Data Science & ML Claude 技能

Arboreto

Infers gene regulatory networks (GRNs) from transcriptomics data using scalable algorithms like GRNBoost2 and GENIE3.

Biopython Molecular Biology

Performs comprehensive biological computation, sequence manipulation, and NCBI database integration using the Biopython toolkit.

CZ CELLxGENE Census

Provides programmatic access to standardized single-cell genomics data for high-scale querying, analysis, and machine learning integration.

COBRApy Scientific Modeling

Performs constraint-based metabolic modeling and systems biology analysis using the COBRApy library.

BioServices Bioinformatics Toolkit

Accesses over 40 bioinformatics web services and databases through a unified Python API for biological data retrieval and analysis.

Financial Model Creation

Generates advanced financial models including DCF analysis, Monte Carlo simulations, and sensitivity testing for investment valuation and risk assessment.

DocETL Data Pipelines

Builds and optimizes agentic LLM-powered data processing pipelines for unstructured document analysis and information extraction.

Distributed Training Debugger

Diagnoses and resolves distributed training issues like hangs, OOM errors, and NCCL communication failures in LLM reasoning frameworks.

Vizro Dashboard Builder

Builds and tests high-quality data visualization dashboards using the McKinsey Vizro low-code toolkit.

Linear Algebra Eigenvalues

Solves complex linear algebra problems by calculating characteristic polynomials, eigenvalues, and eigenvectors using Sympy and Z3 verification.

ClawRouter

Optimizes AI inference spending by intelligently routing requests to the most cost-effective model across five major providers.

Gemini Web Integration

Generates text and images using the Gemini Web API to provide vision-capable AI features and multi-turn conversations within Claude Code.

Advanced Excel & Financial Modeling

Enables Claude to create, analyze, and format professional Excel spreadsheets and financial models with formula-preserving capabilities.

Excel & Spreadsheet Scientific Toolkit

Creates, edits, and analyzes Excel spreadsheets with production-grade formulas, industry-standard financial formatting, and automated recalculation.

BioServices Bioinformatics Tool

Streamlines access to over 40 bioinformatics web services and databases for biological data retrieval and cross-database analysis.

HMDB Scientific Database Access

Accesses the Human Metabolome Database (HMDB) to retrieve comprehensive data on small molecule metabolites, clinical biomarkers, and biochemical pathways.

DiffDock Molecular Docking

Predicts high-accuracy 3D protein-ligand binding poses using state-of-the-art diffusion-based deep learning models.

DeepChem Molecular Machine Learning

Applies advanced machine learning techniques to chemistry, biology, and materials science for molecular property prediction and drug discovery.

Biopython Molecular Biology

Performs complex biological computation, sequence analysis, and bioinformatics workflows using the Biopython library.

Datamol Cheminformatics

Simplifies molecular cheminformatics workflows by providing a Pythonic wrapper for RDKit with sensible defaults and parallel processing.

Pysam Genomic Toolkit

Manipulates genomic datasets including SAM, BAM, VCF, and FASTA files through a Pythonic interface to htslib.

Polars Data Analysis

Optimizes data processing workflows with high-performance Polars expressions, lazy evaluation, and efficient DataFrame manipulations.

Dask Parallel Computing

Enables parallel and distributed computing in Python to scale data processing beyond memory limits.

COSMIC Cancer Database

Integrates the world's most comprehensive cancer mutation database into your research workflow to query somatic mutations, signatures, and gene census data.

Scientific Data Visualization

Generates publication-ready scientific figures and multi-panel layouts using Matplotlib, Seaborn, and Plotly.

Medicinal Chemistry Toolkit

Applies medicinal chemistry rules and structural filters to prioritize drug-like compounds in molecular discovery workflows.

PyDESeq2 Analysis

Performs comprehensive differential gene expression analysis from bulk RNA-seq count data using the Python implementation of DESeq2.

ETE Toolkit for Phylogenetics

Manipulates, analyzes, and visualizes phylogenetic and hierarchical trees for genomic research and evolutionary biology.

OMERO Microscopy Integration

Manages and analyzes microscopy data programmatically using the OMERO Python API and data management platform.

Open Targets Database

Queries the Open Targets Platform to identify and prioritize therapeutic drug targets using human genetics, omics, and clinical evidence.