Browse Tools

Use when working with PharmVar (Pharmacogene Variation Consortium) to access curated pharmacogenomics variant data for CYP2D6, CYP2C19, CYP2C9, CYP3A5, DPYD, SLCO1B1, and other clinically actionable p

Use when working with pheatmap, Pretty Heatmaps, clustered heatmaps in R, or publication-grade matrix visualization. pheatmap draws annotated heatmaps from numeric matrices, supports row and column an

GA4GH Phenopacket Schema for computable representation of clinical phenotypic data. Build, validate, and convert phenopackets encoding patient phenotypes, diagnoses, genomic interpretations, and medic

Picante routing skill for community phylogenetics, phylogenetic diversity, and comparative analyses in R. Use this skill when users mention picante, phylogenetic diversity, PD, MPD, MNTD, NRI, NTI, se

pingouin — statistical analysis library for Python built on pandas, NumPy, and SciPy. Provides parametric and non-parametric tests including t-tests, ANOVAs (one-way, repeated-measures, mixed), pairwi

plotnine is a grammar-of-graphics plotting library for Python inspired by ggplot2. Use this skill when users need declarative statistical graphics, layer-based plot construction, faceting, scales/them

PMDtools routing skill for ancient DNA post-mortem damage filtering and authentication. Use this skill when users mention PMDtools, PMD score, post-mortem damage, ancient DNA filtering, aDNA read auth

POD5 — Oxford Nanopore Technologies signal storage format based on Apache Arrow. Stores raw nanopore electrical signal (squiggle) data per read with calibration, pore, and run metadata. Replaces FAST5

PredictDB builds elastic-net genetic prediction models of gene expression stored as SQLite .db files for use with PrediXcan, S-PrediXcan, and S-MultiXcan TWAS workflows. Use this skill for training ex

ProGen — protein language model suite by Salesforce Research for generating functional protein sequences and scoring protein fitness. Trained on 280M+ protein sequences with conditional control tags f

Use when working with PROGENy or footprintR — saezlab R/Python tools for inferring pathway and transcription factor (TF) activity from omics data. PROGENy computes activity scores for 14 cancer-releva

Pronto is a Python library for parsing, editing, and serializing biomedical ontologies in OBO, OWL, and OBO JSON formats. Supports the Gene Ontology (GO), Human Phenotype Ontology (HPO), Disease Ontol

Use when working with ProteinShake, a Python library for protein 3D structure datasets and benchmark tasks that can be converted to graph, point-cloud, or voxel representations and loaded into PyTorch

ProtGPT2 — autoregressive protein language model for de novo protein sequence generation. Generate novel proteins unconditionally or from a seed sequence using a GPT-2 transformer trained on UniRef90.

PubTator3 — NCBI AI-powered biomedical text mining system for automatic annotation of PubMed abstracts and PMC full-text articles. Identifies and normalizes six entity types: genes/proteins, diseases,

PURPLE (Purity/Ploidy Estimator) — HMFtools Java tool for tumor purity and ploidy estimation from whole-genome sequencing. Consumes AMBER allele frequencies and COBALT read-depth ratios to fit the opt

pwr — Statistical power analysis functions along the lines of Cohen (1988). Computes sample size, effect size, significance level, or power for t-tests, ANOVA, chi-square tests, correlation tests, pro

Use when querying, indexing, or manipulating BIDS (Brain Imaging Data Structure) neuroimaging datasets with PyBIDS. Covers BIDSLayout construction, file querying with get(), metadata retrieval, BIDS v

Pysam — Python interface to htslib for reading, writing, and manipulating SAM/BAM/CRAM alignment files, VCF/BCF variant files, FASTA/FASTQ sequences, and tabix-indexed files. Provides Pythonic wrapper

PySB is a Python framework for rule-based mathematical modeling of biochemical systems. Use this skill for mechanistic signaling models, reaction-rule model construction, deterministic or stochastic s

pysheds — simple and fast watershed delineation in Python. Processes digital elevation models (DEMs) for hydrological analysis including pit filling, depression filling, flat resolution, D8 flow direc

QIIME2 food-science plugin routing skill for amplicon-based microbiome analysis in food, fermentation, and agricultural contexts. Use this skill when users mention QIIME2, qiime2, q2-food-science, foo

The rasterVis package provides a set of methods for enhanced visualization and interaction with raster data. It includes functions for visualizing raster and RasterStack objects, with a particular foc

Raven Pro and Raven Lite bioacoustics software from the Cornell Lab of Ornithology for visualizing, measuring, and annotating audio recordings. Produces selection tables (tab-delimited .txt) with acou

Use when working with Rcpp, the core R package for integrating R and C++. Supports interactive prototyping with `cppFunction`, standalone C++ files with `sourceCpp`, package workflows with `Rcpp.packa

Use this skill for regionmask, the Python package that builds 2D integer masks, 3D boolean masks, and 3D approximate fractional-overlap masks for geospatial regions on lon/lat grids. Trigger when user

related — R package for estimating pairwise relatedness coefficients from molecular marker data (microsatellites, SNPs). Implements eight estimators: Wang (2002), Lynch & Ritland (1999), Queller & Goo

Bioconductor ExperimentHub — unified R interface for discovering and downloading global experimental genomics data resources (single-cell RNA-seq, bulk RNA-seq, ChIP-seq, ATAC-seq, proteomics, methyla

Use when working with Rhtslib, the Bioconductor package that vendors HTSlib inside R packages for high-throughput sequencing development. Covers pkgconfig("PKG_LIBS"), pkgconfig("PKG_CPPFLAGS"), Rhtsl

RNAfold is the primary command-line tool in the ViennaRNA Package for RNA secondary structure prediction via minimum free energy (MFE) and partition function algorithms. Predicts MFE dot-bracket struc

ROBOT — command-line tool for automating OWL and OBO ontology workflows. Build, transform, validate, and publish biomedical ontologies from the command line. Supports merging ontologies, running OWL r

Use when working with ROHan — Runs of Homozygosity analyzer for ancient and modern genomes. Detects ROH regions directly from BAM files using a hidden Markov model (HMM) without explicit genotype call

Use when working with Rsamtools, the Bioconductor R package for indexed BAM, BCF, FASTA, and tabix-backed genomic files. Covers BamFile, ScanBamParam, filterBam, sortBam, indexBam, pileup, TabixFile,

Use when working with rtracklayer — rtracklayer — Bioconductor R package

samblaster is a streaming duplicate marker and structural-variant read extractor for read-id grouped paired-end SAM. Use it when a user needs fast duplicate marking, discordant read extraction, split-

Use this skill for statistical simulation of single-cell and spatial omics data with scDesign3. Route here when users ask about generating synthetic scRNA-seq data, benchmarking analysis tools with re

schmutzi — Bayesian contamination estimation and decontamination for ancient mitochondrial DNA. Estimates the fraction of modern human contamination in ancient DNA libraries by comparing observed sequ

scib-metrics — single-cell integration benchmarking metrics for evaluating batch correction and biological conservation in single-cell RNA-seq data. Compute batch correction metrics (kBET, iLISI, PCR,

scispaCy is a Python package for biomedical and scientific text processing built on spaCy. Provides pretrained NLP models for biomedical NER (disease, chemical, gene, mutation entities), entity linkin

scJoint integrates atlas-scale single-cell RNA-seq and scATAC-seq data using transfer learning. Transfers cell type labels from annotated RNA datasets to unannotated ATAC datasets via joint neural net

scvi-tools — probabilistic deep learning framework for single-cell omics analysis built on PyTorch and AnnData. Provides variational autoencoders for dimensionality reduction and batch integration (sc

seq_io — high-performance Rust FASTA/FASTQ parser with zero-copy design. Read and write FASTA and FASTQ files using fasta::Reader, fastq::Reader, and the Record trait. Supports multi-line FASTA, paral

SingleCellExperiment — core R/Bioconductor container class for single-cell genomics data. Stores assays (counts, logcounts, normalized), cell metadata (colData), gene metadata (rowData), dimensionalit

snapgene-reader — Python library for parsing SnapGene *.dna binary files into Python dicts or Biopython SeqRecord objects. Converts proprietary SnapGene format to GenBank (.gbk), extracts annotated se

SpadeR (Species-richness Prediction And Diversity Estimation in R) estimates species richness and diversity indices from abundance or incidence-frequency data. Implements Chao1, ACE, jackknife, and bo

Use when working with sQTLseekeR — splicing quantitative trait locus (sQTL) mapping using transcript ratio tests. R package that identifies genetic variants (SNPs, indels) associated with changes in s

Use when working with StabMap for mosaic single-cell integration across assays that only partially share features, especially RNA plus Multiome, RNA plus ATAC via a bridging assay, or other feature-ov