Skills dnanexus-integration
🧬

dnanexus-integration

Safe ⚙️ External commands🌐 Network access

Integrate DNAnexus genomics platform workflows

Also available from: davila7

DNAnexus provides cloud-based genomics analysis but requires platform-specific knowledge. This skill offers complete documentation for building apps, managing data, and running bioinformatics workflows.

Supports: Claude Codex Code(CC)
🥉 73 Bronze
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "dnanexus-integration". How do I upload a FASTQ file and run quality control?

Expected outcome:

  • 1. First authenticate: dx login
  • 2. Upload your file: dx upload sample.fastq --project project-xxxx
  • 3. Find a QC applet: dx find_applets --name '*qc*'
  • 4. Run analysis: dx run applet-xxxx -i reads=file-yyyy
  • 5. Monitor progress: dx watch job-zzzz
  • 6. Download results when complete

Using "dnanexus-integration". Create a simple app that filters reads by quality

Expected outcome:

  • Define dxapp.json with inputSpec for reads file and outputSpec for filtered reads
  • Use @dxpy.entry_point('main') decorator for the main function
  • Download input with dxpy.download_dxfile()
  • Process with subprocess.call() to external tool
  • Upload output with dxpy.upload_local_file()
  • Return result using dxpy.dxlink()

Security Audit

Safe
v4 • 1/17/2026

All 455 static findings are false positives. The skill is documentation for DNAnexus cloud genomics platform. The flagged 'external_commands' are legitimate DNAnexus CLI commands (dx, dxpy) in documentation code blocks. The 'weak cryptographic algorithm' findings incorrectly identified API version fields like 'dxapi: 1.0.0' as cryptographic code. The 'Windows SAM database' alert misidentified authentication documentation (DX_SECURITY_CONTEXT) as Windows system files. No malicious patterns exist.

7
Files scanned
2,858
Lines analyzed
2
findings
4
Total audits
Audited by: claude View Audit History →

Quality Score

45
Architecture
100
Maintainability
85
Content
41
Community
100
Security
83
Spec Compliance

What You Can Build

Process sequencing data pipeline

Upload FASTQ files, run alignment and variant calling workflows, download results for research analysis

Build custom analysis apps

Create DNAnexus apps for specialized genomics analyses with proper input and output handling

Organize genomic datasets

Search, categorize, and manage large genomic datasets across multiple DNAnexus projects

Try These Prompts

Upload and analyze FASTQ
Help me upload a FASTQ file to DNAnexus and run a basic quality control analysis using an existing applet
Create alignment app
I need to create a DNAnexus app that takes FASTQ input and outputs BAM alignment using BWA-MEM
Batch process samples
Show me how to find all FASTQ files in a project and run the same analysis on each in parallel
Configure complex dependencies
Help me configure dxapp.json for an app that needs samtools, bcftools, and a custom Docker image with reference genomes

Best Practices

  • Always validate input files before processing in DNAnexus apps
  • Use appropriate DNAnexus instance types for compute-intensive analyses
  • Include comprehensive error handling and logging in custom apps

Avoid

  • Hardcoding project IDs or file paths in production apps
  • Processing large files without checking available disk space
  • Ignoring DNAnexus job states and error conditions

Frequently Asked Questions

What file formats does DNAnexus support?
DNAnexus supports common genomics formats: FASTQ, BAM, VCF, BED, GFF, and custom formats through file objects
How do I authenticate with DNAnexus?
Use dx login command or set DX_SECURITY_CONTEXT environment variable with your authentication token
Can I run existing command-line tools?
Yes, package them in apps with execDepends or Docker images, then call via subprocess in Python apps
What is the difference between apps and applets?
Applets are project-specific for development. Apps are versioned, shareable executables across projects
How do I handle large datasets efficiently?
Use parallel job execution, appropriate instance types, and consider data locality when designing workflows
Can I integrate with external databases?
Yes, DNAnexus apps have internet access. Use APIs or download reference data during execution