Skip to content

Experimental Features

The Experimental section of the web app provides tools for quick, one-off tasks — useful for testing new features.

Predicts BCR epitope clusters for a single antibody using a trained classifier.

  1. Select a Model version from the dropdown (current: model_v1.2)
  2. Enter the Heavy chain sequence (required) — full amino acid sequence
  3. Optionally enter a Light chain sequence to improve prediction accuracy
  4. Set Top clusters to report (default: 10)
  5. Set Min probability threshold (recommended: 0.5)
  6. Click Predict Epitope Clusters
ColumnDescription
rankRank for this query (1 = highest probability)
mean_probMean classifier probability across all reference antibodies in this cluster
msa_cluster_idFine-grained epitope cluster ID (MSA-based)
epitope_clusterBroader epitope cluster grouping
ag_cluster_idAntigen cluster ID
antigenAntigen name associated with the predicted cluster
n_ref_absNumber of reference antibodies in this cluster
rep_idsTop-3 representative reference antibody IDs

Search a single amino acid sequence against one or more reference databases using nearest-neighbor retrieval. Chain type and species are auto-detected from the input sequence.

  1. Enter an amino acid Query sequence — chain type and species are detected automatically
  2. Select one or more Databases to search (default: SAbDab)
  3. Set Nearest neighbors to retrieve — candidates fetched from the indexes (default: 1000)
  4. Set Results to keep — top hits returned after scoring (default: 100)
  5. Choose Search mode: Full paratope (default) or CDR3 only
  6. Click Search

Results can be downloaded as CSV.

ColumnDescription
databaseSource database for this match
aligned_sequencePseudo-sequence alignment of the matched target
distanceRaw levenshtein distance — lower is more similar
sequence_identityFraction of matching residues at non-gap positions (0–1)
coverageFraction of positions where both sequences have a residue (0–1)
blosum62_scoreMean per-position BLOSUM62 score — higher is more similar
nw_scoreNeedleman–Wunsch score normalised by the longer sequence — higher is more similar
cdr3_length_diffCDR3 length difference (query − target; 0 = equal length)
refinedWhether CDR3 gap positions were repositioned via BLOSUM62 sliding-window refinement
dataset_nameSource dataset the target sequence belongs to
conditionCondition label associated with the target sequence
subject_idxSubject identifier within the source dataset
extra columnsDatabase-specific metadata (e.g. antigen.epitope, v.alpha) — fields listed under Database Info

ScenarioUse
Testing one sequenceExperimental tools
Analyzing a full cohort (100+ sequences)Bulk pipeline jobs
Need results saved on cloudBulk pipeline jobs
Quick sanity check before a batch runExperimental tools