Drug discovery researchers need standardized datasets for training ML models. PyTDC provides curated ADME, toxicity, and drug-target interaction datasets with proper train-test splits and evaluation oracles.

Process and analyze DNA sequencing data with tools for reading BAM, VCF, and FASTQ files. Extract genomic regions, calculate coverage statistics, and integrate multiple file types for comprehensive variant analysis.

Process proteomics and metabolomics data with comprehensive mass spectrometry tools. This skill provides access to OpenMS algorithms for file format handling, spectral processing, feature detection, and peptide identification workflows.

Multi-objective optimization involves finding trade-off solutions when multiple conflicting objectives must be satisfied. This skill provides comprehensive access to pymoo algorithms including NSGA-II, NSGA-III, and MOEA/D for finding Pareto-optimal solutions and visualizing trade-off fronts.

Build, fit, and validate Bayesian models using PyMC. Create hierarchical models, run MCMC sampling, and compare models with LOO and WAIC metrics.

Work with crystal structures and materials data. Convert file formats, compute phase diagrams, analyze symmetry, and access the Materials Project database for computational materials science research.

Automate laboratory workflows by controlling liquid handling robots, plate readers, and lab equipment through unified Python commands. This skill enables reproducible protocols across Hamilton, Tecan, and Opentrons platforms with built-in simulation for testing.

Healthcare researchers and data scientists struggle with complex clinical data formats and coding systems. PyHealth provides a unified toolkit for loading medical datasets, processing EHR data, training predictive models, and working with standard medical codes.

Process DICOM medical images including CT, MRI, X-ray, and ultrasound. Read, write, anonymize, convert, and extract metadata from healthcare imaging files.

PyDESeq2 enables differential gene expression analysis from bulk RNA-seq count data. Perform statistical testing, multiple comparison correction, and generate publication-ready volcano and MA plots for your genomics research.

Training RL agents requires high-performance parallel environments and efficient algorithms. PufferLib provides optimized PPO+LSTM training with 2-10x speedups through vectorization, shared memory buffers, and multi-agent support.

Researchers need efficient access to biomedical literature for systematic reviews and evidence-based research. This skill provides comprehensive documentation for PubMed queries including Boolean operators, MeSH terms, and E-utilities API access.

Researchers need quick access to molecular properties and chemical structures. This skill connects to PubChem's 110M+ compound database for instant cheminformatics queries.

This skill provides comprehensive integration with protocols.io API for managing scientific protocols. Use it to search existing protocols, create new protocols, manage collaborative workspaces, handle discussions, and organize laboratory documentation workflows.

Transform research content into professional research posters using HTML and CSS with AI-generated visuals. Export to PDF for printing or convert to PowerPoint for conference presentations.

Stop manually creating presentations. This skill converts HTML to PowerPoint, edits existing slides, and extracts content using proven XML workflows. Build presentations faster with code.

Process large datasets in memory with Polars, the high-performance DataFrame library. Features lazy evaluation, parallel execution, and Apache Arrow backend for 10x faster operations than pandas.

Data visualization often requires complex code and lacks interactivity for exploration. This skill provides comprehensive guidance for creating interactive, publication-quality charts with Plotly, featuring hover tooltips, zoom, pan, and 40+ chart types for dashboards and data analysis.

This skill enables AI-powered web searches to find current information, recent scientific research, and grounded answers with source citations. It provides access to multiple Perplexity models through a single OpenRouter API key.

Building quantum machine learning models requires understanding quantum circuits, gradient computation, and hybrid classical-quantum workflows. This skill provides comprehensive documentation for PennyLane, enabling developers to train quantum circuits with automatic differentiation across simulators and real quantum hardware.