Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab
Official@mims-harvard · Harvard
Harvard Zitnik Lab provides a standardized framework for scientific discovery, integrating multi-omics, protein design, and clinical variant interpretation for biomedical research.
Agent Skills by Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab
Showing 162 vetted skills indexed across 1 GitHub repositories.
mims-harvardtooluniverse-gwas-study-explorer
Compare GWAS studies, meta-analyze loci, and assess replication across cohorts.
mims-harvardtooluniverse-microbiome-research
Analyze microbiome studies, taxonomic profiles, and genome quality using MGnify, GTDB, ENA, and EuropePMC.
mims-harvardtooluniverse-metabolomics-analysis
Analyze metabolomics data from identification through pathway enrichment and multi-omics integration.
mims-harvardtooluniverse-data-wrangling
Download and parse scientific data from APIs and file formats using Python code.
mims-harvardtooluniverse-immune-repertoire-analysis
Analyzes TCR and BCR repertoire sequencing data for clonality, diversity, and antigen specificity.
mims-harvardtooluniverse-single-cell
Analyze single-cell RNA-seq data with scanpy from QC gating through clustering and annotation.
mims-harvardtooluniverse-admet-prediction
Profiles ADMET properties and toxicity of drug candidates from SMILES or compound names.
mims-harvardtooluniverse-variant-to-mechanism
Trace genetic variants through regulatory context, target genes, and pathways to disease mechanisms.
mims-harvardtooluniverse-proteomics-data-retrieval
Search and retrieve proteomics dataset metadata from MassIVE and ProteomeXchange repositories.
mims-harvardtooluniverse-gpcr-structural-pharmacology
Analyzes GPCR ligands, structures, mutations, and antibody interfaces via GPCRdb, SAbDab, and PDBePISA.
mims-harvardtooluniverse-meta-analysis
Pool effect sizes across multiple studies with fixed- or random-effects meta-analysis and heterogeneity statistics.
mims-harvardtooluniverse-dataset-discovery
Find and evaluate research datasets across scientific repositories for any research question.
mims-harvardtooluniverse-metabolomics-pathway
Maps metabolites to pathways, enzymes, genes, and disease associations across HMDB, KEGG, Reactome, and MetaCyc.
mims-harvardtooluniverse-acmg-variant-classification
Classifies germline variants using ACMG/AMP criteria with evidence from ClinVar, gnomAD, and computational predictors.
mims-harvardtooluniverse-epidemiological-analysis
Conducts observational epidemiology studies from PECO question to publication-ready statistical report.
mims-harvardtooluniverse-structural-proteomics
Integrates PDB, AlphaFold, GPCRdb, and BindingDB data for drug target structural validation.
mims-harvardtooluniverse-variant-interpretation
Classify genetic variants using ACMG guidelines with population, structural, and literature evidence.
mims-harvardtooluniverse-protein-structure-prediction
Predicts protein 3D structures from sequence using ESMFold, AlphaFold, and RCSB experimental data.
mims-harvardtooluniverse-microbial-genome-characterization
Discovers, quality-controls, and maps genome assemblies and replicons via NCBI Datasets.
mims-harvardtooluniverse
Routes scientific data analysis questions to specialized ToolUniverse sub-skills and authoritative pipelines.
mims-harvardtooluniverse-clinical-risk-scoring
Compute and interpret validated bedside clinical risk scores for individual patients.
mims-harvardtooluniverse-adverse-outcome-pathway
Maps environmental chemicals to adverse outcome pathways using AOPWiki, PubChemTox, and CTD data.
mims-harvardtooluniverse-spatial-transcriptomics
Analyze spatial transcriptomics data to identify tissue domains, spatially variable genes, and cell-cell interactions.
mims-harvardtooluniverse-rare-disease-genomics
Investigate rare disease genetics from disease identification through variant interpretation using Orphanet, GenCC, and ClinVar.
Frequently Asked Questions About Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab
FAQPage SchemaWhat specific scientific tasks can researchers perform using these resources?▼
Researchers can execute complex biomedical tasks including protein therapeutic design, rare disease phenotype matching, drug repurposing candidate identification, and precision oncology treatment mapping. The framework synthesizes data from public repositories like RCSB PDB, PubChem, and Open Targets to generate evidence-graded, citation-rich research reports.
Which professional personas benefit most from this research framework?▼
This framework is designed for computational biologists, bioinformaticians, and pharmaceutical researchers. It serves professionals focused on drug discovery, clinical genetics, and molecular medicine who require standardized, reproducible methods for retrieving and analyzing multi-omics, chemical, and clinical data at scale.
What are the prerequisites for integrating these research capabilities?▼
Integration requires a configured environment supporting MCP-compatible modules. Users must establish connectivity with the registry to access the underlying scientific modules, ensuring that local environments are prepared to handle structured JSON configurations and evidence-graded metadata blocks for consistent research output.