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.

Finding relevant biomedical research is time-consuming. This skill provides advanced search techniques, MeSH term guidance, and E-utilities API documentation to quickly locate articles, clinical trials, and systematic reviews in PubMed's database of millions of citations.

Finding chemical information requires navigating multiple databases and complex API queries. This skill provides unified access to PubChem database with simple search by name, structure, or identifier plus property retrieval and similarity searches for cheminformatics workflows.

Scientists spend hours searching for and documenting lab protocols manually. This skill provides complete integration with protocols.io API v3, enabling programmatic access to search, create, manage, and publish scientific protocols with team collaboration features.

Peer review of scientific manuscripts requires consistent methodology across disciplines. This skill provides structured frameworks for evaluating methodology, statistics, reproducibility, ethics, and reporting standards for comprehensive manuscript and grant assessment.

Finding 3D biological structures requires navigating multiple databases and file formats. This skill provides unified access to the RCSB PDB repository for searching, downloading, and analyzing over 200,000 experimentally determined and computed molecular structures.

Working with computational pathology requires specialized tools for whole-slide image analysis. This skill provides comprehensive reference documentation for PathML, enabling you to load gigapixel pathology images, preprocess H&E stains, train machine learning models, and analyze spatial proteomics data.

Transform academic papers into professional promotional materials for conferences and online sharing. This skill automates the creation of interactive websites, presentation videos, and conference posters from LaTeX or PDF sources.

Scientists and researchers need efficient ways to manage large microscopy image datasets. This skill provides complete reference documentation for the OMERO Python API, enabling automated image retrieval, pixel analysis, ROI management, and batch processing for high-content screening workflows.

Research requires finding relevant academic papers and analyzing publication trends. This skill provides direct access to the OpenAlex database containing 240M+ scholarly works, enabling literature searches, citation analysis, and research output evaluation without manual database navigation.

Find therapeutic targets and drug candidates using integrated genetic, omics, and clinical data. Query gene-disease associations with evidence scores to accelerate drug discovery.

Researching information scattered across multiple Notion pages takes time and risks missing key details. This skill provides a structured workflow to search, fetch, and synthesize Notion content into organized briefs, summaries, comparisons, or comprehensive reports with proper citations.

Analyzing Neuropixels recordings requires expertise with multiple tools and complex pipelines. This skill provides a complete workflow from raw data to curated units with preprocessing, spike sorting, quality metrics, and AI-assisted curation following best practices from SpikeInterface, Allen Institute, and IBL.

Search thousands of metabolomics studies and metabolite data from the NIH database. Access standardized nomenclature, mass spectrometry data, and study metadata for biomarker discovery and metabolic research.

Screening large compound libraries for drug candidates is time-consuming. This skill applies established medicinal chemistry rules like Lipinski Rule of Five, PAINS filters, and structural alerts to automatically identify promising compounds for further study.

Writing comprehensive market research reports is time-consuming and requires expertise in frameworks, formatting, and visual design. This skill streamlines the entire process by providing structured templates, automated visual generation, and professional LaTeX formatting that matches top consulting firm deliverables.

Researchers spend hours searching multiple databases and verifying citations manually. This skill streamlines literature reviews by searching academic databases, deduplicating results, verifying citations against CrossRef, and generating professional PDFs with proper formatting.