Skip to main content
GET
Search for similar proteins using SAE feature vectors

Query Parameters

sequence
string
required

Amino acid sequence

Required string length: 1 - 2048
topk_results
integer
default:10

Number of similar proteins to return

Required range: x <= 100
topk_features
integer
default:20

Number of top features to return

Required range: x <= 100
min_similarity
number
default:0.5

Minimum similarity score; results below this threshold are excluded

Required range: 0 <= x <= 1
cluster_pct_characterized_max
integer | null

If set, only return hits whose cluster_pct_characterized is <= this value. Use 0 to find clusters whose members have no characterized Pfam annotations (proxy for uncharacterized / novel).

Required range: 0 <= x <= 100
include_cluster_info
boolean
default:false

If true, each result includes the representative protein's cluster_size and human-readable protein_name, sparing the caller a follow-up /clusters/{hash} request per result.

Response

Successful Response

Response schema for V2 SAE search endpoint.

query_sequence
string
required

Normalized query amino acid sequence

similar_proteins
SimilarProtein · object[]
required

List of similar proteins

protein_hash
string | null

MD5 hash of the query sequence; present only when the protein exists in the atlas

top_features_across_results
TopFeatureAcrossResultsV2 · object[]

Top SAE features commonly activated across similar proteins

restricted_count
integer
default:0

Number of proteins removed from results that are similar to the deny list proteins