Finding purchasable compounds for drug discovery is time-consuming and requires specialized database knowledge. This skill provides complete documentation for accessing the ZINC database with 230M+ compounds, enabling efficient virtual screening, similarity searches, and 3D structure downloads for molecular docking studies.

Finding patent and trademark information requires navigating multiple USPTO systems. This skill provides unified access to PatentSearch, PEDS, TSDR, and assignment databases for comprehensive IP research.

Predict molecular properties, generate new compounds, and analyze proteins using TorchDrug ML library. Train graph neural networks on molecules, proteins, and biomedical knowledge graphs for drug discovery and computational chemistry tasks.

Statistical analysis skills are essential for research but require proper methodology. This toolkit provides comprehensive guidance on hypothesis testing, regression, Bayesian methods, and APA reporting to help researchers conduct rigorous, reproducible analyses.

Complex systems with queues and shared resources are difficult to analyze without simulation. SimPy provides a Python-based framework for modeling processes, resources, and time-based events to predict system behavior before implementation.

Single-cell genomics analysis requires specialized probabilistic models for dimensionality reduction, batch correction, and integration across diverse modalities. scvi-tools provides deep generative models built on PyTorch for comprehensive single-cell data analysis.

Biological research requires specialized tools for DNA sequence analysis, phylogenetic trees, and diversity metrics. This skill provides guidance for using scikit-bio to process sequences, calculate alpha and beta diversity, and perform statistical tests on microbiome data.

Scientists spend hours formatting figures for journal submission. This skill provides pre-configured matplotlib styles, colorblind-friendly palettes, and automated export tools to create professional figures in minutes instead of hours.

Build professional scientific presentations for conferences, seminars, and thesis defenses. Generate AI-powered slides with consistent formatting, use LaTeX Beamer templates, and follow research-backed design principles.

Scientific claims often go unquestioned despite containing methodological flaws, biases, and overstated conclusions. This skill provides systematic frameworks to assess research quality using established methodologies like GRADE and Cochrane ROB, enabling accurate evidence evaluation.

Scientists need fresh research directions but often get stuck in established thinking patterns. This skill acts as a collaborative ideation partner to generate hypotheses, explore unexpected interdisciplinary connections, and develop innovative methodologies through structured brainstorming techniques.

Finding current research and academic papers takes significant time. This skill uses Perplexity Sonar models through OpenRouter to search academic literature, recent studies, and technical documentation with automatic citations.

Writing competitive research grants for federal agencies is complex and time-consuming. This skill provides agency-specific guidance, templates, and best practices for NSF, NIH, DOE, and DARPA proposals.

Researching biological pathways requires searching multiple databases and performing statistical analysis. This skill provides direct access to Reactome database REST API for pathway enrichment analysis, gene-pathway mapping, and molecular interaction queries.

RDKit is a powerful open-source cheminformatics library for molecular analysis. This skill provides comprehensive guidance for calculating molecular properties, performing similarity searches, filtering compounds by substructure, and visualizing chemical structures.

Quantum computing development requires understanding complex circuit design, transpilation, and hardware-specific optimization. This skill provides comprehensive guidance for building quantum circuits, running algorithms like VQE and QAOA on simulators or real hardware, and visualizing results.

Working with drug discovery datasets requires navigating scattered sources and inconsistent formats. PyTDC provides 50+ curated therapeutic ML datasets with standardized APIs, meaningful splits, and benchmark evaluation protocols.

Engineers and researchers need to find optimal trade-offs between conflicting objectives like cost, weight, and performance. This skill provides access to NSGA-II, NSGA-III, and other evolutionary algorithms through pymoo to discover Pareto-optimal solutions for complex design problems.

Developing machine learning models for healthcare requires understanding complex clinical data formats, medical coding systems, and specialized model architectures. This skill provides comprehensive guidance on using PyHealth to build, train, and evaluate clinical prediction models for mortality prediction, drug recommendation, and medical coding tasks.

Identify differentially expressed genes from bulk RNA-seq count data with statistical rigor. PyDESeq2 provides complete DESeq2 workflows including normalization, dispersion estimation, Wald testing, FDR correction, and publication-ready visualizations.