agentic-flow 1.9.0 → 1.9.2

package/agentic-flow/examples/crispr-cas13-pipeline/docs/mongodb-collections.json

@@ -1,759 +0,0 @@
-{
-  "_schema_version": "1.0.0",
-  "_description": "MongoDB collections for CRISPR-Cas13 genomic data storage",
-  "_database": "crispr_cas13_genomics",
-
-  "collections": {
-    "genomic_sequences": {
-      "description": "Raw genomic sequences and large sequence data",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["sequence_id", "sequence_type", "sequence", "length", "checksum"],
-          "properties": {
-            "sequence_id": {
-              "bsonType": "string",
-              "description": "Unique sequence identifier (UUID)"
-            },
-            "experiment_id": {
-              "bsonType": "string",
-              "description": "Parent experiment UUID (foreign key to PostgreSQL)"
-            },
-            "sequence_type": {
-              "bsonType": "string",
-              "enum": ["genomic_dna", "transcript", "guide_rna", "amplicon", "custom"],
-              "description": "Type of sequence"
-            },
-            "sequence": {
-              "bsonType": "string",
-              "pattern": "^[ACGTN]+$",
-              "description": "DNA sequence (IUPAC nucleotide codes)"
-            },
-            "length": {
-              "bsonType": "int",
-              "minimum": 1,
-              "description": "Sequence length in bp"
-            },
-            "chromosome": {
-              "bsonType": "string",
-              "description": "Chromosome name (e.g., chr1, chrX)"
-            },
-            "start": {
-              "bsonType": "long",
-              "minimum": 1,
-              "description": "Genomic start coordinate (1-based)"
-            },
-            "end": {
-              "bsonType": "long",
-              "minimum": 1,
-              "description": "Genomic end coordinate (inclusive)"
-            },
-            "strand": {
-              "bsonType": "string",
-              "enum": ["+", "-"],
-              "description": "DNA strand"
-            },
-            "gc_content": {
-              "bsonType": "double",
-              "minimum": 0.0,
-              "maximum": 1.0,
-              "description": "GC content fraction"
-            },
-            "repeat_content": {
-              "bsonType": "double",
-              "minimum": 0.0,
-              "maximum": 1.0,
-              "description": "Repetitive element content"
-            },
-            "quality_scores": {
-              "bsonType": "array",
-              "items": {
-                "bsonType": "int"
-              },
-              "description": "Per-base Phred quality scores (optional)"
-            },
-            "checksum": {
-              "bsonType": "string",
-              "description": "MD5 checksum of sequence"
-            },
-            "metadata": {
-              "bsonType": "object",
-              "description": "Additional metadata"
-            },
-            "created_at": {
-              "bsonType": "date",
-              "description": "Creation timestamp"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_sequence_id",
-          "keys": {"sequence_id": 1},
-          "options": {"unique": true}
-        },
-        {
-          "name": "idx_experiment_id",
-          "keys": {"experiment_id": 1}
-        },
-        {
-          "name": "idx_sequence_type",
-          "keys": {"sequence_type": 1}
-        },
-        {
-          "name": "idx_genomic_location",
-          "keys": {"chromosome": 1, "start": 1, "end": 1}
-        },
-        {
-          "name": "idx_checksum",
-          "keys": {"checksum": 1}
-        }
-      ]
-    },
-
-    "read_alignments": {
-      "description": "Individual read alignment records (supplement to BAM files)",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["read_id", "query_name", "reference_name", "position", "mapping_quality", "cigar"],
-          "properties": {
-            "read_id": {
-              "bsonType": "string",
-              "description": "Unique read identifier"
-            },
-            "alignment_id": {
-              "bsonType": "string",
-              "description": "Parent alignment UUID (PostgreSQL foreign key)"
-            },
-            "query_name": {
-              "bsonType": "string",
-              "description": "Read name from FASTQ"
-            },
-            "reference_name": {
-              "bsonType": "string",
-              "description": "Reference sequence name (chromosome/transcript)"
-            },
-            "position": {
-              "bsonType": "long",
-              "minimum": 1,
-              "description": "1-based leftmost mapping position"
-            },
-            "mapping_quality": {
-              "bsonType": "int",
-              "minimum": 0,
-              "maximum": 60,
-              "description": "MAPQ score"
-            },
-            "cigar": {
-              "bsonType": "string",
-              "description": "CIGAR string (e.g., 100M)"
-            },
-            "flag": {
-              "bsonType": "int",
-              "description": "SAM flag (bitwise flags)"
-            },
-            "is_reverse": {
-              "bsonType": "bool",
-              "description": "Read is reverse complemented"
-            },
-            "is_secondary": {
-              "bsonType": "bool",
-              "description": "Secondary alignment"
-            },
-            "is_supplementary": {
-              "bsonType": "bool",
-              "description": "Supplementary alignment"
-            },
-            "is_duplicate": {
-              "bsonType": "bool",
-              "description": "PCR or optical duplicate"
-            },
-            "sequence": {
-              "bsonType": "string",
-              "description": "Read sequence"
-            },
-            "quality": {
-              "bsonType": "string",
-              "description": "Base quality string (ASCII Phred+33)"
-            },
-            "tags": {
-              "bsonType": "object",
-              "description": "SAM optional tags (NH, AS, XS, etc.)",
-              "properties": {
-                "NH": {"bsonType": "int", "description": "Number of reported alignments"},
-                "AS": {"bsonType": "int", "description": "Alignment score"},
-                "XS": {"bsonType": "int", "description": "Suboptimal alignment score"},
-                "NM": {"bsonType": "int", "description": "Edit distance"}
-              }
-            },
-            "mate_reference": {
-              "bsonType": "string",
-              "description": "Mate reference name (paired-end)"
-            },
-            "mate_position": {
-              "bsonType": "long",
-              "description": "Mate position (paired-end)"
-            },
-            "insert_size": {
-              "bsonType": "int",
-              "description": "Template length (paired-end)"
-            },
-            "created_at": {
-              "bsonType": "date"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_read_id",
-          "keys": {"read_id": 1},
-          "options": {"unique": true}
-        },
-        {
-          "name": "idx_alignment_id",
-          "keys": {"alignment_id": 1}
-        },
-        {
-          "name": "idx_query_name",
-          "keys": {"query_name": 1}
-        },
-        {
-          "name": "idx_reference_position",
-          "keys": {"reference_name": 1, "position": 1}
-        },
-        {
-          "name": "idx_mapping_quality",
-          "keys": {"mapping_quality": -1}
-        }
-      ],
-      "sharding": {
-        "enabled": true,
-        "shard_key": {"reference_name": 1, "position": 1},
-        "description": "Shard by genomic location for horizontal scaling"
-      }
-    },
-
-    "expression_matrices": {
-      "description": "Gene/transcript expression quantification",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["matrix_id", "experiment_id", "gene_id", "sample_id", "expression_values"],
-          "properties": {
-            "matrix_id": {
-              "bsonType": "string",
-              "description": "Unique matrix entry ID"
-            },
-            "experiment_id": {
-              "bsonType": "string",
-              "description": "Experiment UUID"
-            },
-            "gene_id": {
-              "bsonType": "string",
-              "description": "Gene identifier (Ensembl/RefSeq)"
-            },
-            "gene_symbol": {
-              "bsonType": "string",
-              "description": "Gene symbol (HGNC/MGI)"
-            },
-            "gene_name": {
-              "bsonType": "string",
-              "description": "Full gene name"
-            },
-            "gene_biotype": {
-              "bsonType": "string",
-              "description": "Gene biotype (protein_coding, lncRNA, etc.)"
-            },
-            "sample_id": {
-              "bsonType": "string",
-              "description": "Sample identifier"
-            },
-            "condition": {
-              "bsonType": "string",
-              "enum": ["control", "treated"],
-              "description": "Experimental condition"
-            },
-            "expression_values": {
-              "bsonType": "object",
-              "required": ["tpm", "read_count"],
-              "properties": {
-                "tpm": {
-                  "bsonType": "double",
-                  "minimum": 0.0,
-                  "description": "Transcripts Per Million"
-                },
-                "fpkm": {
-                  "bsonType": "double",
-                  "minimum": 0.0,
-                  "description": "Fragments Per Kilobase per Million"
-                },
-                "rpkm": {
-                  "bsonType": "double",
-                  "minimum": 0.0,
-                  "description": "Reads Per Kilobase per Million"
-                },
-                "read_count": {
-                  "bsonType": "long",
-                  "minimum": 0,
-                  "description": "Raw read count"
-                },
-                "normalized_count": {
-                  "bsonType": "double",
-                  "description": "Normalized count (DESeq2/edgeR)"
-                }
-              }
-            },
-            "transcript_abundance": {
-              "bsonType": "array",
-              "items": {
-                "bsonType": "object",
-                "properties": {
-                  "transcript_id": {"bsonType": "string"},
-                  "tpm": {"bsonType": "double"},
-                  "read_count": {"bsonType": "long"}
-                }
-              },
-              "description": "Isoform-level expression"
-            },
-            "chromosome": {
-              "bsonType": "string"
-            },
-            "start": {
-              "bsonType": "long"
-            },
-            "end": {
-              "bsonType": "long"
-            },
-            "strand": {
-              "bsonType": "string",
-              "enum": ["+", "-"]
-            },
-            "effective_length": {
-              "bsonType": "int",
-              "description": "Effective transcript length (bp)"
-            },
-            "gc_content": {
-              "bsonType": "double"
-            },
-            "created_at": {
-              "bsonType": "date"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_matrix_id",
-          "keys": {"matrix_id": 1},
-          "options": {"unique": true}
-        },
-        {
-          "name": "idx_experiment_sample",
-          "keys": {"experiment_id": 1, "sample_id": 1}
-        },
-        {
-          "name": "idx_gene_id",
-          "keys": {"gene_id": 1}
-        },
-        {
-          "name": "idx_gene_symbol",
-          "keys": {"gene_symbol": 1}
-        },
-        {
-          "name": "idx_condition",
-          "keys": {"condition": 1}
-        },
-        {
-          "name": "idx_expression_tpm",
-          "keys": {"expression_values.tpm": -1}
-        },
-        {
-          "name": "idx_genomic_location",
-          "keys": {"chromosome": 1, "start": 1}
-        }
-      ]
-    },
-
-    "variant_calls": {
-      "description": "Genetic variants (SNPs, indels) from RNA-seq data",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["variant_id", "experiment_id", "chromosome", "position", "reference", "alternate"],
-          "properties": {
-            "variant_id": {
-              "bsonType": "string",
-              "description": "Unique variant ID"
-            },
-            "experiment_id": {
-              "bsonType": "string"
-            },
-            "chromosome": {
-              "bsonType": "string"
-            },
-            "position": {
-              "bsonType": "long",
-              "minimum": 1,
-              "description": "1-based position"
-            },
-            "reference": {
-              "bsonType": "string",
-              "pattern": "^[ACGTN]+$",
-              "description": "Reference allele"
-            },
-            "alternate": {
-              "bsonType": "array",
-              "items": {
-                "bsonType": "string",
-                "pattern": "^[ACGTN]+$"
-              },
-              "description": "Alternate allele(s)"
-            },
-            "variant_type": {
-              "bsonType": "string",
-              "enum": ["SNP", "insertion", "deletion", "MNP", "complex"],
-              "description": "Variant type"
-            },
-            "quality_score": {
-              "bsonType": "double",
-              "minimum": 0.0,
-              "description": "Phred-scaled quality score"
-            },
-            "filter": {
-              "bsonType": "array",
-              "items": {"bsonType": "string"},
-              "description": "Filter flags (PASS, low_qual, etc.)"
-            },
-            "info": {
-              "bsonType": "object",
-              "description": "VCF INFO fields",
-              "properties": {
-                "DP": {"bsonType": "int", "description": "Total depth"},
-                "AF": {"bsonType": "array", "items": {"bsonType": "double"}, "description": "Allele frequency"},
-                "AC": {"bsonType": "array", "items": {"bsonType": "int"}, "description": "Allele count"},
-                "AN": {"bsonType": "int", "description": "Total allele number"}
-              }
-            },
-            "genotypes": {
-              "bsonType": "array",
-              "items": {
-                "bsonType": "object",
-                "properties": {
-                  "sample_id": {"bsonType": "string"},
-                  "GT": {"bsonType": "string", "description": "Genotype (0/0, 0/1, 1/1)"},
-                  "DP": {"bsonType": "int", "description": "Read depth"},
-                  "AD": {"bsonType": "array", "items": {"bsonType": "int"}, "description": "Allelic depth"},
-                  "GQ": {"bsonType": "int", "description": "Genotype quality"}
-                }
-              }
-            },
-            "annotations": {
-              "bsonType": "object",
-              "properties": {
-                "gene_id": {"bsonType": "string"},
-                "gene_symbol": {"bsonType": "string"},
-                "transcript_id": {"bsonType": "string"},
-                "consequence": {"bsonType": "string", "description": "Variant consequence (VEP)"},
-                "impact": {"bsonType": "string", "enum": ["HIGH", "MODERATE", "LOW", "MODIFIER"]},
-                "codon_change": {"bsonType": "string"},
-                "amino_acid_change": {"bsonType": "string"},
-                "polyphen_prediction": {"bsonType": "string"},
-                "sift_prediction": {"bsonType": "string"}
-              }
-            },
-            "created_at": {
-              "bsonType": "date"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_variant_id",
-          "keys": {"variant_id": 1},
-          "options": {"unique": true}
-        },
-        {
-          "name": "idx_experiment_id",
-          "keys": {"experiment_id": 1}
-        },
-        {
-          "name": "idx_genomic_position",
-          "keys": {"chromosome": 1, "position": 1}
-        },
-        {
-          "name": "idx_variant_type",
-          "keys": {"variant_type": 1}
-        },
-        {
-          "name": "idx_gene_symbol",
-          "keys": {"annotations.gene_symbol": 1}
-        }
-      ]
-    },
-
-    "genome_annotations": {
-      "description": "Gene annotations, exons, transcripts (from GTF/GFF3)",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["annotation_id", "feature_type", "chromosome", "start", "end", "strand"],
-          "properties": {
-            "annotation_id": {
-              "bsonType": "string"
-            },
-            "reference_genome_id": {
-              "bsonType": "string",
-              "description": "Reference genome UUID"
-            },
-            "feature_type": {
-              "bsonType": "string",
-              "enum": ["gene", "transcript", "exon", "CDS", "UTR", "start_codon", "stop_codon"],
-              "description": "Feature type (GTF column 3)"
-            },
-            "chromosome": {
-              "bsonType": "string"
-            },
-            "start": {
-              "bsonType": "long",
-              "minimum": 1
-            },
-            "end": {
-              "bsonType": "long",
-              "minimum": 1
-            },
-            "strand": {
-              "bsonType": "string",
-              "enum": ["+", "-", "."]
-            },
-            "score": {
-              "bsonType": "double",
-              "description": "Feature score (GTF column 6)"
-            },
-            "frame": {
-              "bsonType": "int",
-              "enum": [0, 1, 2],
-              "description": "Reading frame (for CDS)"
-            },
-            "attributes": {
-              "bsonType": "object",
-              "description": "GTF attributes (gene_id, transcript_id, etc.)",
-              "properties": {
-                "gene_id": {"bsonType": "string"},
-                "gene_name": {"bsonType": "string"},
-                "gene_biotype": {"bsonType": "string"},
-                "transcript_id": {"bsonType": "string"},
-                "transcript_name": {"bsonType": "string"},
-                "transcript_biotype": {"bsonType": "string"},
-                "exon_number": {"bsonType": "int"},
-                "protein_id": {"bsonType": "string"}
-              }
-            },
-            "created_at": {
-              "bsonType": "date"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_annotation_id",
-          "keys": {"annotation_id": 1},
-          "options": {"unique": true}
-        },
-        {
-          "name": "idx_reference_genome",
-          "keys": {"reference_genome_id": 1}
-        },
-        {
-          "name": "idx_feature_type",
-          "keys": {"feature_type": 1}
-        },
-        {
-          "name": "idx_genomic_range",
-          "keys": {"chromosome": 1, "start": 1, "end": 1}
-        },
-        {
-          "name": "idx_gene_id",
-          "keys": {"attributes.gene_id": 1}
-        },
-        {
-          "name": "idx_transcript_id",
-          "keys": {"attributes.transcript_id": 1}
-        }
-      ]
-    },
-
-    "sequence_features": {
-      "description": "Custom sequence features (repeat regions, conserved elements, etc.)",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["feature_id", "feature_type", "chromosome", "start", "end"],
-          "properties": {
-            "feature_id": {
-              "bsonType": "string"
-            },
-            "feature_type": {
-              "bsonType": "string",
-              "description": "Feature type (repeat, conservation, regulatory, custom)"
-            },
-            "feature_name": {
-              "bsonType": "string"
-            },
-            "chromosome": {
-              "bsonType": "string"
-            },
-            "start": {
-              "bsonType": "long"
-            },
-            "end": {
-              "bsonType": "long"
-            },
-            "strand": {
-              "bsonType": "string",
-              "enum": ["+", "-", "."]
-            },
-            "score": {
-              "bsonType": "double",
-              "description": "Feature score/confidence"
-            },
-            "source": {
-              "bsonType": "string",
-              "description": "Feature source (RepeatMasker, PhyloP, custom)"
-            },
-            "properties": {
-              "bsonType": "object",
-              "description": "Feature-specific properties"
-            },
-            "created_at": {
-              "bsonType": "date"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_feature_id",
-          "keys": {"feature_id": 1},
-          "options": {"unique": true}
-        },
-        {
-          "name": "idx_feature_type",
-          "keys": {"feature_type": 1}
-        },
-        {
-          "name": "idx_genomic_location",
-          "keys": {"chromosome": 1, "start": 1, "end": 1}
-        }
-      ]
-    },
-
-    "pipeline_metrics": {
-      "description": "Detailed pipeline execution metrics and performance data",
-      "validator": {
-        "$jsonSchema": {
-          "bsonType": "object",
-          "required": ["metric_id", "job_id", "stage", "timestamp"],
-          "properties": {
-            "metric_id": {
-              "bsonType": "string"
-            },
-            "job_id": {
-              "bsonType": "string",
-              "description": "Processing job UUID"
-            },
-            "stage": {
-              "bsonType": "string",
-              "description": "Pipeline stage (qc, alignment, quantification, etc.)"
-            },
-            "timestamp": {
-              "bsonType": "date"
-            },
-            "cpu_percent": {
-              "bsonType": "double",
-              "minimum": 0.0,
-              "maximum": 100.0
-            },
-            "memory_gb": {
-              "bsonType": "double",
-              "minimum": 0.0
-            },
-            "disk_read_mbps": {
-              "bsonType": "double"
-            },
-            "disk_write_mbps": {
-              "bsonType": "double"
-            },
-            "network_recv_mbps": {
-              "bsonType": "double"
-            },
-            "network_sent_mbps": {
-              "bsonType": "double"
-            },
-            "progress_percent": {
-              "bsonType": "double",
-              "minimum": 0.0,
-              "maximum": 100.0
-            },
-            "reads_processed": {
-              "bsonType": "long"
-            },
-            "reads_per_second": {
-              "bsonType": "double"
-            },
-            "custom_metrics": {
-              "bsonType": "object",
-              "description": "Stage-specific metrics"
-            }
-          }
-        }
-      },
-      "indexes": [
-        {
-          "name": "idx_metric_id",
-          "keys": {"metric_id": 1}
-        },
-        {
-          "name": "idx_job_id",
-          "keys": {"job_id": 1}
-        },
-        {
-          "name": "idx_timestamp",
-          "keys": {"timestamp": -1}
-        }
-      ],
-      "time_series": {
-        "enabled": true,
-        "timeField": "timestamp",
-        "metaField": "job_id",
-        "granularity": "seconds",
-        "description": "Use time-series collection for performance metrics"
-      }
-    }
-  },
-
-  "administration": {
-    "backup_strategy": {
-      "frequency": "daily",
-      "retention_days": 30,
-      "method": "mongodump with gzip compression",
-      "s3_bucket": "s3://crispr-pipeline-backups/mongodb/"
-    },
-    "sharding_plan": {
-      "collections_to_shard": ["read_alignments", "expression_matrices"],
-      "shard_key_strategy": "Shard by genomic location (chromosome + position) for optimal query performance"
-    },
-    "monitoring": {
-      "tools": ["MongoDB Atlas", "Prometheus + Grafana"],
-      "alerts": [
-        "Replication lag > 10 seconds",
-        "Storage usage > 80%",
-        "Query response time > 1 second"
-      ]
-    }
-  }
-}