> ## Documentation Index > Fetch the complete documentation index at: https://docs.biohub.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get protein metadata, sequence, and top SAE features > Look up a protein by its MD5 hash and return its metadata, amino acid sequence, and top-activating SAE features. ## OpenAPI ````yaml openapi/metagenomic-atlas-openapi.json GET /esm/protein/api/v1alpha1/proteins/{protein_hash} openapi: 3.1.0 info: title: ESM Atlas API Reference description: Interfaces may change without notice. version: 0.1.0 servers: - url: https://biohub.ai security: [] paths: /esm/protein/api/v1alpha1/proteins/{protein_hash}: get: tags: - Proteins summary: Get protein metadata, sequence, and top SAE features description: >- Look up a protein by its MD5 hash and return its metadata, amino acid sequence, and top-activating SAE features. operationId: get_protein_v2_esm_protein_api_v1alpha1_proteins__protein_hash__get parameters: - name: protein_hash in: path required: true schema: type: string pattern: ^[0-9a-f]{32}$ title: Protein Hash - name: topk_features in: query required: false schema: type: integer maximum: 100 minimum: 1 default: 10 title: Topk Features - name: fold_on_miss in: query required: false schema: type: boolean default: true title: Fold On Miss - name: normalize_features in: query required: false schema: type: boolean description: >- When true (default), feature activation values are scaled per-feature so they are comparable across proteins (matches the ranking shown in the UI). When false, returns raw SAE activations — useful for callers doing their own normalization. default: true title: Normalize Features description: >- When true (default), feature activation values are scaled per-feature so they are comparable across proteins (matches the ranking shown in the UI). When false, returns raw SAE activations — useful for callers doing their own normalization. - name: feature_indices in: query required: false schema: anyOf: - type: array items: type: integer maxItems: 100 - type: 'null' description: >- When provided, return values for exactly these feature indices (in the given order) instead of the top-K ranking. Features with no recorded activation are returned with value 0.0; indices not in the catalog are skipped. Capped at 100 entries. title: Feature Indices description: >- When provided, return values for exactly these feature indices (in the given order) instead of the top-K ranking. Features with no recorded activation are returned with value 0.0; indices not in the catalog are skipped. Capped at 100 entries. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ProteinV2Response' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: ProteinV2Response: properties: protein_hash: type: string title: Protein Hash header: anyOf: - type: string - type: 'null' title: Header source: anyOf: - type: string - type: 'null' title: Source accession: anyOf: - type: string - type: 'null' title: Accession sequence: anyOf: - type: string - type: 'null' title: Sequence sequence_length: anyOf: - type: integer - type: 'null' title: Sequence Length ptm: anyOf: - type: number - type: 'null' title: Ptm mean_plddt: anyOf: - type: number - type: 'null' title: Mean Plddt residues_plddt: anyOf: - items: type: number type: array - type: 'null' title: Residues Plddt sae_features: items: $ref: '#/components/schemas/SAEFeatureResponse' type: array title: Sae Features default: [] protein_activations: anyOf: - $ref: '#/components/schemas/SparseActivations' - type: 'null' per_residue_activations: anyOf: - $ref: '#/components/schemas/SparseActivations' - type: 'null' pdb: anyOf: - type: string - type: 'null' title: Pdb cluster_rep_protein_hash: anyOf: - type: string - type: 'null' title: Cluster Rep Protein Hash folded_on_demand: type: boolean title: Folded On Demand default: false type: object required: - protein_hash title: ProteinV2Response description: 'Protein details: metadata, sequence, structure, and SAE features.' HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError SAEFeatureResponse: properties: feature_index: type: integer title: Feature Index label: type: string title: Label description: type: string title: Description value: type: number title: Value residue_regions: items: $ref: '#/components/schemas/ResidueRegion' type: array title: Residue Regions default: [] type: object required: - feature_index - label - description - value title: SAEFeatureResponse description: An SAE feature that is activated for a protein. SparseActivations: properties: indices: items: items: type: integer type: array type: array title: Indices description: COO indices [[residue_indices], [feature_indices]] values: items: type: number type: array title: Values description: Activation values corresponding to indices shape: items: type: integer type: array title: Shape description: Tensor shape [seq_len, num_features] type: object required: - indices - values - shape title: SparseActivations description: >- Sparse tensor representation of per-residue SAE activations in COO format. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError ResidueRegion: properties: start: type: integer title: Start end: type: integer title: End peak_residue: type: integer title: Peak Residue mean_activation: type: number title: Mean Activation type: object required: - start - end - peak_residue - mean_activation title: ResidueRegion description: A contiguous stretch of residues where an SAE feature is active. ````