diff --git a/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb b/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb
index b2453ff2d4b542ee3e719b0c9737ef08e9a9ee8b..35dcfeebe6d1c30490746e659e54020de83c676d 100644
--- a/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb
+++ b/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb
@@ -2,8 +2,8 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 11,
- "id": "767c8226",
+ "execution_count": 2,
+ "id": "d1c58516",
"metadata": {
"scrolled": true
},
@@ -18,42 +18,439 @@
},
{
"cell_type": "code",
- "execution_count": 19,
- "id": "bf2d37ca",
+ "execution_count": 7,
+ "id": "df7df2a7",
"metadata": {},
"outputs": [],
"source": [
- "data=[]\n",
- "for i in df[\"vstrands\"]:\n",
- " data.append(i)\n",
- "df=pd.DataFrame(data=d)"
+ "import cadnano\n",
+ "from cadnano.document import Document\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "a24cd262",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df=pd.DataFrame(data=d)\n",
+ "df=df.set_index(\"num\")"
]
},
{
"cell_type": "code",
- "execution_count": 58,
- "id": "22a5db0b-2ce5-4af9-83f1-88114342c36d",
+ "execution_count": 5,
+ "id": "806af23a",
"metadata": {},
"outputs": [
{
"data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>row</th>\n",
+ " <th>col</th>\n",
+ " <th>scaf</th>\n",
+ " <th>stap</th>\n",
+ " <th>loop</th>\n",
+ " <th>skip</th>\n",
+ " <th>scafLoop</th>\n",
+ " <th>stapLoop</th>\n",
+ " <th>stap_colors</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>num</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>12</td>\n",
+ " <td>16</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ...</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [0, 3, -1...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[]</td>\n",
+ " <td>[]</td>\n",
+ " <td>[[23, 13369809], [38, 12060012]]</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>12</td>\n",
+ " <td>15</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ...</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[]</td>\n",
+ " <td>[]</td>\n",
+ " <td>[[3, 1501302]]</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>13</td>\n",
+ " <td>15</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [3, 2, 2,...</td>\n",
+ " <td>[[2, 1, -1, -1], [2, 2, 2, 0], [2, 3, 2, 1], [...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[]</td>\n",
+ " <td>[]</td>\n",
+ " <td>[[34, 8947848]]</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>13</td>\n",
+ " <td>16</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [3, 3, 2,...</td>\n",
+ " <td>[[-1, -1, 3, 1], [3, 0, 3, 2], [3, 1, 3, 3], [...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[]</td>\n",
+ " <td>[]</td>\n",
+ " <td>[[0, 13369344]]</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>13</td>\n",
+ " <td>17</td>\n",
+ " <td>[[-1, -1, 4, 1], [4, 0, 4, 2], [4, 1, 4, 3], [...</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[]</td>\n",
+ " <td>[]</td>\n",
+ " <td>[[39, 8947848]]</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>12</td>\n",
+ " <td>17</td>\n",
+ " <td>[[5, 1, -1, -1], [5, 2, 5, 0], [5, 3, 5, 1], [...</td>\n",
+ " <td>[[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
+ " <td>[]</td>\n",
+ " <td>[]</td>\n",
+ " <td>[[9, 0]]</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
"text/plain": [
- "[-1, -1, -1, -1]"
+ " row col scaf \\\n",
+ "num \n",
+ "0 12 16 [[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ... \n",
+ "1 12 15 [[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ... \n",
+ "2 13 15 [[-1, -1, -1, -1], [-1, -1, -1, -1], [3, 2, 2,... \n",
+ "3 13 16 [[-1, -1, -1, -1], [-1, -1, -1, -1], [3, 3, 2,... \n",
+ "4 13 17 [[-1, -1, 4, 1], [4, 0, 4, 2], [4, 1, 4, 3], [... \n",
+ "5 12 17 [[5, 1, -1, -1], [5, 2, 5, 0], [5, 3, 5, 1], [... \n",
+ "\n",
+ " stap \\\n",
+ "num \n",
+ "0 [[-1, -1, -1, -1], [-1, -1, -1, -1], [0, 3, -1... \n",
+ "1 [[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ... \n",
+ "2 [[2, 1, -1, -1], [2, 2, 2, 0], [2, 3, 2, 1], [... \n",
+ "3 [[-1, -1, 3, 1], [3, 0, 3, 2], [3, 1, 3, 3], [... \n",
+ "4 [[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ... \n",
+ "5 [[-1, -1, -1, -1], [-1, -1, -1, -1], [-1, -1, ... \n",
+ "\n",
+ " loop \\\n",
+ "num \n",
+ "0 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... \n",
+ "1 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... \n",
+ "2 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... \n",
+ "3 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... \n",
+ "4 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... \n",
+ "5 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... \n",
+ "\n",
+ " skip scafLoop stapLoop \\\n",
+ "num \n",
+ "0 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... [] [] \n",
+ "1 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... [] [] \n",
+ "2 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... [] [] \n",
+ "3 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... [] [] \n",
+ "4 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... [] [] \n",
+ "5 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... [] [] \n",
+ "\n",
+ " stap_colors \n",
+ "num \n",
+ "0 [[23, 13369809], [38, 12060012]] \n",
+ "1 [[3, 1501302]] \n",
+ "2 [[34, 8947848]] \n",
+ "3 [[0, 13369344]] \n",
+ "4 [[39, 8947848]] \n",
+ "5 [[9, 0]] "
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "db28a621",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ }
+ ],
+ "source": [
+ "doc = Document()\n",
+ "def read_json_file(filename):\n",
+ " import json\n",
+ " import re\n",
+ "\n",
+ " try:\n",
+ " with open(filename) as ch:\n",
+ " data = json.load(ch)\n",
+ " except:\n",
+ " with open(filename) as ch:\n",
+ " content = \"\"\n",
+ " for l in ch:\n",
+ " l = re.sub(r\"'\", r'\"', l)\n",
+ " # https://stackoverflow.com/questions/4033633/handling-lazy-json-in-python-expecting-property-name\n",
+ " # l = re.sub(r\"{\\s*(\\w)\", r'{\"\\1', l)\n",
+ " # l = re.sub(r\",\\s*(\\w)\", r',\"\\1', l)\n",
+ " # l = re.sub(r\"(\\w):\", r'\\1\":', l)\n",
+ " content += l+\"\\n\"\n",
+ " data = json.loads(content)\n",
+ " return data\n",
+ "f=read_json_file(\"test.json\")\n",
+ "cadnano.fileio.v2decode.decode(doc, f)\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "cf748a26",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_lattice(part):\n",
+ " lattice_type = None\n",
+ " _gt = part.getGridType()\n",
+ " try:\n",
+ " lattice_type = _gt.name.lower()\n",
+ " except:\n",
+ " if _gt == 1:\n",
+ " lattice_type = 'square'\n",
+ " elif _gt == 2:\n",
+ " lattice_type = 'honeycomb'\n",
+ " else:\n",
+ " print(\"WARNING: unable to determine cadnano part lattice type\")\n",
+ " return lattice_type\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 70,
+ "id": "fde9e6b9",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_json_file(filename):\n",
+ " import json\n",
+ " import re\n",
+ " import cadnano\n",
+ " from cadnano.document import Document\n",
+ "\n",
+ " try:\n",
+ " with open(filename) as ch:\n",
+ " json_data = json.load(ch)\n",
+ " except:\n",
+ " with open(filename) as ch:\n",
+ " content = \"\"\n",
+ " for l in ch:\n",
+ " l = re.sub(r\"'\", r'\"', l)\n",
+ " # https://stackoverflow.com/questions/4033633/handling-lazy-json-in-python-expecting-property-name\n",
+ " # l = re.sub(r\"{\\s*(\\w)\", r'{\"\\1', l)\n",
+ " # l = re.sub(r\",\\s*(\\w)\", r',\"\\1', l)\n",
+ " # l = re.sub(r\"(\\w):\", r'\\1\":', l)\n",
+ " content += l+\"\\n\"\n",
+ " json_data = json.loads(content)\n",
+ "\n",
+ " try:\n",
+ " doc = Document()\n",
+ " cadnano.fileio.v3decode.decode(doc, json_data)\n",
+ " decoder = 3\n",
+ " except:\n",
+ " doc = Document()\n",
+ " cadnano.fileio.v2decode.decode(doc, json_data)\n",
+ " decoder = 2\n",
+ "\n",
+ " parts = [p for p in doc.getParts()]\n",
+ " if len(parts) != 1:\n",
+ " raise Exception(\"Only documents containing a single cadnano part are implemented at this time.\")\n",
+ " part = parts[0]\n",
+ "\n",
+ " if decoder == 2:\n",
+ " \"\"\" It seems cadnano2.5 (as of ce6ff019) does not set the EulerZ for square lattice structures correctly, doing so here \"\"\"\n",
+ " l = get_lattice(part)\n",
+ " if l == 'square':\n",
+ " for id_num in part.getIdNums():\n",
+ " if part.vh_properties.loc[id_num,'eulerZ'] == 0:\n",
+ " part.vh_properties.loc[id_num,'eulerZ'] = 360*(6/10.5)\n",
+ " df=pd.DataFrame(json_data[\"vstrands\"])\n",
+ " n_df=df.set_index(\"num\")\n",
+ " return part,n_df\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "id": "608b53b9",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[42, 42, 42, 42, 42, 42]"
+ ]
+ },
+ "execution_count": 44,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "bpnum=[len(df[\"scaf\"][i]) for i in df.index]\n",
+ "bpnum"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 71,
+ "id": "abf6006a",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ }
+ ],
+ "source": [
+ "f,b=read_json_file(\"test.json\")\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "id": "57f22778",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Int64Index([0, 1, 2, 3, 4, 5], dtype='int64', name='num')"
]
},
- "execution_count": 58,
+ "execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "df[\"stap\"][0][0]"
+ "b.index"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "id": "399ada62",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def ntcount(b):\n",
+ " def judge(i):\n",
+ " if i ==[-1,-1,-1,-1]:\n",
+ " return 0\n",
+ " else: return 1\n",
+ " n=np.array([judge(i) for i in b])\n",
+ " return np.sum(n)\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 78,
+ "id": "1d63a717",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "35\n",
+ "35\n",
+ "34\n",
+ "36\n",
+ "35\n",
+ "35\n",
+ "37\n",
+ "36\n",
+ "35\n",
+ "35\n",
+ "31\n",
+ "31\n"
+ ]
+ }
+ ],
+ "source": [
+ "b[\"scafnt\"]=[ntcount(b['scaf'][i]) for i in b.index]\n",
+ "b[\"stapnt\"]=[ntcount(b['stap'][i]) for i in b.index]"
]
},
{
"cell_type": "code",
"execution_count": 13,
- "id": "46079e58-4747-42ff-8b68-906c94440474",
+ "id": "6e30e6ec",
"metadata": {},
"outputs": [
{
@@ -74,7 +471,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "625c831b",
+ "id": "d2a55c6a",
"metadata": {},
"outputs": [
{
@@ -93,10 +490,32 @@
"len(vh_vb._scaf)"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 198,
+ "id": "b36a118e",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "TypeError",
+ "evalue": "file must have 'read' and 'readline' attributes",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[198], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpickle\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtest.virt2nuc\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
+ "\u001b[0;31mTypeError\u001b[0m: file must have 'read' and 'readline' attributes"
+ ]
+ }
+ ],
+ "source": [
+ "df = pickle.load(\"test.virt2nuc\")"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 15,
- "id": "6a4129c2",
+ "id": "c1fd0214",
"metadata": {},
"outputs": [
{
@@ -116,8 +535,8 @@
},
{
"cell_type": "code",
- "execution_count": 18,
- "id": "aefe656e",
+ "execution_count": 173,
+ "id": "21f20d54",
"metadata": {},
"outputs": [],
"source": [
@@ -152,8 +571,8 @@
},
{
"cell_type": "code",
- "execution_count": 160,
- "id": "e154a8c3",
+ "execution_count": 177,
+ "id": "ca75e9ec",
"metadata": {},
"outputs": [],
"source": [
@@ -168,26 +587,19 @@
"\n",
"#class\n",
"def decode_vh_vb(virt2nuc):\n",
- " vh_list=[]\n",
+ " vh_list={}\n",
" vh_vb,pattern=pd.read_pickle(virt2nuc)\n",
" for i in pattern.keys():\n",
" s=strands()\n",
" s.row,s.col=pattern[i]\n",
" s.num=i\n",
- " vh_list.append(s)\n",
+ " vh_list[s.num]=s\n",
" scafs=vh_vb._scaf\n",
" staps=vh_vb._stap\n",
" scaf_strands=find_segs(scafs)\n",
" scaf_oligos=list(scaf_strands.keys())\n",
" for i in scaf_oligos:\n",
- " bases=len(scaf_oligos)\n",
- " vh0,vb0=scaf_oligos[i][0]\n",
- " vh1,vb1=scaf_oligos[i][1]\n",
- " if vb0>vb1 and vh0==vh1:#53\n",
- " scaf_contact\n",
- " \n",
- " else: #35\n",
- " for i in stap_oligos:\n",
+ " pass\n",
" \n",
" \n",
" return vh_list"
@@ -195,428 +607,489 @@
},
{
"cell_type": "code",
- "execution_count": 106,
- "id": "125b30e0-7dcc-464a-b3cf-cfbf090d3982",
- "metadata": {},
- "outputs": [],
- "source": [
- "\n",
- "def decode_vh_vb(virt2nuc):\n",
- " vh_vb,pattern=pd.read_pickle(virt2nuc)\n",
- " vi={'row':0, 'col':0, 'num':0, 'scaf':dict(), 'stap':dict(), 'loop':[], 'skip':[], 'scafLoop':[],'stapLoop':[], 'stap_colors':[]}\n",
- " vs=[] \n",
- " for i in range(len(pattern.keys())):\n",
- " vhi=vi.copy()\n",
- " vhi[\"row\"],vhi[\"col\"]=list(pattern.values())[i]\n",
- " vhi[\"num\"]=list(pattern.keys())[i]\n",
- " vs.append(vhi)\n",
- " vhelices=pd.DataFrame(vs)\n",
- " scafs=vh_vb._scaf\n",
- " staps=vh_vb._stap\n",
- " s\n",
- " return vhelices"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 107,
- "id": "5b149587-3224-4137-a7bc-e41aa4049034",
+ "execution_count": 187,
+ "id": "daa13243",
"metadata": {},
"outputs": [
{
"data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>row</th>\n",
- " <th>col</th>\n",
- " <th>num</th>\n",
- " <th>scaf</th>\n",
- " <th>stap</th>\n",
- " <th>loop</th>\n",
- " <th>skip</th>\n",
- " <th>scafLoop</th>\n",
- " <th>stapLoop</th>\n",
- " <th>stap_colors</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>12</td>\n",
- " <td>16</td>\n",
- " <td>0</td>\n",
- " <td>{}</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>12</td>\n",
- " <td>15</td>\n",
- " <td>1</td>\n",
- " <td>{}</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>13</td>\n",
- " <td>15</td>\n",
- " <td>2</td>\n",
- " <td>{}</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>13</td>\n",
- " <td>16</td>\n",
- " <td>3</td>\n",
- " <td>{}</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>13</td>\n",
- " <td>17</td>\n",
- " <td>4</td>\n",
- " <td>{}</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>5</th>\n",
- " <td>12</td>\n",
- " <td>17</td>\n",
- " <td>5</td>\n",
- " <td>{}</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " <td>[]</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
"text/plain": [
- " row col num scaf stap loop skip scafLoop stapLoop stap_colors\n",
- "0 12 16 0 {} [] [] [] [] [] []\n",
- "1 12 15 1 {} [] [] [] [] [] []\n",
- "2 13 15 2 {} [] [] [] [] [] []\n",
- "3 13 16 3 {} [] [] [] [] [] []\n",
- "4 13 17 4 {} [] [] [] [] [] []\n",
- "5 12 17 5 {} [] [] [] [] [] []"
+ "[[(2, 34),\n",
+ " (2, 33),\n",
+ " (2, 32),\n",
+ " (2, 31),\n",
+ " (2, 30),\n",
+ " (2, 29),\n",
+ " (2, 28),\n",
+ " (2, 27),\n",
+ " (2, 26),\n",
+ " (2, 25),\n",
+ " (2, 24),\n",
+ " (2, 23),\n",
+ " (2, 22),\n",
+ " (2, 21),\n",
+ " (2, 20),\n",
+ " (2, 19),\n",
+ " (2, 18),\n",
+ " (2, 17),\n",
+ " (2, 16),\n",
+ " (2, 15),\n",
+ " (2, 14),\n",
+ " (2, 13),\n",
+ " (2, 12),\n",
+ " (2, 11),\n",
+ " (2, 10),\n",
+ " (2, 9),\n",
+ " (2, 8),\n",
+ " (2, 7),\n",
+ " (2, 6),\n",
+ " (2, 5),\n",
+ " (2, 4),\n",
+ " (2, 3),\n",
+ " (2, 2),\n",
+ " (2, 1),\n",
+ " (2, 0)],\n",
+ " [(1, 3),\n",
+ " (1, 4),\n",
+ " (1, 5),\n",
+ " (1, 6),\n",
+ " (1, 7),\n",
+ " (1, 8),\n",
+ " (1, 9),\n",
+ " (1, 10),\n",
+ " (1, 11),\n",
+ " (1, 12),\n",
+ " (1, 13),\n",
+ " (1, 14),\n",
+ " (1, 15),\n",
+ " (1, 16),\n",
+ " (1, 17),\n",
+ " (1, 18),\n",
+ " (1, 19),\n",
+ " (1, 20),\n",
+ " (0, 20),\n",
+ " (0, 19),\n",
+ " (0, 18),\n",
+ " (0, 17),\n",
+ " (0, 16),\n",
+ " (0, 15),\n",
+ " (0, 14),\n",
+ " (0, 13),\n",
+ " (0, 12),\n",
+ " (0, 11),\n",
+ " (0, 10),\n",
+ " (0, 9),\n",
+ " (0, 8),\n",
+ " (0, 7),\n",
+ " (0, 6),\n",
+ " (0, 5),\n",
+ " (0, 4),\n",
+ " (0, 3),\n",
+ " (0, 2)],\n",
+ " [(0, 23),\n",
+ " (0, 22),\n",
+ " (0, 21),\n",
+ " (1, 21),\n",
+ " (1, 22),\n",
+ " (1, 23),\n",
+ " (1, 24),\n",
+ " (1, 25),\n",
+ " (1, 26),\n",
+ " (1, 27),\n",
+ " (1, 28),\n",
+ " (1, 29),\n",
+ " (1, 30),\n",
+ " (1, 31),\n",
+ " (1, 32),\n",
+ " (1, 33),\n",
+ " (1, 34),\n",
+ " (1, 35),\n",
+ " (1, 36),\n",
+ " (1, 37),\n",
+ " (1, 38)],\n",
+ " [(5, 9),\n",
+ " (5, 10),\n",
+ " (5, 11),\n",
+ " (5, 12),\n",
+ " (5, 13),\n",
+ " (5, 14),\n",
+ " (5, 15),\n",
+ " (5, 16),\n",
+ " (5, 17),\n",
+ " (5, 18),\n",
+ " (5, 19),\n",
+ " (5, 20),\n",
+ " (5, 21),\n",
+ " (5, 22),\n",
+ " (5, 23),\n",
+ " (5, 24),\n",
+ " (5, 25),\n",
+ " (5, 26),\n",
+ " (5, 27),\n",
+ " (0, 27),\n",
+ " (0, 26),\n",
+ " (0, 25),\n",
+ " (0, 24)],\n",
+ " [(0, 38),\n",
+ " (0, 37),\n",
+ " (0, 36),\n",
+ " (0, 35),\n",
+ " (0, 34),\n",
+ " (0, 33),\n",
+ " (0, 32),\n",
+ " (0, 31),\n",
+ " (0, 30),\n",
+ " (0, 29),\n",
+ " (0, 28),\n",
+ " (5, 28),\n",
+ " (5, 29),\n",
+ " (5, 30),\n",
+ " (5, 31),\n",
+ " (5, 32),\n",
+ " (5, 33),\n",
+ " (5, 34),\n",
+ " (5, 35),\n",
+ " (5, 36),\n",
+ " (5, 37),\n",
+ " (5, 38),\n",
+ " (5, 39)],\n",
+ " [(3, 0),\n",
+ " (3, 1),\n",
+ " (3, 2),\n",
+ " (3, 3),\n",
+ " (3, 4),\n",
+ " (3, 5),\n",
+ " (3, 6),\n",
+ " (3, 7),\n",
+ " (3, 8),\n",
+ " (3, 9),\n",
+ " (3, 10),\n",
+ " (3, 11),\n",
+ " (3, 12),\n",
+ " (3, 13),\n",
+ " (3, 14),\n",
+ " (3, 15),\n",
+ " (3, 16),\n",
+ " (3, 17),\n",
+ " (3, 18),\n",
+ " (3, 19),\n",
+ " (3, 20),\n",
+ " (4, 20),\n",
+ " (4, 19),\n",
+ " (4, 18),\n",
+ " (4, 17),\n",
+ " (4, 16),\n",
+ " (4, 15),\n",
+ " (4, 14),\n",
+ " (4, 13),\n",
+ " (4, 12),\n",
+ " (4, 11),\n",
+ " (4, 10),\n",
+ " (4, 9)],\n",
+ " [(4, 39),\n",
+ " (4, 38),\n",
+ " (4, 37),\n",
+ " (4, 36),\n",
+ " (4, 35),\n",
+ " (4, 34),\n",
+ " (4, 33),\n",
+ " (4, 32),\n",
+ " (4, 31),\n",
+ " (4, 30),\n",
+ " (4, 29),\n",
+ " (4, 28),\n",
+ " (4, 27),\n",
+ " (4, 26),\n",
+ " (4, 25),\n",
+ " (4, 24),\n",
+ " (4, 23),\n",
+ " (4, 22),\n",
+ " (4, 21),\n",
+ " (3, 21),\n",
+ " (3, 22),\n",
+ " (3, 23),\n",
+ " (3, 24),\n",
+ " (3, 25),\n",
+ " (3, 26),\n",
+ " (3, 27),\n",
+ " (3, 28),\n",
+ " (3, 29),\n",
+ " (3, 30),\n",
+ " (3, 31),\n",
+ " (3, 32),\n",
+ " (3, 33),\n",
+ " (3, 34)]]"
]
},
- "execution_count": 107,
+ "execution_count": 187,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "s=decode_vh_vb(\"test.virt2nuc\")\n",
- "s"
+ "s1=decode_vh_vb(\"test.virt2nuc\")\n",
+ "vh_vb,pattern=pd.read_pickle(\"test.virt2nuc\")\n",
+ "list(find_segs(vh_vb._stap).values())"
]
},
{
"cell_type": "code",
- "execution_count": 90,
- "id": "e7a10fc3-6c30-49da-ae43-81cdb2048cdf",
+ "execution_count": 142,
+ "id": "687c6f64",
"metadata": {},
"outputs": [],
"source": [
+ "def find_segs(vir2nuc_scaf):\n",
+ " oligos={}\n",
+ " for i in range(len(vir2nuc_scaf)):\n",
+ " oligo,ox_ind=list(vir2nuc_scaf.values())[i]\n",
+ " if oligo not in oligos.keys():\n",
+ " oligos[oligo]=[]\n",
+ " oligos[oligo].append(list(vir2nuc_scaf.keys())[i])\n",
+ " return oligos\n",
"\n",
- "s=pd.Series(vi)"
+ "def decode_vh_vb(virt2nuc):\n",
+ " vh_vb,pattern=pd.read_pickle(virt2nuc)\n",
+ " vi={'row':0, 'col':0, 'num':0, 'scaf':dict(), 'stap':dict(), 'loop':[], 'skip':[], 'scafLoop':[],'stapLoop':[], 'stap_colors':[],\"scaf53\":True}\n",
+ " vs=[] \n",
+ " for i in range(len(pattern.keys())):\n",
+ " vhi=vi.copy()\n",
+ " vhi[\"row\"],vhi[\"col\"]=list(pattern.values())[i]\n",
+ " vhi[\"num\"]=list(pattern.keys())[i]\n",
+ " vs.append(vhi)\n",
+ " vhelices=pd.DataFrame(vs)\n",
+ " vhelices=vhelices.set_index('num')\n",
+ " scafs=vh_vb._scaf\n",
+ " staps=vh_vb._stap\n",
+ " scaf_strands=find_segs(scafs)\n",
+ " stap_strands=find_segs(staps)\n",
+ " scaf_oligos=list(scaf_strands.keys())\n",
+ "\n",
+ " \n",
+ " return vhelices"
]
},
{
"cell_type": "code",
- "execution_count": 92,
- "id": "ae3c8887-0d73-4151-958c-32adfd708611",
+ "execution_count": 117,
+ "id": "4d610626",
"metadata": {},
"outputs": [],
"source": [
- "s[\"scaf\"].append(1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 93,
- "id": "f24b00b3-e0f0-42b0-88b6-1e7a956ef7ac",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "row 0\n",
- "col 0\n",
- "num 0\n",
- "scaf [1]\n",
- "stap []\n",
- "loop []\n",
- "skip []\n",
- "scafLoop []\n",
- "stapLoop []\n",
- "stap_colors []\n",
- "dtype: object"
- ]
- },
- "execution_count": 93,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s"
+ "def find_base_map(oligo,i,vhx,scaf=True):\n",
+ " vh0,vb0=oligo[i]\n",
+ " vh1,vb1=oligo[i+1]\n",
+ " if scaf==True:\n",
+ " if vb0 not in vhx[\"scaf\"][vh0].keys():\n",
+ " \n",
+ " if vh0==vh1 and scaf==True:\n",
+ " if vb0>vb1:\n",
+ " vhx[vh0][\"scaf\"][vb0]=\n",
+ " \n",
+ "\n",
+ " \n"
]
},
{
"cell_type": "code",
- "execution_count": 163,
- "id": "09619e4e",
+ "execution_count": 116,
+ "id": "ab5c6907",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "{0: [(0, 39), (0, 40), (0, 41)],\n",
- " 1: [(1, 41), (1, 40), (1, 39)],\n",
- " 2: [(2, 39), (2, 40), (2, 41)],\n",
- " 4: [(3, 41), (3, 40), (3, 39), (3, 38), (3, 37)],\n",
- " 5: [(4, 0), (4, 1), (4, 2), (4, 3)],\n",
- " 6: [(5, 3), (5, 2), (5, 1), (5, 0)],\n",
- " 7: [(5, 22),\n",
- " (5, 21),\n",
- " (5, 20),\n",
- " (5, 19),\n",
- " (5, 18),\n",
- " (5, 17),\n",
- " (5, 16),\n",
- " (5, 15),\n",
- " (5, 14),\n",
- " (5, 13),\n",
- " (5, 12),\n",
- " (5, 11),\n",
- " (5, 10),\n",
- " (5, 9),\n",
- " (4, 9),\n",
- " (4, 10),\n",
- " (4, 11),\n",
- " (4, 12),\n",
- " (4, 13),\n",
- " (4, 14),\n",
- " (4, 15),\n",
- " (3, 15),\n",
- " (3, 14),\n",
- " (3, 13),\n",
- " (3, 12),\n",
- " (3, 11),\n",
- " (3, 10),\n",
- " (3, 9),\n",
- " (3, 8),\n",
- " (3, 7),\n",
- " (3, 6),\n",
- " (3, 5),\n",
- " (3, 4),\n",
- " (3, 3),\n",
- " (3, 2),\n",
- " (2, 2),\n",
- " (2, 3),\n",
- " (2, 4),\n",
- " (2, 5),\n",
- " (2, 6),\n",
- " (2, 7),\n",
- " (2, 8),\n",
- " (2, 9),\n",
- " (2, 10),\n",
- " (2, 11),\n",
- " (2, 12),\n",
- " (2, 13),\n",
- " (2, 14),\n",
- " (2, 15),\n",
- " (2, 16),\n",
- " (2, 17),\n",
- " (2, 18),\n",
- " (1, 18),\n",
- " (1, 17),\n",
- " (1, 16),\n",
- " (1, 15),\n",
- " (1, 14),\n",
- " (1, 13),\n",
- " (1, 12),\n",
- " (1, 11),\n",
- " (1, 10),\n",
- " (1, 9),\n",
- " (1, 8),\n",
- " (1, 7),\n",
- " (1, 6),\n",
- " (1, 5),\n",
- " (0, 5),\n",
- " (0, 6),\n",
- " (0, 7),\n",
- " (0, 8),\n",
- " (0, 9),\n",
- " (0, 10),\n",
- " (0, 11),\n",
- " (0, 12),\n",
- " (0, 13),\n",
- " (0, 14),\n",
- " (0, 15),\n",
- " (0, 16),\n",
- " (0, 17),\n",
- " (0, 18),\n",
- " (0, 19),\n",
- " (0, 20),\n",
- " (0, 21),\n",
- " (0, 22),\n",
- " (0, 23),\n",
- " (0, 24),\n",
- " (0, 25),\n",
- " (0, 26),\n",
- " (0, 27),\n",
- " (0, 28),\n",
- " (0, 29),\n",
- " (0, 30),\n",
- " (0, 31),\n",
- " (0, 32),\n",
- " (0, 33),\n",
- " (0, 34),\n",
- " (0, 35),\n",
- " (0, 36),\n",
- " (1, 36),\n",
- " (1, 35),\n",
- " (1, 34),\n",
- " (1, 33),\n",
- " (1, 32),\n",
- " (1, 31),\n",
- " (1, 30),\n",
- " (1, 29),\n",
- " (1, 28),\n",
- " (1, 27),\n",
- " (1, 26),\n",
- " (1, 25),\n",
- " (1, 24),\n",
- " (1, 23),\n",
- " (1, 22),\n",
- " (1, 21),\n",
- " (1, 20),\n",
- " (1, 19),\n",
- " (2, 19),\n",
- " (2, 20),\n",
- " (2, 21),\n",
- " (2, 22),\n",
- " (2, 23),\n",
- " (2, 24),\n",
- " (2, 25),\n",
- " (2, 26),\n",
- " (2, 27),\n",
- " (2, 28),\n",
- " (2, 29),\n",
- " (2, 30),\n",
- " (2, 31),\n",
- " (2, 32),\n",
- " (3, 32),\n",
- " (3, 31),\n",
- " (3, 30),\n",
- " (3, 29),\n",
- " (3, 28),\n",
- " (3, 27),\n",
- " (3, 26),\n",
- " (3, 25),\n",
- " (3, 24),\n",
- " (3, 23),\n",
- " (3, 22),\n",
- " (3, 21),\n",
- " (3, 20),\n",
- " (3, 19),\n",
- " (3, 18),\n",
- " (3, 17),\n",
- " (3, 16),\n",
- " (4, 16),\n",
- " (4, 17),\n",
- " (4, 18),\n",
- " (4, 19),\n",
- " (4, 20),\n",
- " (4, 21),\n",
- " (4, 22),\n",
- " (4, 23),\n",
- " (4, 24),\n",
- " (4, 25),\n",
- " (4, 26),\n",
- " (4, 27),\n",
- " (4, 28),\n",
- " (4, 29),\n",
- " (4, 30),\n",
- " (4, 31),\n",
- " (4, 32),\n",
- " (4, 33),\n",
- " (4, 34),\n",
- " (4, 35),\n",
- " (4, 36),\n",
- " (4, 37),\n",
- " (4, 38),\n",
- " (4, 39),\n",
- " (5, 39),\n",
- " (5, 38),\n",
- " (5, 37),\n",
- " (5, 36),\n",
- " (5, 35),\n",
- " (5, 34),\n",
- " (5, 33),\n",
- " (5, 32),\n",
- " (5, 31),\n",
- " (5, 30),\n",
- " (5, 29),\n",
- " (5, 28),\n",
- " (5, 27),\n",
- " (5, 26),\n",
- " (5, 25),\n",
- " (5, 24),\n",
- " (5, 23)]}"
+ "[(5, 22),\n",
+ " (5, 21),\n",
+ " (5, 20),\n",
+ " (5, 19),\n",
+ " (5, 18),\n",
+ " (5, 17),\n",
+ " (5, 16),\n",
+ " (5, 15),\n",
+ " (5, 14),\n",
+ " (5, 13),\n",
+ " (5, 12),\n",
+ " (5, 11),\n",
+ " (5, 10),\n",
+ " (5, 9),\n",
+ " (4, 9),\n",
+ " (4, 10),\n",
+ " (4, 11),\n",
+ " (4, 12),\n",
+ " (4, 13),\n",
+ " (4, 14),\n",
+ " (4, 15),\n",
+ " (3, 15),\n",
+ " (3, 14),\n",
+ " (3, 13),\n",
+ " (3, 12),\n",
+ " (3, 11),\n",
+ " (3, 10),\n",
+ " (3, 9),\n",
+ " (3, 8),\n",
+ " (3, 7),\n",
+ " (3, 6),\n",
+ " (3, 5),\n",
+ " (3, 4),\n",
+ " (3, 3),\n",
+ " (3, 2),\n",
+ " (2, 2),\n",
+ " (2, 3),\n",
+ " (2, 4),\n",
+ " (2, 5),\n",
+ " (2, 6),\n",
+ " (2, 7),\n",
+ " (2, 8),\n",
+ " (2, 9),\n",
+ " (2, 10),\n",
+ " (2, 11),\n",
+ " (2, 12),\n",
+ " (2, 13),\n",
+ " (2, 14),\n",
+ " (2, 15),\n",
+ " (2, 16),\n",
+ " (2, 17),\n",
+ " (2, 18),\n",
+ " (1, 18),\n",
+ " (1, 17),\n",
+ " (1, 16),\n",
+ " (1, 15),\n",
+ " (1, 14),\n",
+ " (1, 13),\n",
+ " (1, 12),\n",
+ " (1, 11),\n",
+ " (1, 10),\n",
+ " (1, 9),\n",
+ " (1, 8),\n",
+ " (1, 7),\n",
+ " (1, 6),\n",
+ " (1, 5),\n",
+ " (0, 5),\n",
+ " (0, 6),\n",
+ " (0, 7),\n",
+ " (0, 8),\n",
+ " (0, 9),\n",
+ " (0, 10),\n",
+ " (0, 11),\n",
+ " (0, 12),\n",
+ " (0, 13),\n",
+ " (0, 14),\n",
+ " (0, 15),\n",
+ " (0, 16),\n",
+ " (0, 17),\n",
+ " (0, 18),\n",
+ " (0, 19),\n",
+ " (0, 20),\n",
+ " (0, 21),\n",
+ " (0, 22),\n",
+ " (0, 23),\n",
+ " (0, 24),\n",
+ " (0, 25),\n",
+ " (0, 26),\n",
+ " (0, 27),\n",
+ " (0, 28),\n",
+ " (0, 29),\n",
+ " (0, 30),\n",
+ " (0, 31),\n",
+ " (0, 32),\n",
+ " (0, 33),\n",
+ " (0, 34),\n",
+ " (0, 35),\n",
+ " (0, 36),\n",
+ " (1, 36),\n",
+ " (1, 35),\n",
+ " (1, 34),\n",
+ " (1, 33),\n",
+ " (1, 32),\n",
+ " (1, 31),\n",
+ " (1, 30),\n",
+ " (1, 29),\n",
+ " (1, 28),\n",
+ " (1, 27),\n",
+ " (1, 26),\n",
+ " (1, 25),\n",
+ " (1, 24),\n",
+ " (1, 23),\n",
+ " (1, 22),\n",
+ " (1, 21),\n",
+ " (1, 20),\n",
+ " (1, 19),\n",
+ " (2, 19),\n",
+ " (2, 20),\n",
+ " (2, 21),\n",
+ " (2, 22),\n",
+ " (2, 23),\n",
+ " (2, 24),\n",
+ " (2, 25),\n",
+ " (2, 26),\n",
+ " (2, 27),\n",
+ " (2, 28),\n",
+ " (2, 29),\n",
+ " (2, 30),\n",
+ " (2, 31),\n",
+ " (2, 32),\n",
+ " (3, 32),\n",
+ " (3, 31),\n",
+ " (3, 30),\n",
+ " (3, 29),\n",
+ " (3, 28),\n",
+ " (3, 27),\n",
+ " (3, 26),\n",
+ " (3, 25),\n",
+ " (3, 24),\n",
+ " (3, 23),\n",
+ " (3, 22),\n",
+ " (3, 21),\n",
+ " (3, 20),\n",
+ " (3, 19),\n",
+ " (3, 18),\n",
+ " (3, 17),\n",
+ " (3, 16),\n",
+ " (4, 16),\n",
+ " (4, 17),\n",
+ " (4, 18),\n",
+ " (4, 19),\n",
+ " (4, 20),\n",
+ " (4, 21),\n",
+ " (4, 22),\n",
+ " (4, 23),\n",
+ " (4, 24),\n",
+ " (4, 25),\n",
+ " (4, 26),\n",
+ " (4, 27),\n",
+ " (4, 28),\n",
+ " (4, 29),\n",
+ " (4, 30),\n",
+ " (4, 31),\n",
+ " (4, 32),\n",
+ " (4, 33),\n",
+ " (4, 34),\n",
+ " (4, 35),\n",
+ " (4, 36),\n",
+ " (4, 37),\n",
+ " (4, 38),\n",
+ " (4, 39),\n",
+ " (5, 39),\n",
+ " (5, 38),\n",
+ " (5, 37),\n",
+ " (5, 36),\n",
+ " (5, 35),\n",
+ " (5, 34),\n",
+ " (5, 33),\n",
+ " (5, 32),\n",
+ " (5, 31),\n",
+ " (5, 30),\n",
+ " (5, 29),\n",
+ " (5, 28),\n",
+ " (5, 27),\n",
+ " (5, 26),\n",
+ " (5, 25),\n",
+ " (5, 24),\n",
+ " (5, 23)]"
]
},
- "execution_count": 163,
+ "execution_count": 116,
"metadata": {},
"output_type": "execute_result"
}
@@ -625,13 +1098,14 @@
"scafs=vh_vb._scaf\n",
"s=list(scafs.values())\n",
"len(scafs)\n",
- "find_segs(scafs)"
+ "ss=find_segs(scafs)[7]\n",
+ "ss"
]
},
{
"cell_type": "code",
"execution_count": 157,
- "id": "88d989b9",
+ "id": "8e05cf62",
"metadata": {},
"outputs": [
{
@@ -655,7 +1129,7 @@
{
"cell_type": "code",
"execution_count": 152,
- "id": "2909c273",
+ "id": "e2e30e0a",
"metadata": {},
"outputs": [
{
@@ -676,7 +1150,7 @@
{
"cell_type": "code",
"execution_count": 62,
- "id": "422e2b48",
+ "id": "03354054",
"metadata": {},
"outputs": [
{
@@ -904,7 +1378,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "69c011ff",
+ "id": "12b28ec3",
"metadata": {},
"outputs": [],
"source": [
@@ -1030,7 +1504,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "f2693e7a",
+ "id": "6d1e1ea1",
"metadata": {},
"outputs": [],
"source": [
@@ -1051,7 +1525,7 @@
{
"cell_type": "code",
"execution_count": 20,
- "id": "a4594752",
+ "id": "17119618",
"metadata": {},
"outputs": [
{
@@ -1113,7 +1587,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "ca071163",
+ "id": "58213565",
"metadata": {},
"outputs": [
{
@@ -1175,7 +1649,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e5913163",
+ "id": "954a6da6",
"metadata": {},
"outputs": [],
"source": [
@@ -1188,7 +1662,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "3eefca8f",
+ "id": "900af65d",
"metadata": {},
"outputs": [
{
@@ -1209,7 +1683,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "268d5c04",
+ "id": "b3dd534e",
"metadata": {},
"outputs": [
{
@@ -1258,7 +1732,7 @@
{
"cell_type": "code",
"execution_count": 36,
- "id": "d3d42e33",
+ "id": "3477f518",
"metadata": {},
"outputs": [
{
@@ -1320,7 +1794,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "2cc3f477",
+ "id": "cb794762",
"metadata": {},
"outputs": [
{
@@ -1346,7 +1820,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "5d50f58a",
+ "id": "7fe2cd8b",
"metadata": {},
"outputs": [],
"source": []
@@ -1354,7 +1828,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "3b40b71b",
+ "id": "0fe00cf6",
"metadata": {},
"outputs": [
{
@@ -1374,7 +1848,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "6915bad6",
+ "id": "f8bb463d",
"metadata": {},
"outputs": [
{
@@ -1395,7 +1869,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "1c16c59d",
+ "id": "bebc29de",
"metadata": {},
"outputs": [
{
@@ -1465,7 +1939,7 @@
{
"cell_type": "code",
"execution_count": 16,
- "id": "c61d9586",
+ "id": "e67598f0",
"metadata": {},
"outputs": [],
"source": [
@@ -1476,7 +1950,7 @@
{
"cell_type": "code",
"execution_count": 26,
- "id": "aeca0546",
+ "id": "51b78d60",
"metadata": {},
"outputs": [
{
@@ -1585,7 +2059,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "90a54834",
+ "id": "b58993ab",
"metadata": {},
"outputs": [
{
@@ -1606,7 +2080,7 @@
{
"cell_type": "code",
"execution_count": 10,
- "id": "de00fb7e",
+ "id": "2554e586",
"metadata": {},
"outputs": [
{
@@ -1637,7 +2111,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "716ff2ed",
+ "id": "c46a53a3",
"metadata": {},
"outputs": [
{
@@ -2134,7 +2608,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "766d0ecd",
+ "id": "7e1b1fb5",
"metadata": {},
"outputs": [
{
@@ -2168,7 +2642,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "05456be4",
+ "id": "14168996",
"metadata": {},
"outputs": [
{
@@ -2188,7 +2662,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "cd1a5604",
+ "id": "b1e6b703",
"metadata": {},
"outputs": [],
"source": [
@@ -2198,7 +2672,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "4346f1fc",
+ "id": "229a0b83",
"metadata": {},
"outputs": [
{
@@ -2219,7 +2693,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "294094f9",
+ "id": "ef1e3f31",
"metadata": {},
"outputs": [
{
@@ -2246,7 +2720,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b3d29c52",
+ "id": "9fcf9231",
"metadata": {},
"outputs": [],
"source": []
@@ -2254,7 +2728,7 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Python 3 (ipykernel)",
+ "display_name": "Python 3",
"language": "python",
"name": "python3"
},
@@ -2268,7 +2742,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.19"
+ "version": "3.8.18"
}
},
"nbformat": 4,
diff --git a/mrdna/readers/libs b/mrdna/readers/libs
index b95cadaeb159900596f7b69e0ea68571008ed0f9..e10e7dfd9849fdf43737462ce6850012e56b2149 120000
--- a/mrdna/readers/libs
+++ b/mrdna/readers/libs
@@ -1 +1 @@
-/Users/pinyili/Documents/research/tacoxDNA/src/libs
\ No newline at end of file
+/home/pinyili2/server5/tacoxDNA/src/libs
\ No newline at end of file
diff --git a/mrdna/readers/rest_scaf_col.json b/mrdna/readers/rest_scaf_col.json
new file mode 100644
index 0000000000000000000000000000000000000000..b0a9979dafc087601de3150abe5111b1050ec9c7
--- /dev/null
+++ b/mrdna/readers/rest_scaf_col.json
@@ -0,0 +1 @@
+{"name":"test.json","vstrands":[{"row":12,"col":16,"num":0,"scaf":[[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[1,5,0,6],[0,5,0,7],[0,6,0,8],[0,7,0,9],[0,8,0,10],[0,9,0,11],[0,10,0,12],[0,11,0,13],[0,12,0,14],[0,13,0,15],[0,14,0,16],[0,15,0,17],[0,16,0,18],[0,17,0,19],[0,18,0,20],[0,19,0,21],[0,20,0,22],[0,21,0,23],[0,22,0,24],[0,23,0,25],[0,24,0,26],[0,25,0,27],[0,26,0,28],[0,27,0,29],[0,28,0,30],[0,29,0,31],[0,30,0,32],[0,31,0,33],[0,32,0,34],[0,33,0,35],[0,34,0,36],[0,35,1,36],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,0,40],[0,39,0,41],[0,40,-1,-1]],"stap":[[-1,-1,-1,-1],[-1,-1,-1,-1],[0,3,-1,-1],[0,4,0,2],[0,5,0,3],[0,6,0,4],[0,7,0,5],[0,8,0,6],[0,9,0,7],[0,10,0,8],[0,11,0,9],[0,12,0,10],[0,13,0,11],[0,14,0,12],[0,15,0,13],[0,16,0,14],[0,17,0,15],[0,18,0,16],[0,19,0,17],[0,20,0,18],[1,20,0,19],[0,22,1,21],[0,23,0,21],[-1,-1,0,22],[0,25,-1,-1],[0,26,0,24],[0,27,0,25],[5,27,0,26],[0,29,5,28],[0,30,0,28],[0,31,0,29],[0,32,0,30],[0,33,0,31],[0,34,0,32],[0,35,0,33],[0,36,0,34],[0,37,0,35],[0,38,0,36],[-1,-1,0,37],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1]],"loop":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"skip":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"scafLoop":[],"stapLoop":[],"stap_colors":[[23,12060012],[38,1507550]]},{"row":12,"col":15,"num":1,"scaf":[[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[1,6,0,5],[1,7,1,5],[1,8,1,6],[1,9,1,7],[1,10,1,8],[1,11,1,9],[1,12,1,10],[1,13,1,11],[1,14,1,12],[1,15,1,13],[1,16,1,14],[1,17,1,15],[1,18,1,16],[2,18,1,17],[1,20,2,19],[1,21,1,19],[1,22,1,20],[1,23,1,21],[1,24,1,22],[1,25,1,23],[1,26,1,24],[1,27,1,25],[1,28,1,26],[1,29,1,27],[1,30,1,28],[1,31,1,29],[1,32,1,30],[1,33,1,31],[1,34,1,32],[1,35,1,33],[1,36,1,34],[0,36,1,35],[-1,-1,-1,-1],[-1,-1,-1,-1],[1,40,-1,-1],[1,41,1,39],[-1,-1,1,40]],"stap":[[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,1,4],[1,3,1,5],[1,4,1,6],[1,5,1,7],[1,6,1,8],[1,7,1,9],[1,8,1,10],[1,9,1,11],[1,10,1,12],[1,11,1,13],[1,12,1,14],[1,13,1,15],[1,14,1,16],[1,15,1,17],[1,16,1,18],[1,17,1,19],[1,18,1,20],[1,19,0,20],[0,21,1,22],[1,21,1,23],[1,22,1,24],[1,23,1,25],[1,24,1,26],[1,25,1,27],[1,26,1,28],[1,27,1,29],[1,28,1,30],[1,29,1,31],[1,30,1,32],[1,31,1,33],[1,32,1,34],[1,33,1,35],[1,34,1,36],[1,35,1,37],[1,36,1,38],[1,37,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1]],"loop":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"skip":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"scafLoop":[],"stapLoop":[],"stap_colors":[[3,13369344]]},{"row":13,"col":15,"num":2,"scaf":[[-1,-1,-1,-1],[-1,-1,-1,-1],[3,2,2,3],[2,2,2,4],[2,3,2,5],[2,4,2,6],[2,5,2,7],[2,6,2,8],[2,7,2,9],[2,8,2,10],[2,9,2,11],[2,10,2,12],[2,11,2,13],[2,12,2,14],[2,13,2,15],[2,14,2,16],[2,15,2,17],[2,16,2,18],[2,17,1,18],[1,19,2,20],[2,19,2,21],[2,20,2,22],[2,21,2,23],[2,22,2,24],[2,23,2,25],[2,24,2,26],[2,25,2,27],[2,26,2,28],[2,27,2,29],[2,28,2,30],[2,29,2,31],[2,30,2,32],[2,31,3,32],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,2,40],[2,39,2,41],[2,40,-1,-1]],"stap":[[2,1,-1,-1],[2,2,2,0],[2,3,2,1],[2,4,2,2],[2,5,2,3],[2,6,2,4],[2,7,2,5],[2,8,2,6],[2,9,2,7],[2,10,2,8],[2,11,2,9],[2,12,2,10],[2,13,2,11],[2,14,2,12],[2,15,2,13],[2,16,2,14],[2,17,2,15],[2,18,2,16],[2,19,2,17],[2,20,2,18],[2,21,2,19],[2,22,2,20],[2,23,2,21],[2,24,2,22],[2,25,2,23],[2,26,2,24],[2,27,2,25],[2,28,2,26],[2,29,2,27],[2,30,2,28],[2,31,2,29],[2,32,2,30],[2,33,2,31],[2,34,2,32],[-1,-1,2,33],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1]],"loop":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"skip":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"scafLoop":[],"stapLoop":[],"stap_colors":[[34,8947848]]},{"row":13,"col":16,"num":3,"scaf":[[-1,-1,-1,-1],[-1,-1,-1,-1],[3,3,2,2],[3,4,3,2],[3,5,3,3],[3,6,3,4],[3,7,3,5],[3,8,3,6],[3,9,3,7],[3,10,3,8],[3,11,3,9],[3,12,3,10],[3,13,3,11],[3,14,3,12],[3,15,3,13],[4,15,3,14],[3,17,4,16],[3,18,3,16],[3,19,3,17],[3,20,3,18],[3,21,3,19],[3,22,3,20],[3,23,3,21],[3,24,3,22],[3,25,3,23],[3,26,3,24],[3,27,3,25],[3,28,3,26],[3,29,3,27],[3,30,3,28],[3,31,3,29],[3,32,3,30],[2,32,3,31],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[3,38,-1,-1],[3,39,3,37],[3,40,3,38],[3,41,3,39],[-1,-1,3,40]],"stap":[[-1,-1,3,1],[3,0,3,2],[3,1,3,3],[3,2,3,4],[3,3,3,5],[3,4,3,6],[3,5,3,7],[3,6,3,8],[3,7,3,9],[3,8,3,10],[3,9,3,11],[3,10,3,12],[3,11,3,13],[3,12,3,14],[3,13,3,15],[3,14,3,16],[3,15,3,17],[3,16,3,18],[3,17,3,19],[3,18,3,20],[3,19,4,20],[4,21,3,22],[3,21,3,23],[3,22,3,24],[3,23,3,25],[3,24,3,26],[3,25,3,27],[3,26,3,28],[3,27,3,29],[3,28,3,30],[3,29,3,31],[3,30,3,32],[3,31,3,33],[3,32,3,34],[3,33,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1]],"loop":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"skip":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"scafLoop":[],"stapLoop":[],"stap_colors":[[0,13369344]]},{"row":13,"col":17,"num":4,"scaf":[[-1,-1,4,1],[4,0,4,2],[4,1,4,3],[4,2,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[5,9,4,10],[4,9,4,11],[4,10,4,12],[4,11,4,13],[4,12,4,14],[4,13,4,15],[4,14,3,15],[3,16,4,17],[4,16,4,18],[4,17,4,19],[4,18,4,20],[4,19,4,21],[4,20,4,22],[4,21,4,23],[4,22,4,24],[4,23,4,25],[4,24,4,26],[4,25,4,27],[4,26,4,28],[4,27,4,29],[4,28,4,30],[4,29,4,31],[4,30,4,32],[4,31,4,33],[4,32,4,34],[4,33,4,35],[4,34,4,36],[4,35,4,37],[4,36,4,38],[4,37,4,39],[4,38,5,39],[-1,-1,-1,-1],[-1,-1,-1,-1]],"stap":[[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[4,10,-1,-1],[4,11,4,9],[4,12,4,10],[4,13,4,11],[4,14,4,12],[4,15,4,13],[4,16,4,14],[4,17,4,15],[4,18,4,16],[4,19,4,17],[4,20,4,18],[3,20,4,19],[4,22,3,21],[4,23,4,21],[4,24,4,22],[4,25,4,23],[4,26,4,24],[4,27,4,25],[4,28,4,26],[4,29,4,27],[4,30,4,28],[4,31,4,29],[4,32,4,30],[4,33,4,31],[4,34,4,32],[4,35,4,33],[4,36,4,34],[4,37,4,35],[4,38,4,36],[4,39,4,37],[-1,-1,4,38],[-1,-1,-1,-1],[-1,-1,-1,-1]],"loop":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"skip":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"scafLoop":[],"stapLoop":[],"stap_colors":[[39,8947848]]},{"row":12,"col":17,"num":5,"scaf":[[5,1,-1,-1],[5,2,5,0],[5,3,5,1],[-1,-1,5,2],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[5,10,4,9],[5,11,5,9],[5,12,5,10],[5,13,5,11],[5,14,5,12],[5,15,5,13],[5,16,5,14],[5,17,5,15],[5,18,5,16],[5,19,5,17],[5,20,5,18],[5,21,5,19],[5,22,5,20],[-1,-1,5,21],[5,24,-1,-1],[5,25,5,23],[5,26,5,24],[5,27,5,25],[5,28,5,26],[5,29,5,27],[5,30,5,28],[5,31,5,29],[5,32,5,30],[5,33,5,31],[5,34,5,32],[5,35,5,33],[5,36,5,34],[5,37,5,35],[5,38,5,36],[5,39,5,37],[4,39,5,38],[-1,-1,-1,-1],[-1,-1,-1,-1]],"stap":[[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1],[-1,-1,5,10],[5,9,5,11],[5,10,5,12],[5,11,5,13],[5,12,5,14],[5,13,5,15],[5,14,5,16],[5,15,5,17],[5,16,5,18],[5,17,5,19],[5,18,5,20],[5,19,5,21],[5,20,5,22],[5,21,5,23],[5,22,5,24],[5,23,5,25],[5,24,5,26],[5,25,5,27],[5,26,0,27],[0,28,5,29],[5,28,5,30],[5,29,5,31],[5,30,5,32],[5,31,5,33],[5,32,5,34],[5,33,5,35],[5,34,5,36],[5,35,5,37],[5,36,5,38],[5,37,5,39],[5,38,-1,-1],[-1,-1,-1,-1],[-1,-1,-1,-1]],"loop":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"skip":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"scafLoop":[],"stapLoop":[],"stap_colors":[[1,1]]}]}
diff --git a/mrdna/readers/segmentmodel_from_cadnano.py b/mrdna/readers/segmentmodel_from_cadnano.py
index 357638870fd6b8cebdd6b0ce81ee6573cd2292a6..676ff60362ccb613ade8070016123b9254c0a3ad 100644
--- a/mrdna/readers/segmentmodel_from_cadnano.py
+++ b/mrdna/readers/segmentmodel_from_cadnano.py
@@ -17,10 +17,42 @@ from ..model.dna_sequence import m13 as m13seq
## - doubly-nicked helices
## - helices that should be stacked across an empty region (crossovers from and end in the helix to another end in the helix)
## - circular constructs
-def decode_cadnano_part(json_data):
+def get_lattice(part):
+ lattice_type = None
+ _gt = part.getGridType()
+ try:
+ lattice_type = _gt.name.lower()
+ except:
+ if _gt == 1:
+ lattice_type = 'square'
+ elif _gt == 2:
+ lattice_type = 'honeycomb'
+ else:
+ print("WARNING: unable to determine cadnano part lattice type")
+ return lattice_type
+
+
+def read_json_file(filename):
+ import json
+ import re
import cadnano
from cadnano.document import Document
+ try:
+ with open(filename) as ch:
+ json_data = json.load(ch)
+ except:
+ with open(filename) as ch:
+ content = ""
+ for l in ch:
+ l = re.sub(r"'", r'"', l)
+ # https://stackoverflow.com/questions/4033633/handling-lazy-json-in-python-expecting-property-name
+ # l = re.sub(r"{\s*(\w)", r'{"\1', l)
+ # l = re.sub(r",\s*(\w)", r',"\1', l)
+ # l = re.sub(r"(\w):", r'\1":', l)
+ content += l+"\n"
+ json_data = json.loads(content)
+
try:
doc = Document()
cadnano.fileio.v3decode.decode(doc, json_data)
@@ -37,43 +69,67 @@ def decode_cadnano_part(json_data):
if decoder == 2:
""" It seems cadnano2.5 (as of ce6ff019) does not set the EulerZ for square lattice structures correctly, doing so here """
- l = _get_lattice(part)
+ l = get_lattice(part)
if l == 'square':
for id_num in part.getIdNums():
if part.vh_properties.loc[id_num,'eulerZ'] == 0:
part.vh_properties.loc[id_num,'eulerZ'] = 360*(6/10.5)
- json_df=pd.read_json("test.json")
- vslist=list(df["vstrands"])
- return part,pd.DataFrame(vslist)
+ df=pd.DataFrame(json_data["vstrands"])
+ n_df=df.set_index("num")
+ return part,n_df
+
+
+def get_helix_angle(part, helix_id, indices):
+ """ Get "start_orientation" for helix """
+ # import ipdb
+ # ipdb.set_trace()
+
+ """ FROM CADNANO2.5
+ + angle is CCW
+ - angle is CW
+ Right handed DNA rotates clockwise from 5' to 3'
+ we use the convention the 5' end starts at 0 degrees
+ and it's pair is minor_groove_angle degrees away
+ direction, hence the minus signs. eulerZ
+ """
+
+ hp, bpr, tpr, eulerZ, mgroove = self.part.vh_properties.loc[helix_id,['helical_pitch',
+ 'bases_per_repeat',
+ 'turns_per_repeat',
+ 'eulerZ',
+ 'minor_groove_angle']]
+ twist_per_base = tpr*360./bpr
+ # angle = eulerZ - twist_per_base*indices + 0.5*mgroove + 180
+ angle = eulerZ + twist_per_base*indices - 0.5*mgroove
+ return angle
+
+def ntcount(scafs):
+ def judge(i):
+ if i ==[-1,-1,-1,-1]:
+ return 0
+ else: return 1
+ n=np.array([judge(i) for i in scafs])
+ return np.sum(n)
-def get_lattice(part):
- lattice_type = None
- _gt = part.getGridType()
- try:
- lattice_type = _gt.name.lower()
- except:
- if _gt == 1:
- lattice_type = 'square'
- elif _gt == 2:
- lattice_type = 'honeycomb'
- else:
- print("WARNING: unable to determine cadnano part lattice type")
- return lattice_type
-
def mrdna_model_from_cadnano(json_data,**model_parameters):
- part,vslist=decode_cadnano_part(json_data)
- props = part.getModelProperties().copy()
+ part,vslist=decode_cadnano_part(json_data)
+ props = part.getModelProperties().copy()
- if props.get('point_type') == PointType.ARBITRARY:
+ if props.get('point_type') == PointType.ARBITRARY:
# TODO add code to encode Parts with ARBITRARY point configurations
- raise NotImplementedError("Not implemented")
- else:
- try:
- vh_props, origins = part.helixPropertiesAndOrigins()
- except:
- origins = {hid:part.getVirtualHelixOrigin(hid)[:2] for hid in part.getidNums()}
- cad_bps=part.getIndices(0)
+ raise NotImplementedError("Not implemented")
+ else:
+ try:
+ vh_props, origins = part.helixPropertiesAndOrigins()
+ except:
+ origins = {hid:part.getVirtualHelixOrigin(hid)[:2] for hid in part.getidNums()}
+ cad_bps=part.getIndices(0)
+ vslist["scafnt"]=[ntcount(vslist['scaf'][i]) for i in vslist.index]
+ vslist["stapnt"]=[ntcount(vslist['stap'][i]) for i in vslist.index]
+ totnt=np.sum(vslist["scafnt"])+np.sum(vslist["stapnt"])
+ nt_prop=pd.DataFrame(index=range(totnt),columns=["vh","zid","r","bp","stack","threeprime","seq","orientation"])
+
model = model_from_basepair_stack_3prime( r, bp, stack, three_prime, seq, orientation, **model_parameters )
diff --git a/mrdna/readers/test.ipynb b/mrdna/readers/test.ipynb
index 2a29aae486818012920dfd24aa4b7be3c7e1d490..34cdcbde6db29625b2d65397714178e712761444 100644
--- a/mrdna/readers/test.ipynb
+++ b/mrdna/readers/test.ipynb
@@ -2,8 +2,8 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 222,
- "id": "767c8226",
+ "execution_count": 2,
+ "id": "ab3deccf",
"metadata": {
"scrolled": true
},
@@ -18,8 +18,30 @@
},
{
"cell_type": "code",
- "execution_count": 226,
- "id": "1dc9b21a-360c-49a4-9ea5-c9916f27d962",
+ "execution_count": 7,
+ "id": "0de414ce",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import cadnano\n",
+ "from cadnano.document import Document\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "fdb603c1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df=pd.DataFrame(data=d)\n",
+ "df=df.set_index(\"num\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "6f322908",
"metadata": {},
"outputs": [
{
@@ -190,7 +212,7 @@
"5 [[9, 0]] "
]
},
- "execution_count": 226,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -201,19 +223,124 @@
},
{
"cell_type": "code",
- "execution_count": 225,
- "id": "bf2d37ca",
+ "execution_count": 14,
+ "id": "f77c2bad",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ }
+ ],
+ "source": [
+ "doc = Document()\n",
+ "def read_json_file(filename):\n",
+ " import json\n",
+ " import re\n",
+ "\n",
+ " try:\n",
+ " with open(filename) as ch:\n",
+ " data = json.load(ch)\n",
+ " except:\n",
+ " with open(filename) as ch:\n",
+ " content = \"\"\n",
+ " for l in ch:\n",
+ " l = re.sub(r\"'\", r'\"', l)\n",
+ " # https://stackoverflow.com/questions/4033633/handling-lazy-json-in-python-expecting-property-name\n",
+ " # l = re.sub(r\"{\\s*(\\w)\", r'{\"\\1', l)\n",
+ " # l = re.sub(r\",\\s*(\\w)\", r',\"\\1', l)\n",
+ " # l = re.sub(r\"(\\w):\", r'\\1\":', l)\n",
+ " content += l+\"\\n\"\n",
+ " data = json.loads(content)\n",
+ " return data\n",
+ "f=read_json_file(\"test.json\")\n",
+ "cadnano.fileio.v2decode.decode(doc, f)\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "a1df854a",
"metadata": {},
"outputs": [],
"source": [
- "df=pd.DataFrame(data=d)\n",
- "df=df.set_index(\"num\")"
+ "def get_lattice(part):\n",
+ " lattice_type = None\n",
+ " _gt = part.getGridType()\n",
+ " try:\n",
+ " lattice_type = _gt.name.lower()\n",
+ " except:\n",
+ " if _gt == 1:\n",
+ " lattice_type = 'square'\n",
+ " elif _gt == 2:\n",
+ " lattice_type = 'honeycomb'\n",
+ " else:\n",
+ " print(\"WARNING: unable to determine cadnano part lattice type\")\n",
+ " return lattice_type\n"
]
},
{
"cell_type": "code",
- "execution_count": 205,
- "id": "22a5db0b-2ce5-4af9-83f1-88114342c36d",
+ "execution_count": 121,
+ "id": "a88086bf",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_json_file(filename):\n",
+ " import json\n",
+ " import re\n",
+ " import cadnano\n",
+ " from cadnano.document import Document\n",
+ "\n",
+ " try:\n",
+ " with open(filename) as ch:\n",
+ " json_data = json.load(ch)\n",
+ " except:\n",
+ " with open(filename) as ch:\n",
+ " content = \"\"\n",
+ " for l in ch:\n",
+ " l = re.sub(r\"'\", r'\"', l)\n",
+ " # https://stackoverflow.com/questions/4033633/handling-lazy-json-in-python-expecting-property-name\n",
+ " # l = re.sub(r\"{\\s*(\\w)\", r'{\"\\1', l)\n",
+ " # l = re.sub(r\",\\s*(\\w)\", r',\"\\1', l)\n",
+ " # l = re.sub(r\"(\\w):\", r'\\1\":', l)\n",
+ " content += l+\"\\n\"\n",
+ " json_data = json.loads(content)\n",
+ "\n",
+ " try:\n",
+ " doc = Document()\n",
+ " cadnano.fileio.v3decode.decode(doc, json_data)\n",
+ " decoder = 3\n",
+ " except:\n",
+ " doc = Document()\n",
+ " cadnano.fileio.v2decode.decode(doc, json_data)\n",
+ " decoder = 2\n",
+ "\n",
+ " parts = [p for p in doc.getParts()]\n",
+ " if len(parts) != 1:\n",
+ " raise Exception(\"Only documents containing a single cadnano part are implemented at this time.\")\n",
+ " part = parts[0]\n",
+ "\n",
+ " if decoder == 2:\n",
+ " \"\"\" It seems cadnano2.5 (as of ce6ff019) does not set the EulerZ for square lattice structures correctly, doing so here \"\"\"\n",
+ " l = get_lattice(part)\n",
+ " if l == 'square':\n",
+ " for id_num in part.getIdNums():\n",
+ " if part.vh_properties.loc[id_num,'eulerZ'] == 0:\n",
+ " part.vh_properties.loc[id_num,'eulerZ'] = 360*(6/10.5)\n",
+ " df=pd.DataFrame(json_data[\"vstrands\"])\n",
+ " n_df=df.set_index(\"num\")\n",
+ " return part,n_df\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "id": "221a82ed",
"metadata": {},
"outputs": [
{
@@ -222,7 +349,7 @@
"[42, 42, 42, 42, 42, 42]"
]
},
- "execution_count": 205,
+ "execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
@@ -232,10 +359,348 @@
"bpnum"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 122,
+ "id": "25accfa8",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ }
+ ],
+ "source": [
+ "f,b=read_json_file(\"test.json\")\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "id": "5a0dec07",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Int64Index([0, 1, 2, 3, 4, 5], dtype='int64', name='num')"
+ ]
+ },
+ "execution_count": 52,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "b.index"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 83,
+ "id": "413e3e88",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def ntcount(scafs):\n",
+ " def judge(i):\n",
+ " if i ==[-1,-1,-1,-1]:\n",
+ " return 0\n",
+ " else: return 1\n",
+ " n=np.array([judge(i) for i in scafs])\n",
+ " return np.sum(n)\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 84,
+ "id": "e36edb50",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "b[\"scafnt\"]=[ntcount(b['scaf'][i]) for i in b.index]\n",
+ "b[\"stapnt\"]=[ntcount(b['stap'][i]) for i in b.index]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 123,
+ "id": "40764fb4",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "i=range(5)\n",
+ "col=[\"vh\",\"zid\",\"r\",\"bp\",\"stack\",\"threeprime\",\"seq\",\"orientation\"]\n",
+ "d=pd.DataFrame(index=i,columns=col)\n",
+ "d['vh']=[0,1,2,3,1]\n",
+ "d['zid']=[0,3,1,2,8]\n",
+ "d.set_index([\"vh\",\"zid\"],inplace=True)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 126,
+ "id": "f6fc8912",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>vh</th>\n",
+ " <th>zid</th>\n",
+ " <th>r</th>\n",
+ " <th>bp</th>\n",
+ " <th>stack</th>\n",
+ " <th>threeprime</th>\n",
+ " <th>seq</th>\n",
+ " <th>orientation</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1</td>\n",
+ " <td>8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " vh zid r bp stack threeprime seq orientation\n",
+ "0 0 0 NaN NaN NaN NaN NaN NaN\n",
+ "1 1 3 NaN NaN NaN NaN NaN NaN\n",
+ "2 2 1 NaN NaN NaN NaN NaN NaN\n",
+ "3 3 2 NaN NaN NaN NaN NaN NaN\n",
+ "4 1 8 NaN NaN NaN NaN NaN NaN"
+ ]
+ },
+ "execution_count": 126,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "d.reset_index()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9e5e1d1b",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 112,
+ "id": "42d23cd4",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>bp</th>\n",
+ " <th>stack</th>\n",
+ " <th>threeprime</th>\n",
+ " <th>seq</th>\n",
+ " <th>orientation</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>r</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1.0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1.0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>NaN</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>NaN</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>NaN</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " bp stack threeprime seq orientation\n",
+ "r \n",
+ "1.0 NaN NaN NaN NaN NaN\n",
+ "1.0 NaN NaN NaN NaN NaN\n",
+ "NaN NaN NaN NaN NaN NaN\n",
+ "NaN NaN NaN NaN NaN NaN\n",
+ "NaN NaN NaN NaN NaN NaN"
+ ]
+ },
+ "execution_count": 112,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "d"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 100,
+ "id": "9ed6d92a",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "KeyError",
+ "evalue": "\"None of [Int64Index([0, 0], dtype='int64')] are in the [columns]\"",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-100-a349feadc600>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0md\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;32m/data/server1/cmaffeo2/miniconda3/lib/python3.8/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 3509\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mis_iterator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3510\u001b[0m \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3511\u001b[0;31m \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_indexer_strict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"columns\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3513\u001b[0m \u001b[0;31m# take() does not accept boolean indexers\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/data/server1/cmaffeo2/miniconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36m_get_indexer_strict\u001b[0;34m(self, key, axis_name)\u001b[0m\n\u001b[1;32m 5780\u001b[0m \u001b[0mkeyarr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnew_indexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reindex_non_unique\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeyarr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5781\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5782\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_raise_if_missing\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeyarr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5783\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5784\u001b[0m \u001b[0mkeyarr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtake\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/data/server1/cmaffeo2/miniconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36m_raise_if_missing\u001b[0;34m(self, key, indexer, axis_name)\u001b[0m\n\u001b[1;32m 5840\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0muse_interval_msg\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5841\u001b[0m \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5842\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"None of [{key}] are in the [{axis_name}]\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5843\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5844\u001b[0m \u001b[0mnot_found\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mensure_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmissing_mask\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnonzero\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munique\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mKeyError\u001b[0m: \"None of [Int64Index([0, 0], dtype='int64')] are in the [columns]\""
+ ]
+ }
+ ],
+ "source": [
+ "d[[0,0]]"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 13,
- "id": "46079e58-4747-42ff-8b68-906c94440474",
+ "id": "41cad09e",
"metadata": {},
"outputs": [
{
@@ -256,7 +721,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "625c831b",
+ "id": "ee7a5b2f",
"metadata": {},
"outputs": [
{
@@ -278,7 +743,7 @@
{
"cell_type": "code",
"execution_count": 198,
- "id": "0f88b0bb-bc42-4ef3-88e7-518ae2628c0d",
+ "id": "5308fd27",
"metadata": {},
"outputs": [
{
@@ -300,7 +765,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "6a4129c2",
+ "id": "a173a0cc",
"metadata": {},
"outputs": [
{
@@ -321,7 +786,7 @@
{
"cell_type": "code",
"execution_count": 173,
- "id": "aefe656e",
+ "id": "3ac307d0",
"metadata": {},
"outputs": [],
"source": [
@@ -357,7 +822,7 @@
{
"cell_type": "code",
"execution_count": 177,
- "id": "e154a8c3",
+ "id": "6c3869e9",
"metadata": {},
"outputs": [],
"source": [
@@ -393,7 +858,7 @@
{
"cell_type": "code",
"execution_count": 187,
- "id": "0a709be4-a426-4eb0-a82f-49905307b07b",
+ "id": "a938b5d1",
"metadata": {},
"outputs": [
{
@@ -620,7 +1085,7 @@
{
"cell_type": "code",
"execution_count": 142,
- "id": "125b30e0-7dcc-464a-b3cf-cfbf090d3982",
+ "id": "28fa9e4a",
"metadata": {},
"outputs": [],
"source": [
@@ -657,7 +1122,7 @@
{
"cell_type": "code",
"execution_count": 117,
- "id": "5b149587-3224-4137-a7bc-e41aa4049034",
+ "id": "5876b835",
"metadata": {},
"outputs": [],
"source": [
@@ -678,7 +1143,7 @@
{
"cell_type": "code",
"execution_count": 116,
- "id": "09619e4e",
+ "id": "b27560ea",
"metadata": {},
"outputs": [
{
@@ -890,7 +1355,7 @@
{
"cell_type": "code",
"execution_count": 157,
- "id": "88d989b9",
+ "id": "c2ac4f18",
"metadata": {},
"outputs": [
{
@@ -914,7 +1379,7 @@
{
"cell_type": "code",
"execution_count": 152,
- "id": "2909c273",
+ "id": "11333080",
"metadata": {},
"outputs": [
{
@@ -935,7 +1400,7 @@
{
"cell_type": "code",
"execution_count": 62,
- "id": "422e2b48",
+ "id": "c15af839",
"metadata": {},
"outputs": [
{
@@ -1163,7 +1628,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "69c011ff",
+ "id": "eda2056d",
"metadata": {},
"outputs": [],
"source": [
@@ -1289,7 +1754,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "f2693e7a",
+ "id": "f7efd378",
"metadata": {},
"outputs": [],
"source": [
@@ -1310,7 +1775,7 @@
{
"cell_type": "code",
"execution_count": 20,
- "id": "a4594752",
+ "id": "1422eca5",
"metadata": {},
"outputs": [
{
@@ -1372,7 +1837,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "ca071163",
+ "id": "cf5a3dbd",
"metadata": {},
"outputs": [
{
@@ -1434,7 +1899,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e5913163",
+ "id": "98cb9b38",
"metadata": {},
"outputs": [],
"source": [
@@ -1447,7 +1912,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "3eefca8f",
+ "id": "ff952b38",
"metadata": {},
"outputs": [
{
@@ -1468,7 +1933,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "268d5c04",
+ "id": "85083378",
"metadata": {},
"outputs": [
{
@@ -1517,7 +1982,7 @@
{
"cell_type": "code",
"execution_count": 36,
- "id": "d3d42e33",
+ "id": "ded55624",
"metadata": {},
"outputs": [
{
@@ -1579,7 +2044,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "2cc3f477",
+ "id": "40a7b76d",
"metadata": {},
"outputs": [
{
@@ -1605,7 +2070,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "5d50f58a",
+ "id": "f994ff10",
"metadata": {},
"outputs": [],
"source": []
@@ -1613,7 +2078,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "3b40b71b",
+ "id": "5144726b",
"metadata": {},
"outputs": [
{
@@ -1633,7 +2098,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "6915bad6",
+ "id": "5c836eac",
"metadata": {},
"outputs": [
{
@@ -1654,7 +2119,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "1c16c59d",
+ "id": "2c3ce8b1",
"metadata": {},
"outputs": [
{
@@ -1724,7 +2189,7 @@
{
"cell_type": "code",
"execution_count": 16,
- "id": "c61d9586",
+ "id": "137db876",
"metadata": {},
"outputs": [],
"source": [
@@ -1735,7 +2200,7 @@
{
"cell_type": "code",
"execution_count": 26,
- "id": "aeca0546",
+ "id": "8210cbee",
"metadata": {},
"outputs": [
{
@@ -1844,7 +2309,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "90a54834",
+ "id": "4ef92d58",
"metadata": {},
"outputs": [
{
@@ -1865,7 +2330,7 @@
{
"cell_type": "code",
"execution_count": 10,
- "id": "de00fb7e",
+ "id": "57059a9e",
"metadata": {},
"outputs": [
{
@@ -1896,7 +2361,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "716ff2ed",
+ "id": "001aef7e",
"metadata": {},
"outputs": [
{
@@ -2393,7 +2858,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "766d0ecd",
+ "id": "8feaa1ca",
"metadata": {},
"outputs": [
{
@@ -2427,7 +2892,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "05456be4",
+ "id": "4455fa61",
"metadata": {},
"outputs": [
{
@@ -2447,7 +2912,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "cd1a5604",
+ "id": "605a19c2",
"metadata": {},
"outputs": [],
"source": [
@@ -2457,7 +2922,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "4346f1fc",
+ "id": "c45d0282",
"metadata": {},
"outputs": [
{
@@ -2478,7 +2943,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "294094f9",
+ "id": "f0d25377",
"metadata": {},
"outputs": [
{
@@ -2505,7 +2970,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b3d29c52",
+ "id": "bf3a74cf",
"metadata": {},
"outputs": [],
"source": []
@@ -2513,7 +2978,7 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Python 3 (ipykernel)",
+ "display_name": "Python 3",
"language": "python",
"name": "python3"
},
@@ -2527,7 +2992,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.19"
+ "version": "3.8.18"
}
},
"nbformat": 4,
diff --git a/mrdna/readers/test3.ipynb b/mrdna/readers/test3.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..0985a5505ceb46c7a9aba91935499a47da069c90
--- /dev/null
+++ b/mrdna/readers/test3.ipynb
@@ -0,0 +1,2137 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 124,
+ "id": "303b2da7",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "dict_keys(['row', 'col', 'num', 'scaf', 'stap', 'loop', 'skip', 'scafLoop', 'stapLoop', 'stap_colors'])"
+ ]
+ },
+ "execution_count": 124,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "import pickle\n",
+ "import numpy as np\n",
+ "df=pd.read_json(\"test.json\")\n",
+ "df[\"vstrands\"][0].keys()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 164,
+ "id": "2d42bba6",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[[-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [0, 3, -1, -1],\n",
+ " [0, 4, 0, 2],\n",
+ " [0, 5, 0, 3],\n",
+ " [0, 6, 0, 4],\n",
+ " [0, 7, 0, 5],\n",
+ " [0, 8, 0, 6],\n",
+ " [0, 9, 0, 7],\n",
+ " [0, 10, 0, 8],\n",
+ " [0, 11, 0, 9],\n",
+ " [0, 12, 0, 10],\n",
+ " [0, 13, 0, 11],\n",
+ " [0, 14, 0, 12],\n",
+ " [0, 15, 0, 13],\n",
+ " [0, 16, 0, 14],\n",
+ " [0, 17, 0, 15],\n",
+ " [0, 18, 0, 16],\n",
+ " [0, 19, 0, 17],\n",
+ " [0, 20, 0, 18],\n",
+ " [1, 20, 0, 19],\n",
+ " [0, 22, 1, 21],\n",
+ " [0, 23, 0, 21],\n",
+ " [-1, -1, 0, 22],\n",
+ " [0, 25, -1, -1],\n",
+ " [0, 26, 0, 24],\n",
+ " [0, 27, 0, 25],\n",
+ " [5, 27, 0, 26],\n",
+ " [0, 29, 5, 28],\n",
+ " [0, 30, 0, 28],\n",
+ " [0, 31, 0, 29],\n",
+ " [0, 32, 0, 30],\n",
+ " [0, 33, 0, 31],\n",
+ " [0, 34, 0, 32],\n",
+ " [0, 35, 0, 33],\n",
+ " [0, 36, 0, 34],\n",
+ " [0, 37, 0, 35],\n",
+ " [0, 38, 0, 36],\n",
+ " [-1, -1, 0, 37],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1]]"
+ ]
+ },
+ "execution_count": 164,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df[\"vstrands\"][0][\"stap\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 65,
+ "id": "5e1ea864",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "UnicodeDecodeError",
+ "evalue": "'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mUnicodeDecodeError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-65-71f198107f5e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"test.virt2nuc\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\"r\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mpickle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;32m/data/server1/cmaffeo2/miniconda3/lib/python3.8/codecs.py\u001b[0m in \u001b[0;36mdecode\u001b[0;34m(self, input, final)\u001b[0m\n\u001b[1;32m 320\u001b[0m \u001b[0;31m# decode input (taking the buffer into account)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 321\u001b[0m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuffer\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 322\u001b[0;31m \u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconsumed\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_buffer_decode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merrors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinal\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 323\u001b[0m \u001b[0;31m# keep undecoded input until the next call\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 324\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuffer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mconsumed\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mUnicodeDecodeError\u001b[0m: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte"
+ ]
+ }
+ ],
+ "source": [
+ "f=open(\"test.virt2nuc\",\"r\")\n",
+ "pickle.load(f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 119,
+ "id": "86a109f4",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "210"
+ ]
+ },
+ "execution_count": 119,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "vh_vb,pattern=pd.read_pickle(\"test.virt2nuc\")\n",
+ "len(vh_vb._scaf)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "id": "ab020675",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{0: (12, 16), 1: (12, 15), 2: (13, 15), 3: (13, 16), 4: (13, 17), 5: (12, 17)}"
+ ]
+ },
+ "execution_count": 66,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pattern"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 141,
+ "id": "0b152186",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(0, 40)\n",
+ "(0, 41)\n"
+ ]
+ },
+ {
+ "ename": "AttributeError",
+ "evalue": "'NoneType' object has no attribute 'append'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-141-a0e59df19136>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0ms\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdecode_vh_vb\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"test.virt2nuc\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_dict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m<ipython-input-140-99891f72666f>\u001b[0m in \u001b[0;36mdecode_vh_vb\u001b[0;34m(virt2nuc)\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0mscafs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvh_vb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_scaf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 22\u001b[0m \u001b[0mstaps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvh_vb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stap\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 23\u001b[0;31m \u001b[0mscaf_strands\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfind_segs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscafs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 25\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mvh_list\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m<ipython-input-140-99891f72666f>\u001b[0m in \u001b[0;36mfind_segs\u001b[0;34m(vir2nuc_scaf)\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0mb\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvir2nuc_scaf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 10\u001b[0;31m \u001b[0moligos\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0moligo\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0moligos\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0moligo\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvir2nuc_scaf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 11\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0moligos\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'append'"
+ ]
+ }
+ ],
+ "source": [
+ "s=decode_vh_vb(\"test.virt2nuc\")[0]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 165,
+ "id": "852198d8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class strands():\n",
+ " def __init__(self):\n",
+ " self.row=0 \n",
+ " self.col=0\n",
+ " self.num=0\n",
+ " self.scaf=[]\n",
+ " self.stap=[]\n",
+ " self.loop=[]\n",
+ " self.skip=[]\n",
+ " self.scafLoop=[]\n",
+ " self.stapLoop=[]\n",
+ " self.stap_colors=[]\n",
+ " self.scaf_contact={}\n",
+ " self.scaf_pattern=True\n",
+ " self.stap_connect={}\n",
+ " def to_dict(self):\n",
+ " d={}\n",
+ " d['row']=self.row\n",
+ " d['col']=self.col\n",
+ " d['num']=self.num\n",
+ " d['scaf']=self.scaf\n",
+ " d['stap']=self.stap\n",
+ " d['loop']=self.loop\n",
+ " d['skip']=self.skip\n",
+ " d['scafLoop']=self.scafLoop\n",
+ " d['stapLoop']=self.stapLoop\n",
+ " d['stap_colors']=self.stap_colors\n",
+ " return d\n",
+ " \n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 160,
+ "id": "b4064749",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def find_segs(vir2nuc_scaf):\n",
+ " oligos={}\n",
+ " for i in range(len(vir2nuc_scaf)):\n",
+ " oligo,ox_ind=list(vir2nuc_scaf.values())[i]\n",
+ " if oligo not in oligos.keys():\n",
+ " oligos[oligo]=[]\n",
+ " oligos[oligo].append(list(vir2nuc_scaf.keys())[i])\n",
+ " return oligos\n",
+ " \n",
+ "def decode_vh_vb(virt2nuc):\n",
+ " vh_list=[]\n",
+ " vh_vb,pattern=pd.read_pickle(virt2nuc)\n",
+ " for i in pattern.keys():\n",
+ " s=strands()\n",
+ " s.row,s.col=pattern[i]\n",
+ " s.num=i\n",
+ " vh_list.append(s)\n",
+ " scafs=vh_vb._scaf\n",
+ " staps=vh_vb._stap\n",
+ " scaf_strands=find_segs(scafs)\n",
+ " scaf_oligos=list(scaf_strands.keys())\n",
+ " for i in scaf_oligos:\n",
+ " bases=len(scaf_oligos)\n",
+ " vh0,vb0=scaf_oligos[i][0]\n",
+ " vh1,vb1=scaf_oligos[i][1]\n",
+ " if vb0>vb1:#53\n",
+ " vh_list[vh0].scaf_contact[vb0]=[-1,-1,vh1,vb1]\n",
+ " self.scaf_pattern=True\n",
+ " else: #35\n",
+ " vh_list[vh0].scaf_contact[vb0]=[vh1,vb1,-1,-1]\n",
+ " self.scaf_pattern=False\n",
+ " for i in range(len()):\n",
+ " \n",
+ " \n",
+ " return vh_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 163,
+ "id": "ae57cd6f",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{0: [(0, 39), (0, 40), (0, 41)],\n",
+ " 1: [(1, 41), (1, 40), (1, 39)],\n",
+ " 2: [(2, 39), (2, 40), (2, 41)],\n",
+ " 4: [(3, 41), (3, 40), (3, 39), (3, 38), (3, 37)],\n",
+ " 5: [(4, 0), (4, 1), (4, 2), (4, 3)],\n",
+ " 6: [(5, 3), (5, 2), (5, 1), (5, 0)],\n",
+ " 7: [(5, 22),\n",
+ " (5, 21),\n",
+ " (5, 20),\n",
+ " (5, 19),\n",
+ " (5, 18),\n",
+ " (5, 17),\n",
+ " (5, 16),\n",
+ " (5, 15),\n",
+ " (5, 14),\n",
+ " (5, 13),\n",
+ " (5, 12),\n",
+ " (5, 11),\n",
+ " (5, 10),\n",
+ " (5, 9),\n",
+ " (4, 9),\n",
+ " (4, 10),\n",
+ " (4, 11),\n",
+ " (4, 12),\n",
+ " (4, 13),\n",
+ " (4, 14),\n",
+ " (4, 15),\n",
+ " (3, 15),\n",
+ " (3, 14),\n",
+ " (3, 13),\n",
+ " (3, 12),\n",
+ " (3, 11),\n",
+ " (3, 10),\n",
+ " (3, 9),\n",
+ " (3, 8),\n",
+ " (3, 7),\n",
+ " (3, 6),\n",
+ " (3, 5),\n",
+ " (3, 4),\n",
+ " (3, 3),\n",
+ " (3, 2),\n",
+ " (2, 2),\n",
+ " (2, 3),\n",
+ " (2, 4),\n",
+ " (2, 5),\n",
+ " (2, 6),\n",
+ " (2, 7),\n",
+ " (2, 8),\n",
+ " (2, 9),\n",
+ " (2, 10),\n",
+ " (2, 11),\n",
+ " (2, 12),\n",
+ " (2, 13),\n",
+ " (2, 14),\n",
+ " (2, 15),\n",
+ " (2, 16),\n",
+ " (2, 17),\n",
+ " (2, 18),\n",
+ " (1, 18),\n",
+ " (1, 17),\n",
+ " (1, 16),\n",
+ " (1, 15),\n",
+ " (1, 14),\n",
+ " (1, 13),\n",
+ " (1, 12),\n",
+ " (1, 11),\n",
+ " (1, 10),\n",
+ " (1, 9),\n",
+ " (1, 8),\n",
+ " (1, 7),\n",
+ " (1, 6),\n",
+ " (1, 5),\n",
+ " (0, 5),\n",
+ " (0, 6),\n",
+ " (0, 7),\n",
+ " (0, 8),\n",
+ " (0, 9),\n",
+ " (0, 10),\n",
+ " (0, 11),\n",
+ " (0, 12),\n",
+ " (0, 13),\n",
+ " (0, 14),\n",
+ " (0, 15),\n",
+ " (0, 16),\n",
+ " (0, 17),\n",
+ " (0, 18),\n",
+ " (0, 19),\n",
+ " (0, 20),\n",
+ " (0, 21),\n",
+ " (0, 22),\n",
+ " (0, 23),\n",
+ " (0, 24),\n",
+ " (0, 25),\n",
+ " (0, 26),\n",
+ " (0, 27),\n",
+ " (0, 28),\n",
+ " (0, 29),\n",
+ " (0, 30),\n",
+ " (0, 31),\n",
+ " (0, 32),\n",
+ " (0, 33),\n",
+ " (0, 34),\n",
+ " (0, 35),\n",
+ " (0, 36),\n",
+ " (1, 36),\n",
+ " (1, 35),\n",
+ " (1, 34),\n",
+ " (1, 33),\n",
+ " (1, 32),\n",
+ " (1, 31),\n",
+ " (1, 30),\n",
+ " (1, 29),\n",
+ " (1, 28),\n",
+ " (1, 27),\n",
+ " (1, 26),\n",
+ " (1, 25),\n",
+ " (1, 24),\n",
+ " (1, 23),\n",
+ " (1, 22),\n",
+ " (1, 21),\n",
+ " (1, 20),\n",
+ " (1, 19),\n",
+ " (2, 19),\n",
+ " (2, 20),\n",
+ " (2, 21),\n",
+ " (2, 22),\n",
+ " (2, 23),\n",
+ " (2, 24),\n",
+ " (2, 25),\n",
+ " (2, 26),\n",
+ " (2, 27),\n",
+ " (2, 28),\n",
+ " (2, 29),\n",
+ " (2, 30),\n",
+ " (2, 31),\n",
+ " (2, 32),\n",
+ " (3, 32),\n",
+ " (3, 31),\n",
+ " (3, 30),\n",
+ " (3, 29),\n",
+ " (3, 28),\n",
+ " (3, 27),\n",
+ " (3, 26),\n",
+ " (3, 25),\n",
+ " (3, 24),\n",
+ " (3, 23),\n",
+ " (3, 22),\n",
+ " (3, 21),\n",
+ " (3, 20),\n",
+ " (3, 19),\n",
+ " (3, 18),\n",
+ " (3, 17),\n",
+ " (3, 16),\n",
+ " (4, 16),\n",
+ " (4, 17),\n",
+ " (4, 18),\n",
+ " (4, 19),\n",
+ " (4, 20),\n",
+ " (4, 21),\n",
+ " (4, 22),\n",
+ " (4, 23),\n",
+ " (4, 24),\n",
+ " (4, 25),\n",
+ " (4, 26),\n",
+ " (4, 27),\n",
+ " (4, 28),\n",
+ " (4, 29),\n",
+ " (4, 30),\n",
+ " (4, 31),\n",
+ " (4, 32),\n",
+ " (4, 33),\n",
+ " (4, 34),\n",
+ " (4, 35),\n",
+ " (4, 36),\n",
+ " (4, 37),\n",
+ " (4, 38),\n",
+ " (4, 39),\n",
+ " (5, 39),\n",
+ " (5, 38),\n",
+ " (5, 37),\n",
+ " (5, 36),\n",
+ " (5, 35),\n",
+ " (5, 34),\n",
+ " (5, 33),\n",
+ " (5, 32),\n",
+ " (5, 31),\n",
+ " (5, 30),\n",
+ " (5, 29),\n",
+ " (5, 28),\n",
+ " (5, 27),\n",
+ " (5, 26),\n",
+ " (5, 25),\n",
+ " (5, 24),\n",
+ " (5, 23)]}"
+ ]
+ },
+ "execution_count": 163,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "scafs=vh_vb._scaf\n",
+ "s=list(scafs.values())\n",
+ "len(scafs)\n",
+ "find_segs(scafs)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 157,
+ "id": "d4698785",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[(1, 2)]"
+ ]
+ },
+ "execution_count": 157,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "oligos[0]=[]\n",
+ "L=[]\n",
+ "L.append((1,2))\n",
+ "L"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 152,
+ "id": "2b98d0e2",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(0, 39)"
+ ]
+ },
+ "execution_count": 152,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "list(scafs.keys())[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "id": "f666ffb1",
+ "metadata": {
+ "scrolled": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{(2, 34): (3, [43]),\n",
+ " (2, 33): (3, [42]),\n",
+ " (2, 32): (3, [41]),\n",
+ " (2, 31): (3, [40]),\n",
+ " (2, 30): (3, [39]),\n",
+ " (2, 29): (3, [38]),\n",
+ " (2, 28): (3, [37]),\n",
+ " (2, 27): (3, [36]),\n",
+ " (2, 26): (3, [35]),\n",
+ " (2, 25): (3, [34]),\n",
+ " (2, 24): (3, [33]),\n",
+ " (2, 23): (3, [32]),\n",
+ " (2, 22): (3, [31]),\n",
+ " (2, 21): (3, [30]),\n",
+ " (2, 20): (3, [29]),\n",
+ " (2, 19): (3, [28]),\n",
+ " (2, 18): (3, [27]),\n",
+ " (2, 17): (3, [26]),\n",
+ " (2, 16): (3, [25]),\n",
+ " (2, 15): (3, [24]),\n",
+ " (2, 14): (3, [23]),\n",
+ " (2, 13): (3, [22]),\n",
+ " (2, 12): (3, [21]),\n",
+ " (2, 11): (3, [20]),\n",
+ " (2, 10): (3, [19]),\n",
+ " (2, 9): (3, [18]),\n",
+ " (2, 8): (3, [17]),\n",
+ " (2, 7): (3, [16]),\n",
+ " (2, 6): (3, [15]),\n",
+ " (2, 5): (3, [14]),\n",
+ " (2, 4): (3, [13]),\n",
+ " (2, 3): (3, [12]),\n",
+ " (2, 2): (3, [11]),\n",
+ " (2, 1): (3, [10]),\n",
+ " (2, 0): (3, [9]),\n",
+ " (1, 3): (8, [281]),\n",
+ " (1, 4): (8, [280]),\n",
+ " (1, 5): (8, [279]),\n",
+ " (1, 6): (8, [278]),\n",
+ " (1, 7): (8, [277]),\n",
+ " (1, 8): (8, [276]),\n",
+ " (1, 9): (8, [275]),\n",
+ " (1, 10): (8, [274]),\n",
+ " (1, 11): (8, [273]),\n",
+ " (1, 12): (8, [272]),\n",
+ " (1, 13): (8, [271]),\n",
+ " (1, 14): (8, [270]),\n",
+ " (1, 15): (8, [269]),\n",
+ " (1, 16): (8, [268]),\n",
+ " (1, 17): (8, [267]),\n",
+ " (1, 18): (8, [266]),\n",
+ " (1, 19): (8, [265]),\n",
+ " (1, 20): (8, [264]),\n",
+ " (0, 20): (8, [263]),\n",
+ " (0, 19): (8, [262]),\n",
+ " (0, 18): (8, [261]),\n",
+ " (0, 17): (8, [260]),\n",
+ " (0, 16): (8, [259]),\n",
+ " (0, 15): (8, [258]),\n",
+ " (0, 14): (8, [257]),\n",
+ " (0, 13): (8, [256]),\n",
+ " (0, 12): (8, [255]),\n",
+ " (0, 11): (8, [254]),\n",
+ " (0, 10): (8, [253]),\n",
+ " (0, 9): (8, [252]),\n",
+ " (0, 8): (8, [251]),\n",
+ " (0, 7): (8, [250]),\n",
+ " (0, 6): (8, [249]),\n",
+ " (0, 5): (8, [248]),\n",
+ " (0, 4): (8, [247]),\n",
+ " (0, 3): (8, [246]),\n",
+ " (0, 2): (8, [245]),\n",
+ " (0, 23): (9, [302]),\n",
+ " (0, 22): (9, [301]),\n",
+ " (0, 21): (9, [300]),\n",
+ " (1, 21): (9, [299]),\n",
+ " (1, 22): (9, [298]),\n",
+ " (1, 23): (9, [297]),\n",
+ " (1, 24): (9, [296]),\n",
+ " (1, 25): (9, [295]),\n",
+ " (1, 26): (9, [294]),\n",
+ " (1, 27): (9, [293]),\n",
+ " (1, 28): (9, [292]),\n",
+ " (1, 29): (9, [291]),\n",
+ " (1, 30): (9, [290]),\n",
+ " (1, 31): (9, [289]),\n",
+ " (1, 32): (9, [288]),\n",
+ " (1, 33): (9, [287]),\n",
+ " (1, 34): (9, [286]),\n",
+ " (1, 35): (9, [285]),\n",
+ " (1, 36): (9, [284]),\n",
+ " (1, 37): (9, [283]),\n",
+ " (1, 38): (9, [282]),\n",
+ " (5, 9): (10, [325]),\n",
+ " (5, 10): (10, [324]),\n",
+ " (5, 11): (10, [323]),\n",
+ " (5, 12): (10, [322]),\n",
+ " (5, 13): (10, [321]),\n",
+ " (5, 14): (10, [320]),\n",
+ " (5, 15): (10, [319]),\n",
+ " (5, 16): (10, [318]),\n",
+ " (5, 17): (10, [317]),\n",
+ " (5, 18): (10, [316]),\n",
+ " (5, 19): (10, [315]),\n",
+ " (5, 20): (10, [314]),\n",
+ " (5, 21): (10, [313]),\n",
+ " (5, 22): (10, [312]),\n",
+ " (5, 23): (10, [311]),\n",
+ " (5, 24): (10, [310]),\n",
+ " (5, 25): (10, [309]),\n",
+ " (5, 26): (10, [308]),\n",
+ " (5, 27): (10, [307]),\n",
+ " (0, 27): (10, [306]),\n",
+ " (0, 26): (10, [305]),\n",
+ " (0, 25): (10, [304]),\n",
+ " (0, 24): (10, [303]),\n",
+ " (0, 38): (11, [348]),\n",
+ " (0, 37): (11, [347]),\n",
+ " (0, 36): (11, [346]),\n",
+ " (0, 35): (11, [345]),\n",
+ " (0, 34): (11, [344]),\n",
+ " (0, 33): (11, [343]),\n",
+ " (0, 32): (11, [342]),\n",
+ " (0, 31): (11, [341]),\n",
+ " (0, 30): (11, [340]),\n",
+ " (0, 29): (11, [339]),\n",
+ " (0, 28): (11, [338]),\n",
+ " (5, 28): (11, [337]),\n",
+ " (5, 29): (11, [336]),\n",
+ " (5, 30): (11, [335]),\n",
+ " (5, 31): (11, [334]),\n",
+ " (5, 32): (11, [333]),\n",
+ " (5, 33): (11, [332]),\n",
+ " (5, 34): (11, [331]),\n",
+ " (5, 35): (11, [330]),\n",
+ " (5, 36): (11, [329]),\n",
+ " (5, 37): (11, [328]),\n",
+ " (5, 38): (11, [327]),\n",
+ " (5, 39): (11, [326]),\n",
+ " (3, 0): (12, [381]),\n",
+ " (3, 1): (12, [380]),\n",
+ " (3, 2): (12, [379]),\n",
+ " (3, 3): (12, [378]),\n",
+ " (3, 4): (12, [377]),\n",
+ " (3, 5): (12, [376]),\n",
+ " (3, 6): (12, [375]),\n",
+ " (3, 7): (12, [374]),\n",
+ " (3, 8): (12, [373]),\n",
+ " (3, 9): (12, [372]),\n",
+ " (3, 10): (12, [371]),\n",
+ " (3, 11): (12, [370]),\n",
+ " (3, 12): (12, [369]),\n",
+ " (3, 13): (12, [368]),\n",
+ " (3, 14): (12, [367]),\n",
+ " (3, 15): (12, [366]),\n",
+ " (3, 16): (12, [365]),\n",
+ " (3, 17): (12, [364]),\n",
+ " (3, 18): (12, [363]),\n",
+ " (3, 19): (12, [362]),\n",
+ " (3, 20): (12, [361]),\n",
+ " (4, 20): (12, [360]),\n",
+ " (4, 19): (12, [359]),\n",
+ " (4, 18): (12, [358]),\n",
+ " (4, 17): (12, [357]),\n",
+ " (4, 16): (12, [356]),\n",
+ " (4, 15): (12, [355]),\n",
+ " (4, 14): (12, [354]),\n",
+ " (4, 13): (12, [353]),\n",
+ " (4, 12): (12, [352]),\n",
+ " (4, 11): (12, [351]),\n",
+ " (4, 10): (12, [350]),\n",
+ " (4, 9): (12, [349]),\n",
+ " (4, 39): (13, [414]),\n",
+ " (4, 38): (13, [413]),\n",
+ " (4, 37): (13, [412]),\n",
+ " (4, 36): (13, [411]),\n",
+ " (4, 35): (13, [410]),\n",
+ " (4, 34): (13, [409]),\n",
+ " (4, 33): (13, [408]),\n",
+ " (4, 32): (13, [407]),\n",
+ " (4, 31): (13, [406]),\n",
+ " (4, 30): (13, [405]),\n",
+ " (4, 29): (13, [404]),\n",
+ " (4, 28): (13, [403]),\n",
+ " (4, 27): (13, [402]),\n",
+ " (4, 26): (13, [401]),\n",
+ " (4, 25): (13, [400]),\n",
+ " (4, 24): (13, [399]),\n",
+ " (4, 23): (13, [398]),\n",
+ " (4, 22): (13, [397]),\n",
+ " (4, 21): (13, [396]),\n",
+ " (3, 21): (13, [395]),\n",
+ " (3, 22): (13, [394]),\n",
+ " (3, 23): (13, [393]),\n",
+ " (3, 24): (13, [392]),\n",
+ " (3, 25): (13, [391]),\n",
+ " (3, 26): (13, [390]),\n",
+ " (3, 27): (13, [389]),\n",
+ " (3, 28): (13, [388]),\n",
+ " (3, 29): (13, [387]),\n",
+ " (3, 30): (13, [386]),\n",
+ " (3, 31): (13, [385]),\n",
+ " (3, 32): (13, [384]),\n",
+ " (3, 33): (13, [383]),\n",
+ " (3, 34): (13, [382])}"
+ ]
+ },
+ "execution_count": 62,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s=vh_vb.__dict__\n",
+ "scafs=s[\"_scaf\"]\n",
+ "staps=s[\"_stap\"]\n",
+ "staps"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "04da1a1e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class vstrands (object):\n",
+ "\n",
+ " def __init__(self):\n",
+ " self.vhelices = []\n",
+ "\n",
+ " def add_vhelix(self, toadd):\n",
+ " self.vhelices.append(toadd)\n",
+ "\n",
+ " def bbox(self):\n",
+ " rows = []\n",
+ " cols = []\n",
+ " lens = []\n",
+ " for h in self.vhelices:\n",
+ " rows.append(h.row)\n",
+ " cols.append(h.col)\n",
+ " lens.append(len(h.stap))\n",
+ "\n",
+ " dr = DIST_SQUARE * (max(rows) - min(rows) + 2)\n",
+ " dc = DIST_SQUARE * (max(cols) - min(cols) + 2)\n",
+ " dl = 0.34 * (max(lens) + 2)\n",
+ " \n",
+ " return 2 * max([dr, dc, dl]) * BOX_FACTOR\n",
+ " \n",
+ " def __str__(self):\n",
+ " a = '{\\n\"vstrands\":[\\n'\n",
+ " if len(self.vhelices) > 0:\n",
+ " for h in self.vhelices:\n",
+ " a = a + str(h) + ','\n",
+ " a = a[0:len(a) - 1]\n",
+ " a = a + '}\\n'\n",
+ " return a\n",
+ "class vhelix (object):\n",
+ "\n",
+ " def __init__(self):\n",
+ " self.stapLoop = []\n",
+ " self.scafLoop = []\n",
+ " self.skip = []\n",
+ " self.loop = []\n",
+ " self.stap_colors = []\n",
+ " self.row = 0\n",
+ " self.col = 0\n",
+ " self.num = 0\n",
+ " self.stap = []\n",
+ " self.scaf = []\n",
+ " self.cad_index = -1\n",
+ " self.skiploop_bases = 0\n",
+ "\n",
+ " def get_length(self):\n",
+ " return max (len(self.scaf), len(self.stap))\n",
+ "\n",
+ " len = property (get_length)\n",
+ "\n",
+ " def add_square(self, toadd, which):\n",
+ " if which == 'stap':\n",
+ " self.stap.append(toadd)\n",
+ " elif which == 'scaf':\n",
+ " self.scaf.append (toadd)\n",
+ " else:\n",
+ " base.Logger.log(\"Cannot add square that is not scaf or stap. Dying now\", base.Logger.CRITICAL)\n",
+ " sys.exit(1)\n",
+ " \n",
+ " def __str__(self):\n",
+ " a = '{\\n'\n",
+ "\n",
+ " a = a + '\"stapLoop\":['\n",
+ " if len(self.stapLoop) > 0:\n",
+ " for i in self.stapLoop:\n",
+ " a = a + str(i) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + '],\\n'\n",
+ " a = a + '\"skip\":['\n",
+ " if len(self.skip) > 0:\n",
+ " for e in self.skip:\n",
+ " a = a + str(e) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + '],\\n'\n",
+ " \n",
+ " a = a + '\"loop\":['\n",
+ " if len(self.loop) > 0:\n",
+ " for e in self.loop:\n",
+ " a = a + str(e) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + '],\\n'\n",
+ " \n",
+ " a = a + '\"stap_colors\":['\n",
+ " if len (self.stap_colors) > 0:\n",
+ " for e in self.stap_colors:\n",
+ " a = a + str(e) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + '],\\n'\n",
+ "\n",
+ " a = a + '\"row\":' + str(self.row) + ',\\n'\n",
+ " a = a + '\"col\":' + str(self.col) + ',\\n'\n",
+ " a = a + '\"num\":' + str(self.num) + ',\\n'\n",
+ " \n",
+ " a = a + '\"scafLoop\":['\n",
+ " if len(self.scafLoop) > 0:\n",
+ " for i in self.scafLoop:\n",
+ " a = a + str(i) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + '],\\n'\n",
+ " \n",
+ " a = a + '\"stap\":['\n",
+ " if len(self.stap) > 0:\n",
+ " for i in self.stap:\n",
+ " a = a + str(i) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + '],\\n'\n",
+ " \n",
+ " a = a + '\"scaf\":['\n",
+ " if len(self.scaf) > 0:\n",
+ " for i in self.scaf:\n",
+ " a = a + str(i) + ','\n",
+ " a = a[0:len(a) - 1] # remove last comma\n",
+ " a = a + ']\\n}'\n",
+ " return a\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "c168b2f4",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "L=[]\n",
+ "for i in df[\"vstrands\"]:\n",
+ " L.append(i)\n",
+ "\n",
+ "cadsys = vstrands()\n",
+ "vh = vhelix()\n",
+ "for s in L:\n",
+ " \n",
+ " vh.stap = [ i for i in s[\"scaf\"]]\n",
+ " vh.scaf = [i for i in s[\"stap\"]]\n",
+ " vh.skiploop_bases = len(s[\"skip\"]) + sum(s[\"loop\"]) - sum(s[\"skip\"])\n",
+ " cadsys.add_vhelix(vh)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "1e29e6a7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['__class__',\n",
+ " '__delattr__',\n",
+ " '__dict__',\n",
+ " '__dir__',\n",
+ " '__doc__',\n",
+ " '__eq__',\n",
+ " '__format__',\n",
+ " '__ge__',\n",
+ " '__getattribute__',\n",
+ " '__gt__',\n",
+ " '__hash__',\n",
+ " '__init__',\n",
+ " '__init_subclass__',\n",
+ " '__le__',\n",
+ " '__lt__',\n",
+ " '__module__',\n",
+ " '__ne__',\n",
+ " '__new__',\n",
+ " '__reduce__',\n",
+ " '__reduce_ex__',\n",
+ " '__repr__',\n",
+ " '__setattr__',\n",
+ " '__sizeof__',\n",
+ " '__str__',\n",
+ " '__subclasshook__',\n",
+ " '__weakref__',\n",
+ " 'add_square',\n",
+ " 'cad_index',\n",
+ " 'col',\n",
+ " 'get_length',\n",
+ " 'len',\n",
+ " 'loop',\n",
+ " 'num',\n",
+ " 'row',\n",
+ " 'scaf',\n",
+ " 'scafLoop',\n",
+ " 'skip',\n",
+ " 'skiploop_bases',\n",
+ " 'stap',\n",
+ " 'stapLoop',\n",
+ " 'stap_colors']"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s0=cadsys.vhelices[0]\n",
+ "dir(s0)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "id": "fd26bfad",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[[-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, 5, 10],\n",
+ " [5, 9, 5, 11],\n",
+ " [5, 10, 5, 12],\n",
+ " [5, 11, 5, 13],\n",
+ " [5, 12, 5, 14],\n",
+ " [5, 13, 5, 15],\n",
+ " [5, 14, 5, 16],\n",
+ " [5, 15, 5, 17],\n",
+ " [5, 16, 5, 18],\n",
+ " [5, 17, 5, 19],\n",
+ " [5, 18, 5, 20],\n",
+ " [5, 19, 5, 21],\n",
+ " [5, 20, 5, 22],\n",
+ " [5, 21, 5, 23],\n",
+ " [5, 22, 5, 24],\n",
+ " [5, 23, 5, 25],\n",
+ " [5, 24, 5, 26],\n",
+ " [5, 25, 5, 27],\n",
+ " [5, 26, 0, 27],\n",
+ " [0, 28, 5, 29],\n",
+ " [5, 28, 5, 30],\n",
+ " [5, 29, 5, 31],\n",
+ " [5, 30, 5, 32],\n",
+ " [5, 31, 5, 33],\n",
+ " [5, 32, 5, 34],\n",
+ " [5, 33, 5, 35],\n",
+ " [5, 34, 5, 36],\n",
+ " [5, 35, 5, 37],\n",
+ " [5, 36, 5, 38],\n",
+ " [5, 37, 5, 39],\n",
+ " [5, 38, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1]]"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s0.scaf"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "438d3345",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "for s in s0.scaf:\n",
+ " if s[0]==-1 and s[1]==-1:\n",
+ " pass\n",
+ " elif s[2]==len(s0.scaf) and abs(s[3])==1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "595fa2ff",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[-1, -1, -1, -1]"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s0.scaf[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "3d614740",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['__class__',\n",
+ " '__delattr__',\n",
+ " '__dict__',\n",
+ " '__dir__',\n",
+ " '__doc__',\n",
+ " '__eq__',\n",
+ " '__format__',\n",
+ " '__ge__',\n",
+ " '__getattribute__',\n",
+ " '__gt__',\n",
+ " '__hash__',\n",
+ " '__init__',\n",
+ " '__init_subclass__',\n",
+ " '__le__',\n",
+ " '__lt__',\n",
+ " '__module__',\n",
+ " '__ne__',\n",
+ " '__new__',\n",
+ " '__reduce__',\n",
+ " '__reduce_ex__',\n",
+ " '__repr__',\n",
+ " '__setattr__',\n",
+ " '__sizeof__',\n",
+ " '__str__',\n",
+ " '__subclasshook__',\n",
+ " '__weakref__',\n",
+ " 'add_vhelix',\n",
+ " 'bbox',\n",
+ " 'vhelices']"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "dir(cadsys)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "id": "831d5ea6",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[[5, 1, -1, -1],\n",
+ " [5, 2, 5, 0],\n",
+ " [5, 3, 5, 1],\n",
+ " [-1, -1, 5, 2],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1],\n",
+ " [5, 10, 4, 9],\n",
+ " [5, 11, 5, 9],\n",
+ " [5, 12, 5, 10],\n",
+ " [5, 13, 5, 11],\n",
+ " [5, 14, 5, 12],\n",
+ " [5, 15, 5, 13],\n",
+ " [5, 16, 5, 14],\n",
+ " [5, 17, 5, 15],\n",
+ " [5, 18, 5, 16],\n",
+ " [5, 19, 5, 17],\n",
+ " [5, 20, 5, 18],\n",
+ " [5, 21, 5, 19],\n",
+ " [5, 22, 5, 20],\n",
+ " [-1, -1, 5, 21],\n",
+ " [5, 24, -1, -1],\n",
+ " [5, 25, 5, 23],\n",
+ " [5, 26, 5, 24],\n",
+ " [5, 27, 5, 25],\n",
+ " [5, 28, 5, 26],\n",
+ " [5, 29, 5, 27],\n",
+ " [5, 30, 5, 28],\n",
+ " [5, 31, 5, 29],\n",
+ " [5, 32, 5, 30],\n",
+ " [5, 33, 5, 31],\n",
+ " [5, 34, 5, 32],\n",
+ " [5, 35, 5, 33],\n",
+ " [5, 36, 5, 34],\n",
+ " [5, 37, 5, 35],\n",
+ " [5, 38, 5, 36],\n",
+ " [5, 39, 5, 37],\n",
+ " [4, 39, 5, 38],\n",
+ " [-1, -1, -1, -1],\n",
+ " [-1, -1, -1, -1]]"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "vh.stap"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "7831eb35",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ModuleNotFoundError",
+ "evalue": "No module named 'mrdna'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mmrdna\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mreaders\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcadnano_segments\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;241m*\u001b[39m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mcadnano\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdocument\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Document\n\u001b[1;32m 3\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mcadnano\u001b[39;00m\n",
+ "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'mrdna'"
+ ]
+ }
+ ],
+ "source": [
+ "\n",
+ "\n",
+ "from mrdna.readers.cadnano_segments import *\n",
+ "from cadnano.document import Document\n",
+ "import cadnano"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "28c9253b",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "a018193b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ }
+ ],
+ "source": [
+ "json_data=read_json_file(\"test.json\")\n",
+ "part=decode_cadnano_part(json_data)\n",
+ "model=cadnano_part(part)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "2bc520fd",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ }
+ ],
+ "source": [
+ "doc=Document()\n",
+ "cadnano.fileio.v2decode.decode(doc, json_data)\n",
+ "parts = [p for p in doc.getParts()]\n",
+ "part=parts[0]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "117520a1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Oligo_(0.1[38])_1328\t23\t'None\n",
+ "Oligo_(2.1[34])_9584\t35\t'None\n",
+ "Oligo_(1.1[36])_7488\t188\t'None\n",
+ "Oligo_(4.1[39])_4384\t33\t'None\n",
+ "Oligo_(5.0[9])_0240\t23\t'None\n",
+ "Oligo_(1.0[3])_8256\t37\t'None\n",
+ "Oligo_(3.0[0])_3296\t33\t'None\n",
+ "Oligo_(0.1[23])_9088\t21\t'None\n",
+ "VH0\n",
+ "\t <fwd_StrandSet(0)> \t [(5, 36)] \n",
+ "\t\t\t\t ['#0066cc']\n",
+ "\t <rev_StrandSet(0)> \t [(2, 20), (21, 23), (24, 27), (28, 38)] \n",
+ "\t\t\t\t ['#cc0000', '#b8056c', '#f74308', '#1700de']\n",
+ "VH1\n",
+ "\t <fwd_StrandSet(1)> \t [(3, 20), (21, 38)] \n",
+ "\t\t\t\t ['#cc0000', '#b8056c']\n",
+ "\t <rev_StrandSet(1)> \t [(5, 18), (19, 36)] \n",
+ "\t\t\t\t ['#0066cc', '#0066cc']\n",
+ "VH2\n",
+ "\t <fwd_StrandSet(2)> \t [(2, 18), (19, 32)] \n",
+ "\t\t\t\t ['#0066cc', '#0066cc']\n",
+ "\t <rev_StrandSet(2)> \t [(0, 34)] \n",
+ "\t\t\t\t ['#888888']\n",
+ "VH3\n",
+ "\t <fwd_StrandSet(3)> \t [(0, 20), (21, 34)] \n",
+ "\t\t\t\t ['#cc0000', '#888888']\n",
+ "\t <rev_StrandSet(3)> \t [(2, 15), (16, 32)] \n",
+ "\t\t\t\t ['#0066cc', '#0066cc']\n",
+ "VH4\n",
+ "\t <fwd_StrandSet(4)> \t [(9, 15), (16, 39)] \n",
+ "\t\t\t\t ['#0066cc', '#0066cc']\n",
+ "\t <rev_StrandSet(4)> \t [(9, 20), (21, 39)] \n",
+ "\t\t\t\t ['#cc0000', '#888888']\n",
+ "VH5\n",
+ "\t <fwd_StrandSet(5)> \t [(9, 27), (28, 39)] \n",
+ "\t\t\t\t ['#f74308', '#1700de']\n",
+ "\t <rev_StrandSet(5)> \t [(9, 39)] \n",
+ "\t\t\t\t ['#0066cc']\n"
+ ]
+ }
+ ],
+ "source": [
+ "part.__dict__.keys()\n",
+ "\n",
+ "oligos = part.oligos()\n",
+ "for oligo in oligos:\n",
+ " print(\"{0}\\t{1}\\t\\'{2}\".format(oligo,\n",
+ " oligo.length(),\n",
+ " oligo.sequence()))\n",
+ "\n",
+ "vhs = list(part.getIdNums()) # convert set to list\n",
+ "for vh_id in vhs: # display first 3 vhs\n",
+ " fwd_ss, rev_ss = part.getStrandSets(vh_id)\n",
+ " print('VH{0}'.format(vh_id))\n",
+ " print('\\t', fwd_ss, '\\t', [s.idxs() for s in fwd_ss.strands()], '\\n\\t\\t\\t\\t',\n",
+ " [s.getColor() for s in fwd_ss.strands()])\n",
+ " print('\\t', rev_ss, '\\t', [s.idxs() for s in rev_ss.strands()], '\\n\\t\\t\\t\\t',\n",
+ " [s.getColor() for s in rev_ss.strands()])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "d8eb98b3",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "strands5 = [o.strand5p() for o in part.oligos()]\n",
+ "strands3 = [o.strand3p() for o in part.oligos()]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "id": "44db9666",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['__class__',\n",
+ " '__delattr__',\n",
+ " '__dict__',\n",
+ " '__dir__',\n",
+ " '__doc__',\n",
+ " '__eq__',\n",
+ " '__format__',\n",
+ " '__ge__',\n",
+ " '__getattribute__',\n",
+ " '__gt__',\n",
+ " '__hash__',\n",
+ " '__init__',\n",
+ " '__init_subclass__',\n",
+ " '__le__',\n",
+ " '__lt__',\n",
+ " '__module__',\n",
+ " '__ne__',\n",
+ " '__new__',\n",
+ " '__reduce__',\n",
+ " '__reduce_ex__',\n",
+ " '__repr__',\n",
+ " '__setattr__',\n",
+ " '__sizeof__',\n",
+ " '__slots__',\n",
+ " '__str__',\n",
+ " '__subclasshook__',\n",
+ " '__weakref__',\n",
+ " '_decrementLength',\n",
+ " '_incrementLength',\n",
+ " '_is_circular',\n",
+ " '_parent',\n",
+ " '_part',\n",
+ " '_props',\n",
+ " '_setColor',\n",
+ " '_setLength',\n",
+ " '_setLoop',\n",
+ " '_setProperty',\n",
+ " '_signals',\n",
+ " '_strand5p',\n",
+ " '_strandMergeUpdate',\n",
+ " '_strandSplitUpdate',\n",
+ " 'addToPart',\n",
+ " 'applyAbstractSequences',\n",
+ " 'applyColor',\n",
+ " 'applySequence',\n",
+ " 'applySequenceCMD',\n",
+ " 'clearAbstractSequences',\n",
+ " 'connect',\n",
+ " 'deleteLater',\n",
+ " 'destroy',\n",
+ " 'disconnect',\n",
+ " 'displayAbstractSequences',\n",
+ " 'dump',\n",
+ " 'editable_properties',\n",
+ " 'getAbsolutePositionAtLength',\n",
+ " 'getColor',\n",
+ " 'getModelProperties',\n",
+ " 'getName',\n",
+ " 'getNumberOfBasesToEachXover',\n",
+ " 'getOutlineProperties',\n",
+ " 'getProperty',\n",
+ " 'getStrandLengths',\n",
+ " 'isCircular',\n",
+ " 'length',\n",
+ " 'locString',\n",
+ " 'oligoPropertyChangedSignal',\n",
+ " 'oligoRemovedSignal',\n",
+ " 'oligoSelectedChangedSignal',\n",
+ " 'oligoSequenceAddedSignal',\n",
+ " 'oligoSequenceClearedSignal',\n",
+ " 'parent',\n",
+ " 'part',\n",
+ " 'refreshLength',\n",
+ " 'remove',\n",
+ " 'removeFromPart',\n",
+ " 'sequence',\n",
+ " 'sequenceExport',\n",
+ " 'setParent',\n",
+ " 'setPart',\n",
+ " 'setProperty',\n",
+ " 'setStrand5p',\n",
+ " 'shallowCopy',\n",
+ " 'shouldHighlight',\n",
+ " 'signals',\n",
+ " 'splitAtAbsoluteLengths',\n",
+ " 'strand3p',\n",
+ " 'strand5p',\n",
+ " 'undoStack']"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "L=[o for o in part.oligos()]\n",
+ "dir(L[2])\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "id": "52ccbb65",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "defaultdict(dict, {0: {}, 1: {}, 2: {}, 3: {}, 4: {}, 5: {}})"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "part.insertions()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "66171e52",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'name': 'NaPart1',\n",
+ " 'color': '#0066cc',\n",
+ " 'is_visible': True,\n",
+ " 'active_phos': None,\n",
+ " 'crossover_span_angle': 45,\n",
+ " 'max_vhelix_length': 42,\n",
+ " 'neighbor_active_angle': '',\n",
+ " 'grid_type': <GridEnum.HONEYCOMB: 2>,\n",
+ " 'virtual_helix_order': [0, 1, 2, 3, 4, 5],\n",
+ " 'is_lattice': True,\n",
+ " <GridEnum.HONEYCOMB: 2>: <GridEnum.NONE: 0>}"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "part.getModelProperties()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "34ff0906",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " _\n",
+ " _____ ___ _| |___ ___\n",
+ "| | _| . | | .'|\n",
+ "|_|_|_|_| |___|_|_|__,| v1.0a.dev74 \n",
+ "it/its\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "import pdb\n",
+ "import numpy as np\n",
+ "import os,sys\n",
+ "import scipy\n",
+ "\n",
+ "from mrdna import logger, devlogger\n",
+ "from mrdna.segmentmodel import SegmentModel, SingleStrandedSegment, DoubleStrandedSegment\n",
+ "from mrdna.arbdmodel.coords import quaternion_from_matrix, rotationAboutAxis, quaternion_slerp\n",
+ "from mrdna import get_resource_path\n",
+ "\n",
+ "ref_stack_position = np.array((-2.41851735, -0.259761333, 3.39999978))\n",
+ "\n",
+ "def _three_prime_list_to_five_prime(three_prime):\n",
+ " five_prime = -np.ones(three_prime.shape, dtype=int)\n",
+ " has_three_prime = np.where(three_prime >= 0)[0]\n",
+ " five_prime[three_prime[has_three_prime]] = has_three_prime\n",
+ " return five_prime \n",
+ "def _primes_list_to_strands(three_prime, five_prime):\n",
+ " five_prime_ends = np.where(five_prime < 0)[0]\n",
+ " strands = []\n",
+ " strand_is_circular = []\n",
+ " \n",
+ " idx_to_strand = -np.ones(three_prime.shape, dtype=int)\n",
+ "\n",
+ " def build_strand(nt_idx, conditional):\n",
+ " strand = [nt_idx]\n",
+ " idx_to_strand[nt_idx] = len(strands)\n",
+ " while conditional(nt_idx):\n",
+ " nt_idx = three_prime[nt_idx]\n",
+ " strand.append(nt_idx)\n",
+ " idx_to_strand[nt_idx] = len(strands)\n",
+ " strands.append( np.array(strand, dtype=int) )\n",
+ "\n",
+ " for nt_idx in five_prime_ends:\n",
+ " build_strand(nt_idx,\n",
+ " lambda nt: three_prime[nt] >= 0)\n",
+ " strand_is_circular.append(False)\n",
+ "\n",
+ " while True:\n",
+ " ## print(\"WARNING: working on circular strand {}\".format(len(strands)))\n",
+ " ids = np.where(idx_to_strand < 0)[0]\n",
+ " if len(ids) == 0: break\n",
+ " build_strand(ids[0],\n",
+ " lambda nt: three_prime[nt] >= 0 and \\\n",
+ " idx_to_strand[three_prime[nt]] < 0)\n",
+ " strand_is_circular.append(True)\n",
+ "\n",
+ " return strands, strand_is_circular\n",
+ "\n",
+ "def find_stacks(centers, transforms):\n",
+ "\n",
+ " ## Find orientation and center of each nucleotide\n",
+ " expected_stack_positions = []\n",
+ " for R,c in zip(transforms,centers):\n",
+ " expected_stack_positions.append( c + ref_stack_position.dot(R) )\n",
+ "\n",
+ " expected_stack_positions = np.array(expected_stack_positions, dtype=np.float32)\n",
+ "\n",
+ " dists = scipy.spatial.distance_matrix(expected_stack_positions, centers)\n",
+ " dists = dists + 5*np.eye(len(dists))\n",
+ " idx1, idx2 = np.where(dists < 3.5)\n",
+ "\n",
+ " ## Convert distances to stacks\n",
+ " stacks_above = -np.ones(len(centers), dtype=int)\n",
+ " _z = np.array((0,0,1))\n",
+ " for i in np.unique(idx1):\n",
+ " js = idx2[ idx1 == i ]\n",
+ " with np.errstate(divide='ignore',invalid='ignore'):\n",
+ " angles = [np.arccos( transforms[j].T.dot( transforms[i].dot(_z) ).dot( _z ) ) for j in js]\n",
+ " angles = np.array( angles )\n",
+ " tmp = np.argmin(dists[i][js] + 1.0*angles)\n",
+ " j = js[tmp]\n",
+ " stacks_above[i] = j\n",
+ "\n",
+ " return stacks_above\n",
+ "\n",
+ "def basepairs_and_stacks_to_helixmap(basepairs,stacks_above):\n",
+ "\n",
+ " helixmap = -np.ones(basepairs.shape, dtype=int)\n",
+ " helixrank = -np.ones(basepairs.shape)\n",
+ " is_fwd = np.ones(basepairs.shape, dtype=int)\n",
+ " \n",
+ " ## Remove stacks with nts lacking a basepairs\n",
+ " nobp = np.where(basepairs < 0)[0]\n",
+ " stacks_above[nobp] = -1\n",
+ " stacks_with_nobp = np.in1d(stacks_above, nobp)\n",
+ " stacks_above[stacks_with_nobp] = -1\n",
+ "\n",
+ " end_ids = np.where( (stacks_above < 0)*(basepairs >= 0) )[0]\n",
+ "\n",
+ " hid = 0\n",
+ " for end in end_ids:\n",
+ " if helixmap[end] >= 0:\n",
+ " continue\n",
+ " rank = 0\n",
+ " nt = basepairs[end]\n",
+ " bp = basepairs[nt]\n",
+ " assert( bp == end )\n",
+ " if helixmap[nt] >= 0 or helixmap[bp] >= 0:\n",
+ " logger.warning(f'Ill-formed helix: problematic basepair or stacking data near nucleotide {nt} or {bp}... skipping')\n",
+ " continue\n",
+ " # assert(helixmap[nt] == -1)\n",
+ " # assert(helixmap[bp] == -1)\n",
+ " helixmap[nt] = helixmap[bp] = hid\n",
+ " helixrank[nt] = helixrank[bp] = rank\n",
+ " is_fwd[bp] = 0\n",
+ " rank +=1\n",
+ "\n",
+ " _tmp = [(nt,bp)]\n",
+ " \n",
+ " while stacks_above[nt] >= 0:\n",
+ " nt = stacks_above[nt]\n",
+ " if basepairs[nt] < 0: break\n",
+ " bp = basepairs[nt]\n",
+ " if helixmap[nt] >= 0 or helixmap[bp] >= 0:\n",
+ " logger.warning(f'Ill-formed helix: problematic basepair or stacking data near nucleotide {nt} or {bp}... skipping')\n",
+ " break\n",
+ " helixmap[nt] = helixmap[bp] = hid\n",
+ " helixrank[nt] = helixrank[bp] = rank\n",
+ " is_fwd[bp] = 0\n",
+ " _tmp.append((nt,bp))\n",
+ " rank +=1\n",
+ "\n",
+ " hid += 1\n",
+ "\n",
+ " ## Create \"helix\" for each circular segment\n",
+ " intrahelical = []\n",
+ " processed = set()\n",
+ " unclaimed_bases = np.where( (basepairs >= 0)*(helixmap == -1) )[0]\n",
+ " for nt0 in unclaimed_bases:\n",
+ " if nt0 in processed: continue\n",
+ "\n",
+ " nt = nt0\n",
+ " all_nts = [nt]\n",
+ "\n",
+ " rank = 0\n",
+ " nt = nt0\n",
+ " bp = basepairs[nt]\n",
+ " if helixmap[nt] >= 0 or helixmap[bp] >= 0:\n",
+ " logger.warning(f'Ill-formed cylic helix: problematic basepair or stacking data near nucleotide {nt} or {bp}... skipping')\n",
+ " continue\n",
+ " helixmap[nt] = helixmap[bp] = hid\n",
+ " helixrank[nt] = helixrank[bp] = rank\n",
+ " is_fwd[bp] = 0\n",
+ " rank +=1\n",
+ " processed.add(nt)\n",
+ " processed.add(bp)\n",
+ "\n",
+ " counter = 0\n",
+ " while stacks_above[nt] >= 0:\n",
+ " lastnt = nt\n",
+ " nt = stacks_above[nt]\n",
+ " bp = basepairs[nt]\n",
+ " if nt == nt0 or nt == basepairs[nt0]:\n",
+ " intrahelical.append((lastnt,nt0))\n",
+ " break\n",
+ " \n",
+ " assert( bp >= 0 )\n",
+ " if helixmap[nt] >= 0 or helixmap[bp] >= 0:\n",
+ " logger.warning(f'Ill-formed cyclic helix: problematic basepair or stacking data near nucleotide {nt} or {bp}... skipping')\n",
+ " break\n",
+ " \n",
+ " helixmap[nt] = helixmap[bp] = hid\n",
+ " helixrank[nt] = helixrank[bp] = rank\n",
+ " is_fwd[bp] = 0\n",
+ " processed.add(nt)\n",
+ " processed.add(bp)\n",
+ " rank +=1\n",
+ " hid += 1\n",
+ "\n",
+ " return helixmap, helixrank, is_fwd, intrahelical\n",
+ "\n",
+ "\n",
+ "def set_splines(seg, coordinate, hid, hmap, hrank, fwd, basepair, orientation=None):\n",
+ " maxrank = np.max( hrank[hmap==hid] )\n",
+ " if maxrank == 0:\n",
+ " ids = np.where((hmap == hid))[0]\n",
+ " pos = np.mean( [coordinate[r,:] for r in ids ], axis=0 )\n",
+ " coords = [pos,pos]\n",
+ " contours = [0,1]\n",
+ " if orientation is not None:\n",
+ " ids = np.where((hmap == hid) * fwd)[0]\n",
+ " assert( len(ids) == 1 )\n",
+ " q = quaternion_from_matrix( orientation[ids[0]] )\n",
+ " quats = [q, q]\n",
+ " coords[-1] = pos + orientation[ids[0]].dot(np.array((0,0,1)))\n",
+ "\n",
+ " else:\n",
+ " coords,contours,quats = [[],[],[]]\n",
+ " last_q = None\n",
+ " for rank in range(int(maxrank)+1):\n",
+ " ids = np.where((hmap == hid) * (hrank == rank))[0]\n",
+ " \n",
+ " coords.append(np.mean( [coordinate[r,:] for r in ids ], axis=0 ))\n",
+ " contours.append( float(rank+0.5)/(maxrank+1) )\n",
+ " if orientation is not None:\n",
+ " ids = np.where((hmap == hid) * (hrank == rank) * fwd)[0]\n",
+ " assert(len(ids) == 1)\n",
+ " q = quaternion_from_matrix( orientation[ids[0]] )\n",
+ "\n",
+ " if last_q is not None and last_q.dot(q) < 0:\n",
+ " q = -q\n",
+ "\n",
+ " ## Average quaterion with reverse direction\n",
+ " bp = basepair[ids[0]]\n",
+ " if bp >= 0:\n",
+ " bp_o = orientation[bp].dot(rotationAboutAxis(np.array((1,0,0)),180))\n",
+ " q2 = quaternion_from_matrix( bp_o )\n",
+ " if q.dot(q2) < 0:\n",
+ " q2 = -q2\n",
+ "\n",
+ " ## probably good enough, but slerp is better: q = (q + q2)*0.5\n",
+ " q = quaternion_slerp(q,q2,0.5)\n",
+ "\n",
+ " quats.append(q)\n",
+ " last_q = q\n",
+ "\n",
+ " coords = np.array(coords)\n",
+ " seg.set_splines(contours,coords)\n",
+ " if orientation is not None:\n",
+ " quats = np.array(quats)\n",
+ " seg.set_orientation_splines(contours,quats)\n",
+ "\n",
+ " seg.start_position = coords[0,:]\n",
+ " seg.end_position = coords[-1,:]\n",
+ "\n",
+ "\n",
+ "def model_from_basepair_stack_3prime(coordinate, basepair, stack, three_prime,\n",
+ " sequence=None, orientation=None,\n",
+ " max_basepairs_per_bead = 5,\n",
+ " max_nucleotides_per_bead = 5,\n",
+ " local_twist = False,\n",
+ " dimensions=(5000,5000,5000),\n",
+ " **model_parameters):\n",
+ " \"\"\" \n",
+ " Creates a SegmentModel object from lists of each nucleotide's\n",
+ " basepair, its stack (on 3' side) and its 3'-connected nucleotide\n",
+ "\n",
+ " The first argument should be an N-by-3 numpy array containing the\n",
+ " coordinate of each nucleotide, where N is the number of\n",
+ " nucleotides. The following three arguments should be integer lists\n",
+ " where the i-th element corresponds to the i-th nucleotide; the\n",
+ " list element should the integer index of the corresponding\n",
+ " basepaired / stacked / phosphodiester-bonded nucleotide. If there\n",
+ " is no such nucleotide, the value should be -1.\n",
+ "\n",
+ " Args:\n",
+ " basepair: List of each nucleotide's basepair's index\n",
+ " stack: List containing index of the nucleotide stacked on the 3' of each nucleotide\n",
+ " three_prime: List of each nucleotide's the 3' end of each nucleotide\n",
+ "\n",
+ " Returns:\n",
+ " SegmentModel\n",
+ " \"\"\"\n",
+ "\n",
+ " \"\"\" Validate Input \"\"\"\n",
+ " inputs = (basepair,three_prime)\n",
+ " try:\n",
+ " basepair,three_prime = [np.array(a,dtype=int) for a in inputs]\n",
+ " except:\n",
+ " raise TypeError(\"One or more of the input lists could not be converted into a numpy array\")\n",
+ " inputs = (basepair,three_prime)\n",
+ " coordinate = np.array(coordinate)\n",
+ "\n",
+ " if np.any( [len(a.shape) > 1 for a in inputs] ):\n",
+ " raise ValueError(\"One or more of the input lists has the wrong dimensionality\")\n",
+ "\n",
+ " if len(coordinate.shape) != 2:\n",
+ " raise ValueError(\"Coordinate array has the wrong dimensionality\")\n",
+ "\n",
+ " inputs = (coordinate,basepair,three_prime)\n",
+ " if not np.all(np.diff([len(a) for a in inputs]) == 0):\n",
+ " raise ValueError(\"Inputs are not the same length\")\n",
+ " \n",
+ " num_nt = len(basepair)\n",
+ " if sequence is not None and len(sequence) != num_nt:\n",
+ " raise ValueError(\"The 'sequence' parameter is the wrong length {} != {}\".format(len(sequence),num_nt))\n",
+ "\n",
+ " if orientation is not None:\n",
+ " orientation = np.array(orientation)\n",
+ " if len(orientation.shape) != 3:\n",
+ " raise ValueError(\"The 'orientation' array has the wrong dimensionality (should be Nx3x3)\")\n",
+ " if orientation.shape != (num_nt,3,3):\n",
+ " raise ValueError(\"The 'orientation' array is not properly formatted\")\n",
+ "\n",
+ " if stack is None:\n",
+ " if orientation is not None:\n",
+ " stack = find_stacks(coordinate, orientation)\n",
+ " else:\n",
+ " ## Guess stacking based on 3' connectivity\n",
+ " stack = np.array(three_prime,dtype=int) # Assume nts on 3' ends are stacked\n",
+ " _stack_below = _three_prime_list_to_five_prime(stack)\n",
+ " _has_bp = (basepair >= 0)\n",
+ " _nostack = np.where( (stack == -1)*_has_bp )[0]\n",
+ " _has_stack_below = _stack_below[basepair[_nostack]] >= 0\n",
+ " _nostack2 = _nostack[_has_stack_below]\n",
+ " stack[_nostack2] = basepair[_stack_below[basepair[_nostack2]]]\n",
+ "\n",
+ " else:\n",
+ " try:\n",
+ " stack = np.array(stack,dtype=int)\n",
+ " except:\n",
+ " raise TypeError(\"The 'stack' array could not be converted into a numpy integer array\")\n",
+ "\n",
+ " if len(stack.shape) != 1:\n",
+ " raise ValueError(\"The 'stack' array has the wrong dimensionality\")\n",
+ "\n",
+ " if len(stack) != num_nt:\n",
+ " raise ValueError(\"The length of the 'stack' array does not match other inputs\")\n",
+ "\n",
+ " bps = basepair # alias\n",
+ "\n",
+ " \"\"\" Fix stacks: require that the stack of a bp of a base's stack is its bp \"\"\"\n",
+ " _has_bp = (bps >= 0)\n",
+ " _has_stack = (stack >= 0)\n",
+ " _stack_has_basepair = (bps[stack] >= 0) * _has_stack\n",
+ " stack = np.where( (stack[bps[stack]] == bps) * _has_bp * _has_stack * _has_bp,\n",
+ " stack, -np.ones(len(stack),dtype=int) )\n",
+ "\n",
+ " five_prime = _three_prime_list_to_five_prime(three_prime)\n",
+ "\n",
+ " \"\"\" Build map of dsDNA helices and strands \"\"\"\n",
+ " hmap,hrank,fwd,intrahelical = basepairs_and_stacks_to_helixmap(bps,stack)\n",
+ " double_stranded_helices = np.unique(hmap[hmap >= 0]) \n",
+ " strands, strand_is_circular = _primes_list_to_strands(three_prime, five_prime)\n",
+ "\n",
+ " \"\"\" Add ssDNA to hmap \"\"\"\n",
+ " if len(double_stranded_helices) > 0:\n",
+ " hid = double_stranded_helices[-1]+1\n",
+ " else:\n",
+ " hid = 0\n",
+ " ss_residues = hmap < 0\n",
+ " #\n",
+ " if np.any(bps[ss_residues] != -1):\n",
+ " logger.warning(f'{np.sum(bps[ss_residues] != -1)} ssDNA nucleotides appear to have basepairs... ignoring')\n",
+ " \n",
+ " for s,c in zip(strands, strand_is_circular):\n",
+ " strand_segment_ends = [i for i in np.where( np.diff(hmap[s]) != 0 )[0]] + [len(s)-1]\n",
+ " seg_start = 0\n",
+ " for i in strand_segment_ends:\n",
+ " if hmap[s[i]] < 0:\n",
+ " ## Found single-stranded segment\n",
+ " ids = s[seg_start:i+1]\n",
+ " assert( np.all(hmap[ids] == -1) )\n",
+ " hmap[ids] = hid\n",
+ " hrank[ids] = np.arange(i+1-seg_start)\n",
+ " hid+=1\n",
+ " seg_start = i+1\n",
+ "\n",
+ " if len(double_stranded_helices) > 0:\n",
+ " single_stranded_helices = np.arange(double_stranded_helices[-1]+1,hid)\n",
+ " else:\n",
+ " single_stranded_helices = np.arange(hid)\n",
+ "\n",
+ " ## Create double-stranded segments\n",
+ " doubleSegments = []\n",
+ " for hid in double_stranded_helices:\n",
+ " seg = DoubleStrandedSegment(name=str(hid),\n",
+ " num_bp = np.sum(hmap==hid)//2)\n",
+ " set_splines(seg, coordinate, hid, hmap, hrank, fwd, basepair, orientation)\n",
+ "\n",
+ " assert(hid == len(doubleSegments))\n",
+ " doubleSegments.append(seg)\n",
+ "\n",
+ " ## Create single-stranded segments\n",
+ " singleSegments = []\n",
+ " for hid in single_stranded_helices:\n",
+ " seg = SingleStrandedSegment(name=str(hid),\n",
+ " num_nt = np.sum(hmap==hid))\n",
+ " set_splines(seg, coordinate, hid, hmap, hrank, fwd, basepair, orientation)\n",
+ "\n",
+ " assert(hid == len(doubleSegments) + len(singleSegments))\n",
+ " singleSegments.append(seg)\n",
+ "\n",
+ " ## Find crossovers and 5prime/3prime ends\n",
+ " crossovers,prime5,prime3 = [[],[],[]]\n",
+ " for s,c in zip(strands,strand_is_circular):\n",
+ " tmp = np.where(np.diff(hmap[s]) != 0)[0]\n",
+ " for i in tmp:\n",
+ " crossovers.append( (s[i],s[i+1]) )\n",
+ " if c:\n",
+ " if hmap[s[-1]] != hmap[s[0]]:\n",
+ " crossovers.append( (s[-1],s[0]) )\n",
+ " else:\n",
+ " prime5.append(s[0])\n",
+ " prime3.append(s[-1])\n",
+ "\n",
+ " ## Add connections\n",
+ " allSegments = doubleSegments+singleSegments\n",
+ "\n",
+ " for r1,r2 in crossovers:\n",
+ " seg1,seg2 = [allSegments[hmap[i]] for i in (r1,r2)]\n",
+ " nt1,nt2 = [hrank[i] for i in (r1,r2)]\n",
+ " f1,f2 = [fwd[i] for i in (r1,r2)]\n",
+ "\n",
+ " ## Handle connections at the ends\n",
+ " is_terminal1 = (nt1,f1) in ((0,0),(seg1.num_nt-1,1))\n",
+ " is_terminal2 = (nt2,f2) in ((0,1),(seg2.num_nt-1,0))\n",
+ "\n",
+ " print(seg1,seg2, r1, r2, is_terminal1, is_terminal2)\n",
+ " if is_terminal1 or is_terminal2:\n",
+ " \"\"\" Ensure that we don't have three-way dsDNA junctions \"\"\"\n",
+ " if is_terminal1 and (bps[r1] >= 0) and (five_prime[bps[r1]] >= 0) and (three_prime[r1] >= 0):\n",
+ " if (bps[five_prime[bps[r1]]] >= 0) and (bps[three_prime[r1]] >= 0):\n",
+ " # is_terminal1 = (three_prime[r1] == bps[five_prime[bps[r1]]])\n",
+ " is_terminal1 = hmap[five_prime[bps[r1]]] == hmap[three_prime[r1]]\n",
+ " if is_terminal2 and (bps[r2] >= 0) and (three_prime[bps[r2]] >= 0) and (five_prime[r2] >= 0):\n",
+ " if (bps[three_prime[bps[r2]]] >= 0) and (bps[five_prime[r2]] >= 0):\n",
+ " # is_terminal2 = (five_prime[r2] == bps[three_prime[bps[r2]]])\n",
+ " is_terminal2 = hmap[three_prime[bps[r2]]] == hmap[five_prime[r2]]\n",
+ " \n",
+ " \"\"\" Place connection \"\"\"\n",
+ " if is_terminal1 and is_terminal2:\n",
+ " end1 = seg1.end3 if f1 else seg1.start3\n",
+ " end2 = seg2.start5 if f2 else seg2.end5\n",
+ " seg1._connect_ends( end1, end2, type_='intrahelical')\n",
+ " else:\n",
+ " seg1.add_crossover(nt1,seg2,nt2,[f1,f2],type_=\"terminal_crossover\")\n",
+ " else:\n",
+ " seg1.add_crossover(nt1,seg2,nt2,[f1,f2])\n",
+ "\n",
+ " ## Add 5prime/3prime ends\n",
+ " for r in prime5:\n",
+ " seg = allSegments[hmap[r]]\n",
+ " seg.add_5prime(hrank[r],fwd[r])\n",
+ " for r in prime3:\n",
+ " seg = allSegments[hmap[r]]\n",
+ " seg.add_3prime(hrank[r],fwd[r])\n",
+ "\n",
+ " ## Add intrahelical connections to circular helical sections\n",
+ " for nt0,nt1 in intrahelical:\n",
+ " seg = allSegments[hmap[nt0]]\n",
+ " assert( seg is allSegments[hmap[nt1]] )\n",
+ " if three_prime[nt0] >= 0:\n",
+ " if hmap[nt0] == hmap[three_prime[nt0]]:\n",
+ " seg.connect_end3(seg.start5)\n",
+ "\n",
+ " bp0,bp1 = [bps[nt] for nt in (nt0,nt1)]\n",
+ " if three_prime[bp1] >= 0:\n",
+ " if hmap[bp1] == hmap[three_prime[bp1]]:\n",
+ " seg.connect_start3(seg.end5)\n",
+ "\n",
+ " ## Assign sequence\n",
+ " if sequence is not None:\n",
+ " for hid in range(len(allSegments)):\n",
+ " resids = np.where( (hmap==hid)*(fwd==1) )[0]\n",
+ " s = allSegments[hid]\n",
+ " s.sequence = [sequence[r] for r in sorted(resids,key=lambda x: hrank[x])]\n",
+ "\n",
+ "\n",
+ " ## Build model\n",
+ " model = SegmentModel( allSegments,\n",
+ " max_basepairs_per_bead = max_basepairs_per_bead,\n",
+ " max_nucleotides_per_bead = max_nucleotides_per_bead,\n",
+ " local_twist = local_twist,\n",
+ " dimensions = dimensions,\n",
+ " **model_parameters )\n",
+ "\n",
+ "\n",
+ " model._reader_list_coordinates = coordinate\n",
+ " model._reader_list_basepair = basepair\n",
+ " model._reader_list_stack = stack\n",
+ " model._reader_list_three_prime = three_prime\n",
+ " model._reader_list_five_prime = five_prime\n",
+ " model._reader_list_sequence = sequence\n",
+ " model._reader_list_orientation = orientation\n",
+ " model._reader_list_hmap = hmap\n",
+ " model._reader_list_fwd = fwd\n",
+ " model._reader_list_hrank = hrank\n",
+ "\n",
+ " if sequence is None:\n",
+ " for s in model.segments:\n",
+ " s.randomize_unset_sequence()\n",
+ "\n",
+ " return model\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "53a3183e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<DoubleStrandedSegment'> 1[1]> <DoubleStrandedSegment'> 0[1]> 5 3 True True\n",
+ "<SingleStrandedSegment'> 2[2]> <DoubleStrandedSegment'> 0[1]> 1 2 True True\n",
+ "<DoubleStrandedSegment'> 0[1]> <DoubleStrandedSegment'> 1[1]> 2 4 True True\n",
+ "<DoubleStrandedSegment'> 1[1]> <SingleStrandedSegment'> 3[1]> 4 6 True True\n",
+ "<SingleStrandedSegment'> 3[1]> <SingleStrandedSegment'> 2[2]> 6 0 True True\n"
+ ]
+ }
+ ],
+ "source": [
+ "coordinate = [(0,0,3.4*i) for i in range(7)]\n",
+ "three_prime = [ 1, 2, 4,-1, 6, 3, 0]\n",
+ "basepair = [-1,-1, 3, 2, 5, 4,-1]\n",
+ "stack = [-1,-1, -1,-1,-1, -1,-1]\n",
+ "for i in [3,5]:\n",
+ " coordinate[i] = (1,0,3.4*i)\n",
+ "\n",
+ "model = model_from_basepair_stack_3prime(coordinate, basepair, stack, three_prime,\n",
+ " max_basepairs_per_bead=1,\n",
+ " max_nucleotides_per_bead=1,\n",
+ " local_twist=False)\n",
+ "model.writePsf(\"list.psf\")\n",
+ "model.writePdb(\"list.pdb\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "fdcadbe9",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[[<SegmentParticle DNA on <DoubleStrandedSegment'> 0[1]>[1.00]>], [<SegmentParticle DNA on <DoubleStrandedSegment'> 1[1]>[0.00]>, <SegmentParticle DNA on <DoubleStrandedSegment'> 1[1]>[1.00]>], [<SegmentParticle NAS on <SingleStrandedSegment'> 2[2]>[0.00]>, <SegmentParticle NAS on <SingleStrandedSegment'> 2[2]>[0.50]>, <SegmentParticle NAS on <SingleStrandedSegment'> 2[2]>[1.00]>], [<SegmentParticle NAS on <SingleStrandedSegment'> 3[1]>[0.50]>]]\n",
+ "[[<Connection <Location 1.end3[0,on_fwd_strand]>--intrahelical--<Location 0.end5[0,on_fwd_strand]>]>, <Connection <Location 2.end3[1,on_fwd_strand]>--sscrossover--<Location 0.end5[0,on_rev_strand]>]>, <Connection <Location 0.end3[0,on_rev_strand]>--intrahelical--<Location 1.end5[0,on_rev_strand]>]>], [<Connection <Location 1.end3[0,on_fwd_strand]>--intrahelical--<Location 0.end5[0,on_fwd_strand]>]>, <Connection <Location 0.end3[0,on_rev_strand]>--intrahelical--<Location 1.end5[0,on_rev_strand]>]>, <Connection <Location 1.end3[0,on_rev_strand]>--intrahelical--<Location 3.end5[0,on_fwd_strand]>]>], [<Connection <Location 2.end3[1,on_fwd_strand]>--sscrossover--<Location 0.end5[0,on_rev_strand]>]>, <Connection <Location 3.end3[0,on_fwd_strand]>--intrahelical--<Location 2.end5[0,on_fwd_strand]>]>], [<Connection <Location 1.end3[0,on_rev_strand]>--intrahelical--<Location 3.end5[0,on_fwd_strand]>]>, <Connection <Location 3.end3[0,on_fwd_strand]>--intrahelical--<Location 2.end5[0,on_fwd_strand]>]>]]\n"
+ ]
+ }
+ ],
+ "source": [
+ "print([i.children for i in model.children])\n",
+ "print([i.connections for i in model.children])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "d27fd998",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "s=model.children[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "fe094a9b",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'0'"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s.segname"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "5e54cf99",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[(0, 0, 0.0),\n",
+ " (0, 0, 3.4),\n",
+ " (0, 0, 6.8),\n",
+ " (1, 0, 10.2),\n",
+ " (0, 0, 13.6),\n",
+ " (1, 0, 17.0),\n",
+ " (0, 0, 20.4)]"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "coordinate"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "bbeb8724",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.8.18"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}