3. Data, Science & AI

Provides a checklist reference for single-cell RNA-seq downstream analysis including AUCell scoring and metacell differential expression using OmicVerse.

Guides users in utilizing OmicVerse's visualization tools for bulk and single-cell omics data, featuring venn/volcano charts and palette selection.

Executes gene set enrichment analysis (GSEA) with proper gene set formatting and pathway database integration for OmicVerse.

Exports data analysis results and tables to Excel format using openpyxl, compatible with any LLM provider.

Analyzes protein-protein interactions by querying STRING database, building PPI graphs with pyPPI, and generating styled network visualizations for gene lists.

Infers ligand-receptor communication networks from single-cell RNA-seq data using CellPhoneDB v5 and generates CellChat-style visualizations.

Creates publication-quality data visualizations using matplotlib and seaborn, compatible with any LLM provider for seamless integration.

Generates intermediate cells for scRNA-seq developmental trajectories using bulk RNA-seq data and AI models (beta-VAE, GNN) for trajectory interpolation.

Guides single-cell RNA-seq data preprocessing with OmicVerse, covering QC, normalization, HVG detection, and dimensionality reduction across CPU/GPU configurations.

Quick-reference guide for OmicVerse tutorials on multi-omics integration techniques including MOFA, SIMBA, and TOSICA for single-cell data analysis.

Transforms, cleans, and reshapes data using pandas and numpy, compatible with any LLM provider for AI/ML pipelines.

Executes bulk RNA-seq differential expression analysis with PyDESeq2, including ID mapping, DE testing, fold-change thresholding, and enrichment visualization.

Guides AI-powered annotation workflows for single-cell omics data using tools like CellVote, GPTAnno, and weighted KNN transfer.

Guides execution of single-cell clustering and batch correction via omicverse, covering preprocessing, QC, multimethod clustering, and cross-batch integration.

Step-by-step guide for reproducing single-cell trajectory analysis workflows with OmicVerse, including PAGA, Palantir, VIA, and fate scoring.

Corrects batch effects in bulk RNA-seq and microarray data using ComBat, exports matrices, and benchmarks visualizations.

Runs bulk WGCNA analysis via omicverse: preprocesses expression matrices, constructs co-expression modules, visualizes eigengenes, and extracts hub genes.

Guides users through omicverse's spatial transcriptomics tutorials for preprocessing, deconvolution, and modeling across Visium, Visium HD, Stereo-seq, and Slide-seq datasets.

AI-powered CLI for visual content analysis, web search, markdown page extraction, and GitHub code exploration using GLM-4.6V and TypeScript tool chains.

Provides benchmarking and performance analysis for PDF parsing operations.

Optimizes PyTorch inference, Transformers model deployment, and FastAPI serving through device management and memory efficiency best practices.

Provides RAG best practices for LlamaIndex, ChromaDB, and Celery, covering ingestion, retrieval, embeddings, and performance optimization.

Best practices for LlamaFarm's common utilities package, covering HuggingFace Hub integration and GGUF model management.

Extracts raw price data in DataFrame format for testing in data science pipelines.