{
 "about": {
  "generatedBy": "pipeline/plasmid-map/reference.py",
  "scriptSha256": "a03bc1a9b73fbe37a56280a6e4f5ac28e5cc7e0c7d1c8ba1d2d627445d8c090b",
  "recordedOn": "2026-10-06",
  "oracle": "Biopython 1.88",
  "oracleLicence": "Biopython Licence Agreement or BSD-3-Clause",
  "text": "dam and dcm outcomes worked by hand from McClelland, Nelson and Raschke 1994, Table I (Nucleic Acids Res 22:3640-3659), one case per outcome, with a flank overlap, an overlap across the origin of a circle, a hemimethylated and a fully methylated site, the host toggles and DpnI; `marks` is this script's own scan of the sequence, a check on the reasoning. Site counts for the plasmid cases from Biopython's search.",
  "source": "McClelland M, Nelson M, Raschke E. Nucleic Acids Res 1994;22:3640-3659, doi 10.1093/nar/22.17.3640"
 },
 "cases": [
  {
   "id": "M01",
   "enzyme": "XbaI",
   "sequence": "AAATCTAGAAAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "cut"
   },
   "reasoning": "No GATC or CCWGG overlaps TCTAGA: no methylated base on the site.",
   "marks": []
  },
  {
   "id": "M02",
   "enzyme": "XbaI",
   "sequence": "AATCTAGATCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "GATC reaches from the site into its right flank (TCTAGATC): dam's m6A falls on the site's sixth base, top strand; Table I p. 3654 lists TCTAGm6A as not cut.",
   "marks": [
    [
     8,
     "top"
    ],
    [
     9,
     "bottom"
    ]
   ]
  },
  {
   "id": "M03",
   "enzyme": "XbaI",
   "sequence": "AAGATCTAGAAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "GATC reaches from the left flank (GATCTAGA): the bottom strand's m6A sits opposite the site's first base, which is the sixth base of the site read on that strand (a palindrome); TCTAGm6A, p. 3654, not cut.",
   "marks": [
    [
     4,
     "top"
    ],
    [
     5,
     "bottom"
    ]
   ]
  },
  {
   "id": "M04",
   "enzyme": "BamHI",
   "sequence": "AAGGATCCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-blocked"
   },
   "reasoning": "GATC lies inside GGATCC: m6A on the third base of both strands; Table I p. 3647 lists GGm6ATCC as cut.",
   "marks": [
    [
     5,
     "top"
    ],
    [
     6,
     "bottom"
    ]
   ]
  },
  {
   "id": "M05",
   "enzyme": "BsaWI",
   "sequence": "TACCGGATCT",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-recorded"
   },
   "reasoning": "GATC reaches into the right flank of ACCGGA: m6A on the site's sixth base; Table I p. 3648 lists only WCm5CGGW for BsaWI, so this mark is not recorded.",
   "marks": [
    [
     7,
     "top"
    ],
    [
     8,
     "bottom"
    ]
   ]
  },
  {
   "id": "M06",
   "enzyme": "AhdI",
   "sequence": "TTGACGATCAGTCTT",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-recorded"
   },
   "reasoning": "GATC inside GACGATCAGTC's N region: AhdI is not in Table I.",
   "marks": [
    [
     7,
     "top"
    ],
    [
     8,
     "bottom"
    ]
   ]
  },
  {
   "id": "M07",
   "enzyme": "EcoRII",
   "sequence": "AACCAGGAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "CCAGG is both the site and dcm's motif: m5C on the second base of both strands; Table I p. 3650 lists Cm5CWGG as not cut (the cited dcm-blocked example).",
   "marks": [
    [
     4,
     "top"
    ],
    [
     6,
     "bottom"
    ]
   ]
  },
  {
   "id": "M08",
   "enzyme": "BstNI",
   "sequence": "AACCTGGAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-blocked"
   },
   "reasoning": "dcm's m5C on the second base of CCTGG, both strands; Table I p. 3649 lists Cm5CWGG as cut by BstNI.",
   "marks": [
    [
     4,
     "top"
    ],
    [
     6,
     "bottom"
    ]
   ]
  },
  {
   "id": "M09",
   "enzyme": "StuI",
   "sequence": "AAGGCCTGGA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "CCTGG reaches from AGGCCT into its right flank: m5C on the site's fifth base, top strand only; Table I p. 3653 lists AGGCm5CT as not cut.",
   "marks": [
    [
     6,
     "top"
    ],
    [
     8,
     "bottom"
    ]
   ]
  },
  {
   "id": "M10",
   "enzyme": "XbaI",
   "sequence": "AGATCGGGGGGGGGGGGTCT",
   "circular": true,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "On the circle, TCTAGA crosses the origin (bases 18 to 3) and GATC (bases 2 to 5) falls on its last two bases: m6A on the site's sixth base; TCTAGm6A, p. 3654.",
   "marks": [
    [
     3,
     "top"
    ],
    [
     4,
     "bottom"
    ]
   ]
  },
  {
   "id": "M11",
   "enzyme": "BglI",
   "sequence": "AAGCCAGGTTGGCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-recorded"
   },
   "reasoning": "CCAGG inside GCCAGGTTGGC puts m5C on the site's third base (top) and opposite its fifth (bottom), the seventh read on the bottom strand; Table I p. 3648 lists GCm5CN5GGC as cut but with its slow-cleavage note, and nothing for the seventh base.",
   "marks": [
    [
     5,
     "top"
    ],
    [
     7,
     "bottom"
    ]
   ]
  },
  {
   "id": "M12",
   "enzyme": "DpnI",
   "sequence": "AAGATCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "cuts-methylated"
   },
   "reasoning": "dam methylates GATC on both strands; Table I p. 3649 lists Gm6ATC as cut by DpnI and GATC as not cut, and its note says DpnI requires adenine methylation on both strands.",
   "marks": [
    [
     4,
     "top"
    ],
    [
     5,
     "bottom"
    ]
   ]
  },
  {
   "id": "M13",
   "enzyme": "DpnI",
   "sequence": "AAGATCAA",
   "circular": false,
   "host": {
    "dam": false,
    "dcm": false
   },
   "expected": {
    "outcome": "uncut-unmethylated"
   },
   "reasoning": "Unmethylated DNA (a PCR product): DpnI does not cut GATC (Table I p. 3649).",
   "marks": []
  },
  {
   "id": "M14",
   "enzyme": "XbaI",
   "sequence": "AATCTAGATCAA",
   "circular": false,
   "host": {
    "dam": false,
    "dcm": true
   },
   "expected": {
    "outcome": "cut"
   },
   "reasoning": "The M02 sequence from a host without dam: no methylated base on the site.",
   "marks": []
  },
  {
   "id": "M15",
   "enzyme": "KpnI",
   "sequence": "AAGGTACCTGGA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-recorded"
   },
   "reasoning": "CCTGG reaches from GGTACC into its right flank: m5C on the site's sixth base, top strand only (hemimethylated); Table I p. 3651 lists GGTACm5C as cut, but its note says KpnI cuts hemimethylated GGTACm5C slowly.",
   "marks": [
    [
     8,
     "top"
    ],
    [
     10,
     "bottom"
    ]
   ]
  },
  {
   "id": "M16",
   "enzyme": "KpnI",
   "sequence": "CCAGGTACCTGG",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-blocked"
   },
   "reasoning": "CCWGG on both sides of GGTACC: m5C on the site's sixth base on both strands (fully methylated); Table I p. 3651 lists GGTACm5C as cut.",
   "marks": [
    [
     2,
     "top"
    ],
    [
     4,
     "bottom"
    ],
    [
     9,
     "top"
    ],
    [
     11,
     "bottom"
    ]
   ]
  },
  {
   "id": "M17",
   "enzyme": "ClaI",
   "sequence": "AAATCGATCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "GATC reaches from ATCGAT into its right flank: m6A on the site's fifth base; Table I p. 3649 lists ATCGm6AT as not cut.",
   "marks": [
    [
     7,
     "top"
    ],
    [
     8,
     "bottom"
    ]
   ]
  },
  {
   "id": "M18",
   "enzyme": "MboI",
   "sequence": "AAGATCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "blocked"
   },
   "reasoning": "Every MboI site is a GATC: m6A on its second base, both strands; Table I p. 3651 lists Gm6ATC as not cut (the cited dam-blocked example).",
   "marks": [
    [
     4,
     "top"
    ],
    [
     5,
     "bottom"
    ]
   ]
  },
  {
   "id": "M19",
   "enzyme": "Sau3AI",
   "sequence": "AAGATCAA",
   "circular": false,
   "host": {
    "dam": true,
    "dcm": true
   },
   "expected": {
    "outcome": "not-blocked"
   },
   "reasoning": "Table I p. 3653 lists Gm6ATC as cut by Sau3AI.",
   "marks": [
    [
     4,
     "top"
    ],
    [
     5,
     "bottom"
    ]
   ]
  }
 ],
 "plasmidCases": [
  {
   "id": "P01",
   "enzyme": "MboI",
   "plasmid": "L09137.2",
   "sites": 15,
   "expected": "every site blocked",
   "reasoning": "Every MboI site is a GATC, methylated by dam; Table I p. 3651, Gm6ATC not cut."
  },
  {
   "id": "P02",
   "enzyme": "EcoRII",
   "plasmid": "J01749.1",
   "sites": 6,
   "expected": "every site blocked",
   "reasoning": "Every EcoRII site is a CCWGG, methylated by dcm; Table I p. 3650, Cm5CWGG not cut."
  }
 ]
}