Data Science & ML Agent Skills

HMDB Metabolome Database

Accesses and queries the Human Metabolome Database for detailed metabolite information, clinical biomarkers, and biochemical pathways.

Genomic Interval Machine Learning (Geniml)

Builds and deploys machine learning models for genomic interval data and single-cell chromatin accessibility analysis.

Gemini 3 Advanced Features

Implements advanced Gemini 3 Pro capabilities including function calling, structured JSON outputs, and cost-efficient context caching for production AI applications.

ClinPGx Pharmacogenomics Database

Accesses comprehensive clinical pharmacogenomics data to guide precision medicine and genotype-based dosing decisions.

Ensembl Genome Database Integration

Queries the Ensembl REST API for genomic data, sequence retrieval, variant analysis, and comparative genomics across 250+ species.

ClinVar Genomic Analysis

Queries the NCBI ClinVar database to retrieve, interpret, and process human genetic variant classifications and clinical significance.

RAG Implementation

Implements advanced Retrieval-Augmented Generation (RAG) workflows to build knowledge-grounded LLM applications and semantic search systems.

Agent Memory System

Implement a multi-layered persistent memory architecture for AI agents to enable cross-session learning and long-term context retention.

Gemini Document Processing

Integrates Google Gemini's native vision capabilities to analyze, summarize, and extract structured data from complex PDF documents.

Datamol Cheminformatics

Simplifies molecular cheminformatics workflows with a Pythonic wrapper for RDKit, featuring structure standardization, descriptor calculation, and 3D conformer generation.

Python Experiment Reproducibility

Ensures deterministic results in Python research code by centralizing configurations, controlling randomness, and recording run metadata.

DNAnexus Genomics Integration

Streamlines genomic data management and bioinformatics app development on the DNAnexus cloud platform using the dxpy Python SDK.

Genomic Tools and Algorithms in Rust (Gtars)

Simplifies high-performance genomic interval analysis and machine learning preprocessing using Rust-powered toolsets.

UMAP Dimensionality Reduction

Performs fast non-linear dimensionality reduction and manifold learning for high-dimensional data visualization and clustering.

Training Curve Interpreter

Analyzes machine learning training logs to visualize loss curves, detect training issues, and provide diagnostic insights.

Pymoo Optimization

Solves complex single and multi-objective optimization problems using evolutionary algorithms and Pareto front analysis.

FinnHub Financial Data

Integrates real-time financial market data including stock quotes, forex rates, crypto prices, and company fundamentals via the FinnHub API.

KEGG Scientific Database Access

Accesses the KEGG REST API for biological pathway analysis, gene mapping, and metabolic network research.

LabArchives ELN Integration

Automates electronic lab notebook workflows including data uploads, notebook backups, and programmatic entry management via the LabArchives REST API.

SymPy Symbolic Mathematics

Performs exact symbolic mathematical computations including algebra, calculus, and equation solving using the SymPy Python library.

Histolab Pathology Processing

Automates digital pathology workflows by processing whole slide images, detecting tissue regions, and extracting informative tiles for deep learning pipelines.

LaminDB Biological Data Framework

Manages biological datasets with automated lineage tracking, ontology-based validation, and FAIR data principles through a unified Python API.

Statistical Trading Symbol Selection

Analyzes market data using Hurst exponent, GARCH models, and Markov regime detection to identify optimal trading symbols for quantitative strategies.

PyOpenMS Mass Spectrometry Analysis

Analyzes mass spectrometry data for proteomics and metabolomics using the OpenMS Python interface.

scvi-tools: Probabilistic Single-Cell Analysis

Implement deep generative models for single-cell omics analysis, enabling batch correction, multimodal integration, and probabilistic differential expression.

FluidSim CFD Simulations

Simulates complex fluid dynamics using Python-based high-performance solvers for Navier-Stokes, shallow water, and stratified flows.

Scanpy Single-Cell Analysis

Performs comprehensive single-cell RNA-seq analysis workflows including quality control, clustering, and visualization.

UniProt Protein Database

Accesses the UniProt REST API to retrieve protein sequences, functional annotations, and map identifiers across biological databases.

ETE Toolkit for Phylogenetics

Manipulates, analyzes, and visualizes phylogenetic and hierarchical trees for genomic research and clustering analysis.

Harmonic Insight AI Assistant

Standardizes the implementation of Claude-powered AI assistants across the Insight Business Suite with built-in persona systems and BYOK management.