Skills
Setup reproducible bioinformatics environments for ENCODE
This skill provisions fully reproducible, version-pinned conda environments and associated scripts for comprehensive ENCODE data analysis. It manages dependencies across multiple modalities (RNA-seq, ChIP-seq, ATAC-seq) using tools like STA…
Aggregate comprehensive open chromatin accessibility maps
This skill builds a comprehensive union map of open chromatin regions by aggregating and merging ATAC-seq and DNase-seq narrowPeak data across multiple ENCODE experiments. It handles cross-platform variation, applies necessary filtering (su…
ENCODE experiment tracking and provenance management
Track and manage local collections of ENCODE experiments, including metadata, publications, and data provenance. It supports experiment comparison, citation management, and exporting datasets to CSV, TSV, or JSON formats.
Visualize ENCODE genomic data for publication
This skill facilitates the creation of publication-quality visualizations of ENCODE genomic data, covering deepTools heatmaps, signal profiles, and interactive IGV browser views. It guides users through advanced techniques like computeMatri…
annotate non-coding variants using encode data
This skill interprets non-coding genetic variation by layering ENCODE functional genomics annotations (e.g., cCREs, enhancers) onto variant sets. It supports the full post-GWAS workflow, including tissue-specific mapping, fine-mapping, and …
ENCODE Single-Cell Genomics Data Analysis Guide
This skill guides the retrieval and analysis of single-cell genomics data (scRNA-seq and scATAC-seq) from ENCODE. It covers data structure, quality control metrics, and best practices for integrating single-cell profiles with bulk epigenomi…
Searching and Exploring ENCODE Genomics Data
Provides a structured strategy for searching and exploring ENCODE Project genomics data using facets and metadata. It facilitates the discovery of experiments, files, and specific biological parameters like assays, organs, and cell lines.
Configure and connect to ENCODE Project data
This skill guides users through the installation, configuration, and authentication process for the ENCODE Toolkit MCP server. It ensures the local environment is correctly connected to the ENCODE Project genomics database for subsequent da…
Cross-study scRNA-seq meta-analysis and integration
This skill integrates multiple single-cell RNA-seq datasets from different sources into a unified cell atlas. It performs rigorous meta-analysis, accounting for technical biases such as batch effects, ambient RNA contamination, and detectio…
Characterise Regulatory Elements with ENCODE Data
Identify and characterise candidate cis-regulatory elements using ENCODE datasets and the cCRE catalog. The skill enables the discovery of active enhancers, promoter state mapping, and super-enhancer identification using ChromHMM and ROSE.
Generate scientific text from ENCODE provenance
This skill auto-generates publication-ready scientific documentation, including methods sections and figure legends, by rigorously compiling experimental and computational metadata from ENCODE provenance records. It ensures adherence to hig…
Assess ENCODE experiment quality metrics and flags
This skill guides the rigorous assessment of ENCODE data quality by interpreting standard metrics (e.g., FRiP, NSC, IDR) and analysing audit flags. It provides context on determining data reliability across various assays and biological sys…
Scientific Publication Trust Assessment
Evaluates the scientific integrity and reliability of research publications by checking for retractions, errata, and independent contradictions. It integrates with PubMed, bioRxiv, and Consensus to assess trust levels based on formal marker…
WGBS Pipeline: FASTQ to Methylation Calling
Executes the full ENCODE Whole Genome Bisulfite Sequencing pipeline, processing paired-end FASTQ files through alignment, deduplication, and methylation extraction. It generates comprehensive per-CpG methylation levels in the standard bedMe…
ENCODE Hi-C Processing Pipeline
Executes the ENCODE Hi-C pipeline using Nextflow to transform FASTQ files into multi-resolution contact matrices and loop calls. The pipeline supports local, SLURM, and cloud-based deployments via Docker.
ENCODE Pipeline Workflow Generation and Management
This skill facilitates the generation and execution of complex ENCODE bioinformatics workflows, supporting custom Nextflow and WDL pipelines. It manages compute resource requirements and deployment across local, HPC, and major cloud platfor…
CUT and CUT Processing Pipeline
Executes a Nextflow-based pipeline for processing CUT and CUT data from FASTQ files to peaks and signal tracks. The workflow incorporates spike-in normalisation and SEACR peak calling for high-resolution chromatin profiling.
DNase-seq pipeline for accessibility and footprints
Executes a comprehensive DNase-seq workflow, processing paired-end FASTQ reads to identify DNase hypersensitive sites (DHSs) and perform transcription factor footprinting. The pipeline leverages Nextflow to manage alignment, peak calling vi…
MediaWiki content search, reading, and analysis
This skill provides comprehensive access to MediaWiki content, allowing agents to search, read, and analyze pages. It supports advanced operations including tracking revisions, checking link quality, and exploring the wiki's structural rela…
ENCODE ChIP-seq Processing Pipeline
This Nextflow-based pipeline executes the complete ENCODE ChIP-seq processing workflow, transforming raw FASTQ files into peaks and signal tracks. It handles quality control, alignment, peak calling with MACS2, and IDR analysis using Docker…
MediaWiki Page Editing and Management
Provides capabilities for automated MediaWiki page editing, including text replacement, formatting, and bulk updates. It implements a preview-before-save workflow to ensure safe content modification.
Annotating Peaks and Functional Enrichment of Genomics
This skill annotates ENCODE peaks by classifying them into specific genomic features (e.g., promoter, intron) using ChIPseeker, and subsequently determines their biological relevance and pathway enrichment using GREAT. It facilitates compre…
Publish Markdown to MediaWiki
Converts markdown files to wikitext and publishes them to a MediaWiki instance using the wiki CLI. The skill supports previewing changes, managing edit summaries, and applying specific themes.
Integrate multi-omics for regulatory landscape
This skill integrates diverse ENCODE datasets, including RNA-seq, ATAC-seq, and various ChIP-seq assays, to construct a comprehensive regulatory landscape. It allows users to map cell-type-specific regulatory elements by correlating gene ex…