bioinformatics

Bioinformatics

Part of Agent Skills™ by googleadsagent.ai™

Description

Bioinformatics provides computational biology workflows for sequence analysis, protein structure prediction, single-cell RNA-seq with Scanpy, gene regulatory network inference, and pathway enrichment analysis. The agent generates reproducible analysis pipelines using BioPython, Scanpy, and standard bioinformatics tools, following community best practices for each analysis type.

Modern biology generates data faster than biologists can analyze it. A single-cell RNA-seq experiment produces expression profiles for tens of thousands of cells, each with thousands of genes measured. This skill encodes the standard analysis pipelines that transform raw sequencing data into biological insights: quality control, normalization, dimensionality reduction, clustering, differential expression, and pathway enrichment.

The skill extends beyond transcriptomics to genomics (variant calling, annotation), proteomics (sequence analysis, domain prediction), and systems biology (gene regulatory networks, protein-protein interactions). Each pipeline is parameterized, documented, and reproducible—the same inputs always produce the same outputs.

Use When

• Analyzing single-cell RNA-seq data with Scanpy
• Performing sequence alignment or homology searches
• Building gene regulatory network models
• Running pathway enrichment analysis (GO, KEGG)
• Processing FASTA/FASTQ files with BioPython
• Predicting protein structure or function from sequence

How It Works

graph TD
    A[Raw Sequencing Data] --> B[Quality Control]
    B --> C[Alignment / Quantification]
    C --> D{Analysis Type}
    D -->|Single-Cell| E[Scanpy Pipeline]
    D -->|Bulk RNA-seq| F[DESeq2 / edgeR]
    D -->|Genomics| G[Variant Calling]
    E --> H[Normalize → PCA → UMAP → Cluster]
    H --> I[Differential Expression]
    I --> J[Pathway Enrichment]
    F --> I
    G --> K[Annotation + Impact Prediction]
    J --> L[Biological Interpretation]
    K --> L