feat: now woth ranges

0.1-jm-Chem-composition2mfql.ipynb

@@ -13,8 +13,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#https://pypi.org/project/molmass/\n",
-    "from molmass import Formula"
+    "from chem_parser import txt2dict\n",
+    "import warnings"
    ]
   },
   {
@@ -39,18 +39,19 @@
     "qn = input('Define query name (no spaces/underscores):')#Ultimate Species!\n",
     "\n",
     "#define formula and use molmass to generate the tuple\n",
-    "f = input ('Specify formula:')\n",
+    "f = input ('Specify formula (eg h2o or C[1..20]H[4..80]O[0..1]):')\n",
     "f = f.upper()\n",
+    "warnings.warn('for H is in a range, the first number will indicate if it should be odd or even')\n",
     "\n",
     "#define adduct and use molmass to generate the tuple\n",
-    "adduct = input('Specify adduct type (H, HCOO, NH4):')\n",
+    "adduct = input('Specify adduct type (optinal for ranges):')\n",
     "adduct = adduct.upper()\n",
     "\n",
     "#define MS mode\n",
     "ms = input('Define MS mode (either + or -):')\n",
     "\n",
     "#define filename\n",
-    "filename = input('Define file name (no special characters):')\n",
+    "filename = input('Define file name:')\n",
     "mfql = '.mfql'\n",
     "filename = \"\".join((filename, mfql))"
    ]
@@ -63,28 +64,8 @@
    },
    "outputs": [],
    "source": [
-    "cc = Formula(f)\n",
-    "af = Formula(adduct) #get chemical composition of adduct"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "cc1 = cc.composition()\n",
-    "cc_dict = {t[0]:t[1] for t in cc1}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "af1 = af.composition()\n",
-    "af_dict = {t[0]:t[1] for t in af1}"
+    "cc = txt2dict(f)\n",
+    "af = txt2dict(adduct) #get chemical composition of adduct"
    ]
   },
   {
@@ -94,17 +75,6 @@
     "### Based on the adduct it will be added or substracted"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "allelems = dict(cc_dict)\n",
-    "allelems.update(af_dict)\n",
-    "allelems.keys()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -113,17 +83,35 @@
    "source": [
     "#adjust for the adduct\n",
     "# only H, NH4 and HCOO are defined\n",
-    "allelems = dict(cc_dict)\n",
-    "allelems.update(af_dict)\n",
+    "allelems = dict(cc)\n",
+    "allelems.update(af)\n",
     "allelems.keys() # just to get all the keys in both dicts\n",
     "if adduct == 'H' and ms == '+':\n",
-    "    res = {key: cc_dict.get(key, 0) + af_dict.get(key, 0)  for key in allelems.keys()}\n",
+    "    res = {}\n",
+    "    for key in allelems.keys():\n",
+    "        low = cc.get(key, (0,0))[0]\n",
+    "        high = cc.get(key, (0,0))[1]\n",
+    "        low += af.get(key, (0,0))[0]\n",
+    "        high += af.get(key, (0,0))[1]\n",
+    "        res[key] = (low,high)\n",
     "    \n",
     "elif adduct == 'H' and ms == '-':\n",
-    "    res = {key: cc_dict.get(key, 0) - af_dict.get(key, 0)  for key in allelems.keys()}\n",
+    "    res = {}\n",
+    "    for key in allelems.keys():\n",
+    "        low = cc.get(key, (0,0))[0]\n",
+    "        high = cc.get(key, (0,0))[1]\n",
+    "        low -= af.get(key, (0,0))[0]\n",
+    "        high -= af.get(key, (0,0))[1]\n",
+    "        res[key] = (low,high)\n",
     "    \n",
-    "else : # al other adduc.getts\n",
-    "    res = {key: cc_dict.get(key, 0) + af_dict.get(key, 0)  for key in allelems.keys()}\n",
+    "else : # al other adducts\n",
+    "    res = {}\n",
+    "    for key in allelems.keys():\n",
+    "        low = cc.get(key, (0,0))[0]\n",
+    "        high = cc.get(key, (0,0))[1]\n",
+    "        low += af.get(key, (0,0))[0]\n",
+    "        high += af.get(key, (0,0))[1]\n",
+    "        res[key] = (low,high)\n",
     "     \n"
    ]
   },
@@ -155,11 +143,10 @@
    "outputs": [],
    "source": [
     "#test for odd/even number of hydrogens\n",
-    "if res['H'] % 2 == 0:\n",
+    "if res['H'][0] % 2 == 0:\n",
     "    such = 'isEven'\n",
     "else:\n",
-    "    such = 'isOdd'\n",
-    "    "
+    "    such = 'isOdd'\n"
    ]
   },
   {
@@ -172,7 +159,10 @@
     "for k,v in res.items():\n",
     "    if k == '2H':\n",
     "        k = 'D' \n",
-    "    ec += f'{k}[{v}] '\n",
+    "    if v[0]==v[1]:\n",
+    "        ec += f'{k}[{v[0]}] '\n",
+    "    else:\n",
+    "        ec += f'{k}[{v[0]}..{v[1]}] '\n",
     "ec"
    ]
   },
@@ -182,7 +172,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dbe = calc_dbe(res)"
+    "low_res = {k:v[0] for k,v in res.items()}\n",
+    "high_res = {k:v[1] for k,v in res.items()}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dbe_low = calc_dbe(low_res)\n",
+    "dbe_high = calc_dbe(high_res)"
    ]
   },
   {
@@ -193,7 +194,7 @@
    "source": [
     "line1 = f'#Identify {cn}#'\n",
     "line2 = f'QUERYNAME = {qn};'\n",
-    "line3 = f\"DEFINE pr = '{ec}' WITH DBR = ({dbe},{dbe}), CHG = {ms}1;\"\n",
+    "line3 = f\"DEFINE pr = '{ec}' WITH DBR = ({dbe_low},{dbe_high}), CHG = {ms}1;\"\n",
     "line4 = f'IDENTIFY\\n\\tpr in MS1{ms}'\n",
     "line5 = f'SUCHTHAT\\n\\t{such}(pr.chemsc[H]) AND \\n\\tisOdd(pr.chemsc[db]*2)'\n",
     "line6 = f'REPORT\\n\\tPRM = pr.mass;\\n\\tEC = pr.chemsc;\\n\\tCLASS = \"{qn}\" % \"()\";\\n\\tQSERR = \"%2.2f\" % \"(pr.errppm)\";\\n\\tQS = pr.intensity;;'\n",