데이터·AI 스킬

Process molecular datasets in Python through a simpler interface to RDKit, a chemistry toolkit. Convert and standardize structures, calculate molecular properties, compare and cluster compounds, generate 3D conformations, and visualize results for drug discovery workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Load and standardize molecular datasets
• Calculate molecular properties and similarities
• Cluster compounds and select diverse subsets

Prepare genomic interval data for machine learning by checking BED files, reference genome consistency, and model compatibility. Plan Region2Vec or scEmbed workflows and assess shared reference regions using local validation and planning helpers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check BED coordinates and reference genome consistency
• Plan Region2Vec or scEmbed training
• Inspect model and tokenizer compatibility

Organize single-cell measurements with cell and gene metadata, read and write h5ad or Zarr files, and prepare subsets or combined datasets. Includes guidance on handling large annotated matrices without loading all measurement values into memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Read and write h5ad or Zarr datasets
• Combine experimental batches with source labels
• Select cells or genes using metadata

Analyze DepMap cancer model data to rank genes required for cell survival, compare groups defined by biological markers, and explore drug responses. Release tracking and statistical checks help organize evidence for research hypotheses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Ranking gene dependencies in cancer models
• Comparing groups defined by biological markers
• Finding genes with similar dependency patterns

Use Dask to process tables, numerical arrays, and file collections in pieces across CPU cores or machines. Helps choose data structures, size memory-friendly chunks, coordinate dependent tasks, and diagnose slow or memory-heavy workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Aggregate CSV or Parquet files that exceed available memory
• Process large scientific arrays in chunks
• Clean JSON records and logs before analysis

Manage scientific datasets with DataLad and git-annex, which tracks large files separately from Git history. Retrieve selected data, record analysis commands and their inputs and outputs, rerun recorded work, and publish history alongside file content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieve only the research data you need
• Resolve files that contain pointers instead of data
• Record and rerun analysis steps

Query public single-cell and spatial gene expression data by tissue, disease, or cell type. Retrieve selected expression values, cell metadata, and summary counts for analysis and comparisons across datasets without first downloading entire collections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore cell types within a tissue
• Retrieve expression values for selected marker genes
• Compare cells across tissues and datasets

Retrieve and combine protein annotations, biological pathways, and chemical identifiers from services such as UniProt, KEGG, and UniChem using Python. Supports cross-database lookups and batch identifier conversion while preserving multiple matches and failed requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Collect protein sequences and functional annotations
• Retrieve pathway information for genes
• Match compound identifiers across databases

Rank possible gene regulatory relationships from bulk or single-cell expression data using GRNBoost2 or GENIE3. The skill guides input preparation, compatible execution, method comparison, and stability checks to help prioritize candidates for further biological investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Rank candidate regulator–target gene relationships
• Compare GRNBoost2 and GENIE3 results
• Check network stability across seeds and resampled data

Convert genomic positions between file conventions, standardize variant representations, and check reference genome or chromosome naming conflicts. The skill helps investigate one-base shifts and compare individual variants against a reference sequence before combining analysis files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting coordinates between BED and GFF/GTF
• Standardizing and comparing insertion or deletion records
• Checking reference genome and chromosome naming conflicts

Use Biohub’s Python SDK to complete protein sequences with ESM3, extract numerical sequence representations with ESMC, and predict all-atom structures with ESMFold2. The skill guides local or hosted inference, input validation, and output checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Completing masked positions in protein sequences
• Extracting numerical features from protein sequences
• Predicting all-atom protein structures

Prepare bulk RNA-seq sequencing files or quantification outputs for gene-level comparisons. Check sample information and data quality, configure processing workflows, and assemble validated count tables and metadata for downstream differential expression analysis with PyDESeq2.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing gene count tables from FASTQ files
• Configuring an nf-core/rnaseq workflow
• Combining Salmon, STAR, or featureCounts outputs

Build molecular property prediction workflows with DeepChem for solubility, toxicity, and related chemistry tasks. Prepare molecular representations, choose compatible models, handle missing labels, and evaluate predictions using data splits designed for the intended scientific question.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Predicting solubility from molecular structures
• Comparing graph models on MoleculeNet datasets
• Checking data splits for information leakage

Implement and debug astronomical data analysis with Astropy in Python. Work with physical units, celestial coordinates, observation files, tables, precise time conversions, and cosmological models to prepare data and calculate astronomical quantities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert celestial coordinates and physical units
• Read and edit FITS observation files
• Match objects across astronomical catalogs

Predict spatial gene expression from H&E-stained tissue images using DeepSpot-M. Query a released panel of about 19,000 genes and combine predictions from small image tiles into slide-wide maps for research analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping predicted marker-gene expression across a tumor section
• Predicting expression across slides without matching gene-expression assays
• Adding predicted expression to a histology image analysis pipeline

Consult bundled technical documentation to understand and integrate Hindsight, a memory system for AI agents. Find guidance on storing and retrieving memories, API calls, configuration, deployment, SDKs, troubleshooting, and performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning how memory storage and retrieval work
• Checking API endpoints and request parameters
• Planning server setup and SDK integration

Plan how an AI application should use Hindsight memory. Identify useful information to retain, define user-scoping tags and memory bank settings, and specify how retrieved facts and synthesized knowledge should reach the model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan memory that carries conversation context across sessions
• Design tags that separate each user's memories
• Plan summaries of customer preferences and recurring issues

Check a Bot’s connection to Hindsight and set up dedicated and shared memory stores. The skill also creates a user knowledge summary when needed and reports which other memory stores are available to read.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up Hindsight for a Bot’s first use
• Checking the connection after a memory tool fails
• Separating project memories from shared knowledge

Develop AxonX plugins and manage quantitative finance research through the command line or MCP, an agent connection interface. Track data preparation, training, prediction, and historical strategy tests using execution status, logs, artifacts, and dependencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Develop research plugins with defined inputs and outputs
• Run data preparation, training, prediction, and backtests
• Investigate failed tasks through status and logs

Build Python AI applications on Microsoft Foundry with azure-ai-projects. Provides examples for creating agents, connecting tools, managing conversations and project resources, and running evaluations through Foundry and OpenAI-compatible clients.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an agent that searches uploaded documents
• Implement conversation threads and response handling
• List model deployments and project connections

Create and manage persistent Azure AI agents from Java. Covers conversation threads that retain messages, agent execution, status checks, response retrieval, and cleanup, using preview SDK examples with guidance on authentication and cloud resource handling.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a Java app with reusable AI agents
• Managing conversation threads and messages
• Checking execution states and handling timeouts

Implement .NET workflows for Azure AI Foundry projects, including agent creation, resource connections, dataset uploads, model deployment inspection, search index management, and evaluations. Examples also cover authentication, asynchronous operations, and resource cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating and running agents from a .NET application
• Inspecting resource connections and model deployments
• Uploading datasets and managing search indexes

Build Python features that identify a speaker’s intent and extract details such as names from conversation text using Azure. Get guidance on request structure, authentication, client cleanup, and exception handling.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding intent detection to a Python application
• Extracting names and other details from conversation text
• Structuring requests for ConversationAnalysisClient

Manage Azure Machine Learning resources from Python with SDK v2. The skill provides implementation examples for registering data and models, configuring compute and environments, submitting training jobs, monitoring logs, and connecting steps into pipelines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Submitting training jobs and monitoring logs
• Registering data and model versions
• Connecting preprocessing and training steps