{
  "alzheimer-mouse": {
    "task_name": "Alzheimer Mouse Models: Comparative Pathway Analysis",
    "gold_tools": [
      "DESeq2",
      "edgeR",
      "limma",
      "clusterProfiler",
      "KEGGREST"
    ],
    "gold_servers": [
      "mcp_bioconductor-deseq2",
      "mcp_bioconductor-edger",
      "mcp_bioconductor-limma",
      "mcp_bioconductor-clusterprofiler",
      "mcp_bioconductor-keggrest"
    ],
    "workflow": [
      {
        "name": "load_mouse_count_tables",
        "tool_patterns": [
          "read",
          "csv",
          "count",
          "pandas",
          "data.table"
        ]
      },
      {
        "name": "normalize_and_model_expression",
        "tool_patterns": [
          "deseq",
          "edger",
          "limma",
          "normalize"
        ]
      },
      {
        "name": "run_kegg_pathway_enrichment",
        "tool_patterns": [
          "clusterprofiler",
          "kegg",
          "enrich",
          "pathway"
        ]
      },
      {
        "name": "compare_shared_pathways",
        "tool_patterns": [
          "merge",
          "join",
          "shared",
          "csv",
          "pandas"
        ]
      }
    ]
  },
  "comparative-genomics": {
    "task_name": "Comparative Genomics: Co-evolving Gene Clusters",
    "gold_tools": [
      "OrthoFinder",
      "BLAST",
      "DIAMOND",
      "gffread",
      "seqkit"
    ],
    "gold_servers": [
      "mcp_orthofinder",
      "mcp_blast",
      "mcp_diamond",
      "mcp_gffread",
      "mcp_seqkit"
    ],
    "workflow": [
      {
        "name": "extract_or_prepare_proteomes",
        "tool_patterns": [
          "gffread",
          "seqkit",
          "fasta",
          "faa"
        ]
      },
      {
        "name": "infer_orthogroups",
        "tool_patterns": [
          "orthofinder",
          "orthogroup",
          "blast",
          "diamond"
        ]
      },
      {
        "name": "filter_core_coding_clusters",
        "tool_patterns": [
          "core",
          "present",
          "coding",
          "orthogroup",
          "pandas"
        ]
      },
      {
        "name": "assign_consensus_annotations",
        "tool_patterns": [
          "blast",
          "diamond",
          "kegg",
          "annotation",
          "consensus"
        ]
      }
    ]
  },
  "cystic-fibrosis": {
    "task_name": "Cystic Fibrosis Mendelian Variant Identification",
    "gold_tools": [
      "BWA",
      "samtools",
      "bcftools",
      "GATK",
      "SnpEff",
      "SnpSift"
    ],
    "gold_servers": [
      "mcp_bwa",
      "mcp_samtools",
      "mcp_bcftools",
      "mcp_gatk4",
      "mcp_snpeff",
      "mcp_snpsift"
    ],
    "workflow": [
      {
        "name": "prepare_family_variant_data",
        "tool_patterns": [
          "bwa",
          "samtools",
          "bam",
          "vcf"
        ]
      },
      {
        "name": "call_or_filter_variants",
        "tool_patterns": [
          "bcftools",
          "gatk",
          "variant",
          "filter"
        ]
      },
      {
        "name": "annotate_with_effect_and_clinvar",
        "tool_patterns": [
          "snpeff",
          "snpsift",
          "clinvar",
          "annotation"
        ]
      },
      {
        "name": "apply_recessive_family_filter",
        "tool_patterns": [
          "recessive",
          "affected",
          "family",
          "genotype",
          "pandas"
        ]
      }
    ]
  },
  "deseq": {
    "task_name": "RNA-Seq Differential Expression (DESeq2)",
    "gold_tools": [
      "STAR",
      "HISAT2",
      "featureCounts",
      "Subread",
      "DESeq2",
      "tximport"
    ],
    "gold_servers": [
      "mcp_star",
      "mcp_hisat2",
      "mcp_subread",
      "mcp_bioconductor-rsubread",
      "mcp_bioconductor-deseq2",
      "mcp_bioconductor-tximport"
    ],
    "workflow": [
      {
        "name": "align_rnaseq_reads",
        "tool_patterns": [
          "star",
          "hisat2",
          "align",
          "bam"
        ]
      },
      {
        "name": "count_gene_features",
        "tool_patterns": [
          "featurecounts",
          "subread",
          "count"
        ]
      },
      {
        "name": "differential_expression",
        "tool_patterns": [
          "deseq",
          "edger",
          "limma",
          "log2foldchange"
        ]
      },
      {
        "name": "write_de_results_csv",
        "tool_patterns": [
          "csv",
          "gene_id",
          "padj",
          "pvalue"
        ]
      }
    ]
  },
  "evolution": {
    "task_name": "Experimental Evolution Variant Calling (E. coli)",
    "gold_tools": [
      "BWA",
      "samtools",
      "bcftools",
      "FreeBayes",
      "SnpEff",
      "SnpSift"
    ],
    "gold_servers": [
      "mcp_bwa",
      "mcp_samtools",
      "mcp_bcftools",
      "mcp_freebayes",
      "mcp_snpeff",
      "mcp_snpsift"
    ],
    "workflow": [
      {
        "name": "align_evolved_and_ancestor_reads",
        "tool_patterns": [
          "bwa",
          "samtools",
          "align",
          "bam"
        ]
      },
      {
        "name": "call_variants_per_line",
        "tool_patterns": [
          "bcftools",
          "freebayes",
          "variant",
          "vcf"
        ]
      },
      {
        "name": "annotate_variant_effects",
        "tool_patterns": [
          "snpeff",
          "effect",
          "impact",
          "moderate"
        ]
      },
      {
        "name": "intersect_shared_variants",
        "tool_patterns": [
          "shared",
          "intersect",
          "evolved",
          "pandas"
        ]
      }
    ]
  },
  "giab": {
    "task_name": "GIAB Variant Calling",
    "gold_tools": [
      "BWA",
      "samtools",
      "bcftools",
      "GATK",
      "FreeBayes",
      "VariantAnnotation"
    ],
    "gold_servers": [
      "mcp_bwa",
      "mcp_samtools",
      "mcp_bcftools",
      "mcp_gatk4",
      "mcp_freebayes",
      "mcp_bioconductor-variantannotation"
    ],
    "workflow": [
      {
        "name": "align_exome_reads",
        "tool_patterns": [
          "bwa",
          "samtools",
          "align",
          "bam"
        ]
      },
      {
        "name": "sort_index_and_qc_bam",
        "tool_patterns": [
          "samtools",
          "sort",
          "index",
          "flagstat"
        ]
      },
      {
        "name": "call_germline_variants",
        "tool_patterns": [
          "gatk",
          "bcftools",
          "freebayes",
          "haplotypecaller"
        ]
      },
      {
        "name": "compress_and_index_vcf",
        "tool_patterns": [
          "vcf",
          "bgzip",
          "tabix",
          "index"
        ]
      }
    ]
  },
  "metagenomics": {
    "task_name": "Metagenomics: Community Comparison (Cuatro Cienegas)",
    "gold_tools": [
      "Kraken2",
      "csvtk",
      "pandas"
    ],
    "gold_servers": [
      "mcp_kraken2",
      "mcp_csvtk"
    ],
    "workflow": [
      {
        "name": "classify_paired_reads",
        "tool_patterns": [
          "kraken2",
          "classify",
          "paired",
          "fastq"
        ]
      },
      {
        "name": "parse_kraken_reports",
        "tool_patterns": [
          "report",
          "taxonomy",
          "taxid",
          "phylum"
        ]
      },
      {
        "name": "compute_bacterial_phylum_relative_abundance",
        "tool_patterns": [
          "bacteria",
          "phylum",
          "relative",
          "abundance"
        ]
      },
      {
        "name": "write_phylum_abundance_csv",
        "tool_patterns": [
          "csv",
          "OTU",
          "Kingdom",
          "Phylum",
          "JP4D",
          "JC1A"
        ]
      }
    ]
  },
  "single-cell": {
    "task_name": "Single-cell RNA-seq: Skeletal Muscle Exercise Response",
    "gold_tools": [
      "Scanpy",
      "Seurat",
      "CellTypist"
    ],
    "gold_servers": [
      "mcp_scanpy",
      "mcp_scanpy-cli",
      "mcp_scanpy-scripts",
      "mcp_seurat-scripts",
      "mcp_celltypist"
    ],
    "workflow": [
      {
        "name": "load_single_cell_matrix",
        "tool_patterns": [
          "scanpy",
          "read_h5ad",
          "h5ad",
          "matrix"
        ]
      },
      {
        "name": "normalize_cluster_and_embed",
        "tool_patterns": [
          "normalize",
          "neighbors",
          "leiden",
          "umap",
          "scanpy"
        ]
      },
      {
        "name": "annotate_cell_types",
        "tool_patterns": [
          "celltypist",
          "marker",
          "annotation",
          "cell_type"
        ]
      },
      {
        "name": "differential_expression_by_condition",
        "tool_patterns": [
          "rank_genes",
          "differential",
          "exercise",
          "wilcoxon"
        ]
      }
    ]
  },
  "transcript-quant": {
    "task_name": "Transcript Quantification (Simulated RNA-Seq)",
    "gold_tools": [
      "Kallisto",
      "Salmon"
    ],
    "gold_servers": [
      "mcp_kallisto",
      "mcp_salmon"
    ],
    "workflow": [
      {
        "name": "build_transcriptome_index",
        "tool_patterns": [
          "kallisto_index",
          "salmon",
          "index",
          "transcriptome"
        ]
      },
      {
        "name": "quantify_paired_end_reads",
        "tool_patterns": [
          "kallisto_quant",
          "salmon",
          "quant",
          "paired"
        ]
      },
      {
        "name": "extract_transcript_counts",
        "tool_patterns": [
          "abundance",
          "est_counts",
          "count",
          "transcript_id"
        ]
      },
      {
        "name": "write_no_header_tsv",
        "tool_patterns": [
          "tsv",
          "transcript_id",
          "count"
        ]
      }
    ]
  },
  "viral-metagenomics": {
    "task_name": "Viral Metagenomics: Species Identification (Dolphin)",
    "gold_tools": [
      "MEGAHIT",
      "SPAdes",
      "Kaiju",
      "fastp",
      "BLAST"
    ],
    "gold_servers": [
      "mcp_megahit",
      "mcp_spades",
      "mcp_kaiju",
      "mcp_fastp",
      "mcp_blast"
    ],
    "workflow": [
      {
        "name": "assemble_viral_metagenomic_contigs",
        "tool_patterns": [
          "megahit",
          "spades",
          "assembly",
          "contig"
        ]
      },
      {
        "name": "classify_contigs_taxonomically",
        "tool_patterns": [
          "kaiju",
          "blast",
          "taxonomy",
          "virus"
        ]
      },
      {
        "name": "resolve_taxon_names",
        "tool_patterns": [
          "names",
          "nodes",
          "taxon",
          "species"
        ]
      },
      {
        "name": "summarize_contig_counts_by_species",
        "tool_patterns": [
          "species",
          "contig_count",
          "domain",
          "csv"
        ]
      }
    ]
  }
}