AlphaFold Sovereign MCP

Export filtered proteins to TSV/CSV for ML pipelines. PROPRIETARY TOOL - TOPOLOGICA LLC Creates tabular exports suitable for: - Training machine learning models - Data analysis in pandas/R - Integration with CAFA pipelines Args: uniprot_ids: List of proteins to export output_format: 'tsv' or 'csv' include_columns: Which columns to include include_go_terms: Include GO annotations include_sequence: Include full sequences filename: Output filename Returns: Path to exported file or data preview

Export the stored knowledge-graph data for downstream analysis. Returns all stored entities as JSON-serialisable dicts, suitable for: - Loading into pandas DataFrames for ML feature engineering - Importing into R or Julia for statistical analysis - Feeding into downstream bioinformatics pipelines Example (Python):: import pandas as pd result = await export_research_dataset(ExportInput(tables=["variants"])) df = pd.DataFrame(result["data"]["variants"]) high_tier = df[df["clinical_tier"] == "HIGH"] Input fields: params.tables: Tables to export (empty = all entity tables).…

Extract Predicted Aligned Error (PAE) matrix from AlphaFold structure. PROPRIETARY TOOL - TOPOLOGICA LLC PAE measures predicted distance error between residue pairs. Low PAE (<5Å) indicates high confidence in relative positioning. Returns: PAE matrix with statistics (min, max, mean, domain blocks)

Filter proteins by organism from local cache. PROPRIETARY TOOL - TOPOLOGICA LLC Searches local AlphaFold structures for organism-specific proteins. Essential for species-specific function prediction. Args: organism: Organism name or taxonomy ID limit: Maximum results include_go_summary: Include GO term counts Returns: List of proteins from specified organism

Traverse the local knowledge graph from a seed entity. Given a seed (UniProt ID, gene symbol, or MONDO disease ID), expands its immediate neighbourhood in the stored drug-gene-disease graph: a gene symbol resolves to its encoded proteins and reported variants, a UniProt accession resolves to its stored protein record, and a MONDO disease resolves to drugs with an indication for it. The store is populated by the curated boot seed and by explicit writes through the storage API. Input fields: params.seed: Starting entity identifier. params.max_hops: Graph traversal depth (1–3).

Rank existing clinical-stage drugs as repurposing candidates for a disease. Surfaces approved or trial-stage drugs whose target carries genetic/association evidence for the disease — i.e. drug-repurposing hypotheses. For the full approved-plus-pipeline drug picture of a disease (not only repurposing candidates), use ``map_disease_drug_landscape`` instead. How it works: take the top ``target_limit`` Open Targets evidence-scored targets for the disease; for each, fetch its ChEMBL drugs at or above ``min_phase``; drop duplicate molecules; rank by ``composite_repurposing_score = OT evidence scor…

Report ortholog sequence identity and exploratory structural distances. Distances between Cα-derived feature vectors are not calibrated evolutionary, functional, binding, or antibody cross-reactivity measures. The GUDHI and geometric-proxy methods are distinguished in each result. There is deliberately no cross-method conservation ranking.

Find proteins similar by sequence or structure. PROPRIETARY TOOL - TOPOLOGICA LLC Uses k-mer based sequence similarity for fast approximate matching. For structure similarity, uses C-alpha RMSD when structures available. Args: uniprot_id: Query protein similarity_type: 'sequence' or 'structure' threshold: Minimum similarity (0-1) limit: Maximum results search_scope: 'local' or 'all' Returns: List of similar proteins with similarity scores

Generate a multi-source variant interpretation report. Cross-references evidence from up to seven upstream databases for a single HGVS variant into one structured research report. It preserves source classifications and computational observations separately; it does not assign an independent clinical tier or establish ACMG criteria. 1. **Ensembl VEP** — functional consequence, SIFT/PolyPhen/CADD predictions 2. **ClinVar** — clinical pathogenicity classifications and review status 3. **gnomAD v4** — population allele frequencies (gnomAD v4, ~807k individuals) 4. **AlphaMissense** — deep-learn…

Compute advanced topological features with full TDA pipeline. PROPRIETARY TOOL - TOPOLOGICA LLC Features: - Persistence diagrams (birth-death pairs) - Betti curves over filtration - Persistence landscapes - Persistence images (vectorization) - Euler characteristic curve Mathematical Foundation: Vietoris-Rips complex on C-alpha atoms. H_k computed via matrix reduction.

Get statistics about the local structure cache. PROPRIETARY TOOL - TOPOLOGICA LLC Returns information about: - Number of local structures - Cache directories and mode - Storage locations - Configuration status

Profile the top drug targets for a curated set of common diseases in one call. Use this for a fast landscape scan across a whole disease area: given a ``category`` (e.g. 'oncology'), it looks up the curated MONDO diseases in that category and returns each one's top Open Targets evidence-scored targets, in parallel. To profile a single disease you already have a MONDO ID for, use ``get_disease_targets`` instead — this tool is its category-level, multi-disease counterpart and does not accept a raw MONDO ID. Queries Open Targets live. Returns a JSON string with the ``category``, the number of d…

Return top protein targets for a disease with Open Targets evidence scores. Evidence score breakdown (0–1 per data type): - ``genetic_association``: GWAS + rare-variant signals - ``somatic_mutation``: Cancer somatic variant evidence - ``known_drug``: Approved or clinical-stage drugs - ``affected_pathway``: Pathway membership (Reactome, SIGNOR) - ``literature``: Text-mining evidence (Europe PMC) - ``animal_model``: Knockout / model organism phenotypes - ``rna_expression``: Differential expression evidence Example: ``get_disease_targets(disease_id='MONDO:0007254', limit=15)`` returns top 15 ta…

Retrieve Pfam/InterPro domain annotations. PROPRIETARY TOOL - TOPOLOGICA LLC Fetches domain annotations from UniProt cross-references. Domains are key features for function prediction. Args: uniprot_ids: List of proteins sources: Annotation sources (Pfam, InterPro, etc.) Returns: Domain annotations for each protein

Get comprehensive protein information combining AlphaFold structure + UniProt metadata. PROPRIETARY TOOL - TOPOLOGICA LLC This tool provides UNIQUE VALUE by combining: 1. AlphaFold structural data (3D coordinates, pLDDT confidence) 2. UniProt functional annotations (function, GO terms, active sites) 3. Disease associations and literature links 4. Computed structural features (secondary structure, binding pockets) Use Cases: - Drug target assessment (structure + function + disease) - Protein characterization (complete biological context) - Research starting point …

Compute detailed structural features for a protein. PROPRIETARY TOOL - TOPOLOGICA LLC Available features: - secondary_structure: Alpha-helix, beta-strand, coil classification - binding_pockets: Cavity detection with druggability scoring - confidence: pLDDT-based quality assessment - contacts: Local structural compactness Args: uniprot_id: UniProt accession feature_types: List of features to compute Returns: Detailed feature analysis

Return all HPO phenotypes associated with a gene, plus gnomAD constraint. Useful for understanding the clinical consequences of variants in a gene before requesting structural context. Returns: - HPO phenotypes linked to the gene (from HPO association database) - gnomAD LOEUF / pLI constraint scores - Interpretation of constraint (haploinsufficient / tolerant / moderate) Example: ``get_gene_phenotype_profile(gene_symbol='SCN1A')``

Navigate GO term parent/child relationships. PROPRIETARY TOOL - TOPOLOGICA LLC Fetches GO term hierarchy from QuickGO API. Essential for GO term propagation in function prediction. Use Cases: - Understand term specificity - Propagate annotations up the hierarchy - Find related terms for training Args: go_term: GO term ID (e.g., 'GO:0003700') direction: 'parents', 'children', or 'both' depth: How many levels to traverse Returns: Hierarchical structure of related GO terms

Return statistics about the local knowledge graph. Shows entity counts, database size, and last activity — useful for understanding the current contents and coverage of the local store.

Get detailed per-residue pLDDT confidence profile. PROPRIETARY TOOL - TOPOLOGICA LLC pLDDT categories: - Very high (>90): High confidence - High (70-90): Good confidence - Low (50-70): Caution - Very low (<50): Likely disordered

Cluster proteins by sequence or GO term similarity. PROPRIETARY TOOL - TOPOLOGICA LLC Groups proteins into families based on similarity. Useful for identifying functionally related proteins. Args: uniprot_ids: Proteins to cluster clustering_method: 'sequence' or 'go_terms' similarity_threshold: Clustering threshold Returns: Protein family assignments

Retrieve a protein's AlphaFold model: metadata, download URLs, optional coordinates. The single entry point for getting the predicted structure itself. Returns the AlphaFold DB entry metadata — entry ID, model version and creation date, organism, gene, UniProt description, the amino-acid sequence and its length, and the model's mean pLDDT — plus stable download URLs for the PDB and mmCIF coordinate files, the PAE matrix, and the AlphaMissense substitutions CSV. The PAE image URL is only present in legacy API responses. Set ``include_coordinates`` to embed the full PDB coordinate text directly…

Retrieve an AlphaFold protein structure by UniProt ID. PROPRIETARY TOOL - TOPOLOGICA LLC Operation (Cache-First Sovereign Strategy): 1. Check local cache (dynamically indexed, grows with usage) 2. If not found, fetch from AlphaFold DB online 3. Auto-cache fetched structures for future sovereign access 4. Optionally compute structural and topological features Args: uniprot_id: UniProt accession (e.g., 'P12345', 'A0A023FBW4') include_features: Compute secondary structure, binding pockets include_topology: Compute persistent homology (slower) force_online: Force…

Return all diseases associated with a protein target via Open Targets. Accepts a UniProt accession and returns the full disease landscape for that target — essential for target-validation and indication-expansion. Example: ``get_target_diseases(uniprot_id='P04637')`` returns all diseases associated with TP53 / p53.

Compute topological features (persistent homology) for a protein. PROPRIETARY TOOL - TOPOLOGICA LLC Mathematical Foundation: Vietoris-Rips filtration on C-alpha atom point cloud. Computes: - beta_0: Connected components (protein domains) - beta_1: Loops/tunnels (structural motifs) - beta_2: Voids/cavities (binding sites) - Euler characteristic: chi = beta_0 - beta_1 + beta_2 - Persistence diagrams: Birth/death pairs for features Args: uniprot_id: UniProt accession max_dimension: Maximum homology dimension (0, 1, or 2) max_filtration: Maximum filt…

Retrieve a disease record from the MONDO unified disease ontology. Returns the canonical MONDO entry with: - Disease name, definition, synonyms - ICD-10 / ICD-11 codes (for clinical coding / EHR integration) - OMIM, Orphanet, MeSH, DOID cross-references - Immediate parent and child terms in the MONDO hierarchy Example: ``lookup_disease(mondo_id='MONDO:0005010')`` returns the record for coronary artery disease.

Retrieve an HPO phenotype term with associated disease annotations. Returns: - Phenotype label, definition, synonyms - Diseases annotated with this phenotype (from HPO + OMIM + Orphanet) - Parent phenotype terms Example: ``lookup_phenotype(hpo_id='HP:0001250')`` returns the Seizure phenotype with ~400 associated diseases.

Map the complete therapeutic landscape for a disease. Returns approved drugs, pipeline agents, top druggable targets, and an investability summary for a given MONDO disease. Combines Open Targets evidence with ChEMBL drug indications and MONDO disease hierarchy to produce a comprehensive landscape report used in business development, competitive intelligence, and R&D portfolio decisions. Input fields: params.disease_mondo_id: MONDO disease ID.

Map a clinical phenotype to the protein structures of its disease targets. Pipeline: 1. Resolve HPO term → associated diseases 2. For each disease → top protein targets (Open Targets) 3. For each target → UniProt ID (for AlphaFold retrieval) Use the returned UniProt IDs with ``analyze_structural_confidence`` to retrieve AlphaFold structural confidence (pLDDT/PAE). Example: ``phenotype_to_structures(hpo_id='HP:0002621')`` maps Atherosclerosis → disease targets → UniProt IDs.

Predict intrinsically disordered regions (IDRs) from pLDDT scores. PROPRIETARY TOOL - TOPOLOGICA LLC Low pLDDT (<50) often indicates disorder/flexibility. Returns IDR regions, propensity profile, and disorder statistics.

Recall proteins already stored in the local knowledge graph. This is a local-recall query, not a live lookup: it returns only proteins that have previously been written to the local SQLite store (the curated boot seed, plus anything added through the knowledge-graph storage API). No upstream API is called. To assess a protein that may not be stored yet, use ``assess_target_druggability`` (druggability tier) or ``analyze_structural_confidence`` (pLDDT), which query live sources. Filters are combined with AND; omit a filter to leave that dimension unconstrained. Returns a JSON record with the …

Search the local knowledge graph for stored variants. Returns variants matching the filter criteria. No upstream API calls are made — all data is served from the local SQLite knowledge graph, which is populated by the curated boot seed and by any explicit writes through the knowledge-graph storage API (the analysis tools do not write to it on their own). Input fields: params.gene: Gene symbol filter. params.tier: Clinical tier (HIGH/MEDIUM/LOW/UNKNOWN). params.clinvar_class: ClinVar classification string. params.min_am_score: Minimum AlphaMissense score. params.max_gnomad…

Resolve an ICD-10 clinical code to MONDO disease ontology terms. Enables integration between clinical / EHR data (which uses ICD-10) and the research-grade MONDO ontology used by Open Targets, HPO, and this MCP. Example: ``resolve_icd10_to_mondo(icd10_code='I21.0')`` maps ST-elevation MI (ICD-10) to MONDO coronary disease terms.

Identify and score putative binding pockets from AlphaFold geometry. Detects pockets with a geometry-only heuristic. Residues in the inner 60 percent of the structure by distance from the centroid are taken as the pocket-forming core, then grown greedily into clusters within an 8 Angstrom radius. A cluster is kept as a putative pocket when it has at least ``min_pocket_residues`` members and a mean pLDDT of at least 50. Each pocket reports a radius of gyration (compactness of the pocket residues), a centroid offset (distance of the pocket centroid from the structure centroid; larger means mor…

Find all proteins with a specific GO annotation. PROPRIETARY TOOL - TOPOLOGICA LLC Searches the inverted index for proteins annotated with a GO term. Essential for building training sets for function prediction. Use Cases: - Find all kinases (GO:0016301) - Find all membrane proteins (GO:0016020) - Build positive training sets for specific functions Args: go_term: GO term ID (e.g., 'GO:0003700') or name pattern include_children: Also include proteins with child terms organism_filter: Filter by organism limit: Maximum results Returns: List of proteins with th…

Search for diseases by name or keyword using the MONDO ontology. Returns a ranked list of matching diseases with MONDO IDs and cross-references. Useful for resolving a clinical term to a canonical identifier before querying targets or phenotypes. Example: ``search_diseases(query='breast cancer', limit=5)``

Search local AlphaFold structure cache. PROPRIETARY TOOL - TOPOLOGICA LLC Searches the sovereign cache (dynamically indexed) by UniProt ID pattern. Includes both pre-downloaded structures and previously-fetched online structures. Args: pattern: Glob-style pattern (e.g., 'A0A*', 'P123*') limit: Maximum results (default 100) offset: Pagination offset Returns: List of matching UniProt IDs

Generate a complete protein intelligence dossier from 7 data sources. It assembles disease associations, drug precedent, population constraint, ClinVar variants, and cross-species orthologs for one protein into a single structured record. It composes upstream databases; it does not add scientific judgement. Sources fused in parallel: - **Open Targets**: disease associations + tractability + drug count - **DisGeNET**: curated GDA scores with publication counts - **ChEMBL**: approved drugs + MoA + bioactivity - **gnomAD**: population constraint (pLI, LOEUF, mis_z) - **ClinVar**: path…

Retrieve source-reported variant evidence for research. Fuses the upstream signals this tool currently wires into a single prioritised report: 1. **Pathogenicity** — ClinVar interpretation + review status. The ``alphamissense_score`` / ``alphamissense_interpretation`` fields are always ``null`` / "Not available" here: AlphaMissense is not wired into this tool. For an AlphaMissense pathogenicity score use ``generate_variant_clinical_report``. 2. **Population genetics** — gnomAD LOEUF / pLI gene-constraint scores. Per-variant allele frequencies and the per-ancestry breakdown …