Precision-medicine tools

ACMG mapping is not validated

Both generate_variant_clinical_report and classify_variant_acmg use an ACMG/AMP criterion mapping that has not been reviewed by an independent clinical geneticist. Treat the output as a research aid, never as clinical decision support. See Limitations L1.

Druggability tier is a heuristic

assess_target_druggability returns a HOT/WARM/COLD/NOT_DRUGGABLE tier from a 4-line scoring heuristic. The thresholds are not calibrated against a benchmark. See Limitations L2.

alphafold_sovereign.tools.precision_medicine

Precision-medicine MCP tools.

These tools compose multiple upstream APIs into per-call synthesis reports. They do not add scientific judgement; they assemble what the upstreams say in one place.

Tool inventory

1. generate_variant_clinical_report — HGVS → multi-source variant report
2. assess_target_druggability — UniProt → heuristic HOT/WARM/COLD/NOT_DRUGGABLE
3. synthesize_protein_dossier — UniProt → multi-source briefing
4. find_drug_repurposing_candidates — MONDO → ranked drug candidates
5. classify_variant_acmg — HGVS → draft ACMG/AMP criteria
6. map_disease_drug_landscape — MONDO → approved + pipeline drugs

Important caveats:

• The ACMG/AMP criteria emitted by classify_variant_acmg and the ACMG section of generate_variant_clinical_report are a draft surface of the upstream evidence (AlphaMissense, ClinVar, gnomAD, Ensembl VEP). They are not a substitute for clinical-laboratory review and must not be used as a diagnostic.
• The "druggability tier" returned by assess_target_druggability is a small hand-tuned heuristic (drug-precedent counts + Open Targets tractability labels + pLDDT + gnomAD LOEUF). It is not a validated predictive model.
• The "composite repurposing score" returned by find_drug_repurposing_candidates is OT evidence × ChEMBL max clinical phase. It is a ranking aid, not an efficacy prediction.

generate_variant_clinical_report async

generate_variant_clinical_report(params: VariantClinicalReportInput) -> dict[str, Any]

Generate a multi-source variant interpretation report.

Cross-references evidence from up to eight upstream databases for a single HGVS variant into one structured report. The report is a research aid: it surfaces the upstream evidence and the ACMG/AMP criteria that the available evidence supports, but it is not a clinical interpretation and must not be used as a diagnostic without independent review by a qualified clinical laboratory.

1. Ensembl VEP — functional consequence, SIFT/PolyPhen/CADD predictions
2. ClinVar — clinical pathogenicity classifications and review status
3. gnomAD v4 — population allele frequencies across 807,162 individuals
4. AlphaMissense — deep-learning missense pathogenicity (Cheng et al. 2023)
5. MONDO — disease ontology context
6. Open Targets — disease-gene evidence scores
7. DisGeNET — curated gene-disease association scores
8. ChEMBL — approved drugs acting on the gene product

The report includes a draft ACMG/AMP criteria checklist with evidence mapping, a structural impact summary, and an actionability statement.

Parameters:

Name	Type	Description	Default
params.hgvs		HGVS expression (gene-relative preferred).	required
params.include_population_breakdown		Include per-ancestry gnomAD data.	required
params.include_drug_context		Include drugs acting on the gene product.	required

assess_target_druggability async

assess_target_druggability(params: DruggabilityInput) -> dict[str, Any]

Comprehensive druggability assessment for a protein target.

Integrates four independent druggability signals into a HOT/WARM/COLD/NOT_DRUGGABLE classification:

1. Drug precedent — ChEMBL approved drugs + clinical compounds
2. Tractability — Open Targets tractability labels (small-molecule, antibody, PROTAC)
3. Structural confidence — AF2 pLDDT (ordered → analysable binding pockets)
4. Population constraint — gnomAD LOEUF (highly constrained → safety risk on inhibition)

It assembles existing public-database evidence into one tier; it does not add scientific judgement and is not a validated predictive model.

Parameters:

Name	Type	Description	Default
params.uniprot_id		UniProt accession.	required
params.include_clinical_stage		Include Phase I–III in drug count.	required

synthesize_protein_dossier async

synthesize_protein_dossier(params: ProteinDossierInput) -> dict[str, Any]

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: pathogenic variants in this gene
• Ensembl: orthologs across 12 species
• MONDO: top disease context

Parameters:

Name	Type	Description	Default
params.uniprot_id		UniProt accession.	required
params.gene_symbol		HGNC gene symbol.	required
params.depth		'brief' | 'standard' | 'comprehensive'.	required

map_disease_drug_landscape async

map_disease_drug_landscape(params: DiseaseDrugLandscapeInput) -> dict[str, Any]

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.

Parameters:

Name	Type	Description	Default
params.disease_mondo_id		MONDO disease ID.	required

classify_variant_acmg async

classify_variant_acmg(params: ACMGVariantInput) -> dict[str, Any]

Generate a draft ACMG/AMP variant classification framework.

Populates ACMG/AMP 2015 criteria (Richards et al.) automatically from computational evidence. Designed to pre-populate variant interpretation forms for clinical laboratory review — NOT a substitute for expert review.

Criteria populated

PVS1 — Null variant in LoF-intolerant gene PS1 — Same AA change as known pathogenic variant (via ClinVar) PM2 — Absent/extremely rare in gnomAD population databases PP3 — Multiple in-silico predictors (AlphaMissense ≥0.564, SIFT, PolyPhen, CADD) BP4 — Multiple in-silico predictors benign (AlphaMissense ≤0.340) BP7 — Silent variant, no splicing impact BS1 — Allele frequency > 5% in gnomAD

Parameters:

Name	Type	Description	Default
params.hgvs		HGVS expression.	required
params.inheritance_pattern		Expected inheritance mode.	required

find_drug_repurposing_candidates async

find_drug_repurposing_candidates(params: DrugRepurposingInput) -> dict[str, Any]

Find clinical-stage drugs that may be repurposed for a disease.

Strategy

1. Identify top evidence-scored targets from Open Targets.
2. For each target, find drugs in clinical development (ChEMBL).
3. Filter by requested development phase threshold.
4. Cross-reference against disease indication history (avoids circular reasoning).
5. Score candidates by (OT evidence × clinical phase).

This is the structural-biology-informed drug repurposing pipeline: by anchoring in AlphaFold structures, future extensions will apply topological fingerprinting to find structurally similar pockets with existing binding agents.

Parameters:

Name	Type	Description	Default
params.disease_mondo_id		MONDO ID for the target disease.	required
params.target_limit		Number of top OT targets to screen.	required
params.min_phase		Minimum clinical phase (4=Approved).	required