target structures, scaffold inputs, or design constraints are available. The platform helps keep designed sequences, predicted structures, confidence values, and downstream validation outputs together for review.
No. ProteinIQ helps prioritize protein engineering candidates computationally. Expression, binding, stability, activity, specificity, and functional assays remain essential before treating a designed or modified protein as experimentally validated.
Yes. ProteinIQ exports candidate evidence such as FASTA files, generated sequences, PDB or CIF structures, score tables, validation reports, confidence metrics, logs, and upstream result artifacts depending on the tool. This makes it easier to review or share the evidence outside ProteinIQ.
Start in ProteinIQ with a protein sequence, structure, or candidate variant set, then choose a workflow template or an individual tool for design, folding, stability, or validation. A small first run helps confirm formatting and output expectations before scaling to larger protein design campaigns.
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.