ToolUniverse

Clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Use for VUS classification, pathogenicity assessment with cited criteria, structure-based variant impact (AlphaFold/PDB), non-coding/regulatory variant effect prediction with sequence deep-learning models (AlphaGenome, Enformer, Borzoi, ChromBPNet, Evo 2), and producing clinical-grade variant reports for return of results or molecular tumor boards. Use this whenever a user asks about a variant's significance, an intronic/promoter/enhancer/UTR non-coding variant's functional impact, or needs ACMG classification — even if they don't say "ACMG".

Functional annotation of protein variants — ProtVar structural/functional context, ClinVar clinical classifications, gnomAD population frequencies, CADD deleteriousness, ClinGen gene-disease validity, plus FAVOR one-call comprehensive GRCh38 annotation. Use for variant annotation pipelines, missense effect prediction, and protein-level variant interpretation with functional context.

Computational vaccine candidate design: peptide/subunit vaccines via MHC-I/MHC-II epitope prediction (IEDB), population HLA coverage optimization, B-cell epitope identification, and cross-strain conservation analysis. Use for vaccine epitope prediction, HLA allele coverage, multi-epitope construct design, and immunogenicity assessment. Combines predicted MHC binding with experimentally validated IEDB epitopes for higher-confidence designs.

Comprehensive drug-target intelligence — tissue expression (GTEx, HPA), pathways, protein interactions (STRING), variant landscape (ClinVar, gnomAD), druggability (DGIdb, ChEMBL approved drugs). 9 parallel research paths with citations. Use for full target profile reports, target characterization for drug discovery, and 'tell me about target X' queries.

Structural variant (SV) clinical interpretation: deletions, duplications, inversions, translocations, complex rearrangements. Applies ACMG-adapted criteria with ClinGen HI/TS dosage scores, gnomAD frequencies, and ClinVar evidence. Produces 5-tier classification with explicit per-criterion evidence. Use for clinical genomics SV review, dosage-sensitivity assessment, breakpoint analysis, and CNV pathogenicity calls. Gene-dosage-driven reasoning.

Structural biology plus proteomics integration for drug target validation. Combines PDB experimental structures, AlphaFold predictions, GPCRdb, SAbDab antibody structures, ProteinsPlus binding-site prediction, and BindingDB ligand-affinity data. Use for druggability assessment, binding-site characterization, ligand-pocket analysis, structural-confidence scoring (resolution, pLDDT), and antibody-target interface analysis.

Spatial transcriptomics analysis — Visium, MERFISH, seqFISH, Slide-seq. Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), tissue-domain segmentation, and cell-cell interaction inference. Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification.

Spatial multi-omics interpretation pipeline. Transforms spatially variable genes (SVGs), domain annotations, and tissue context into biological insights via domain-by-domain characterization, cell-type composition, spatial gene expression patterns, RNA+protein+metabolite integration. Use for Visium, MERFISH, seqFISH, Slide-seq, spatial proteomics, and spatial multi-omics interpretation. Goes beyond statistics to disease mechanisms and therapeutic opportunities.

Small molecule identification, characterization, and procurement — PubChem, ChEMBL, BindingDB, ADMET-AI, SwissADME, eMolecules, Enamine. Covers compound name to structure to activity to ADMET properties to commercial sourcing. Use for chemical biology, lead identification, probe selection, and the full small-molecule discovery pipeline.

Single-cell RNA-seq analysis with scanpy/anndata — h5ad data loading, scRNA-seq quality control and QC gating (n_genes_by_counts, total_counts, mitochondrial percent / pct_counts_mt, pct_counts_ribo, doublet detection with Scrublet/scDblFinder, ambient RNA / SoupX awareness, empty-droplet filtering, MAD-based thresholds), normalization, dimensionality reduction (PCA, UMAP, t-SNE), clustering (Leiden, Louvain), marker gene identification, cell-type annotation, pseudotime/trajectory analysis. Use for any scRNA-seq workflow, including deciding which cells to filter, flag, or investigate before downstream analysis.

Retrieve DNA/RNA/protein sequences from NCBI and ENA with disambiguation. Quality hierarchy: RefSeq (NM_/NP_) > RefSeq predicted (XM_/XP_) > GenBank submissions. Use for fetching specific sequences by accession, gene-symbol-to-sequence lookup, transcript-isoform retrieval, and curated-vs-raw-submission preference.

Biological sequence analysis — gene/protein sequence retrieval (NCBI, Ensembl, UniProt), nucleotide/protein search, ortholog discovery, and FASTQ QC + alignment workflows (Trimmomatic, BWA, samtools, coverage depth). Use for sequence retrieval, sequence comparison, FASTQ QC analysis, and read alignment pre-processing.

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

Given a set of residues in a protein, explain WHY they are functionally critical by combining structural context (binding interface, ligand pocket, core, secondary structure), UniProt features (active sites, binding sites, PTM sites, disulfides), optional SAE feature evidence, and optional DMS data. Accepts residues from any source: DMS hotspots (top-K by max effect), ClinVar recurrent variants, literature-reported hot regions, evolutionarily conserved positions, or user-curated lists. Returns a per-cluster mechanism call: catalytic / ligand-binding / interface / structural-core / PTM / regulatory / unknown.

Non-coding/regulatory variant interpretation — GWAS association lookup, eQTL evidence (GTEx), chromatin state (ENCODE), regulatory variant scoring (RegulomeDB, CADD), and TF-binding disruption. Use for non-coding GWAS hit interpretation, eQTL-based gene assignment, and regulatory mechanism reasoning. Distinct from coding-variant tools.

Rare disease genomics — disease identification (Orphanet), causative gene discovery, gene-disease validity (GenCC), variant interpretation (ClinVar), and translational research (ClinicalTrials.gov, drug repurposing for orphans). Use for rare-disease-gene curation, novel-gene-discovery analysis, and rare-disease drug-development support.

Find and retrieve proteomics datasets from MassIVE and ProteomeXchange. Search by species, keyword, or accession; retrieve detailed metadata (instruments, publications, species, PTMs studied). Use for locating public proteomics datasets to reanalyze, comparing instrument/protocol coverage across studies, and pre-download dataset evaluation.

AI-guided de novo protein design — RFdiffusion backbone generation, ProteinMPNN sequence design, structure validation (pLDDT, pTM, MPNN scores). Use for designing therapeutic protein binders, novel scaffolds, enzyme variants, and miniprotein/protein-interface design before experimental validation.

Protein 3D structure prediction from sequence — ESMFold de novo prediction, AlphaFold database retrieval, experimental structures from RCSB, ProtVar variant impact assessment, ProtParam sequence properties. Use for structure prediction when no experimental structure exists, fold-confidence scoring, and structure-guided variant interpretation.

Given a PDB structure, produce a per-residue annotation table: which residues sit at a binding interface (vs a partner chain), which line a ligand pocket, which are buried (core) vs solvent-exposed (surface), and optionally secondary structure. This is the structural track drawn under a DMS heatmap and the structural prior SAE feature drops are read against. Use when you need to anchor a variant-interpretation or DMS analysis to the protein's actual physical context.

Interpret a missense variant via ESMC-6B Sparse Autoencoder (SAE) feature activations. For a given protein + variant, computes which interpretable SAE features (catalytic, ligand-binding, PTM, structural motif, domain, etc.) are lost or gained at the mutation site. Use when standard pathogenicity scores (AlphaMissense, ClinVar) say a variant is damaging but you need a MECHANISTIC explanation — e.g. 'why is this variant LoF?' Complements (does not replace) variant-interpretation and variant-to-mechanism skills, which focus on ACMG classification or regulatory mechanism.

Propose the mechanism by which a missense variant causes loss-of-function (LoF), synthesizing evidence from 5 independent layers: AlphaMissense pathogenicity, AlphaFold structural context, ESMC sequence likelihood, SAE feature disruption, and DynaMut2 stability ΔΔG. Distinguishes 'structural stability LoF' (mis-folding) from 'direct functional disruption' (catalytic / binding / PTM site damage). Use for coding missense variants where you need a mechanistic causal model, not just a pathogenicity score.

Protein-protein interaction (PPI) network analysis — STRING (predicted + experimental), BioGRID (curated), SASBDB (small-angle scattering). Distinguishes physical interactions (binding) from functional associations (co-expression, co-regulation). Use for interactome queries, complex partner identification, and pathway-level interaction analysis.

Post-market safety surveillance and recall/adverse-event RETRIEVAL across the full spectrum of FDA-regulated products that are NOT covered by the drug-AE signal skills: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages). Orchestrates openFDA endpoints (MAUDE device adverse events + device recalls + 510(k), CAERS food/supplement/ cosmetic adverse events, veterinary adverse events, drug shortages, and cross-product enforcement/recall reports). USE WHEN the user asks: "are there adverse events for [device / pacemaker / infusion pump / insulin pump]", "device recalls for [firm/product]", "supplement / vitamin / cosmetic adverse reactions", "is [drug] in shortage", "what injectables are on shortage", "veterinary / animal adverse events for [drug] in [dog/cat/horse]", "food recall for listeria", "MAUDE report for [device]", "CAERS reactions for [brand]". DO NOT USE for drug adverse-event SIGNAL detection or disproportionality (PRR / ROR / IC) or drug-AE association scoring — that is `tooluniverse-pharmacovigilance` / `tooluniverse-adverse-event-detection`. This skill is multi-product surveillance and retrieval, not drug-AE statistical signal mining.

Cancer treatment recommendations from molecular profile (mutations + cancer type + biomarkers) — FDA-approved + investigational therapies, resistance mechanisms, matching clinical trials, prognosis. Uses CIViC, ClinVar, OpenTargets, ClinicalTrials.gov. Use for tumor-board treatment recommendations, evidence-tiered actionability assessment, and FDA-precedent-driven therapy selection.