--- type: "firecrawl-provider" description: "AlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page." use_when: "AlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page.\n\nAlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page.\n\nAlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page." categories: "Health" capabilities: 3 credits_per_call: 5 --- # AlphaFold Protein Structure Database on Firecrawl Alexandria AlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page. - Categories: Health - Category index: [Health category](https://firecrawl.dev/alexandria/agents/categories/health) - Provider key: `alphafold-ebi-ac-uk` - Access: Firecrawl credits - Cost: 5 credits per call ## More - [Human guide](https://firecrawl.dev/app/alexandria/alphafold-ebi-ac-uk) - [OpenAPI spec](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/openapi.json) ## Capabilities - [Prediction](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/structures/prediction): The AlphaFold DB predicted structure of one protein, by UniProt accession (P04637), isoform (P04637-2), entry name (P53_HUMAN), AlphaFold model ID (AF-P04637-F1, AF-0000000000710001), alphafold.ebi.ac.uk entry URL, or gene symbol and organism. Returns the model ID, version, date, method and provider, the UniProt residue range it covers, mean pLDDT and the share of residues per confidence band with a one-line reading, confident_regions (pLDDT 70 or more) and disordered_regions (pLDDT under 50) as UniProt residue ranges, whether AlphaMissense data exists, and links to the mmCIF, BinaryCIF, PDB, PAE and per-residue confidence files (coordinates are linked, never returned). Isoform and alternative models of the entry are listed in other_models. Merged UniProt accessions are followed. Unknown or deleted accessions and proteins AlphaFold DB does not model (it covers 16 to 2,700 residues) are not_found with the reason. - [Complexes](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/interactions/complexes): Predicted protein complexes in AlphaFold DB that contain a protein, by UniProt accession, entry name, model ID, entry URL or gene symbol and organism; or one complex by its model ID (AF-0000000065932364). Each complex lists its partners (UniProt accession, gene, protein name, organism, copies), assembly, the provider dataset (mostly NVIDIA's proteome-scale homo- and heterodimers), mean pLDDT, the interface scores ipTM, ipSAE, pDockQ, pDockQ2 and LIS, interface_confidence from ipTM (high 0.8 or more, medium 0.6 to 0.8, low under 0.6), links to the mmCIF and PAE image, and its entry page. Sorted by ipTM, highest first; min_iptm filters and limit caps the list. A protein with no predicted complexes returns an empty list. - [Missense](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/variants/missense): AlphaMissense pathogenicity predictions (Google DeepMind) for a human protein, from AlphaFold DB: every possible amino-acid substitution scored 0 to 1 and classed likely benign (under 0.34), ambiguous, or likely pathogenic (over 0.564). Pass variants (R175H, p.Arg175His; up to 50) for their scores and classes, checked against the UniProt canonical sequence. Every call also returns a protein summary: class fractions, mean score and sensitive_regions, the residue ranges whose mean score is above 0.564. Takes the same identifiers as prediction. Canonical human sequences only: other organisms and isoforms are not_found. These are research predictions, not clinical classifications. ## 1. Choose this provider when AlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page. AlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page. AlphaFold DB, EMBL-EBI and Google DeepMind's database of over 260 million predicted protein structures, through its keyless API at alphafold.ebi.ac.uk: the predicted structure of a protein with its pLDDT confidence, the residue ranges that are confident and those likely disordered, and links to the model, PAE and confidence files; predicted complexes containing a protein with their partners and interface scores (ipTM, ipSAE, pDockQ); and AlphaMissense pathogenicity predictions for every possible missense substitution in a human protein. Takes UniProt accessions, entry names, AlphaFold model IDs, entry URLs or gene symbols. Data is CC BY 4.0: every result carries its licence, citations and entry page. ## 2. Minimal request Call `POST https://api.firecrawl.dev/v2/scrape` with `{ alexandria: { provider, capability, options } }`. For a batch, send `{ alexandria: [...] }` with up to 10 calls. ```json { "provider": "alphafold-ebi-ac-uk", "capability": "structures/prediction", "options": { "id": "P04637" } } ``` ## 3. Add provider options Use only the options needed for the task: - `gene` (string): Gene symbol (TP53, CD52, HLA-A), resolved to the one reviewed (Swiss-Prot) UniProt entry with that gene name, or that synonym, in organism. A symbol shared by several entries is invalid_input listing them. Example: `` - `id` (string): UniProt accession (P04637), isoform (P04637-2), entry name (P53_HUMAN), AlphaFold DB model ID (AF-P04637-F1, AF-0000000000710001) or alphafold.ebi.ac.uk entry URL; case-insensitive. Exactly one of id and gene. Example: `` - `organism` (string): Organism for gene: NCBI taxonomy ID (9606) or name (human, Mus musculus). Default 9606 (human). Only with gene. Example: `` ## 4. Request through your preferred interface ### JavaScript ```javascript const result = await firecrawl.scrape({ alexandria: { provider: "alphafold-ebi-ac-uk", capability: "structures/prediction", options: { id: "P04637", }, }, }); ``` ### Python ```python result = firecrawl.scrape_alexandria({ "provider": "alphafold-ebi-ac-uk", "capability": "structures/prediction", "options": { "id": "P04637" } }) ``` ### cURL ```sh curl https://api.firecrawl.dev/v2/scrape \ -H "Authorization: Bearer $FIRECRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "alexandria": { "provider": "alphafold-ebi-ac-uk", "capability": "structures/prediction", "options": { "id": "P04637" } } }' ``` ### CLI ```sh firecrawl scrape 'alphafold-ebi-ac-uk/structures/prediction' \ --options '{"id":"P04637"}' ``` ### MCP Call the FCX MCP retrieve tool with this object: ```json { "provider": "alphafold-ebi-ac-uk", "capability": "structures/prediction", "options": { "id": "P04637" } } ``` Ask for only the returned fields needed by the task. ## 5. Full request shape ```json { "provider": "alphafold-ebi-ac-uk", "capability": "structures/prediction", "options": { "id": "P04637" } } ``` ## 6. Response data The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. This example shows the provider payload in `data`: ```json { "entry_name": "P53_HUMAN", "gene": "TP53", "license": { "attribution": "Data from the AlphaFold Protein Structure Database (alphafold.ebi.ac.uk), EMBL-EBI and Google DeepMind, CC BY 4.0. Cite Jumper J et al., Highly accurate protein structure prediction with AlphaFold, Nature 2021; Fleming J et al., AlphaFold Protein Structure Database and 3D-Beacons: New Data and Capabilities, J Mol Biol 2025, and the dataset publication named on the entry page for third-party predictions.", "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/" }, "model": { "alphamissense": true, "confidence": { "confident": 0.071, "low": 0.104, "very_high": 0.527, "very_low": 0.298 }, "confident_regions": [ { "end": 25, "length": 6, "mean_plddt": 73.8, "start": 20 }, { "end": 292, "length": 199, "mean_plddt": 95.3, "start": 94 }, { "end": 355, "length": 32, "mean_plddt": 91, "start": 324 } ], "created": "2025-08-01", "disordered_regions": [ { "end": 14, "length": 14, "mean_plddt": 44.5, "start": 1 }, { "end": 79, "length": 51, "mean_plddt": 42.8, "start": 29 }, { "end": 321, "length": 27, "mean_plddt": 45.2, "start": 295 }, { "end": 393, "length": 36, "mean_plddt": 43, "start": 358 } ], "files": { "bcif": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.bcif", "cif": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-predicted_aligned_error_v6.png", "pae_json": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-predicted_aligned_error_v6.json", "pdb": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.pdb", "plddt_json": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-confidence_v6.json" }, "length": 393, "mean_plddt": 75.06, "method": "AlphaFold Monomer v2.0 pipeline", "model_id": "AF-P04637-F1", "provider": "Google DeepMind", "reading": "Mean pLDDT 75.1: 53% of residues very high confidence, 7% confident, 10% low and 30% very low (likely disordered).", "sequence_version_date": "2009-11-24", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-F1", "uniprot_accession": "P04637", "uniprot_end": 393, "uniprot_start": 1, "version": 6, "versions": [ 1, 2, 3, 4, 5, 6 ] }, "no_model_reason": null, "observed_at_ms": 1792534178966, "organism": { "name": "Homo sapiens", "taxon_id": 9606 }, "other_models": [ { "length": 341, "mean_plddt": 76.94, "model_id": "AF-P04637-2-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-2-F1", "uniprot_accession": "P04637-2" }, { "length": 346, "mean_plddt": 76.94, "model_id": "AF-P04637-3-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-3-F1", "uniprot_accession": "P04637-3" }, { "length": 354, "mean_plddt": 77.81, "model_id": "AF-P04637-4-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-4-F1", "uniprot_accession": "P04637-4" }, { "length": 302, "mean_plddt": 81.5, "model_id": "AF-P04637-5-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-5-F1", "uniprot_accession": "P04637-5" }, { "length": 307, "mean_plddt": 82.44, "model_id": "AF-P04637-6-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-6-F1", "uniprot_accession": "P04637-6" }, { "length": 261, "mean_plddt": 81.44, "model_id": "AF-P04637-7-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-7-F1", "uniprot_accession": "P04637-7" }, { "length": 209, "mean_plddt": 83.56, "model_id": "AF-P04637-8-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-8-F1", "uniprot_accession": "P04637-8" }, { "length": 214, "mean_plddt": 82.94, "model_id": "AF-P04637-9-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-9-F1", "uniprot_accession": "P04637-9" } ], "protein_name": "Cellular tumor antigen p53", "reference_proteome": true, "requested": "P04637", "resolved_via": null, "reviewed": true, "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-F1", "uniprot_accession": "P04637" } ``` ## API reference-derived contract The following capability contract is generated from the same normalized Alexandria API reference exposed in the API spec. ### Prediction - Capability: `structures/prediction` - Description: The AlphaFold DB predicted structure of one protein, by UniProt accession (P04637), isoform (P04637-2), entry name (P53_HUMAN), AlphaFold model ID (AF-P04637-F1, AF-0000000000710001), alphafold.ebi.ac.uk entry URL, or gene symbol and organism. Returns the model ID, version, date, method and provider, the UniProt residue range it covers, mean pLDDT and the share of residues per confidence band with a one-line reading, confident_regions (pLDDT 70 or more) and disordered_regions (pLDDT under 50) as UniProt residue ranges, whether AlphaMissense data exists, and links to the mmCIF, BinaryCIF, PDB, PAE and per-residue confidence files (coordinates are linked, never returned). Isoform and alternative models of the entry are listed in other_models. Merged UniProt accessions are followed. Unknown or deleted accessions and proteins AlphaFold DB does not model (it covers 16 to 2,700 residues) are not_found with the reason. - Instructions: To check whether a protein has a reliable predicted 3D structure and which residue ranges are ordered or likely disordered, e.g. before choosing a construct, docking, or judging where a variant sits. For experimentally determined structures use rcsb-org structures/search with uniprot_accession; for function and annotation use uniprot-org proteins/get. - Cost: 5 credits per call - Capability file: [Prediction](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/structures/prediction) Accepted options: - `gene` (string): Gene symbol (TP53, CD52, HLA-A), resolved to the one reviewed (Swiss-Prot) UniProt entry with that gene name, or that synonym, in organism. A symbol shared by several entries is invalid_input listing them. Example: `` - `id` (string): UniProt accession (P04637), isoform (P04637-2), entry name (P53_HUMAN), AlphaFold DB model ID (AF-P04637-F1, AF-0000000000710001) or alphafold.ebi.ac.uk entry URL; case-insensitive. Exactly one of id and gene. Example: `` - `organism` (string): Organism for gene: NCBI taxonomy ID (9606) or name (human, Mus musculus). Default 9606 (human). Only with gene. Example: `` Response schema example: ```json { "entry_name": "P53_HUMAN", "gene": "TP53", "license": { "attribution": "Data from the AlphaFold Protein Structure Database (alphafold.ebi.ac.uk), EMBL-EBI and Google DeepMind, CC BY 4.0. Cite Jumper J et al., Highly accurate protein structure prediction with AlphaFold, Nature 2021; Fleming J et al., AlphaFold Protein Structure Database and 3D-Beacons: New Data and Capabilities, J Mol Biol 2025, and the dataset publication named on the entry page for third-party predictions.", "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/" }, "model": { "alphamissense": true, "confidence": { "confident": 0.071, "low": 0.104, "very_high": 0.527, "very_low": 0.298 }, "confident_regions": [ { "end": 25, "length": 6, "mean_plddt": 73.8, "start": 20 }, { "end": 292, "length": 199, "mean_plddt": 95.3, "start": 94 }, { "end": 355, "length": 32, "mean_plddt": 91, "start": 324 } ], "created": "2025-08-01", "disordered_regions": [ { "end": 14, "length": 14, "mean_plddt": 44.5, "start": 1 }, { "end": 79, "length": 51, "mean_plddt": 42.8, "start": 29 }, { "end": 321, "length": 27, "mean_plddt": 45.2, "start": 295 }, { "end": 393, "length": 36, "mean_plddt": 43, "start": 358 } ], "files": { "bcif": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.bcif", "cif": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-predicted_aligned_error_v6.png", "pae_json": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-predicted_aligned_error_v6.json", "pdb": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.pdb", "plddt_json": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-confidence_v6.json" }, "length": 393, "mean_plddt": 75.06, "method": "AlphaFold Monomer v2.0 pipeline", "model_id": "AF-P04637-F1", "provider": "Google DeepMind", "reading": "Mean pLDDT 75.1: 53% of residues very high confidence, 7% confident, 10% low and 30% very low (likely disordered).", "sequence_version_date": "2009-11-24", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-F1", "uniprot_accession": "P04637", "uniprot_end": 393, "uniprot_start": 1, "version": 6, "versions": [ 1, 2, 3, 4, 5, 6 ] }, "no_model_reason": null, "observed_at_ms": 1792534178966, "organism": { "name": "Homo sapiens", "taxon_id": 9606 }, "other_models": [ { "length": 341, "mean_plddt": 76.94, "model_id": "AF-P04637-2-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-2-F1", "uniprot_accession": "P04637-2" }, { "length": 346, "mean_plddt": 76.94, "model_id": "AF-P04637-3-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-3-F1", "uniprot_accession": "P04637-3" }, { "length": 354, "mean_plddt": 77.81, "model_id": "AF-P04637-4-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-4-F1", "uniprot_accession": "P04637-4" }, { "length": 302, "mean_plddt": 81.5, "model_id": "AF-P04637-5-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-5-F1", "uniprot_accession": "P04637-5" }, { "length": 307, "mean_plddt": 82.44, "model_id": "AF-P04637-6-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-6-F1", "uniprot_accession": "P04637-6" }, { "length": 261, "mean_plddt": 81.44, "model_id": "AF-P04637-7-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-7-F1", "uniprot_accession": "P04637-7" }, { "length": 209, "mean_plddt": 83.56, "model_id": "AF-P04637-8-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-8-F1", "uniprot_accession": "P04637-8" }, { "length": 214, "mean_plddt": 82.94, "model_id": "AF-P04637-9-F1", "provider": "Google DeepMind", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-9-F1", "uniprot_accession": "P04637-9" } ], "protein_name": "Cellular tumor antigen p53", "reference_proteome": true, "requested": "P04637", "resolved_via": null, "reviewed": true, "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-F1", "uniprot_accession": "P04637" } ``` ### Complexes - Capability: `interactions/complexes` - Description: Predicted protein complexes in AlphaFold DB that contain a protein, by UniProt accession, entry name, model ID, entry URL or gene symbol and organism; or one complex by its model ID (AF-0000000065932364). Each complex lists its partners (UniProt accession, gene, protein name, organism, copies), assembly, the provider dataset (mostly NVIDIA's proteome-scale homo- and heterodimers), mean pLDDT, the interface scores ipTM, ipSAE, pDockQ, pDockQ2 and LIS, interface_confidence from ipTM (high 0.8 or more, medium 0.6 to 0.8, low under 0.6), links to the mmCIF and PAE image, and its entry page. Sorted by ipTM, highest first; min_iptm filters and limit caps the list. A protein with no predicted complexes returns an empty list. - Instructions: To see which partners AlphaFold DB predicts a protein binds and how confident each interface is. These are predictions from a selective dataset (AlphaFold DB shows NVIDIA complexes only above its own pDockQ2 and ipSAE cut-offs), so a missing partner is not evidence of no interaction, and partners can come from other species: check each partner's organism. - Cost: 5 credits per call - Capability file: [Complexes](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/interactions/complexes) Accepted options: - `gene` (string): Gene symbol (TP53, CD52, HLA-A), resolved to the one reviewed (Swiss-Prot) UniProt entry with that gene name, or that synonym, in organism. A symbol shared by several entries is invalid_input listing them. Example: `` - `id` (string): UniProt accession (P04637), isoform (P04637-2), entry name (P53_HUMAN), AlphaFold DB model ID (AF-P04637-F1, AF-0000000000710001) or alphafold.ebi.ac.uk entry URL; case-insensitive. Exactly one of id and gene. Example: `` - `limit` (number): Most complexes to return, highest ipTM first. Example: `25` - `min_iptm` (number): Only complexes with ipTM at least this (0.8 keeps confident interfaces). Example: `1` - `organism` (string): Organism for gene: NCBI taxonomy ID (9606) or name (human, Mus musculus). Default 9606 (human). Only with gene. Example: `` Response schema example: ```json { "complexes": [ { "assembly": "homomer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000065932364-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000065932364-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.88, "iptm": 0.93, "lis": 0.73, "mean_plddt": 96.03, "model_id": "AF-0000000065932364", "name": "Homodimer of Hemoglobin subunit alpha", "oligomeric_state": "dimer", "partners": [ { "copies": 2, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" } ], "pdockq": 0.53, "pdockq2": 0.94, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000065932364", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000211046780-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000211046780-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.87, "iptm": 0.92, "lis": 0.69, "mean_plddt": 94.52, "model_id": "AF-0000000211046780", "name": "Complex of Hemoglobin subunit alpha/Hemoglobin subunit beta", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "HBB", "organism": "Pan troglodytes", "protein_name": "Hemoglobin subunit beta", "taxon_id": 9598, "uniprot_accession": "P68873" } ], "pdockq": 0.57, "pdockq2": 0.94, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000211046780", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852721-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852721-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.85, "iptm": 0.91, "lis": 0.66, "mean_plddt": 93.52, "model_id": "AF-0000000203852721", "name": "Complex of Hemoglobin subunit alpha/Hemoglobin subunit zeta", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "HBZ", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit zeta", "taxon_id": 9606, "uniprot_accession": "P02008" } ], "pdockq": 0.53, "pdockq2": 0.91, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852721", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852814-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852814-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.85, "iptm": 0.91, "lis": 0.65, "mean_plddt": 92.89, "model_id": "AF-0000000203852814", "name": "Complex of Hemoglobin subunit alpha/Hemoglobin subunit delta", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "HBD", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit delta", "taxon_id": 9606, "uniprot_accession": "P02042" } ], "pdockq": 0.56, "pdockq2": 0.92, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852814", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852694-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852694-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.82, "iptm": 0.9, "lis": 0.63, "mean_plddt": 92.48, "model_id": "AF-0000000203852694", "name": "Complex of Hemoglobin subunit theta-1/Hemoglobin subunit alpha", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBQ1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit theta-1", "taxon_id": 9606, "uniprot_accession": "P09105" }, { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" } ], "pdockq": 0.53, "pdockq2": 0.89, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852694", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852815-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852815-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.82, "iptm": 0.9, "lis": 0.64, "mean_plddt": 91.79, "model_id": "AF-0000000203852815", "name": "Complex of Hemoglobin subunit alpha/Hemoglobin subunit epsilon", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "HBE1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit epsilon", "taxon_id": 9606, "uniprot_accession": "P02100" } ], "pdockq": 0.55, "pdockq2": 0.9, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852815", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852801-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852801-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.83, "iptm": 0.89, "lis": 0.69, "mean_plddt": 92.8, "model_id": "AF-0000000203852801", "name": "Complex of Alpha-hemoglobin-stabilizing protein/Hemoglobin subunit alpha", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "AHSP", "organism": "Homo sapiens", "protein_name": "Alpha-hemoglobin-stabilizing protein", "taxon_id": 9606, "uniprot_accession": "Q9NZD4" }, { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" } ], "pdockq": 0.46, "pdockq2": 0.82, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852801", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852812-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852812-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.82, "iptm": 0.89, "lis": 0.61, "mean_plddt": 91.54, "model_id": "AF-0000000203852812", "name": "Complex of Hemoglobin subunit zeta/Hemoglobin subunit alpha", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBZ", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit zeta", "taxon_id": 9606, "uniprot_accession": "P02008" }, { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" } ], "pdockq": 0.52, "pdockq2": 0.88, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852812", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203853219-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203853219-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.8, "iptm": 0.89, "lis": 0.61, "mean_plddt": 90.3, "model_id": "AF-0000000203853219", "name": "Complex of Hemoglobin subunit epsilon/Hemoglobin subunit alpha", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBE1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit epsilon", "taxon_id": 9606, "uniprot_accession": "P02100" }, { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" } ], "pdockq": 0.54, "pdockq2": 0.87, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203853219", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852817-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852817-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.8, "iptm": 0.89, "lis": 0.6, "mean_plddt": 90.12, "model_id": "AF-0000000203852817", "name": "Complex of Hemoglobin subunit alpha/Hemoglobin subunit mu", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "HBM", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit mu", "taxon_id": 9606, "uniprot_accession": "Q6B0K9" } ], "pdockq": 0.49, "pdockq2": 0.86, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852817", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203484700-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203484700-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.82, "iptm": 0.88, "lis": 0.69, "mean_plddt": 92.23, "model_id": "AF-0000000203484700", "name": "Complex of Hemoglobin subunit alpha/Alpha-hemoglobin-stabilizing protein", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "AHSP", "organism": "Homo sapiens", "protein_name": "Alpha-hemoglobin-stabilizing protein", "taxon_id": 9606, "uniprot_accession": "Q9NZD4" } ], "pdockq": 0.45, "pdockq2": 0.81, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203484700", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852816-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852816-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.76, "iptm": 0.86, "lis": 0.55, "mean_plddt": 88.14, "model_id": "AF-0000000203852816", "name": "Complex of Hemoglobin subunit alpha/Hemoglobin subunit gamma-2", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "HBG2", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit gamma-2", "taxon_id": 9606, "uniprot_accession": "P69892" } ], "pdockq": 0.53, "pdockq2": 0.82, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852816", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000203852921-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000203852921-predicted_aligned_error_v1.png" }, "interface_confidence": "high", "ipsae": 0.71, "iptm": 0.86, "lis": 0.51, "mean_plddt": 83.75, "model_id": "AF-0000000203852921", "name": "Complex of Hemoglobin subunit alpha/Globin domain-containing protein", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": null, "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": null, "organism": "Homo sapiens", "protein_name": "Globin domain-containing protein", "taxon_id": 9606, "uniprot_accession": "A0A2R8Y7X9" } ], "pdockq": 0.43, "pdockq2": 0.5, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000203852921", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000211014131-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000211014131-predicted_aligned_error_v1.png" }, "interface_confidence": "medium", "ipsae": 0.81, "iptm": 0.79, "lis": 0.58, "mean_plddt": 92.21, "model_id": "AF-0000000211014131", "name": "Complex of Hemoglobin subunit alpha/Small ribosomal subunit protein uS8", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" }, { "copies": 1, "gene": "Rps15a", "organism": "Rattus norvegicus", "protein_name": "Small ribosomal subunit protein uS8", "taxon_id": 10116, "uniprot_accession": "P62246" } ], "pdockq": 0.35, "pdockq2": 0.55, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000211014131", "version": 1 }, { "assembly": "heteromer", "files": { "cif": "https://alphafold.ebi.ac.uk/files/AF-0000000211047586-model_v1.cif", "pae_image": "https://alphafold.ebi.ac.uk/files/AF-0000000211047586-predicted_aligned_error_v1.png" }, "interface_confidence": "low", "ipsae": 0.92, "iptm": 0.18, "lis": 0.7, "mean_plddt": 86.79, "model_id": "AF-0000000211047586", "name": "Complex of 3-oxoacyl-/Hemoglobin subunit alpha", "oligomeric_state": "dimer", "partners": [ { "copies": 1, "gene": "OXSM", "organism": "Homo sapiens", "protein_name": "3-oxoacyl-", "taxon_id": 9606, "uniprot_accession": "Q9NWU1" }, { "copies": 1, "gene": "HBA1", "organism": "Homo sapiens", "protein_name": "Hemoglobin subunit alpha", "taxon_id": 9606, "uniprot_accession": "P69905" } ], "pdockq": 0.33, "pdockq2": 0.54, "provider": "NVIDIA", "source_url": "https://alphafold.ebi.ac.uk/entry/AF-0000000211047586", "version": 1 } ], "license": { "attribution": "Data from the AlphaFold Protein Structure Database (alphafold.ebi.ac.uk), EMBL-EBI and Google DeepMind, CC BY 4.0. Cite Jumper J et al., Highly accurate protein structure prediction with AlphaFold, Nature 2021; Fleming J et al., AlphaFold Protein Structure Database and 3D-Beacons: New Data and Capabilities, J Mol Biol 2025, and the dataset publication named on the entry page for third-party predictions.", "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/" }, "observed_at_ms": 1792534183348, "requested": "P69905", "resolved_via": null, "source_url": "https://alphafold.ebi.ac.uk/entry/P69905", "total_count": 15, "uniprot_accession": "P69905" } ``` ### Missense - Capability: `variants/missense` - Description: AlphaMissense pathogenicity predictions (Google DeepMind) for a human protein, from AlphaFold DB: every possible amino-acid substitution scored 0 to 1 and classed likely benign (under 0.34), ambiguous, or likely pathogenic (over 0.564). Pass variants (R175H, p.Arg175His; up to 50) for their scores and classes, checked against the UniProt canonical sequence. Every call also returns a protein summary: class fractions, mean score and sensitive_regions, the residue ranges whose mean score is above 0.564. Takes the same identifiers as prediction. Canonical human sequences only: other organisms and isoforms are not_found. These are research predictions, not clinical classifications. - Instructions: To judge whether a missense variant is likely damaging, or which parts of a protein tolerate substitution least. Pair with prediction to see whether a variant sits in a confident or disordered region. - Cost: 5 credits per call - Capability file: [Missense](https://firecrawl.dev/alexandria/agents/providers/alphafold-ebi-ac-uk/variants/missense) Accepted options: - `gene` (string): Gene symbol (TP53, CD52, HLA-A), resolved to the one reviewed (Swiss-Prot) UniProt entry with that gene name, or that synonym, in organism. A symbol shared by several entries is invalid_input listing them. Example: `` - `id` (string): UniProt accession (P04637), isoform (P04637-2), entry name (P53_HUMAN), AlphaFold DB model ID (AF-P04637-F1, AF-0000000000710001) or alphafold.ebi.ac.uk entry URL; case-insensitive. Exactly one of id and gene. Example: `` - `organism` (string): Organism for gene: NCBI taxonomy ID (9606) or name (human, Mus musculus). Default 9606 (human). Only with gene. Example: `` - `variants` (string[]): Protein-level missense changes on the canonical sequence: one-letter (R175H) or three-letter (p.Arg175His) form. Example: `[]` Response schema example: ```json { "entry_name": "P53_HUMAN", "files": { "hg19_csv": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-hg19.csv", "hg38_csv": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-hg38.csv", "substitutions_csv": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-aa-substitutions.csv" }, "gene": "TP53", "license": { "attribution": "AlphaMissense predictions by Google DeepMind, served by the AlphaFold Protein Structure Database (alphafold.ebi.ac.uk), CC BY 4.0. Cite Cheng J et al., Accurate proteome-wide missense variant effect prediction with AlphaMissense, Science 2023; and Jumper J et al., Highly accurate protein structure prediction with AlphaFold, Nature 2021; Fleming J et al., AlphaFold Protein Structure Database and 3D-Beacons: New Data and Capabilities, J Mol Biol 2025.", "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/" }, "model_id": "AF-P04637-F1", "observed_at_ms": 1792534185281, "organism": { "name": "Homo sapiens", "taxon_id": 9606 }, "protein_name": "Cellular tumor antigen p53", "reference_proteome": true, "requested": "P04637", "resolved_via": null, "reviewed": true, "sequence_length": 393, "source_url": "https://alphafold.ebi.ac.uk/entry/AF-P04637-F1", "summary": { "ambiguous": 0.102, "likely_benign": 0.44, "likely_pathogenic": 0.458, "mean_pathogenicity": 0.5267, "reading": "46% of the 7467 possible missense substitutions are likely pathogenic, 10% ambiguous and 44% likely benign.", "sensitive_regions": [ { "end": 26, "length": 13, "mean_pathogenicity": 0.58, "start": 14 }, { "end": 105, "length": 12, "mean_pathogenicity": 0.581, "start": 94 }, { "end": 181, "length": 75, "mean_pathogenicity": 0.751, "start": 107 }, { "end": 288, "length": 103, "mean_pathogenicity": 0.791, "start": 186 }, { "end": 352, "length": 25, "mean_pathogenicity": 0.676, "start": 328 } ], "substitutions": 7467 }, "uniprot_accession": "P04637", "variants": [ { "alternate": "H", "am_class": "likely_pathogenic", "am_pathogenicity": 0.9857, "input": "R175H", "position": 175, "reference": "R", "residue_mean_pathogenicity": 0.989, "variant": "R175H" }, { "alternate": "H", "am_class": "likely_pathogenic", "am_pathogenicity": 0.9889, "input": "p.Arg273His", "position": 273, "reference": "R", "residue_mean_pathogenicity": 0.9949, "variant": "R273H" }, { "alternate": "R", "am_class": "likely_benign", "am_pathogenicity": 0.0724, "input": "P72R", "position": 72, "reference": "P", "residue_mean_pathogenicity": 0.1277, "variant": "P72R" } ] } ```