Found 66 total tags.

antibodies

Antibodies are proteins with two heavy chains and two light chains produced by B cells, central to the adaptive immune system. Their structure consists of a variable region (containing CDRs and a framework region) and three constant regions (CH1, CH2, CH3). The variable region and CH1 form the Fab, while the remainder forms the Fc region. B cell receptors are antibodies with an additional CH4 domain.

Types of antibodies

IgA is found in mucous membranes, cannot activate the complement system, and makes up roughly two-thirds of antibodies in healthy adults. It is notable for being double-sided.

IgE has only one binding site, mainly protects against large organisms like parasites, and is responsible for allergic reactions.

IgG is the standard antibody class used in therapeutic design. Cannot activate the complement system and can pass through the placenta.

  • IgG1 makes up 67% of all antibodies in the human body, is capable of antibody-dependent cellular phagocytosis, and has the longest hinge region. IgG1 immune repertoires consist mostly of just a few dozen dominant clones and are unique to each individual, remaining largely stable over time.
  • IgG2 — mice have IgG2a and IgG2b instead; some strains have IgG2c instead of IgG2a.
  • IgG3 makes up ~7% of IgGs and has a notably shorter half-life due to poor binding to FcRn, attributed to an H435R mutation.
  • IgG4 is the rarest IgG and undergoes Fab-arm exchange, dissociating into half-bodies and forming novel combinations via R409 in the hinge. Therapeutic IgG4 antibodies use the S228P substitution to stabilize the hinge and prevent this.

IgM is far less subject to affinity maturation than IgG, responds to lipids and polysaccharides, and activates the complement system.

Datasets

SAbDab is a database of all antibody and nanobody structures in the PDB. The full list can be downloaded with:

curl -s https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab/summary/all/

antibodies/architecture

CDR and framework organization, heavy/light-chain pairing, loop geometry, numbering, and antibody formats as structures.

antibodies/maturation

Somatic mutation and selection during in-vivo affinity maturation, including effects on stability, specificity, and expression. Laboratory optimization goes under design.

30 items with this tag. Showing first 10 tags.

antibodies/nanobodies

Findings specific to single-domain antibodies, especially their differences from conventional antibodies; do not add merely because a generic method was tested on one VHH.

antibodies/recognition

Paratopes, epitopes, binding modes, cross-reactivity, and the molecular basis of antibody recognition.

antibodies/repertoires

Repertoire diversity, germline usage, V(D)J recombination, chain pairing across populations, and sequencing-derived repertoire patterns.

biophysics

Physical properties and mechanisms connecting protein sequence, structure, dynamics, binding, and catalysis.

biophysics/catalysis

Catalytic mechanisms, active-site organization, substrate turnover, and enzyme function.

biophysics/dynamics

Conformational equilibria, flexibility, allostery, and their functional consequences.

biophysics/ensemble-analysis

Inferring populations, kinetics, collective variables, and reduced descriptions from ensembles or trajectories.

biophysics/folding

Physical folding and unfolding pathways, rates, cooperativity, and intermediates; not the computational task of predicting a structure.

biophysics/interactions

Physical determinants of binding, specificity, interfaces, oligomerization, and assembly.

biophysics/molecular-simulation

Molecular dynamics, force fields, simulation setup, and enhanced sampling of physical trajectories.

biophysics/stability

What determines thermodynamic or thermal stability, and how stability couples to other properties. Keep melting temperature, folding free energy, and kinetic stability distinct in the notes.

biophysics/thermodynamics

Free energies, statistical ensembles, partition functions, and the mathematical foundations of equilibrium sampling.

cell-biology

Immune signaling and cellular mechanisms relevant to protein therapeutics.

cell-biology/immune-signaling

Immune cells, antigen presentation, cytokines, receptors, and signaling biology.

cell-biology/therapeutic-mechanisms

How therapeutics act: receptor modulation, multivalency, payload delivery, targeted degradation, and circulation or clearance mechanisms.

design

Engineering sequences, folds, binding, catalytic function, and properties that make proteins useful.

224 items with this tag. Showing first 10 tags.

design/antibodies

Computational antibody discovery, CDR design, and in-vitro or in-silico affinity optimization.

design/backbones

Generating backbones, folds, and motif scaffolds; includes designability and structural-diversity limitations.

33 items with this tag. Showing first 10 tags.

design/binders

Designing non-antibody protein binders and cross-format binder workflows; antibody-only work goes under design/antibodies.

design/developability

Expression, solubility, nonspecific binding, self-association, immunogenicity, humanization, and other constraints on making usable protein products.

design/directed-evolution

Iterative experimental optimization, library design, mutagenesis, selection, and model-guided experimental search.

design/enzymes

Engineering catalytic activity, enzyme specificity, active sites, and functional enzyme designs.

16 items with this tag. Showing first 10 tags.

design/inverse-folding

Designing or scoring amino-acid sequences conditioned on a structure or structural ensemble; includes inverse-folding training and applications to property prediction.

55 items with this tag. Showing first 10 tags.

design/modular-proteins

Domain insertion, fusion, oligomerization modules, and engineering proteins as structural or functional tools.

design/sequence-generation

Generating and optimizing sequences with sequence models, evolutionary profiles, or hallucination, including general sequence-search strategies. Fixed-structure sequence design goes under design/inverse-folding.

25 items with this tag. Showing first 10 tags.

evidence

Dataset composition, generalization, experimental validation, and the interpretation of measurements.

181 items with this tag. Showing first 10 tags.

evidence/datasets

Dataset resources, composition, clustering, taxonomic bias, negative examples, synthetic data, and coverage.

52 items with this tag. Showing first 10 tags.

evidence/design-validation

Whether computational design scores, refolding tests, or rankings predict useful experimental outcomes; includes appropriate prospective and baseline comparisons.

48 items with this tag. Showing first 10 tags.

evidence/generalization

Memorization, leakage, out-of-distribution performance, shortcuts, robustness, and when apparent progress does not transfer.

49 items with this tag. Showing first 10 tags.

evidence/measurements

Assay definitions, reproducibility, experimental artifacts, structural evidence, and interpretation of evaluation statistics.

evolution

Selection, mutation effects, ancestry, and homology across natural and engineered proteins.

115 items with this tag. Showing first 10 tags.

evolution/ancestry

Ancestral reconstruction, consensus sequences, historical inference, and their uses in engineering.

evolution/homology

Homology detection, sequence and structural alignment, remote similarity, and conservation across related proteins.

evolution/mutation-effects

Biological effects of substitutions and indels, fitness landscapes, epistasis, and accessible evolutionary paths. Prediction algorithms go under prediction/variant-effects.

47 items with this tag. Showing first 10 tags.

evolution/selection

Natural selection, evolutionary constraints, adaptation, evolvability, and the natural distribution of sequence and fold space.

inference

How to obtain useful outputs from existing models through conditioning, feature extraction, sampling, guidance, and ensembling.

inference/conditioning

How runtime inputs such as MSAs, homolog prompts, templates, ligands, and initial structures affect predictions. Active reward-driven changes to conditioning also belong under inference/guidance.

15 items with this tag. Showing first 10 tags.

inference/ensembling

Combining predictions, scores, prompts, or samples from multiple model runs. Weight merging is documented separately under training/fine-tuning.

inference/feature-extraction

Using learned embeddings, attention-derived features, pooling, or probes for downstream prediction and retrieval. A frozen base model may supply features to a separately trained head.

29 items with this tag. Showing first 10 tags.

inference/guidance

Steering a fixed model with rewards, constraints, gradients, activation edits, or importance reweighting. Backpropagation to an input is not model fine-tuning.

inference/sampling-and-search

Exploring candidate sequences, structures, or designs through sampling, recycles, decoding order, search algorithms, and increased inference compute. Physical MD sampling stays under biophysics/molecular-simulation.

14 items with this tag. Showing first 10 tags.

model-analysis

What models represent internally, how that information is organized, and how it affects their behavior.

42 items with this tag. Showing first 10 tags.

model-analysis/interpretability

What models internally encode and how they use it: attention analysis, layer-wise probing, sparse autoencoders, and mechanistic explanations. Generalization tests remain under evidence/generalization.

29 items with this tag. Showing first 10 tags.

model-analysis/representation-geometry

How similarities, clusters, distances, and manifolds in model representations relate to sequence, structure, or function. Practical feature extraction is a separate inference topic.

14 items with this tag. Showing first 10 tags.

model-design

How models are constructed: network architectures, multimodal representations, and generative formulations.

model-design/architectures

Network components and architecture choices, including attention, equivariance, graph networks, and computational efficiency.

model-design/generative-models

Diffusion, flow matching, VAEs, and energy-based generative formulations. Pair with the substantive design or prediction task when relevant.

model-design/multimodal

Combining sequence, structure, or other modalities; structural tokenization, feature fusion, and hybrid models.

prediction

What can be predicted about proteins, and how confidence relates to the quantity being predicted.

287 items with this tag. Showing first 10 tags.

prediction/antibody-structure

Predicting isolated antibody and nanobody structures, CDR conformations, and interdomain orientations.

prediction/binding

Predicting affinity, binding versus nonbinding, specificity, and ligand-binding residues; does not imply a predicted complex geometry.

26 items with this tag. Showing first 10 tags.

prediction/complexes

Predicting macromolecular complex geometry, including antibody-antigen complexes and oligomer stoichiometry; distinct from predicting affinity.

prediction/confidence

What model confidence scores and uncertainty estimates mean, how they are calibrated, and what they fail to predict.

prediction/ensembles

Predicting multiple conformations, populations, or conformational landscapes with learned models.

prediction/function

Predicting functional annotations, catalytic activity, and enzyme specificity.

10 items with this tag.

prediction/ligand-docking

Predicting small-molecule binding pockets and poses, including co-folding; distinct from affinity prediction.

prediction/stability-expression

Predicting stability, folding cooperativity, expression, solubility, and related physical developability properties.

40 items with this tag. Showing first 10 tags.

prediction/structure

Predicting protein structures, contacts, sidechains, and structural refinement; includes relevant tool/reference notes.

prediction/variant-effects

Predicting mutation-induced effects on fitness or pathogenicity. Add a property-specific tag only when that property is a substantive focus.

53 items with this tag. Showing first 10 tags.

training

How models are trained and adapted: pretraining, fine-tuning, objectives, optimization, and scaling.

training/fine-tuning

Updating or adapting pretrained parameters: fine-tuning, adapters, forgetting, transfer, and combining task-specific weights. Test-time parameter updates still belong here.

training/objectives-and-optimization

Training losses, auxiliary objectives, regularization, optimization schedules, and gradient estimators. Optimizing inputs through frozen models belongs under inference/guidance.

21 items with this tag. Showing first 10 tags.

training/pretraining-and-scaling

Pretraining objectives, masking, model/data/compute scaling, and foundation-model learning dynamics. Dataset composition is covered by evidence/datasets when central.

39 items with this tag. Showing first 10 tags.