3. Data, Science & AI

Integrates with Benchling R&D platform to automate lab data management via API, including DNA/protein registry, inventory, and ELN workflows.

Enables comprehensive spreadsheet creation, editing, analysis, and visualization with formula support across multiple formats including XLSX and CSV.

Standard pipeline for single-cell RNA-seq analysis including QC, normalization, dimensionality reduction, clustering, and visualization.

A Python framework implementing NSGA-II, MOEA/D, and Pareto front algorithms for engineering design and scientific optimization problems.

Processes and generates multimedia content including audio, images, videos, and documents using Google Gemini API for enhanced vision and multimodal capabilities.

Accesses RCSB PDB for searching, downloading, and retrieving 3D protein/nucleic acid structural data to support research and drug discovery.

Provides AI-ready drug discovery datasets including ADME, toxicity, and DTI with benchmarks and molecular oracles for therapeutic ML prediction.

Query PubChem database for chemical compounds, properties, and bioactivity via PUG-REST API or PubChemPy.

Python library for reading, writing, and processing DICOM medical imaging files, including metadata extraction and anonymization.

Enables ML analysis of genomic interval data (BED files, scATAC-seq) for region embeddings, consensus peaks, and chromatin accessibility feature learning.

Packages code repositories into AI-optimized files with customizable patterns, preserving structure for efficient AI analysis and documentation.

Queries NHGRI-EBI GWAS Catalog for SNP-trait associations, p-values, and summary statistics to support genetic epidemiology and polygenic risk score research.

Generates publication-quality scientific figures with journal-specific formatting, multi-panel layouts, significance annotations, and colorblind-safe palettes using matplotlib, seaborn, and plotly.

Manages persistent storage and retrieval of user-defined patterns, decisions, and learnings across AI sessions for context continuity.

Quantum physics simulation library for open quantum systems, supporting master equations, Lindblad dynamics, and quantum optics research and education.

Comprehensive toolkit for building, testing, and deploying AI models using clinical data, EHR, and healthcare datasets for prediction tasks.

Manages Claude's learned patterns, enabling listing, viewing, archiving, and confidence adjustment for effectiveness review and library management.

Performs UMAP dimensionality reduction for visualizing high-dimensional data in 2D/3D, enabling clustering and preprocessing for machine learning workflows.

Provides machine learning capabilities including classification, regression, clustering, and model evaluation using scikit-learn in Python.

Manages biological datasets (scRNA-seq, spatial) with FAIR principles, ensuring traceability, reproducibility, and integration with workflow/MLOps tools.

Queries ClinicalTrials.gov API to search and retrieve clinical trial data by condition, drug, location, and phase for research and patient matching.

Tool for metabolomics spectral matching, computing similarity scores (cosine, modified cosine), and identifying compounds from spectral libraries.

Provides comprehensive drug data access and analysis from DrugBank for pharmacology research and drug discovery.

Provides real-time AI-powered web searches using Perplexity models via LiteLLM and OpenRouter, delivering grounded answers with source citations for current information and scientific literature.