diff --git a/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb b/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb
index 35dcfeebe6d1c30490746e659e54020de83c676d..e061577f760f9585f978ee7f330364b3c04f5d06 100644
--- a/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb
+++ b/mrdna/readers/.ipynb_checkpoints/test-checkpoint.ipynb
@@ -3,7 +3,7 @@
{
"cell_type": "code",
"execution_count": 2,
- "id": "d1c58516",
+ "id": "b7b6b57a",
"metadata": {
"scrolled": true
},
@@ -19,7 +19,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "df7df2a7",
+ "id": "d7794e7b",
"metadata": {},
"outputs": [],
"source": [
@@ -30,7 +30,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "a24cd262",
+ "id": "a18ffc26",
"metadata": {},
"outputs": [],
"source": [
@@ -41,7 +41,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "806af23a",
+ "id": "22e5fd1e",
"metadata": {},
"outputs": [
{
@@ -224,7 +224,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "db28a621",
+ "id": "6ddb3f62",
"metadata": {},
"outputs": [
{
@@ -264,7 +264,7 @@
{
"cell_type": "code",
"execution_count": 18,
- "id": "cf748a26",
+ "id": "9a6e2f17",
"metadata": {},
"outputs": [],
"source": [
@@ -285,8 +285,8 @@
},
{
"cell_type": "code",
- "execution_count": 70,
- "id": "fde9e6b9",
+ "execution_count": 121,
+ "id": "0253e593",
"metadata": {},
"outputs": [],
"source": [
@@ -340,7 +340,7 @@
{
"cell_type": "code",
"execution_count": 44,
- "id": "608b53b9",
+ "id": "2929c2ed",
"metadata": {},
"outputs": [
{
@@ -361,8 +361,8 @@
},
{
"cell_type": "code",
- "execution_count": 71,
- "id": "abf6006a",
+ "execution_count": 122,
+ "id": "20eab478",
"metadata": {
"scrolled": true
},
@@ -382,7 +382,7 @@
{
"cell_type": "code",
"execution_count": 52,
- "id": "57f22778",
+ "id": "4ab55565",
"metadata": {},
"outputs": [
{
@@ -402,55 +402,333 @@
},
{
"cell_type": "code",
- "execution_count": 74,
- "id": "399ada62",
+ "execution_count": 83,
+ "id": "c55fdc19",
"metadata": {},
"outputs": [],
"source": [
- "def ntcount(b):\n",
+ "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 b])\n",
+ " n=np.array([judge(i) for i in scafs])\n",
" return np.sum(n)\n",
"\n"
]
},
{
"cell_type": "code",
- "execution_count": 78,
- "id": "1d63a717",
+ "execution_count": 84,
+ "id": "3552d3d6",
+ "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": "58b92427",
+ "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": "aaf6cb45",
"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"
+ "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": 128,
+ "id": "6daf8f3b",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(array([0, 2]),)"
+ ]
+ },
+ "execution_count": 128,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s=[True,False,True,False,False]\n",
+ "np.where(np.array(s)==True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 127,
+ "id": "126916f8",
+ "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></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",
+ " <tr>\n",
+ " <th>vh</th>\n",
+ " <th>zid</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",
+ " <th>0</th>\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",
+ " <th>3</th>\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",
+ " <th>1</th>\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",
+ " <th>2</th>\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",
+ " <th>8</th>\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": [
+ " r bp stack threeprime seq orientation\n",
+ "vh zid \n",
+ "0 0 NaN NaN NaN NaN NaN NaN\n",
+ "1 3 NaN NaN NaN NaN NaN NaN\n",
+ "2 1 NaN NaN NaN NaN NaN NaN\n",
+ "3 2 NaN NaN NaN NaN NaN NaN\n",
+ "1 8 NaN NaN NaN NaN NaN NaN"
+ ]
+ },
+ "execution_count": 127,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "d"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 100,
+ "id": "18f368b0",
+ "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": [
- "b[\"scafnt\"]=[ntcount(b['scaf'][i]) for i in b.index]\n",
- "b[\"stapnt\"]=[ntcount(b['stap'][i]) for i in b.index]"
+ "d[[0,0]]"
]
},
{
"cell_type": "code",
"execution_count": 13,
- "id": "6e30e6ec",
+ "id": "998eed5e",
"metadata": {},
"outputs": [
{
@@ -471,7 +749,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "d2a55c6a",
+ "id": "6e62da4d",
"metadata": {},
"outputs": [
{
@@ -493,7 +771,7 @@
{
"cell_type": "code",
"execution_count": 198,
- "id": "b36a118e",
+ "id": "b786e74c",
"metadata": {},
"outputs": [
{
@@ -515,7 +793,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "c1fd0214",
+ "id": "e36b19a3",
"metadata": {},
"outputs": [
{
@@ -536,7 +814,7 @@
{
"cell_type": "code",
"execution_count": 173,
- "id": "21f20d54",
+ "id": "46b64c39",
"metadata": {},
"outputs": [],
"source": [
@@ -572,7 +850,7 @@
{
"cell_type": "code",
"execution_count": 177,
- "id": "ca75e9ec",
+ "id": "4d59fd91",
"metadata": {},
"outputs": [],
"source": [
@@ -608,7 +886,7 @@
{
"cell_type": "code",
"execution_count": 187,
- "id": "daa13243",
+ "id": "d49175db",
"metadata": {},
"outputs": [
{
@@ -835,7 +1113,7 @@
{
"cell_type": "code",
"execution_count": 142,
- "id": "687c6f64",
+ "id": "a033b838",
"metadata": {},
"outputs": [],
"source": [
@@ -872,7 +1150,7 @@
{
"cell_type": "code",
"execution_count": 117,
- "id": "4d610626",
+ "id": "2f0d79a6",
"metadata": {},
"outputs": [],
"source": [
@@ -893,7 +1171,7 @@
{
"cell_type": "code",
"execution_count": 116,
- "id": "ab5c6907",
+ "id": "7874ae4e",
"metadata": {},
"outputs": [
{
@@ -1105,7 +1383,7 @@
{
"cell_type": "code",
"execution_count": 157,
- "id": "8e05cf62",
+ "id": "ba99db6a",
"metadata": {},
"outputs": [
{
@@ -1129,7 +1407,7 @@
{
"cell_type": "code",
"execution_count": 152,
- "id": "e2e30e0a",
+ "id": "c26f006c",
"metadata": {},
"outputs": [
{
@@ -1150,7 +1428,7 @@
{
"cell_type": "code",
"execution_count": 62,
- "id": "03354054",
+ "id": "108484f8",
"metadata": {},
"outputs": [
{
@@ -1378,7 +1656,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "12b28ec3",
+ "id": "3c44e8e6",
"metadata": {},
"outputs": [],
"source": [
@@ -1504,7 +1782,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "6d1e1ea1",
+ "id": "2b15ebca",
"metadata": {},
"outputs": [],
"source": [
@@ -1525,7 +1803,7 @@
{
"cell_type": "code",
"execution_count": 20,
- "id": "17119618",
+ "id": "b115cc56",
"metadata": {},
"outputs": [
{
@@ -1587,7 +1865,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "58213565",
+ "id": "3ef5fda5",
"metadata": {},
"outputs": [
{
@@ -1649,7 +1927,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "954a6da6",
+ "id": "6e4cec2f",
"metadata": {},
"outputs": [],
"source": [
@@ -1662,7 +1940,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "900af65d",
+ "id": "c194aaf1",
"metadata": {},
"outputs": [
{
@@ -1683,7 +1961,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "b3dd534e",
+ "id": "fd8812c1",
"metadata": {},
"outputs": [
{
@@ -1732,7 +2010,7 @@
{
"cell_type": "code",
"execution_count": 36,
- "id": "3477f518",
+ "id": "eb8c3d36",
"metadata": {},
"outputs": [
{
@@ -1794,7 +2072,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "cb794762",
+ "id": "fc31059a",
"metadata": {},
"outputs": [
{
@@ -1820,7 +2098,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "7fe2cd8b",
+ "id": "87e1b359",
"metadata": {},
"outputs": [],
"source": []
@@ -1828,7 +2106,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "0fe00cf6",
+ "id": "8ed06a4e",
"metadata": {},
"outputs": [
{
@@ -1848,7 +2126,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "f8bb463d",
+ "id": "dc56eb01",
"metadata": {},
"outputs": [
{
@@ -1869,7 +2147,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "bebc29de",
+ "id": "e24820fe",
"metadata": {},
"outputs": [
{
@@ -1939,7 +2217,7 @@
{
"cell_type": "code",
"execution_count": 16,
- "id": "e67598f0",
+ "id": "adabfec6",
"metadata": {},
"outputs": [],
"source": [
@@ -1950,7 +2228,7 @@
{
"cell_type": "code",
"execution_count": 26,
- "id": "51b78d60",
+ "id": "83617f96",
"metadata": {},
"outputs": [
{
@@ -2059,7 +2337,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "b58993ab",
+ "id": "a9e7ae70",
"metadata": {},
"outputs": [
{
@@ -2080,7 +2358,7 @@
{
"cell_type": "code",
"execution_count": 10,
- "id": "2554e586",
+ "id": "062ccc4d",
"metadata": {},
"outputs": [
{
@@ -2111,7 +2389,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "c46a53a3",
+ "id": "225701b3",
"metadata": {},
"outputs": [
{
@@ -2608,7 +2886,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "7e1b1fb5",
+ "id": "eb0dfa9d",
"metadata": {},
"outputs": [
{
@@ -2642,7 +2920,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "14168996",
+ "id": "2ea725af",
"metadata": {},
"outputs": [
{
@@ -2662,7 +2940,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "b1e6b703",
+ "id": "e7ecad72",
"metadata": {},
"outputs": [],
"source": [
@@ -2672,7 +2950,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "229a0b83",
+ "id": "921ab252",
"metadata": {},
"outputs": [
{
@@ -2693,7 +2971,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "ef1e3f31",
+ "id": "5e3ddee4",
"metadata": {},
"outputs": [
{
@@ -2720,7 +2998,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "9fcf9231",
+ "id": "16b9a0f0",
"metadata": {},
"outputs": [],
"source": []
diff --git a/mrdna/readers/segmentmodel_from_cadnano.py b/mrdna/readers/segmentmodel_from_cadnano.py
index fe6b46cd9bf5da8c8ee90287e8365bf76bfcf50b..cd92d4896e42c893b6751c15572a6b97d092c6aa 100644
--- a/mrdna/readers/segmentmodel_from_cadnano.py
+++ b/mrdna/readers/segmentmodel_from_cadnano.py
@@ -5,6 +5,7 @@ import os,sys
from glob import glob
import re
import pandas as pd
+pd.options.mode.chained_assignment = None # default='warn'
from ..arbdmodel.coords import readArbdCoords, readAvgArbdCoords, rotationAboutAxis
from ..segmentmodel import SegmentModel, SingleStrandedSegment, DoubleStrandedSegment
@@ -78,32 +79,32 @@ def read_json_file(filename):
n_df=df.set_index("num")
return part,n_df
-
def get_helix_angle(part, helix_id, indices):
- """ Get "start_orientation" for helix """
+ """ 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',
+ """ 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 = 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 + 180
angle = eulerZ + twist_per_base*indices - 0.5*mgroove
- return angle
+ return rotationAboutAxis(np.array((0,0,1)),angle)
-def ntcount(scafs):
+def nttype(scafs):
def judge(i):
if i ==[-1,-1,-1,-1]:
return 0
@@ -112,32 +113,66 @@ def ntcount(scafs):
return n
-def mrdna_model_from_cadnano(json_data,**model_parameters):
- part,vslist=decode_cadnano_part(json_data)
+def gen_prop_table(json_file):
+ part,vslist=read_json_file(json_file)
props = part.getModelProperties().copy()
-
- if props.get('point_type') == PointType.ARBITRARY:
+ try:
+ if props.get('point_type') == PointType.ARBITRARY:
# TODO add code to encode Parts with ARBITRARY point configurations
- raise NotImplementedError("Not implemented")
- else:
+ raise NotImplementedError("Not implemented")
+ except:
try:
vh_props, origins = part.helixPropertiesAndOrigins()
except:
origins = {hid:part.getVirtualHelixOrigin(hid)[:2] for hid in part.getidNums()}
- scaf_id=[ntcount(vslist['scaf'][i]) for i in vslist.index]
- stap_id=[ntcount(vslist['stap'][i]) for i in vslist.index]
+ scaf_id=[nttype(vslist['scaf'][i]) for i in vslist.index]
+ stap_id=[nttype(vslist['stap'][i]) for i in vslist.index]
cad_bps=part.getIndices(0)
- vslist["scafnt"]=np.sum(scaf_id)
- vslist["stapnt"]=np.sum(stap_id)
+ vslist["scafnt"]=np.sum(np.array(scaf_id),axis=1)
+ vslist["stapnt"]=np.sum(np.array(stap_id),axis=1)
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"])
- ind=0
- for vs in range(len(scaf_id)):
- for j in range(len(vs)):
- if j ==True
- nt_prop.loc[ind]["vh"]=vs
- nt_prop.loc[ind]["zid"]
-
-
-
- model = model_from_basepair_stack_3prime( r, bp, stack, three_prime, seq, orientation, **model_parameters )
+ is_scaf=np.zeros(totnt,dtype=bool)
+ is_scaf[0:np.sum(vslist["scafnt"])]=1
+ nt_prop=pd.DataFrame(index=range(totnt),columns=["vh","zid","is_scaf","r","bp","stack","threeprime","seq","orientation"])
+ nt_prop["is_scaf"]=is_scaf
+ tot_id=scaf_id+stap_id
+ vhi,zidi=np.where(np.array(scaf_id)==1)
+ vhj,zidj=np.where(np.array(stap_id)==1)
+ nt_prop["vh"]=list(vhi)+list(vhj)
+ nt_prop["zid"]=list(zidi)+list(zidj)
+ vhzid=list(zip(nt_prop["vh"],nt_prop["zid"]))
+ nt_prop["r"]=[part.getCoordinate(i,j) for i,j in zip(nt_prop["vh"],nt_prop["zid"])]
+ nt_prop["orientation"]=[get_helix_angle(part, helix_id, indices) for i,j in zip(nt_prop["vh"],nt_prop["zid"])]
+ nt_prop=nt_prop.fillna(-1)
+ for i in range(int(len(vhzid)/2)):
+ try:
+ bp1,bp2=(i,1+i+vhzid[i+1:].index(vhzid[i]))
+ nt_prop["bp"][bp1]=bp2
+ nt_prop["bp"][bp2]=bp1
+ except:
+ pass
+ tprime_list=-np.ones(len(nt_prop.index),dtype=int)
+ for i in range(len(nt_prop.index)):
+ ((m,n),p)=list(zip(vhzid,nt_prop["is_scaf"]))[i]
+ if p==True:
+ k,l=(vslist["scaf"][m])[n][2:]
+ if k!=-1 and l!=-1:
+ n=index2.index(((k,l),True))
+ tprime_list[i]=int(n)
+
+ else:
+ k,l=(vslist["stap"][m])[n][2:]
+ if k!=-1 and l!=-1:
+ n=index2.index(((k,l),False))
+ tprime_list[i]=int(n)
+ nt_prop["threeprime"]=tprime_list
+ (n,)=np.where(nt_prop["threeprime"]==-1)
+ stackid=nt_prop["bp"][[list(nt_prop["threeprime"]).index(i) for i in n]]
+ nt_prop["stack"][stackid.index[np.where(np.array(stackid)!=-1)]]=nt_prop["threeprime"][stackid.index[np.where(np.array(stackid)!=-1)]]
+
+
+ return nt_prop
+
+def mrdna_model_from_cadnano(json_file,**model_parameters):
+ nt_prop=gen_prop_table(json_file)
+ model = model_from_basepair_stack_3prime( nt_prop["r"], nt_prop["bp"], stack, three_prime, seq, orientation, **model_parameters )
diff --git a/mrdna/readers/test.ipynb b/mrdna/readers/test.ipynb
index b039b19ba5fb41f02a4d667e381a224bba2ccbca..217f357447273e9f86e51310d3571ace6b59a97c 100644
--- a/mrdna/readers/test.ipynb
+++ b/mrdna/readers/test.ipynb
@@ -2,8 +2,8 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 2,
- "id": "065c6b08",
+ "execution_count": 342,
+ "id": "767fe31e",
"metadata": {
"scrolled": true
},
@@ -12,25 +12,27 @@
"import pandas as pd\n",
"import pickle\n",
"import numpy as np\n",
+ "\n",
"df=pd.read_json(\"test.json\")\n",
"d=list(df[\"vstrands\"])"
]
},
{
"cell_type": "code",
- "execution_count": 7,
- "id": "e2409533",
+ "execution_count": 343,
+ "id": "52f3059d",
"metadata": {},
"outputs": [],
"source": [
"import cadnano\n",
- "from cadnano.document import Document\n"
+ "from cadnano.document import Document\n",
+ "from mrdna.arbdmodel.coords import readArbdCoords, readAvgArbdCoords, rotationAboutAxis"
]
},
{
"cell_type": "code",
"execution_count": 4,
- "id": "f3880b54",
+ "id": "2fb0f9e3",
"metadata": {},
"outputs": [],
"source": [
@@ -41,7 +43,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "5e4380bc",
+ "id": "312a3b3c",
"metadata": {},
"outputs": [
{
@@ -224,7 +226,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "6f670828",
+ "id": "df00a798",
"metadata": {},
"outputs": [
{
@@ -264,7 +266,7 @@
{
"cell_type": "code",
"execution_count": 18,
- "id": "ff3c11b6",
+ "id": "ab971d26",
"metadata": {},
"outputs": [],
"source": [
@@ -285,8 +287,8 @@
},
{
"cell_type": "code",
- "execution_count": 121,
- "id": "40fffe7e",
+ "execution_count": 195,
+ "id": "1a5439a1",
"metadata": {},
"outputs": [],
"source": [
@@ -339,88 +341,659 @@
},
{
"cell_type": "code",
- "execution_count": 44,
- "id": "d640032c",
+ "execution_count": 358,
+ "id": "254f8faf",
"metadata": {},
"outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found cadnano version 2 file\n"
+ ]
+ },
{
"data": {
"text/plain": [
- "[42, 42, 42, 42, 42, 42]"
+ "NucleicAcidPart_-1_3904"
]
},
- "execution_count": 44,
+ "execution_count": 358,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "bpnum=[len(df[\"scaf\"][i]) for i in df.index]\n",
- "bpnum"
+ "p,f=read_json_file(\"test.json\")\n",
+ "p"
]
},
{
"cell_type": "code",
- "execution_count": 122,
- "id": "7559115b",
- "metadata": {
- "scrolled": true
- },
+ "execution_count": 199,
+ "id": "054ffa7d",
+ "metadata": {},
"outputs": [
{
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Found cadnano version 2 file\n"
+ "data": {
+ "text/plain": [
+ "array([0. , 2.25, 3.4 ])"
+ ]
+ },
+ "execution_count": 199,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "p.getCoordinate(0,10)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 434,
+ "id": "5b268b86",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def mrdna_model_from_cadnano(json_file,**model_parameters):\n",
+ " part,vslist=read_json_file(json_file)\n",
+ " props = part.getModelProperties().copy()\n",
+ " try:\n",
+ " if props.get('point_type') == PointType.ARBITRARY:\n",
+ " # TODO add code to encode Parts with ARBITRARY point configurations\n",
+ " raise NotImplementedError(\"Not implemented\")\n",
+ " except:\n",
+ " try:\n",
+ " vh_props, origins = part.helixPropertiesAndOrigins()\n",
+ " except:\n",
+ " origins = {hid:part.getVirtualHelixOrigin(hid)[:2] for hid in part.getidNums()}\n",
+ " scaf_id=[nttype(vslist['scaf'][i]) for i in vslist.index]\n",
+ " stap_id=[nttype(vslist['stap'][i]) for i in vslist.index]\n",
+ " cad_bps=part.getIndices(0)\n",
+ " vslist[\"scafnt\"]=np.sum(np.array(scaf_id),axis=1)\n",
+ " vslist[\"stapnt\"]=np.sum(np.array(stap_id),axis=1)\n",
+ " totnt=np.sum(vslist[\"scafnt\"])+np.sum(vslist[\"stapnt\"])\n",
+ " is_scaf=np.zeros(totnt,dtype=bool)\n",
+ " is_scaf[0:np.sum(vslist[\"scafnt\"])]=1\n",
+ " nt_prop=pd.DataFrame(index=range(totnt),columns=[\"vh\",\"zid\",\"is_scaf\",\"r\",\"bp\",\"stack\",\"threeprime\",\"seq\",\"orientation\"])\n",
+ " nt_prop[\"is_scaf\"]=is_scaf\n",
+ " tot_id=scaf_id+stap_id\n",
+ " vhi,zidi=np.where(np.array(scaf_id)==1)\n",
+ " vhj,zidj=np.where(np.array(stap_id)==1)\n",
+ " nt_prop[\"vh\"]=list(vhi)+list(vhj)\n",
+ " nt_prop[\"zid\"]=list(zidi)+list(zidj)\n",
+ " vhzid=list(zip(nt_prop[\"vh\"],nt_prop[\"zid\"]))\n",
+ " nt_prop[\"r\"]=[part.getCoordinate(i,j) for i,j in zip(nt_prop[\"vh\"],nt_prop[\"zid\"])]\n",
+ " nt_prop[\"orientation\"]=[get_helix_angle(part, helix_id, indices) for i,j in zip(nt_prop[\"vh\"],nt_prop[\"zid\"])]\n",
+ " nt_prop=nt_prop.fillna(-1)\n",
+ " for i in range(int(len(vhzid)/2)):\n",
+ " try:\n",
+ " bp1,bp2=(i,1+i+vhzid[i+1:].index(vhzid[i]))\n",
+ " nt_prop[\"bp\"][bp1]=bp2\n",
+ " nt_prop[\"bp\"][bp2]=bp1\n",
+ " except:\n",
+ " pass\n",
+ " tprime_list=-np.ones(len(nt_prop.index),dtype=int)\n",
+ " for i in range(len(nt_prop.index)):\n",
+ " ((m,n),p)=list(zip(vhzid,nt_prop[\"is_scaf\"]))[i]\n",
+ " if p==True:\n",
+ " k,l=(vslist[\"scaf\"][m])[n][2:]\n",
+ " if k!=-1 and l!=-1:\n",
+ " n=index2.index(((k,l),True))\n",
+ " tprime_list[i]=int(n)\n",
+ "\n",
+ " else:\n",
+ " k,l=(vslist[\"stap\"][m])[n][2:]\n",
+ " if k!=-1 and l!=-1:\n",
+ " n=index2.index(((k,l),False))\n",
+ " tprime_list[i]=int(n)\n",
+ " nt_prop[\"threeprime\"]=tprime_list\n",
+ " (n,)=np.where(nt_prop[\"threeprime\"]==-1)\n",
+ " stackid=nt_prop[\"bp\"][[list(nt_prop[\"threeprime\"]).index(i) for i in n]]\n",
+ " nt_prop[\"stack\"][stackid.index[np.where(np.array(stackid)!=-1)]]=nt_prop[\"threeprime\"][stackid.index[np.where(np.array(stackid)!=-1)]]\n",
+ "\n",
+ "\n",
+ " return nt_prop\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 437,
+ "id": "67d740a5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225,\n",
+ " 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238,\n",
+ " 239, 240, 241, 242, 243, 244, -1, -1, -1, 249, 250, 251, 252,\n",
+ " 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265,\n",
+ " 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278,\n",
+ " 279, 280, -1, -1, -1, 285, 286, 287, 288, 289, 290, 291, 292,\n",
+ " 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305,\n",
+ " 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, -1, -1, -1,\n",
+ " 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332,\n",
+ " 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345,\n",
+ " 346, 347, 348, 349, 350, -1, -1, -1, -1, -1, -1, -1, -1,\n",
+ " -1, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364,\n",
+ " 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377,\n",
+ " 378, 379, 380, 381, 382, 383, -1, -1, -1, -1, 384, 385, 386,\n",
+ " 387, 388, 389, 390, 391, 392, 393, 394, 395, 396, 397, 398, 399,\n",
+ " 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, -1,\n",
+ " -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7,\n",
+ " 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,\n",
+ " 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, -1, -1,\n",
+ " -1, -1, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45,\n",
+ " 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58,\n",
+ " 59, 60, 61, 62, 63, 64, 65, 66, -1, -1, -1, -1, 70,\n",
+ " 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83,\n",
+ " 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96,\n",
+ " 97, 98, 99, 100, -1, -1, -1, -1, 104, 105, 106, 107, 108,\n",
+ " 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121,\n",
+ " 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134,\n",
+ " -1, -1, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154,\n",
+ " 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167,\n",
+ " 168, 169, 170, 171, 172, 173, 174, 179, 180, 181, 182, 183, 184,\n",
+ " 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197,\n",
+ " 198, 199, 200, 201, 202, 203, 204, 205, 206, -1, -1, -1])"
+ ]
+ },
+ "execution_count": 437,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "np.array(nt_prop[\"bp\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 302,
+ "id": "8df80d92",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "tprime_list=-np.ones(len(nt_prop.index),dtype=int)\n",
+ "for i in range(len(nt_prop.index)):\n",
+ " ((m,n),p)=list(zip(vhzid,nt_prop[\"is_scaf\"]))[i]\n",
+ " if p==True:\n",
+ " k,l=(vslist[\"scaf\"][m])[n][2:]\n",
+ " if k!=-1 and l!=-1:\n",
+ " n=index2.index(((k,l),True))\n",
+ " tprime_list[i]=int(n)\n",
+ " \n",
+ " else:\n",
+ " k,l=(vslist[\"stap\"][m])[n][2:]\n",
+ " if k!=-1 and l!=-1:\n",
+ " n=index2.index(((k,l),False))\n",
+ " tprime_list[i]=int(n)\n",
+ "nt_prop[\"threeprime\"]=tprime_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 368,
+ "id": "1ba36ce9",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_helix_angle(part, helix_id, indices):\n",
+ " \"\"\" Get \"start_orientation\" for helix \"\"\"\n",
+ " # import ipdb\n",
+ " # ipdb.set_trace()\n",
+ "\n",
+ " \"\"\" FROM CADNANO2.5\n",
+ " + angle is CCW\n",
+ " - angle is CW\n",
+ " Right handed DNA rotates clockwise from 5' to 3'\n",
+ " we use the convention the 5' end starts at 0 degrees\n",
+ " and it's pair is minor_groove_angle degrees away\n",
+ " direction, hence the minus signs. eulerZ\n",
+ " \"\"\"\n",
+ "\n",
+ " hp, bpr, tpr, eulerZ, mgroove = part.vh_properties.loc[helix_id,\n",
+ " ['helical_pitch',\n",
+ " 'bases_per_repeat',\n",
+ " 'turns_per_repeat',\n",
+ " 'eulerZ',\n",
+ " 'minor_groove_angle']]\n",
+ " twist_per_base = tpr*360./bpr\n",
+ " # angle = eulerZ - twist_per_base*indices + 0.5*mgroove + 180\n",
+ " angle = eulerZ + twist_per_base*indices - 0.5*mgroove\n",
+ " return rotationAboutAxis(np.array((0,0,1)),angle)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 429,
+ "id": "c275fa92",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "(n,)=np.where(nt_prop[\"threeprime\"]==-1)\n",
+ "\n",
+ "stackid=nt_prop[\"bp\"][[list(nt_prop[\"threeprime\"]).index(i) for i in n]]\n",
+ "\n",
+ "nt_prop[\"stack\"][stackid.index[np.where(np.array(stackid)!=-1)]]=nt_prop[\"threeprime\"][stackid.index[np.where(np.array(stackid)!=-1)]]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 430,
+ "id": "05d1934e",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "33 -1\n",
+ "68 -1\n",
+ "102 -1\n",
+ "136 -1\n",
+ "142 -1\n",
+ "176 -1\n",
+ "194 399\n",
+ "211 -1\n",
+ "233 20\n",
+ "281 -1\n",
+ "284 -1\n",
+ "351 -1\n",
+ "354 145\n",
+ "413 -1\n",
+ "Name: bp, dtype: int64"
+ ]
+ },
+ "execution_count": 430,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "stackid"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 431,
+ "id": "7d0daba0",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "232"
+ ]
+ },
+ "execution_count": 431,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "nt_prop[\"stack\"][233]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 433,
+ "id": "214ff037",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "353"
+ ]
+ },
+ "execution_count": 433,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "nt_prop[\"stack\"][354]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 167,
+ "id": "eb07d74e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "scaf_id=[nttype(vslist[\"scaf\"][i]) for i in vslist.index]\n",
+ "stap_id=[nttype(vslist[\"stap\"][i]) for i in vslist.index]\n",
+ "nts=scaf_id+stap_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 360,
+ "id": "63302624",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "nt_prop[\"orientation\"]=[get_helix_angle(p,i,j) for i,j in zip(nt_prop[\"vh\"],nt_prop[\"zid\"])]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 190,
+ "id": "bc0af039",
+ "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": [
+ " 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": 190,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "vslist"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 200,
+ "id": "fd6b27af",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def mrdna_model_from_cadnano(json_data,**model_parameters):\n",
+ " part,vslist=decode_cadnano_part(json_data)\n",
+ " props = part.getModelProperties().copy()\n",
+ "\n",
+ " if props.get('point_type') == PointType.ARBITRARY:\n",
+ " # TODO add code to encode Parts with ARBITRARY point configurations\n",
+ " raise NotImplementedError(\"Not implemented\")\n",
+ " else:\n",
+ " try:\n",
+ " vh_props, origins = part.helixPropertiesAndOrigins()\n",
+ " except:\n",
+ " origins = {hid:part.getVirtualHelixOrigin(hid)[:2] for hid in part.getidNums()}\n",
+ " scaf_id=np.array([nttype(vslist['scaf'][i]) for i in vslist.index])\n",
+ " stap_id=np.array([nttype(vslist['stap'][i]) for i in vslist.index])\n",
+ " cad_bps=part.getIndices(0)\n",
+ " vslist[\"scafnt\"]=np.sum(scaf_id,axis=1)\n",
+ " vslist[\"stapnt\"]=np.sum(stap_id,axis=1)\n",
+ " totnt=np.sum(vslist[\"scafnt\"])+np.sum(vslist[\"stapnt\"])\n",
+ " is_scaf=np.zeros(totnt)\n",
+ " is_scaf[0:np.sum(vslist[\"scafnt\"])]=1\n",
+ " nt_prop=pd.DataFrame(index=range(totnt),columns=[\"vh\",\"zid\",\"is_scaf\",\"r\",\"bp\",\"stack\",\"threeprime\",\"seq\",\"orientation\"])\n",
+ " nt_prop[\"is_scaf\"]=is_scaf\n",
+ " vhi,zids=np.where(np.array(scaf_id+stap_id)==1)\n",
+ " nt_prop[\"vh\"]=vhi\n",
+ " nt_prop[\"zid\"]=zids\n",
+ " nt_prop[\"r\"] =part.getCoordinate(nt_prop[\"vh\"],nt_prop[\"zid\"])\n",
+ " return nt_prop\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 201,
+ "id": "1130c056",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'decode_cadnano_part' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-201-c5d589a8b80d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmrdna_model_from_cadnano\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"test.json\"\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<ipython-input-200-181a924488ad>\u001b[0m in \u001b[0;36mmrdna_model_from_cadnano\u001b[0;34m(json_data, **model_parameters)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mmrdna_model_from_cadnano\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjson_data\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mmodel_parameters\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----> 2\u001b[0;31m \u001b[0mpart\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mvslist\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdecode_cadnano_part\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjson_data\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 3\u001b[0m \u001b[0mprops\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpart\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetModelProperties\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\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 4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mprops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'point_type'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mPointType\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mARBITRARY\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'decode_cadnano_part' is not defined"
]
}
],
"source": [
- "f,b=read_json_file(\"test.json\")\n"
+ "mrdna_model_from_cadnano(\"test.json\")"
]
},
{
"cell_type": "code",
- "execution_count": 52,
- "id": "1c4cd407",
+ "execution_count": 146,
+ "id": "7a77a10c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "a,b=np.where(np.array(nts)==1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 148,
+ "id": "07bed4f1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "Int64Index([0, 1, 2, 3, 4, 5], dtype='int64', name='num')"
+ "array([ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,\n",
+ " 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 39, 40,\n",
+ " 41, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,\n",
+ " 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 39,\n",
+ " 40, 41, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,\n",
+ " 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 39,\n",
+ " 40, 41, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,\n",
+ " 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 37,\n",
+ " 38, 39, 40, 41, 0, 1, 2, 3, 9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
+ " 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34,\n",
+ " 35, 36, 37, 38, 39, 0, 1, 2, 3, 9, 10, 11, 12, 13, 14, 15, 16,\n",
+ " 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,\n",
+ " 34, 35, 36, 37, 38, 39])"
]
},
- "execution_count": 52,
+ "execution_count": 148,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "b.index"
+ "nt_prop=pd.DataFrame(index)"
]
},
{
"cell_type": "code",
- "execution_count": 83,
- "id": "b85be77d",
+ "execution_count": 137,
+ "id": "efe96d4a",
"metadata": {},
"outputs": [],
"source": [
- "def ntcount(scafs):\n",
+ "def nttype(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",
+ " return n\n",
"\n"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9ac7ac46",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
{
"cell_type": "code",
"execution_count": 84,
- "id": "1b2f9268",
+ "id": "a28688b9",
"metadata": {},
"outputs": [],
"source": [
@@ -430,23 +1003,134 @@
},
{
"cell_type": "code",
- "execution_count": 123,
- "id": "5042c85d",
+ "execution_count": 156,
+ "id": "7583686f",
"metadata": {},
- "outputs": [],
+ "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></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",
+ " <tr>\n",
+ " <th>vh</th>\n",
+ " <th>zid</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",
+ " <th>0</th>\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",
+ " <th>3</th>\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",
+ " <th>1</th>\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",
+ " <th>2</th>\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",
+ " <th>8</th>\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": [
+ " r bp stack threeprime seq orientation\n",
+ "vh zid \n",
+ "0 0 NaN NaN NaN NaN NaN NaN\n",
+ "1 3 NaN NaN NaN NaN NaN NaN\n",
+ "2 1 NaN NaN NaN NaN NaN NaN\n",
+ "3 2 NaN NaN NaN NaN NaN NaN\n",
+ "1 8 NaN NaN NaN NaN NaN NaN"
+ ]
+ },
+ "execution_count": 156,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"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"
+ "d.set_index([\"vh\",\"zid\"],inplace=True)\n",
+ "d"
]
},
{
"cell_type": "code",
- "execution_count": 126,
- "id": "b91c2367",
+ "execution_count": 157,
+ "id": "1b71d3f6",
"metadata": {},
"outputs": [
{
@@ -549,19 +1233,21 @@
"4 1 8 NaN NaN NaN NaN NaN NaN"
]
},
- "execution_count": 126,
+ "execution_count": 157,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "d.reset_index()"
+ "\n",
+ "d=d.reset_index()\n",
+ "d"
]
},
{
"cell_type": "code",
"execution_count": 128,
- "id": "3c1fc0c9",
+ "id": "65e31a02",
"metadata": {},
"outputs": [
{
@@ -583,7 +1269,7 @@
{
"cell_type": "code",
"execution_count": 127,
- "id": "59833d98",
+ "id": "9e9fe8c1",
"metadata": {},
"outputs": [
{
@@ -703,7 +1389,7 @@
{
"cell_type": "code",
"execution_count": 100,
- "id": "1139214c",
+ "id": "7a82b9f7",
"metadata": {},
"outputs": [
{
@@ -728,7 +1414,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "ca81ed00",
+ "id": "759146bc",
"metadata": {},
"outputs": [
{
@@ -749,7 +1435,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "895861eb",
+ "id": "817cf65c",
"metadata": {},
"outputs": [
{
@@ -771,7 +1457,7 @@
{
"cell_type": "code",
"execution_count": 198,
- "id": "82bc0749",
+ "id": "683deaa8",
"metadata": {},
"outputs": [
{
@@ -793,7 +1479,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "1f5791d0",
+ "id": "cf734789",
"metadata": {},
"outputs": [
{
@@ -814,7 +1500,7 @@
{
"cell_type": "code",
"execution_count": 173,
- "id": "b36dc7e5",
+ "id": "7561d936",
"metadata": {},
"outputs": [],
"source": [
@@ -850,7 +1536,7 @@
{
"cell_type": "code",
"execution_count": 177,
- "id": "e0f42e86",
+ "id": "2fd676d8",
"metadata": {},
"outputs": [],
"source": [
@@ -886,7 +1572,7 @@
{
"cell_type": "code",
"execution_count": 187,
- "id": "0ca50f51",
+ "id": "6b288cdc",
"metadata": {},
"outputs": [
{
@@ -1113,7 +1799,7 @@
{
"cell_type": "code",
"execution_count": 142,
- "id": "6b3a92fd",
+ "id": "c516286a",
"metadata": {},
"outputs": [],
"source": [
@@ -1150,7 +1836,7 @@
{
"cell_type": "code",
"execution_count": 117,
- "id": "09ac3efa",
+ "id": "461e5389",
"metadata": {},
"outputs": [],
"source": [
@@ -1171,7 +1857,7 @@
{
"cell_type": "code",
"execution_count": 116,
- "id": "20b8e5fb",
+ "id": "1cfe41f9",
"metadata": {},
"outputs": [
{
@@ -1383,7 +2069,7 @@
{
"cell_type": "code",
"execution_count": 157,
- "id": "0978d11f",
+ "id": "b1e9c75c",
"metadata": {},
"outputs": [
{
@@ -1407,7 +2093,7 @@
{
"cell_type": "code",
"execution_count": 152,
- "id": "b9ffc57d",
+ "id": "91717641",
"metadata": {},
"outputs": [
{
@@ -1428,7 +2114,7 @@
{
"cell_type": "code",
"execution_count": 62,
- "id": "91c8bda1",
+ "id": "c2735ea2",
"metadata": {},
"outputs": [
{
@@ -1656,7 +2342,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "9d00775e",
+ "id": "21ebd651",
"metadata": {},
"outputs": [],
"source": [
@@ -1782,7 +2468,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "fe38ddd0",
+ "id": "29d8b2a3",
"metadata": {},
"outputs": [],
"source": [
@@ -1803,7 +2489,7 @@
{
"cell_type": "code",
"execution_count": 20,
- "id": "47af43f2",
+ "id": "ac70d73d",
"metadata": {},
"outputs": [
{
@@ -1865,7 +2551,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "92ee5de3",
+ "id": "b531515d",
"metadata": {},
"outputs": [
{
@@ -1927,7 +2613,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e99ffa71",
+ "id": "f11056d9",
"metadata": {},
"outputs": [],
"source": [
@@ -1940,7 +2626,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "9f251d5c",
+ "id": "7c724714",
"metadata": {},
"outputs": [
{
@@ -1961,7 +2647,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "ddff8ccc",
+ "id": "44e3bf14",
"metadata": {},
"outputs": [
{
@@ -2010,7 +2696,7 @@
{
"cell_type": "code",
"execution_count": 36,
- "id": "9bc201d2",
+ "id": "e0b4e485",
"metadata": {},
"outputs": [
{
@@ -2072,7 +2758,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "ab8da587",
+ "id": "97c05d36",
"metadata": {},
"outputs": [
{
@@ -2098,7 +2784,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "4141882b",
+ "id": "5818a167",
"metadata": {},
"outputs": [],
"source": []
@@ -2106,7 +2792,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "ce1031ed",
+ "id": "005b032e",
"metadata": {},
"outputs": [
{
@@ -2126,7 +2812,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "0f02b96f",
+ "id": "95c7c24d",
"metadata": {},
"outputs": [
{
@@ -2147,7 +2833,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "eb6d271c",
+ "id": "7bec19b6",
"metadata": {},
"outputs": [
{
@@ -2217,7 +2903,7 @@
{
"cell_type": "code",
"execution_count": 16,
- "id": "db9fb42a",
+ "id": "289d2009",
"metadata": {},
"outputs": [],
"source": [
@@ -2228,7 +2914,7 @@
{
"cell_type": "code",
"execution_count": 26,
- "id": "6e28886e",
+ "id": "8ac5cdf9",
"metadata": {},
"outputs": [
{
@@ -2337,7 +3023,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "8532c958",
+ "id": "f39f61c8",
"metadata": {},
"outputs": [
{
@@ -2358,7 +3044,7 @@
{
"cell_type": "code",
"execution_count": 10,
- "id": "42c985e8",
+ "id": "a4e2fc7b",
"metadata": {},
"outputs": [
{
@@ -2389,7 +3075,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "d26babc9",
+ "id": "3a00cb97",
"metadata": {},
"outputs": [
{
@@ -2886,7 +3572,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "eacb35b4",
+ "id": "8ba9d3ad",
"metadata": {},
"outputs": [
{
@@ -2920,7 +3606,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "0ff274ec",
+ "id": "9dcaba3d",
"metadata": {},
"outputs": [
{
@@ -2940,7 +3626,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "cb4b20bc",
+ "id": "5a768b47",
"metadata": {},
"outputs": [],
"source": [
@@ -2950,7 +3636,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "9694a3bb",
+ "id": "d64d0055",
"metadata": {},
"outputs": [
{
@@ -2971,7 +3657,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "d8dec327",
+ "id": "c7e397f4",
"metadata": {},
"outputs": [
{
@@ -2998,7 +3684,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "6af9f1ff",
+ "id": "24d5d7e8",
"metadata": {},
"outputs": [],
"source": []