Browse the BioContext7 deep skill library. Tool pages surface documentation, registry links, and install details for agent-facing workflows.
2,064 tools — page 30 of 42
| Tool | Registry | Domain | Docs |
|---|---|---|---|
SignalP predicts signal peptides and their cleavage sites in protein sequences. Use when users ask about SignalP, signal peptide prediction, secreted protein identification, Sec/SPI, Sec/SPII, Tat/SPI | manual | Genomics | 8 |
SILVA — comprehensive quality-checked database of aligned ribosomal RNA (rRNA) sequences for Bacteria, Archaea, and Eukaryota. Provides SSU (16S/18S) and LSU (23S/28S) rRNA reference databases for tax | manual | Utilities & Infrastructure | 8 |
SingleR — automated cell type annotation for single-cell RNA-seq data using reference-based scoring. Assigns cell type labels by correlating query expression profiles against curated reference dataset | dviraran/SingleR |
| Single-Cell |
| 8 |
Use when performing rare variant association tests with SKAT, SKAT-O, or burden tests. SKAT (Sequence Kernel Association Test) is an R package for gene-based and region-based rare variant association | leeshawn/SKAT | Population Genetics | 8 |
Use when performing rare variant association testing with SKAT-O (Sequence Kernel Association Test - Optimal). Optimal unified test combining SKAT and burden tests for SNP-set or gene-based analysis. | leeshawn/SKAT | Population Genetics | 8 |
SlideGraph+ — graph-based deep learning framework for whole slide image (WSI) analysis in computational digital pathology. Builds spatial and hierarchical graphs from WSI patch features, then trains g | mahmoodlab/SlideGraph | Imaging | 8 |
SLiM (Selection on Linked Mutations) is a forward-time, individual-based population genetics simulator with the Eidos scripting language. Use when users need to simulate natural selection, genetic dri | MesserLab/SLiM | QC & Preprocessing | 8 |
SMR/HEIDI — Summary-data-based Mendelian Randomization with HEIDI test for colocalization and causal inference between eQTL summary data and GWAS traits. Identifies genes whose expression levels are c | jianyangqt/smr | Population Genetics | 8 |
Use when working with SnapGene Viewer, the free desktop application for visualizing plasmid maps, DNA sequences, and genomic features in molecular biology. Covers reading and converting .dna files (Sn | Edinburgh-Genome-Foundry/snapgene-reader | Systems Biology | 8 |
Use when working with SNF, SNFtool, or Similarity Network Fusion for multi-omics integration, patient subtyping, fused similarity networks, or multi-view clustering in R. SNFtool accepts feature matri | BCooperA/SNFtool | Systems Biology | 8 |
Space Ranger is 10x Genomics software for processing Visium spatial gene expression and HD Visium datasets. Use this skill when users need to run `spaceranger count`, aggregate multiple runs with `spa | 10XGenomics/spaceranger | Single-Cell | 8 |
Use when working with SpaGCN for spatial transcriptomics domain detection, histology-aware adjacency construction, graph-convolution clustering, spatially variable gene (SVG) discovery, or meta-gene i | jianhuupenn/SpaGCN | Imaging | 8 |
ST Pipeline — automated processing pipeline for spatial transcriptomics (Spatial Transcriptomics method). Handles demultiplexing, quality trimming, contamination filtering, genome alignment, annotatio | SpatialTranscriptomicsResearch/st_pipeline | Genomics | 8 |
Spectra routing skill for mass spectrometry data representation and manipulation in R/Bioconductor. Use this skill when users mention Spectra, RforMassSpectrometry, MsBackend, MsBackendMzR, MsBackendH | rformassspectrometry/Spectra | Systems Biology | 8 |
Spectre is an R toolkit for high-dimensional single-cell cytometry and imaging analysis, including data import (CSV/FCS), metadata integration, arcsinh/logicle transformation, clustering (FlowSOM, Phe | ImmuneDynamics/Spectre | Single-Cell | 8 |
Use this skill for SpiecEasi — sparse inverse covariance estimation for ecological association inference in microbiome studies. Route here when users ask about SPIEC-EASI, microbial co-occurrence netw | zdk123/SpiecEasi | Metagenomics | 8 |
Splatter is an R/Bioconductor package for simulating single-cell RNA-seq (scRNA-seq) count data. Use when users need to generate synthetic scRNA-seq datasets for benchmarking clustering, trajectory, o | Oshlack/splatter | QC & Preprocessing | 8 |
SPM12 (Statistical Parametric Mapping 12) — the standard neuroimaging analysis framework for fMRI, PET, VBM, and EEG/MEG data. Use for preprocessing (realignment, slice-timing, normalisation, smoothin | spm/spm | Imaging | 8 |
squidpy plots — sq.pl visualization module for spatial omics data. Generates publication-ready spatial scatter plots with cell-type or gene-expression overlays, neighborhood enrichment heatmaps, co-oc | scverse/squidpy | Visualization | 8 |
Use when working with STAAR — Sequence Kernel Association Test Accounting for Relatedness. R package for rare-variant association analysis of whole-genome sequencing (WGS) data. Supports BURDEN, SKAT, | xihaoli/STAAR | Population Genetics | 8 |
Use when working with STAARpipeline for biobank-scale whole-genome or whole-exome rare-variant association analysis in R. Covers aGDS preparation, null model fitting, single-variant tests, gene-centri | xihaoli/STAARpipeline | Population Genetics | 8 |
Use when working with stageR, the Bioconductor R package for stage-wise testing in RNA-seq transcriptomics. Covers two-stage testing workflows for differential expression (DESeq2/edgeR/limma-voom) and | statOmics/stageR | Transcriptomics | 8 |
StarDist — deep learning framework for cell and nuclei detection and instance segmentation in 2D and 3D microscopy images using star-convex polygons. Predicts radial distances to object boundaries alo | stardist/stardist | Imaging | 8 |
STARsolo — ultrafast single-cell RNA-seq alignment, barcode processing, and UMI counting. STARsolo is a high-performance alternative to Cell Ranger for processing droplet-based (10x Genomics, Drop-seq | alexdobin/STAR | Genomics | 8 |
STELLAR (Spatial TEmporal Learning of cell-type cLAssification on multiple Regions) — graph neural network method for automated cell-type annotation in multiplexed imaging data. Transfers cell-type la | snap-stanford/stellar | Imaging | 8 |
Use when working with StellarPGx, the Nextflow pipeline for calling star alleles in highly polymorphic pharmacogenes using genome graph-based variant detection. Covers CYP2D6, CYP2A6, CYP2B6, CYP2C19, | Illumina/StellarPGx | Drug Discovery | 8 |
sumstatcolumns — GWAS summary statistics column harmonization utility from Nealelab's sumstat_utils. Standardizes, renames, filters, and validates column headers across summary statistics formats (BOL | Nealelab/sumstat_utils | Population Genetics | 8 |
surfplot — Python library for publication-quality cortical surface visualization in neuroimaging. Creates brain surface plots from GIFTI, CIfTI, or numpy array data overlaid on standard surfaces (fsLR | danjgale/surfplot | Imaging | 8 |
SuSiE-inf — Bayesian fine-mapping with an infinitely large number of effects. Python implementation extending SuSiE to handle highly polygenic regions by placing a spike-and-slab prior on infinitely m | FinucaneLab/SuSiE-inf | Population Genetics | 8 |
Use when working with susieR (Sum of Single Effects in R) for Bayesian fine-mapping of genetic associations. Covers individual-level genotype fine-mapping with susie(), summary-statistics fine-mapping | stephenslab/susieR | Population Genetics | 8 |
SymSim is an R package for simulating single-cell RNA sequencing (scRNA-seq) data using a mechanistic two-stage kinetic model. Use when users need to generate realistic synthetic scRNA-seq datasets wi | YosefLab/SymSim | QC & Preprocessing | 8 |
SynVisio is a web-based interactive tool for visualizing plant genome synteny blocks. Takes collinearity files from MCScan/MCScanX and genome annotation files (GFF/BED) to produce dot plots, synteny b | LiChenPU/SynVisio | Other | 8 |
table2asn is the NCBI command-line tool for converting FASTA sequences and feature tables into ASN.1 (.sqn) files for submission to GenBank, RefSeq, and related NCBI databases. Handles prokaryotic and | manual | Utilities & Infrastructure | 8 |
TAIR (The Arabidopsis Information Resource) — the primary genomic database for Arabidopsis thaliana, providing gene models, functional annotations, protein sequences, metabolic pathways (AraCyc), stoc | manual | Utilities & Infrastructure | 8 |
Tangram — deep learning framework for mapping single-cell and single-nucleus gene expression data onto spatial transcriptomics data. Built on PyTorch and scanpy, Tangram optimizes a probabilistic mapp | broadinstitute/Tangram | Single-Cell | 8 |
TargetScan predicts biological targets of miRNAs in vertebrates by searching 3'UTR sequences for conserved matches to the miRNA seed region (8mer, 7mer-m8, 7mer-A1, 6mer sites). Computes context++ sco | manual | Transcriptomics | 8 |
Use when working with tascCODA for tree-aggregated compositional analysis of high-throughput sequencing data, especially single-cell RNA-seq, microbiome, or amplicon count tables with a lineage or tax | theislab/tascCODA | Machine Learning | 8 |
Tax4Fun2 is an R package for predicting the functional capabilities of prokaryotic communities based on 16S rRNA gene sequencing data. It allows for the functional annotation of amplicon sequence vari | bennibalzer/Tax4Fun2 | Other | 8 |
TensorFlow — open-source machine learning framework for building and deploying deep learning models. Provides Keras high-level API for model building, tf.data for input pipelines, tf.image for image p | tensorflow/tensorflow | Machine Learning | 8 |
TeselaGen — integrated synthetic biology platform for DNA sequence design, combinatorial library construction, lab automation, NGS analysis, and ML-guided protein engineering. Modules: DESIGN (sequenc | TeselaGen/teselagen-python | Systems Biology | 9 |
TEtools is a Docker container suite maintained by the Dfam consortium that bundles RepeatMasker, RepeatModeler2, and complementary tools for transposable element (TE) annotation, repeat library constr | Dfam-consortium/TETools | Genomics | 8 |
Use when working with TIAToolbox (TIA Toolbox) for computational pathology, whole-slide imaging, stain processing, patch extraction, and model inference. Covers documented TIAToolbox CLI workflows inc | TissueImageAnalytics/tiatoolbox | Imaging | 8 |
Use when working with tidybulk, the Bioconductor R package that brings transcriptomics into tidyverse-style pipelines. Covers SummarizedExperiment-aware workflows for identify_abundant, keep_abundant, | stemangiola/tidybulk | Transcriptomics | 8 |
Use when working with tidySingleCellExperiment, the R/Bioconductor adapter that makes SingleCellExperiment objects behave like tidy tibbles while preserving compatibility with the Bioconductor single- | stemangiola/tidySingleCellExperiment | Single-Cell | 8 |
TMHMM predicts transmembrane helices in protein sequences using a hidden Markov model. Use when users ask for transmembrane topology prediction, TM helix counting, inside/outside orientation assignmen | manual | Genomics | 8 |
Use when working with topGO, the Bioconductor package for Gene Ontology enrichment analysis that accounts for the GO graph topology. Covers `topGOdata` object construction, `annFUN.org`, `annFUN.gene2 | manual | Transcriptomics | 8 |
Use this skill for TotalSegmentator, the deep-learning tool for robust segmentation of 104-117 anatomical structures from CT (and MRI) images. Covers CLI usage (`TotalSegmentator -i ct.nii.gz -o seg/` | wasserth/TotalSegmentator | Imaging | 8 |
ToxoDB — integrated genomic and functional database for Toxoplasma gondii and related apicomplexan parasites within the VEuPathDB ecosystem. Provides gene search, BLAST, genome browser (GBrowse/JBrows | manual | Transcriptomics | 8 |
trackViewer is an R/Bioconductor package for visualizing multi-omics data as tracks or lollipop plots. It facilitates integrated analysis of NGS data such as ChIP-seq, RNA-seq, miRNA-seq, DNA-seq, SNP | jianhong/trackViewer | Imaging | 8 |
treeio — Bioconductor R package for importing and exporting phylogenetic tree data with associated metadata. Reads and writes Newick, Nexus, BEAST, RAxML, FastTree, IQ-TREE, MrBayes, PHYLODOG, r8s, ME | YuLab-SMU/treeio | Phylogenetics | 8 |