Dados e Análise

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

Crie aplicações de IA com o SDK Python do Azure AI Projects (azure-ai-projects), ideal para clientes Foundry, criação de agentes versionados, avaliações, gerenciamento de recursos e uso de clientes compatíveis com OpenAI. Para operações de agente de baixo nível, use a skill azure-ai-agents-python.

Esta skill infere redes reguladoras de genes (GRNs) a partir de dados de expressão gênica usando algoritmos escaláveis como GRNBoost2 e GENIE3. É ideal para analisar dados transcriptômicos (RNA-seq em massa e de célula única) para identificar relações entre fatores de transcrição e genes-alvo, suportando computação distribuída para grandes conjuntos de dados.

Security patterns for session keys, caching, logging, and environment variables. Use when implementing authentication, caching sensitive data, or setting up logging. Triggers on: session key, private key, cache, logging, secrets, environment variable.

Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.

Call protein-RNA binding site peaks from CLIP-seq data using CLIPper, PureCLIP, or Piranha. Use when identifying RBP binding sites from aligned CLIP reads.

Analise e otimize consultas SQL para melhor desempenho e eficiência.

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

Single-cell ATAC-seq analysis with Signac (R/Seurat) and ArchR. Process 10X Genomics scATAC data, perform QC, dimensionality reduction, clustering, peak calling, and motif activity scoring with chromVAR. Use when analyzing single-cell ATAC-seq data.

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

Query openFDA REST API for adverse events (FAERS), labeling, product info, recalls, enforcement. Search by drug name, ingredient, MedDRA, or NDC. 1k req/day no key; 120k with free key. For trials use clinicaltrials-database-search; for structures use drugbank-database-access or chembl-database-bioactivity.

Detect A/B compartments from Hi-C data using cooltools and eigenvector decomposition. Identify active (A) and inactive (B) chromatin compartments from contact matrices. Use when identifying A/B compartments from Hi-C data.