Data Science & ML Agent Skills

UniProt Protein Database

Accesses the UniProt REST API to search, retrieve, and map protein sequence and functional data directly within scientific workflows.

ZINC Database Search

Accesses over 230 million purchasable chemical compounds for virtual screening, drug discovery, and molecular docking studies.

LatchBio Bioinformatics Workflows

Builds and deploys serverless bioinformatics pipelines using the Latch SDK and cloud infrastructure.

DNAnexus Integration

Streamlines biomedical data management and genomics workflow automation on the DNAnexus cloud platform.

SHAP Model Interpretability

Explains machine learning model predictions and feature importance using Shapley values for improved transparency and debugging.

Transformers

Implements, fine-tunes, and deploys pre-trained transformer models for natural language processing, computer vision, and audio tasks.

PufferLib RL

Accelerates reinforcement learning workflows through high-performance training, optimized environment vectorization, and seamless multi-agent integration.

Vaex Data Analysis

Processes and visualizes billion-row tabular datasets exceeding available RAM through lazy, out-of-core DataFrame operations.

Histolab

Processes digital pathology whole slide images (WSI) through automated tissue detection, tile extraction, and specialized image preprocessing.

Scikit Survival

Performs advanced survival analysis and time-to-event modeling in Python using specialized machine learning techniques for censored data.

LaminDB

Manages biological datasets with end-to-end lineage tracking, ontology-based curation, and FAIR data principles using a unified Python API.

DrugBank Database

Accesses and analyzes comprehensive pharmaceutical data from DrugBank including molecular structures, drug interactions, targets, and pharmacological properties.

NeuroKit2

Processes and analyzes physiological signals like ECG, EEG, and EDA to extract research-grade biometrics and psychophysiological insights.

Stable Baselines3

Implements reinforcement learning workflows including agent training, custom environment design, and parallelized experimentation using the Stable Baselines3 library.

Aeon Time Series Machine Learning

Provides specialized algorithms and workflows for comprehensive time series analysis, including classification, forecasting, and anomaly detection.

Biomni Biomedical AI

Executes complex autonomous biomedical research tasks across genomics, drug discovery, and clinical analysis using integrated databases and code execution.

SymPy Symbolic Mathematics

Executes exact symbolic mathematics in Python to solve equations, perform calculus, and manipulate algebraic expressions with mathematical precision.

Denario Scientific Research

Automates the end-to-end scientific research lifecycle from data-driven hypothesis generation to the production of publication-ready LaTeX manuscripts.

Scientific Resource Detection

Detects system hardware capabilities and generates strategic recommendations for optimized scientific computing and data processing tasks.

Scientific Hypothesis Generation

Generates and tests scientific hypotheses from observational data and research literature to accelerate empirical discovery and predictive modeling.

ESM Protein Modeling

Generates and designs novel proteins using evolutionary scale language models for sequence, structure, and functional analysis.

SimPy Simulation

Models complex discrete-event systems where entities interact with shared resources over time using process-based Python simulations.

OpenAlex Database

Queries and analyzes millions of scholarly works, authors, and institutions using the OpenAlex API to facilitate comprehensive bibliometric research.

AnnData

Manages and analyzes annotated data matrices for single-cell genomics and large-scale biological datasets in Python.

Cirq Quantum Computing

Designs, simulates, and executes quantum circuits across diverse hardware backends and simulators using Google's open-source framework.

Astropy Astrophysics Toolkit

Facilitates advanced astronomical research and data analysis using Python for coordinate transformations, FITS file manipulation, and cosmological calculations.

PathML Computational Pathology

Analyzes whole-slide pathology images and multiparametric imaging data using advanced machine learning, spatial graph construction, and automated preprocessing pipelines.

scvi-tools Single-Cell Analysis

Analyzes single-cell genomics data using probabilistic deep generative models for tasks like batch correction, cell type annotation, and multi-omic integration.

PyHealth Healthcare AI

Develops, tests, and deploys healthcare-specific machine learning models using clinical data, medical coding systems, and physiological signals.

Data Commons Client

Provides programmatic access to global statistical data, demographics, and economic indicators via the Data Commons knowledge graph.