Does it require specific local repositories?

Yes, it requires ApiCommonPresenters and EbrcModelCommon repositories to be present in your curation workspace to function correctly.

What is the primary purpose of this skill?

It automates the complex workflow of preparing and annotating bulk RNA-seq datasets for integration into VEuPathDB genomic resources.

How does the PDF extraction feature work?

If you provide a journal article PDF, the skill uses a subagent to parse the methods and abstract to automatically identify library prep protocols, strandedness, and experimental factors.

What outputs are generated for the data processing team?

It produces analysisConfig.xml and samplesheet.csv files, which are the standard inputs for the VEuPathDB data processing pipeline.

Can it handle GEO-linked datasets?

Yes, the skill includes specialized commands to fetch MINiML metadata for datasets originally submitted to the Gene Expression Omnibus.

Bulk RNA-seq Dataset Curator

Name: Bulk RNA-seq Dataset Curator
Author: VEuPathDB

byVEuPathDB

データサイエンスとML

Automates the end-to-end processing and curation of bulk RNA-seq datasets for VEuPathDB genomic resources.

概要

This skill provides a comprehensive workflow for bioinformatics curators to process bulk RNA-seq datasets within the VEuPathDB ecosystem. It streamlines technical tasks such as fetching metadata from ENA, NCBI BioSample, and GEO, while offering advanced capabilities like extracting experimental context from journal PDFs via subagents. By guiding users through sample analysis, strandedness detection, and contact curation, it ensures the standardized generation of datasetPresenter XML and pipeline configuration files (samplesheets and analysis configs) required for backend data processing.

主な機能

Automated generation of VEuPathDB-specific datasetPresenter XML
Intelligent sample annotation and technical replicate grouping
Standardized pipeline delivery outputs including samplesheet.csv and analysisConfig.xml
Automated metadata retrieval from ENA and NCBI BioSample
0 GitHub stars
Subagent-driven extraction of experimental details from journal PDFs

ユースケース

Generating pipeline-ready configuration files for bioinformatics processing teams
Integrating new RNA-seq BioProjects into VEuPathDB databases like ToxoDB or PlasmoDB
Standardizing metadata for large-scale transcriptomic datasets

概要

主な機能

Automated generation of VEuPathDB-specific datasetPresenter XML
Intelligent sample annotation and technical replicate grouping
Standardized pipeline delivery outputs including samplesheet.csv and analysisConfig.xml
Automated metadata retrieval from ENA and NCBI BioSample
0 GitHub stars
Subagent-driven extraction of experimental details from journal PDFs

ユースケース

Generating pipeline-ready configuration files for bioinformatics processing teams
Integrating new RNA-seq BioProjects into VEuPathDB databases like ToxoDB or PlasmoDB
Standardizing metadata for large-scale transcriptomic datasets