Data Science & ML Agent Skills

Opentrons Lab Automation

Automates laboratory liquid handling workflows by writing Python-based Protocol API v2 scripts for Opentrons Flex and OT-2 robots.

Benchling Integration

Automates R&D data management by integrating Claude with the Benchling platform for biological entity tracking, inventory control, and lab notebook documentation.

STRING Database Analysis

Accesses and analyzes protein-protein interaction networks and functional enrichment data using the STRING API.

Seaborn Statistical Visualization

Generates publication-quality statistical graphics and complex data visualizations using a high-level, dataset-oriented Python interface.

ClinVar Database Integration

Access and analyze genomic variant clinical significance data from NCBI's ClinVar archive.

PyOpenMS Mass Spectrometry Analysis

Analyzes mass spectrometry data using Python bindings for OpenMS to process complex proteomics and metabolomics workflows.

Reactome Database

Facilitates systems biology research by querying the Reactome REST API for pathway analysis, gene mapping, and molecular interactions.

PDB Structural Biology & Drug Discovery

Accesses and analyzes RCSB Protein Data Bank (PDB) structures, metadata, and 3D coordinates for structural biology and drug discovery research.

ClinPGx Pharmacogenomics Database

Accesses comprehensive pharmacogenomics data including gene-drug interactions, CPIC guidelines, and allele functions for precision medicine.

Open Targets Database

Queries the Open Targets Platform to identify therapeutic drug targets and analyze disease-target associations using human genetics and omics data.

FDA Database Access

Accesses and analyzes comprehensive FDA regulatory data for drugs, medical devices, and food safety through the openFDA API.

Scientific Brainstorming

Facilitates collaborative research ideation and hypothesis generation for scientists and academic researchers.

Pysam Genomic Toolkit

Reads, manipulates, and writes genomic datasets including BAM, VCF, and FASTA files using a Pythonic interface to htslib.

Statistical Analysis

Performs comprehensive statistical testing, hypothesis verification, and research data modeling using Python's scientific ecosystem.

PennyLane Quantum Computing

Enables building, training, and optimizing quantum circuits and hybrid quantum-classical models using automatic differentiation and hardware-agnostic execution.

Medicinal Chemistry Toolkit

Filters and prioritizes molecular libraries using medicinal chemistry rules, structural alerts, and drug-likeness metrics.

Pymatgen Materials Science

Analyzes crystal structures, generates phase diagrams, and integrates with the Materials Project for advanced computational materials science.

Molfeat - Molecular Featurization Hub

Simplifies molecular featurization for machine learning by providing a unified interface for over 100 descriptors, fingerprints, and pretrained embeddings.

Matchms

Processes and analyzes mass spectrometry data using advanced spectral similarity metrics and automated metadata harmonization.

Matplotlib Scientific Visualization

Generates publication-quality scientific plots and data visualizations using Python's foundational plotting library.

NetworkX Graph Analysis

Builds, analyzes, and visualizes complex network structures and graph algorithms using Python's NetworkX library.

Bioinformatics & Genomic Data (gget)

Simplifies bioinformatics workflows by providing unified access to over 20 genomic and proteomic databases for sequence analysis and protein modeling.

Gtars Genomic Toolkit

Performs high-performance genomic interval analysis and sequence tokenization using Rust-powered tools and Python bindings.

Plotly Scientific Visualization

Generates interactive, publication-quality scientific and statistical visualizations using the Plotly Python library.

deepTools NGS Analysis

Facilitates comprehensive Next-Generation Sequencing (NGS) data processing, quality control, and publication-quality visualization.

Polars High-Performance Dataframes

Accelerates data analysis workflows using Polars' lightning-fast, expression-based API and lazy evaluation framework.

FluidSim CFD Framework

Simulates high-performance computational fluid dynamics using pseudospectral methods and Python-based solvers.

Datamol Cheminformatics

Simplifies molecular cheminformatics and drug discovery workflows with a Pythonic abstraction layer for RDKit.

Dask Parallel Computing

Accelerates and scales Python data processing by providing parallel and distributed computing capabilities for NumPy, pandas, and custom workflows.

GeoPandas Geospatial Analysis

Extends pandas to enable powerful spatial operations and vector data analysis for complex geographic workflows.