Explore skills

This skill is for machine learning tasks involving genomic interval data (BED files), such as training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), or building consensus peaks. It applies to BED file collections, scATAC-seq data, and chromatin accessibility datasets.

A Python library for working with geospatial vector data like shapefiles, GeoJSON, and GeoPackage files. It's used for spatial analysis, geometric operations, coordinate transformations, and other tasks involving vector geographic data, supporting PostGIS databases and interactive maps.

This skill detects and reports available system resources (CPU cores, GPUs, memory, disk space) at the start of computationally intensive scientific tasks. It generates a JSON file with resource information and strategic recommendations to guide computational approach decisions, such as using parallel processing or out-of-core computing.

Perform fast CLI/Python queries across 20+ bioinformatics databases for quick lookups of gene info, BLAST searches, AlphaFold structures, and enrichment analysis. It's best for interactive exploration and simple queries, with biopython or bioservices recommended for batch processing or advanced workflows.

Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench) for glycoprotein engineering, therapeutic antibody optimization, and vaccine design.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. It's used for genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

This tool provides lightweight WSI tile extraction and preprocessing, ideal for basic slide processing, tissue detection, and stain normalization for H&E images. It's best suited for simple pipelines, dataset preparation, and quick tile-based analysis, with pathml recommended for advanced applications.

Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces, designed for users engaged in AI/ML work across various scientific domains like biology, chemistry, and physics.

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use to systematically explore patterns in empirical data, combining literature insights with data-driven hypothesis testing.

Formulates structured, testable hypotheses from experimental observations or data, including predictions, proposed mechanisms, and experimental designs, following the scientific method.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Access large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research without authentication, querying by metadata, visualizing in browser, and checking licenses.

This skill is for working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use it for managing biological datasets, tracking workflows, curating data with ontologies, building lakehouses, or ensuring data lineage and reproducibility.