Browse the BioContext7 deep skill library. Tool pages surface documentation, registry links, and install details for agent-facing workflows.
2,064 tools — page 36 of 42
| Tool | Registry | Domain | Docs |
|---|---|---|---|
Use this skill for StainTools stain normalization and augmentation in digital pathology image workflows. Route here when users ask about Macenko or Vahadane stain normalization, Reinhard color normali | Peter554/StainTools | Imaging | 8 |
statsmodels is a Python package for statistical and econometric modeling, including linear models (OLS, GLS, WLS), generalized linear models (GLM), mixed-effects models (MixedLM), time-series models ( | statsmodels/statsmodels | Utilities & Infrastructure | 8 |
stdpopsim is a community-maintained catalog of standardized population genetic simulation models. Use when users need to simulate genetic data under published demographic models for specific species ( |
| popsim-consortium/stdpopsim |
| QC & Preprocessing |
| 8 |
Use when building, running, or validating STEPS (STochastic Engine for Pathway Simulation) models for stochastic reaction-diffusion systems in realistic 3D tetrahedral geometries. Covers source builds | CNS-OIST/STEPS | Systems Biology | 8 |
stringr — tidyverse R package for consistent, human-readable string manipulation built on stringi/ICU. Provides str_detect, str_match, str_extract, str_replace, str_split, str_pad, str_trim, str_wrap, | tidyverse/stringr | Utilities & Infrastructure | 8 |
STRUCTURE — Bayesian MCMC software for inferring population structure from multi-locus genotype data (microsatellites, SNPs, AFLPs). Assigns individuals to K populations by maximizing Hardy-Weinberg a | royfrancis/pophelper | Other | 8 |
styler formats R source code according to the tidyverse style guide or custom style guides. Use this skill when users need deterministic formatting for .R/.Rmd/.qmd files, repo-wide style normalizatio | r-lib/styler | Workflows | 8 |
survival — the foundational R package for time-to-event analysis, including Kaplan-Meier survival curves, Cox proportional hazards regression, log-rank tests, and parametric survival models. Use for: | therneau/survival | Clinical Genomics | 8 |
Use when working with systemPipeR, the Bioconductor workflow environment that combines R and command-line tools through CWL-backed workflow definitions. Covers systemPipeRdata::genWorkenvir, genWorken | tgirke/systemPipeR | Workflows | 8 |
Use when working with TAPE (Tasks Assessing Protein Embeddings) for protein representation learning, benchmark evaluation, or sequence embedding. Covers training and evaluating transformer, LSTM, ResN | songlab-cal/tape | Proteomics | 8 |
Use when working with nf-core/taxprofiler for shotgun metagenomics taxonomic classification and profiling across multiple tools and databases. Covers samplesheet/database sheet preparation, opt-in pro | nf-core/taxprofiler | Metagenomics | 8 |
tensorQTL — GPU-accelerated QTL mapping tool for cis-eQTL, trans-eQTL, sQTL, and pQTL analysis. Uses PyTorch tensors to achieve 100-1000x speedup over CPU-based methods. Accepts PLINK-format genotypes | broadinstitute/tensorqtl | Population Genetics | 8 |
testthat is the standard R testing framework for package and script validation. Use this skill when users need to write `test_that()` tests, run `devtools::test()` or `testthat::test_local()`, validat | r-lib/testthat | Workflows | 8 |
tidygraph is an R package that provides a tidy API for graph manipulation by exposing node and edge tables through dplyr-style workflows. Use this skill when users need graph analytics in R with tbl_g | thomasp85/tidygraph | Visualization | 8 |
Use when working with tidyseurat, the R package that lets Seurat objects act like tidyverse tibbles while staying compatible with Seurat workflows. Covers tidy(), as_tibble(), join_features(), aggrega | stemangiola/tidyseurat | Single-Cell | 8 |
Use when working with tidyverse — the collection of R packages for data science including ggplot2 (visualization), dplyr (data manipulation), tidyr (reshaping), readr (file I/O), purrr (functional pro | tidyverse/tidyverse | Utilities & Infrastructure | 8 |
Use when working with Python tifffile workflows for TIFF, BigTIFF, OME-TIFF, ImageJ hyperstack, and other TIFF-like microscopy and image formats. Covers image reading via imread(), metadata inspection | cgohlke/tifffile | Imaging | 8 |
TissUUmaps is a browser-based and desktop spatial-omics viewer for large tissue images, marker tables, region annotations, and shareable .tmap projects. Use this skill when users ask about TissUUmaps | TissUUmaps/TissUUmaps | Imaging | 8 |
tmap (R) is a thematic mapping package for static and interactive geospatial visualization. Use this skill for choropleths, symbol maps, facets, map layout, and export workflows with `tm_shape()`, `tm | r-tmap/tmap | Genomics | 8 |
This skill provides tools for working with data from the Trans-Omics for Precision Medicine (TOPMed) program. It includes capabilities for quality control, analysis, and visualization of large-scale g | manual | Utilities & Infrastructure | 8 |
TorchDrug — PyTorch-based machine learning platform for drug discovery and graph representation learning. Supports molecule property prediction, molecular generation, retrosynthesis planning, knowledg | DeepGraphLearning/torchdrug | Structure Prediction | 8 |
Tripal routing skill for building and managing biological web databases using Drupal and the Chado biological schema. Use this skill when users mention Tripal, Chado, biological data portals, crop gen | tripal/tripal | Other | 8 |
UMAP — Uniform Manifold Approximation and Projection for dimension reduction. Constructs a fuzzy topological representation of high-dimensional data and optimizes a low-dimensional layout preserving t | lmcinnes/umap | Statistics | 9 |
Use when working with Uni-Fold — DP Technology's open-source PyTorch reimplementation of AlphaFold2 for protein structure prediction. Supports monomer, multimer (Uni-Fold-Multimer), and symmetric homo | dptech-corp/Uni-Fold | Structure Prediction | 8 |
Tools for interacting with the UNITE database for fungal ITS sequence data. Provides functionality for searching, downloading, and formatting UNITE reference datasets. Useful for metabarcoding and tax | manual | Other | 8 |
Use this skill for unmarked (R), a hierarchical modeling package for ecological occurrence and abundance data with imperfect detection. Covers single-season occupancy (occu), dynamic occupancy (colext | rbchan/unmarked | Utilities & Infrastructure | 8 |
UTMOST (Unified Test for MOlecular SignaTures) performs cross-tissue transcriptome-wide association studies (TWAS) by aggregating gene expression evidence across multiple tissues using the Generalized | Joker-Jerome/UTMOST | Population Genetics | 8 |
Use when working with Bioconductor VariantAnnotation, VCF import in R, ScanVcfParam field or range subsetting, locateVariants(), predictCoding(), filterVcf(), or coding consequence workflows that comb | manual | Genomics | 8 |
vedo — Python library for scientific visualization and analysis of 3D objects and point clouds, built on VTK. Loads and renders meshes (STL, PLY, OBJ, VTK, GLTF), volumes (NIfTI, DICOM, NRRD), and poi | marcomusy/vedo | Visualization | 8 |
vegan — R package for community ecology: ordination (NMDS, RDA, CCA, PCA), diversity indices (Shannon, Simpson, Chao1, ACE), dissimilarity matrices (Bray-Curtis, Jaccard, UniFrac-style), PERMANOVA (ad | vegandevs/vegan | Metagenomics | 8 |
VennDiagram - R package for generating high-resolution, highly customizable Venn diagrams for one to five sets and Euler diagrams for selected two- and three-set cases. Use when users need publication | cran/VennDiagram | Imaging | 8 |
Use when working with the R package viridis for colorblind-safe, perceptually uniform color palettes in data visualization. viridis provides eight palettes (viridis, magma, plasma, inferno, cividis, m | sjmgarnier/viridis | Visualization | 8 |
vRhyme bins viral genome fragments from metagenomes into viral metagenome- assembled genomes (vMAGs) using coverage comparisons, sequence-feature models, dereplication, and refinement. Use this skill | AnantharamanLab/vRhyme | Metagenomics | 8 |
wrf-python is the Python diagnostics and interpolation toolkit for WRF-ARW NetCDF output. Use this skill for extracting diagnostics with wrf.getvar, pressure/height interpolation with wrf.interplevel | NCAR/wrf-python | Other | 8 |
xeofs is a Python package for multidimensional EOF analysis and PCA, built on xarray and Dask for scalable climate data analysis. It supports MCA, CCA, and varimax rotation, providing efficient comput | nicrie/xeofs | Other | 8 |
Zarr — chunked, compressed N-dimensional array storage for large numerical datasets in bioinformatics and scientific computing. Supports cloud-native storage (S3, GCS, Azure), parallel read/write, and | zarr-developers/zarr-python | Utilities & Infrastructure | 8 |
BioStudies and BioSamples are EMBL-EBI databases for storing and retrieving biological study metadata and sample provenance. BioSamples holds structured metadata for biological samples (accessions SAM | manual | Utilities & Infrastructure | 8 |
OpenAQ — open-source platform providing free, real-time and historical air quality data from government and research-grade monitoring stations worldwide. Query PM2.5, PM10, O3, NO2, CO, SO2 measuremen | openaq/openaq-python | Other | 11 |
PubMed Database — NCBI's comprehensive biomedical literature database providing free access to over 37 million citations from MEDLINE, life science journals, and online books. Query via E-utilities RE | manual | Clinical Genomics | 15 |
Terra/Firecloud -- Broad Institute cloud-based genomics platform for managing workspaces, executing WDL workflows at scale via Cromwell, organizing data tables, and running interactive Jupyter analyse | broadinstitute/terra-ui | Genomics | 9 |
Use when working with validate-paper-tools — an MCP tool that verifies whether bioinformatics tools or methods referenced in a scientific paper exist in the 25K+ BioContext7 registry, checks their mai | Hordago-Labs/biocontext7 | Utilities & Infrastructure | 12 |
Use when working with Akita — a sequence-to-function deep learning model that predicts 3D genome organization (Hi-C and Micro-C contact maps) from DNA sequence. Part of the Basenji codebase (calico/ba | calico/basenji | Genomics | 8 |
Use when working with ALoFT, annotating loss-of-function variants, predicting LoF variant impact, classifying stop-gained, frameshift, or essential splice site mutations, or interpreting rare variant | aalty/ALoFT | Population Genetics | 8 |
Detects gene fusions and other structural rearrangements from RNA-Seq data. | suhrig/arriba | Transcriptomics | 3 |
Broad Institute tools — access Terra cloud genomics platform, GSEA/MSigDB gene set enrichment analysis, GenePattern workflow server, Picard sequencing utilities, and FireBrowse TCGA data portal progra | manual | Genomics | 8 |
DepMap (Cancer Dependency Map) — Broad Institute portal and Python toolkit for downloading, querying, and analyzing genome-scale CRISPR/RNAi gene effect scores, copy number, expression, mutation, and | broadinstitute/depmap | Utilities & Infrastructure | 8 |
DesInventar is a disaster loss accounting and inventory system used to build national or subnational disaster databases, query geo-referenced datacards, produce charts and thematic maps, export KML an | desinventar/desinventar-online | Other | 8 |
Use when working with gencode — GENCODE — comprehensive gene annotation | GENCODE/gencode-genes | Utilities & Infrastructure | 8 |
GNOVA (GeNetic cOVariance Analyzer) — annotation-stratified genetic covariance and genetic correlation estimation from GWAS summary statistics. Partitions genetic covariance between two traits by geno | xtonyjiang/GNOVA | Population Genetics | 8 |
Institute — utilities for discovering, querying, and downloading datasets from major genomics and bioinformatics research institutes, including Broad Institute (gnomAD, Terra, Hail), European Bioinfor | manual | Utilities & Infrastructure | 8 |