tooluniverse-acmg-variant-classification
ACMG/AMP Variant Classification
ACMG Reasoning
Each criterion (PS, PM, PP for pathogenic; BS, BP for benign) contributes a weighted piece of evidence for or against pathogenicity. The classification is the COMBINATION of all activated criteria, not any single criterion. Do not overweight a single finding.
The hierarchy is: PVS1 (very strong) > PS (strong) > PM (moderate) > PP (supporting). On the benign side: BA1 (stand-alone) > BS (strong) > BP (supporting). A frameshift in a LOF-intolerant gene (PVS1) plus a ClinVar expert-panel pathogenic entry (PS1) is pathogenic. A single PP criterion alone is not. The combination rule is what matters.
Two common errors to avoid: (1) seeing a "Pathogenic" ClinVar entry and stopping — that is PP5 (supporting) unless it has expert-panel review, not automatic confirmation; (2) dismissing a variant because one predictor says "tolerated" — discordant predictors mean neither PP3 nor BP4 applies, which is neutral evidence, not benign evidence.
Always apply criteria conservatively. When evidence is ambiguous, leave the criterion unmet. Cite the source for every criterion you activate so clinicians can audit the reasoning.
KEY PRINCIPLES:
- Criteria-driven — cite which criteria were activated and why
- Conservative — do not upgrade a criterion when evidence is ambiguous
- Gene-aware — adjust thresholds based on gene mechanism (LOF vs. gain-of-function)
- Population-calibrated — use ancestry-specific gnomAD frequencies, not just global AF
- Transparent — show evidence for each criterion
- Source-referenced — every criterion activation must cite the database/tool source
More from mims-harvard/tooluniverse
tooluniverse-sequence-retrieval
Retrieves biological sequences (DNA, RNA, protein) from NCBI and ENA with gene disambiguation, accession type handling, and comprehensive sequence profiles. Creates detailed reports with sequence metadata, cross-database references, and download options. Use when users need nucleotide sequences, protein sequences, genome data, or mention GenBank, RefSeq, EMBL accessions.
1.4Ktooluniverse-image-analysis
Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ/CellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV/TSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area/circularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.
405tooluniverse-literature-deep-research
Comprehensive literature deep research across any academic domain using 120+ ToolUniverse tools. Conducts subject disambiguation, systematic literature search with citation network expansion, evidence grading (T1-T4), and structured theme extraction. Produces detailed reports with mandatory completeness checklists, integrated models, and testable hypotheses. Use when users need thorough literature reviews, target/drug/disease profiles, topic deep-dives, claim verification, or systematic evidence synthesis. Supports biomedical (genes, proteins, drugs, diseases), computer science, social science, and general academic topics. For single factoid questions, uses a fast verification mode with inline answer.
383tooluniverse
Router skill for ToolUniverse tasks. First checks if specialized tooluniverse skills (105+ skills covering disease/drug/target research, gene-disease associations, clinical decision support, genomics, epigenomics, proteomics, comparative genomics, chemical safety, toxicology, systems biology, and more) can solve the problem, then falls back to general strategies for using 2300+ scientific tools. Covers tool discovery, multi-hop queries, comprehensive research workflows, disambiguation, evidence grading, and report generation. Use when users need to research any scientific topic, find biological data, or explore drug/target/disease relationships. ALSO USE for any biology, medicine, chemistry, pharmacology, or life science question — even simple factoid questions like "how many X in protein Y", "what drug interacts with Z", "what gene causes disease W", or "translate this sequence". These questions benefit from database lookups (UniProt, PubMed, ChEMBL, ClinVar, GWAS Catalog, etc.) rather than answering from memory alone. When in doubt about a scientific fact, USE THIS SKILL to verify against real databases.
274tooluniverse-clinical-trial-design
Strategic clinical trial design feasibility assessment using ToolUniverse. Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways. Creates comprehensive feasibility reports with evidence grading, enrollment projections, and trial design recommendations. Use when planning Phase 1/2 trials, assessing trial feasibility, or designing biomarker-driven studies.
270tooluniverse-drug-research
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.
270