Databases Skills

Constructs and validates polygenic risk scores using LDpred2-auto, SBayesRC, MegaPRS, PRS-CS, PROSPER, MUSSEL, BridgePRS, JointPRS, PRSmix, or PGS Catalog Calculator with ancestry-aware reference panels (HapMap3, UKB-LD), Pejaver-style calibration, and PRS-RS reporting standards. Use when computing PRS for cohorts, applying Whiffin-style absolute-risk transformation, assessing cross-ancestry portability (Martin 2017 / Ding 2023 continuous ancestry), or auditing PRS manuscripts against the 22-item PRS-RS reviewer checklist.

Reactome pathway enrichment using ReactomePA package. Use when analyzing gene lists against Reactome's curated peer-reviewed pathway database. Performs over-representation analysis and GSEA with visualization and pathway hierarchy exploration.

Extracts and assigns COSMIC v3.4 mutational signatures (84 SBS / 11 DBS / 18 ID / 24 CN / 16 SV) from somatic VCFs using SigProfilerSuite, MutationalPatterns, MuSiCal mvNMF, SigNet, or HRDetect. Use when characterizing DNA-damage etiology (BRCA1/2 HRD, MMR-D, POLE, APOBEC3A, UV, tobacco, aflatoxin, 5-FU/SBS17b, platinum, colibactin SBS88), routing PARP inhibitor decisions, or auditing de novo extraction vs refit choice for cohort size.

Predict miRNA target genes using sequence-based algorithms and database lookups. Use when identifying potential mRNA targets of differentially expressed or functionally important miRNAs.

Taxonomic classification of ASVs using reference databases like SILVA, GTDB, or UNITE. Covers naive Bayes classifiers (DADA2, IDTAXA) and exact matching approaches. Use when assigning taxonomy to ASVs after DADA2 amplicon processing.

Calculates tumor mutational burden from WES/WGS/panel data with Friends of Cancer Research harmonization equations, per-assay calibration (FDA 10/Mb = 7.8 TSO500 = 8.4 OncomineTML), synonymous/indel/germline filtering, hypermutator tiering, blood TMB, and integration with HLA-LOH and neoantigen quality (Luksza 2017 fitness). Use when assessing ICI eligibility under tumor-specific cutoffs (McGrail 2021), comparing tissue vs bTMB, or auditing TMB-H reporting against ESMO 2024 and FDA pembrolizumab pan-tumor 2020.

Comprehensive variant annotation using bcftools annotate/csq, VEP, SnpEff, and ANNOVAR. Add database annotations, predict functional consequences, and assess clinical significance with MANE transcript selection and pathogenicity scoring. Use when annotating variants with functional and clinical information.

Normalize indel representation, decompose MNPs, and split multiallelic variants using bcftools norm. Use when comparing variants from different callers, preparing VCF for database annotation, or merging VCFs from multiple sources.

Prioritizes rare-disease variants from trio/quad WES/WGS with de novo (DeNovoGear, Triodenovo), compound-heterozygous phasing (WhatsHap), mosaic VAF tiering, phenotype-driven ranking (Exomiser, Phen2Gene, AMELIE), ClinGen gene-disease validity gating, and ACMG SF v3.2 secondary findings reporting. Use when running diagnostic exome / genome pipelines, identifying candidate Mendelian disease genes, screening for incidental findings, or auditing VUS reclassification cycles. The ACMG/AMP classification framework (PVS1 decision tree, Pejaver PP3/BP4 calibration, Tavtigian point system) is in clinical-databases/acmg-classification.

Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation history, token usage, cost accounting, execution log, or artifact metadata beyond what host.frames()/host.artifacts() provide — e.g. "how many tokens has this session used", "what was my last tool call", "list every file I've written", "where are messages stored", "what tables can I query", "inspect frames.context_data", or any time you're about to PRAGMA-probe the Claude Science metadata DB to discover its schema.

Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.

Build, query, and analyse biomedical knowledge graphs in TuringDB, a columnar graph database with git-like versioning.

> Query the ADReCS (Adverse Drug Reaction Classification System) v3.3 database. Use whenever the user asks about adverse drug reactions, drug safety profiles, ADR classification, ADR severity/frequency, or wants to look up any entity (drug name, BADD Drug ID, DrugBank ID, ATC code, CAS RN, PubChem CID, KEGG ID, ADR term, ADReCS ID, MedDRA code, MeSH ID) in ADReCS.

> Query the BindingDB drug-target binding affinity database. Use whenever the user asks about protein-ligand binding data, affinity measurements (Ki, IC50, Kd, EC50), or wants to look up binding partners for a UniProt ID, PDB ID, or compound SMILES string.

> Query the CADEC (CSIRO Adverse Drug Event Corpus). Use whenever the user asks about adverse drug event mentions in consumer health text, entity annotations from patient forum posts, MedDRA/SNOMED-CT normalised ADR spans, or wants to look up drugs, symptoms, or coded entities in the CADEC corpus.

> Query the ChEBI (Chemical Entities of Biological Interest) database. Use whenever the user asks about small molecule identifiers, chemical ontology roles, molecular formulae, SMILES, InChI, synonyms, or cross-references for biologically relevant chemical compounds via ChEBI.

> Query the ChEMBL database for drug molecules, bioactivity data, and drug targets via the ChEMBL REST API. Use whenever the user asks about drug properties (molecular weight, logP, Lipinski violations), drug-target interactions, bioactivity assay results, or wants to look up any entity by ChEMBL ID or drug/gene name in ChEMBL. Supports single entity or batch queries. No API key required.

> Query DailyMed for FDA drug label / package insert information. Use whenever the user asks about drug labeling, SPL documents, prescribing information, NDC codes, or needs to look up current FDA-approved drug details by name or NDC. Supports single entity or batch queries.

> Query the DDInter drug-drug interaction database. Use whenever the user asks about drug-drug interactions, DDI severity levels, or wants to look up interactions for a drug name or DDInter ID.

> Query the DGIdb (Drug-Gene Interaction Database) for drug-gene interactions, gene druggability categories, and drug target information. Use whenever the user asks about drug targets, druggable genes, gene-drug interactions, or wants to look up any entity (gene name, drug name, druggability category) in DGIdb.

> Query the DRKG (Drug Repurposing Knowledge Graph). Use whenever the user asks about drug–gene, drug–disease, gene–disease, or other biomedical entity relationships in a knowledge-graph context, drug repurposing candidates, COVID-19 drug repurposing, or wants to explore neighbours of any biomedical entity (compound, gene, disease, pathway, side effect, etc.) in DRKG.

> Query a locally downloaded DrugBank database. Use whenever the user asks about drug information, drug targets, drug-drug interactions, drug categories, or wants to look up any entity (DrugBank ID, drug name, CAS number, synonym) in DrugBank.

> Query the DrugCentral drug pharmacology database. Use whenever the user asks about approved drug structures, drug targets, pharmacological actions, or wants to look up any entity (drug name, DrugCentral ID, CAS number, InChIKey) in DrugCentral.

> Query the DrugComb drug combination database for cancer cell-line synergy and sensitivity data. Use whenever the user asks about drug combinations, synergy scores (ZIP/Bliss/Loewe/HSA), combination sensitivity (CSS), or wants to look up how two drugs interact in a specific cancer cell line.

> Query canonical DrugCombDB combination records. Use when the user asks about drug pairs, synergy values, or cell-line-specific combination evidence.

> Query the DrugMechDB drug mechanism-of-action database. Use whenever the user asks about drug mechanisms, drug-to-disease paths, biological targets of a drug, or wants to look up any biomedical entity (drug name, protein, disease, DrugBank ID, MESH ID, UniProt ID, GO term, etc.) in DrugMechDB.

> Query the DrugRepoBank drug repurposing evidence database. Use whenever the user asks about repurposing candidates, drug–disease–target repurposing evidence, or wants to look up any entity (drug name, DrugBank ID, ChEMBL ID, PubChem CID, TTD target ID, UniProt ID, disease name) in DrugRepoBank.

> Query the FDA Adverse Event Reporting System (FAERS) via openFDA API. Use whenever the user asks about adverse drug reactions, side effects, drug safety signals, or wants to look up reported adverse events for one or more drug names.

> Query or inspect the FDA Orange Book - FDA-Approved Drug Products Listing resource for drug-centric tasks with emphasis on drug knowledgebase Use whenever Codex needs the calling pattern, downloadable entrypoint, or example query flow from this skill example script.

> Query the Gene-Drug Knowledge Database (GDKD) for variant-specific gene–drug associations in oncology. Use when the user asks about cancer genomic biomarkers, drug sensitivity/resistance by gene or variant, targetable mutations, or clinical evidence for cancer therapeutics.

> Query the MecDDI mechanism-based drug-drug interaction database. Use whenever the user asks about drug-drug interactions, DDI mechanisms (PK/PD), enzyme or transporter-mediated interactions, or wants to look up interacting drug pairs by drug name or MecDDI drug ID. Trigger on keywords like DDI, drug interaction, MecDDI, mechanism-based interaction, pharmacokinetic interaction, pharmacodynamic interaction, or any query involving two drugs that may interact.

> Query the NCI CCDI Molecular Targets Platform (pediatric oncology) for targets (genes), diseases, drugs, and target-disease associations via its public GraphQL API. Auto-detects entity type from input string.

> Query the NCI-60 Molecular Target (Protein) database from the Developmental Therapeutics Program. Use when the user asks about protein expression of drug targets across the NCI-60 cancer cell line panel, or wants to look up a gene, cell line, or cancer panel in the NCI DTP molecular target dataset.

> Query the nSIDES drug side effect databases (OnSIDES, OffSIDES, KidSIDES). Use whenever the user asks about drug adverse reactions, side effects, off-label safety signals, or pediatric drug safety for a given drug name.

> Query the OREGANO knowledge graph for computational drug repurposing. Use whenever the user asks about drug–target–disease–gene–pathway relationships, compound cross-references, drug repurposing hypotheses, or wants to explore neighbors of any biomedical entity in a knowledge graph that includes natural compounds.

> Query the PharmKG knowledge graph (180k entities, 39 relation types, >1M triples). Use whenever the user asks about biomedical relationships among genes, drugs/chemicals, and diseases — e.g. drug–gene interactions, drug–disease associations, gene–disease links, or drug–drug relationships derived from literature and curated databases.

> Query the PHEE pharmacovigilance event extraction dataset. Use whenever the user asks about annotated adverse drug events, pharmacovigilance case reports, drug–effect associations from medical literature, or wants to find PHEE examples mentioning a drug name, adverse effect, or condition.

> Query the PsyTAR psychiatric adverse-reaction corpus. Use when the user asks about patient-reported ADRs, withdrawal symptoms, drug indications, or effectiveness for Zoloft, Lexapro, Cymbalta, or Effexor XR. Accepts drug names (brand or generic), symptom terms, or UMLS CUIs.

> Query the RepoDB drug repurposing database. Use whenever the user asks about drug-disease associations, drug repurposing candidates, or wants to look up any entity (drug name, indication, DrugBank ID, UMLS CUI, NCT ID) in RepoDB.

> Query the RepurposeDrugs single-agent drug repurposing database. Use whenever the user asks about drug-disease repurposing associations, clinical trial phases for repurposed drugs, or wants to look up any entity (drug name, disease name, NCT ID) in RepurposeDrugs.

> Query the RxNorm drug naming and normalization API. Use whenever the user asks to look up an RxCUI, normalize a drug name, find drug interactions, retrieve brand/trade names, or resolve any clinical drug name via RxNorm. Supports single drug or batch queries. Trigger on mentions of RxNorm, RxCUI, drug normalization, drug interaction lookup, or brand-name resolution.

> Query the STITCH chemical-protein interaction database. Use whenever the user asks about chemical-protein interactions, drug-target binding, compound action modes, or wants to look up any entity (chemical name, STITCH CID, STRING protein ID) in STITCH.

> Query the Therapeutic Target Database (TTD) for drug-target-disease interaction data. Use this skill when the user asks about therapeutic targets, drugs, diseases, or their relationships — including target-drug mappings, clinical status of drugs, disease indications, UniProt/gene associations, and pathway annotations. Triggers on queries like "what drugs target EGFR", "which diseases is Imatinib used for", "find targets for lung cancer", or any lookup involving TTD IDs, gene symbols, drug names, or disease names.

> Query the UniTox drug toxicity database. Use whenever the user asks about organ-system toxicity ratings for a drug, multi-organ toxicity profiles, or wants to look up any entity (drug name, SMILES, SPL_ID) in UniTox.

> Query the WHO Model List of Essential Medicines (23rd list, 2023). Use whenever the user asks about essential medicines, WHO-recommended drugs, dosage forms, therapeutic sections, or AWaRe antibiotic classification.

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

Search 78 public scientific, biomedical, materials science, and economic databases via REST APIs. Covers physics/astronomy (NASA, NIST, SDSS, SIMBAD), earth/environment (USGS, NOAA, EPA), chemistry/drugs (PubChem, ChEMBL, DrugBank, FDA, KEGG, ZINC, BindingDB), materials (Materials Project, COD), biology/genomics (Reactome, UniProt, STRING, Ensembl, NCBI Gene, GEO, GTEx, PDB, AlphaFold, InterPro, BioGRID, Gene Ontology, dbSNP, gnomAD, ENCODE, Human Protein Atlas, Human Cell Atlas), disease/clinical (COSMIC, Open Targets, ClinicalTrials.gov, OMIM, ClinVar, GDC/TCGA, cBioPortal, DisGeNET, GWAS Catalog), regulatory (FDA, USPTO, SEC EDGAR), economics/finance (FRED, World Bank, US Treasury), demographics (US Census, Eurostat, WHO). Use when looking up compounds, genes, proteins, pathways, variants, clinical trials, patents, economic indicators, or any public database API query.

Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.