Manual hypothesis generation is slow and limited by human creativity. Hypogenic automates systematic hypothesis generation and testing using LLMs, combining data-driven patterns with literature insights for accelerated scientific discovery.

Researchers need quick access to metabolite information for metabolomics studies. This skill provides guidance for searching the Human Metabolome Database to find chemical properties, biomarkers, and spectral data for metabolite identification and research.

Digital pathology workflows require processing gigapixel whole slide images for computational analysis. This skill provides comprehensive guidance for extracting tiles, detecting tissue regions, and preparing datasets for deep learning pipelines in histopathology research.

Finding genetic associations for diseases requires navigating complex genomic databases. This skill provides clear guidance for querying the NHGRI-EBI GWAS Catalog to retrieve SNP-trait associations, p-values, and summary statistics for research.

Genomic interval analysis requires specialized tools for processing BED files, detecting overlaps, and generating coverage tracks. Gtars provides high-performance Rust implementations with Python bindings for computational genomics and machine learning workflows.

Need quick access to gene information, protein structures, or expression data? This skill provides unified access to 20+ bioinformatics databases through a single interface. Search genes, retrieve sequences, predict structures, and analyze disease associations without switching tools.

Finding and processing gene expression datasets requires navigating complex database structures and file formats. This skill provides ready-to-use code patterns for searching, downloading, and analyzing GEO microarray and RNA-seq data.

Working with genomic interval data for machine learning tasks requires specialized tools. Geniml provides unsupervised methods for learning embeddings of genomic regions, single cells, and metadata labels for similarity searches, clustering, and downstream analysis.

Search and retrieve gene information from NCBI Gene database. Get gene symbols, RefSeq sequences, GO annotations, chromosomal locations, and phenotype associations for research and analysis.

Protein engineering requires specialized AI models to analyze sequence-structure-function relationships. ESM provides state-of-the-art protein language models for generating novel sequences, predicting structures, and designing functional proteins through multimodal AI.

Genomic researchers need access to gene sequences, variants, and comparative data across species. This skill queries the Ensembl database REST API to retrieve gene information, DNA sequences, variant predictions, orthologs, and regulatory features for over 250 vertebrate species.

Finding and downloading nucleotide sequences requires understanding complex API syntax and multiple endpoint patterns. This skill provides comprehensive documentation for querying the European Nucleotide Archive to retrieve DNA/RNA sequences, genome assemblies, and raw sequencing reads by accession.

Denario automates the complete research pipeline from data analysis to publication. It uses AI agents to generate hypotheses, develop methodologies, execute experiments, and produce journal-formatted papers.

Cancer researchers need programmatic access to the world's largest somatic mutation database. This skill enables authenticated downloads of COSMIC cancer genomics data including mutations, gene annotations, and clinical variants for research and precision oncology.

Finding clinical trials for patients, research, or drug development requires navigating a complex registry. This skill provides a Python interface to query the official ClinicalTrials.gov database. Search by condition, drug, location, or sponsor to find recruiting trials, retrieve detailed study information, and export data for analysis.

Managing citations manually is time-consuming and error-prone. This skill automates searching academic databases, extracting metadata from DOIs and PMIDs, validating citations, and generating publication-ready BibTeX entries.

Finding drug discovery data requires searching multiple databases and understanding complex API queries. This skill provides ready-to-use functions for querying ChEMBL's database of over 2 million bioactive compounds, 19 million bioactivity measurements, and approved drug information.

Researchers need efficient access to population-scale single-cell data for genomics studies. This skill provides AI-powered access to the CZ CELLxGENE Census with optimized query patterns and integration guides for downstream analysis.

Finding enzyme kinetic parameters from literature requires extensive searching. This skill provides direct access to the BRENDA database through a simple interface for retrieving Km values, reaction equations, and organism-specific enzyme data for biochemical research.

Researchers need to retrieve biological data from multiple databases. This skill provides unified access to 40+ bioinformatics services including UniProt, KEGG, ChEMBL, and Reactome for protein sequences, pathways, compounds, and interactions.