Molecular machine learning requires converting chemical structures into numerical representations. Molfeat provides 100+ featurizers to transform SMILES strings into machine learning-ready features for QSAR modeling and drug discovery.

Modal is a serverless platform for running Python code in the cloud. It provides instant access to GPUs, automatic scaling, and pay-per-use billing. Deploy ML models, run batch processing jobs, and serve APIs without managing infrastructure.

Search and retrieve metabolomics data from the NIH Metabolomics Workbench database containing 4,200+ studies. Access metabolite structures, study metadata, RefMet nomenclature, and perform mass spectrometry searches.

Drug discovery requires filtering large compound libraries for drug-like properties. This skill applies established medicinal chemistry rules including Rule of Five, Veber, and PAINS filters to prioritize compounds and identify structural alerts efficiently.

Matplotlib provides complete control over every visual element for creating publication-quality figures. Master both pyplot and object-oriented interfaces to build any chart type from simple line plots to complex multi-panel scientific visualizations.

Scientists and engineers often struggle with MATLAB syntax and best practices. This skill provides comprehensive reference documentation for matrix operations, visualization, and numerical analysis.

Mass spectrometry data contains complex spectral information that requires specialized processing. Matchms provides comprehensive tools to import, filter, and compare mass spectra for metabolite identification and compound analysis.

Converting documents to Markdown makes them token-efficient and easy to process for AI models. MarkItDown supports 15+ formats including PDF, DOCX, PPTX, XLSX, images, audio, and web pages.

Create comprehensive 50+ page market research reports with professional LaTeX formatting. Generate strategic visuals, perform multi-framework analysis, and produce consulting-quality deliverables for business decisions.

Conducting literature reviews manually wastes hours searching databases and formatting citations. This skill automates systematic literature reviews by searching PubMed, arXiv, bioRxiv, and Semantic Scholar, verifying all citations, and generating professional PDFs.

Research posters are essential for scientific communication at conferences. This skill provides comprehensive guidance for creating professional research posters using LaTeX packages like beamerposter, tikzposter, and baposter. Generate publication-quality posters with proper layout, typography, and visual hierarchy.

Deploy production-ready bioinformatics workflows without managing infrastructure. Create serverless pipelines using Python decorators with automatic containerization, GPU support, and integrated cloud storage.

Biological research generates complex datasets that are difficult to track, query, and reproduce. LaminDB provides a unified framework for managing biological data with automatic lineage tracking, ontology-based annotations, and seamless integration with workflow managers.

Manage electronic lab notebooks programmatically. Automate data uploads, backup notebooks, and integrate with scientific tools like Jupyter and REDCap for research workflows.

Researchers need efficient access to KEGG bioinformatics data for pathway analysis and gene mapping. This skill provides Python helper functions for all KEGG REST API operations including pathway retrieval, gene-pathway mapping, compound searches, and ID conversion between databases.

Medical device companies need comprehensive ISO 13485 documentation for quality management certification. This skill provides templates, gap analysis tools, and step-by-step guidance to create all required QMS documents efficiently.

Transform observations into structured, testable scientific hypotheses. This skill guides you through literature synthesis, mechanism development, experimental design, and prediction formulation using proven scientific method frameworks.

Manual hypothesis generation is time-consuming and prone to cognitive bias. Hypogenic automates hypothesis generation and testing using LLMs, enabling researchers to systematically explore patterns in tabular datasets and combine empirical findings with literature insights.

This skill provides access to the Human Metabolome Database containing over 220,000 metabolite entries. Researchers can search by chemical name, structure, or ID to retrieve properties, spectra, and biomarker data for metabolomics studies.

Histolab automates tissue detection and tile extraction from gigapixel whole slide images. It processes WSI files to extract informative tiles for deep learning pipelines and medical research.