diff --git a/work/run_partner_manifest_validation.ipynb b/work/run_partner_manifest_validation.ipynb
index 3efb895..099fcbd 100644
--- a/work/run_partner_manifest_validation.ipynb
+++ b/work/run_partner_manifest_validation.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "2ed8b533",
    "metadata": {},
    "outputs": [
@@ -24,7 +24,7 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mException\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m/var/folders/g7/vnlptw7d5pb544zsj_bypk44000h93/T/ipykernel_5923/3036708010.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'run'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'validate_partner_manifest_dev.ipynb'\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/var/folders/g7/vnlptw7d5pb544zsj_bypk44000h93/T/ipykernel_712/3036708010.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'run'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'validate_partner_manifest_dev.ipynb'\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~/miniconda3/envs/validate_partner_manifest_dev/lib/python3.7/site-packages/IPython/core/interactiveshell.py\u001b[0m in \u001b[0;36mrun_line_magic\u001b[0;34m(self, magic_name, line, _stack_depth)\u001b[0m\n\u001b[1;32m   2362\u001b[0m                 \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'local_ns'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_local_scope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstack_depth\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2363\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuiltin_trap\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2364\u001b[0;31m                 \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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   2365\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2366\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;32m~/miniconda3/envs/validate_partner_manifest_dev/lib/python3.7/site-packages/decorator.py\u001b[0m in \u001b[0;36mfun\u001b[0;34m(*args, **kw)\u001b[0m\n\u001b[1;32m    230\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mkwsyntax\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    231\u001b[0m                 \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkw\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkw\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msig\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 232\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mcaller\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mextras\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkw\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    233\u001b[0m     \u001b[0mfun\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    234\u001b[0m     \u001b[0mfun\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__doc__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__doc__\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;32m~/miniconda3/envs/validate_partner_manifest_dev/lib/python3.7/site-packages/IPython/core/magic.py\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(f, *a, **k)\u001b[0m\n\u001b[1;32m    185\u001b[0m     \u001b[0;31m# but it's overkill for just that one bit of state.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    186\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mmagic_deco\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marg\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--> 187\u001b[0;31m         \u001b[0mcall\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mlambda\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mk\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    188\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    189\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcallable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marg\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",
@@ -32,7 +32,7 @@
       "\u001b[0;32m~/miniconda3/envs/validate_partner_manifest_dev/lib/python3.7/site-packages/IPython/core/interactiveshell.py\u001b[0m in \u001b[0;36msafe_execfile_ipy\u001b[0;34m(self, fname, shell_futures, raise_exceptions)\u001b[0m\n\u001b[1;32m   2849\u001b[0m                     \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_cell\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcell\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msilent\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshell_futures\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mshell_futures\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2850\u001b[0m                     \u001b[0;32mif\u001b[0m \u001b[0mraise_exceptions\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2851\u001b[0;31m                         \u001b[0mresult\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraise_error\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   2852\u001b[0m                     \u001b[0;32melif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msuccess\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2853\u001b[0m                         \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;32m~/miniconda3/envs/validate_partner_manifest_dev/lib/python3.7/site-packages/IPython/core/interactiveshell.py\u001b[0m in \u001b[0;36mraise_error\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    330\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_before_exec\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    331\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_in_exec\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 332\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror_in_exec\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    333\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    334\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__repr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\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;31m[... skipping hidden 1 frame]\u001b[0m\n",
-      "\u001b[0;32m/var/folders/g7/vnlptw7d5pb544zsj_bypk44000h93/T/ipykernel_5923/3693612858.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Done for now'\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/var/folders/g7/vnlptw7d5pb544zsj_bypk44000h93/T/ipykernel_712/3693612858.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Done for now'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
       "\u001b[0;31mException\u001b[0m: Done for now"
      ]
     }
@@ -44,7 +44,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "c342af6c",
    "metadata": {},
    "outputs": [
@@ -52,45 +52,193 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "[WARNING] # manifest ../results/20220322/BP_ST_changes_22.03.22_Sam_NHM-BIOSCAN-Manifest Jan 2022.xlsx\n",
+      "[WARNING] # manifest ../results/20220405/NBGW-[20210527]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20210527]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c238872a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20210805]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n",
+      "[WARNING] ORDER: found unexpected rank for Acari (taxid 6933): subclass\n",
+      "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
+      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
+      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
+      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
+      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20210805]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f441b0df",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20210903]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n",
+      "[ERROR] ORDER: {'Opilones'} not found in NCBI Taxonomy\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20210903]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9524459e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20210930]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20210930]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fdff8970",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20211026]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n",
+      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"0.5\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20211026]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "962321eb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20211130]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20211130]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "940b497d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20220105]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n",
+      "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20220105]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "3c0658fc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NBGW-[20220201]-manifest.xlsx\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = validate('../results/20220405/NBGW-[20220201]-manifest.xlsx', template_fn, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "f38deb80",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[WARNING] # manifest ../results/20220405/NHM-BIOSCAN-Manifest_05042022.xlsx\n",
       "[WARNING] trailing spaces found in column 'FAMILY', SERIES [396]. Removing for validation\n",
       "[WARNING] trailing spaces found in column 'GENUS', SERIES [294, 295, 394, 395, 397, 398, 409, 410, 411, 412, 635, 636, 639]. Removing for validation\n",
       "[WARNING] trailing spaces found in column 'SCIENTIFIC_NAME', SERIES [294, 295]. Removing for validation\n",
-      "[WARNING] extra columns in filled manifest compared to template: {'Other/best taxon ID', 'CATCH_BOTTLE_TEMPERATURE_STORAGE', 'PLATE_TEMPERATURE_STORAGE', 'BAITED_TRAPS', 'SORTING_SOLUTION_USED'}\n",
+      "[WARNING] extra columns in filled manifest compared to template: {'BAITED_TRAPS', 'Other/best taxon ID', 'PLATE_TEMPERATURE_STORAGE', 'CATCH_BOTTLE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED'}\n",
       "[ERROR] template columns missing from filled manifest: {'MISC_METADATA'}\n",
-      "[ERROR] last well H12 is not blank at SERIES [192, 384, 480, 576, 672, 768, 864, 960, 1056, 288, 96]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']. These samples will be included in further analysis.\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] problem parsing coordinates 'NOT_APPLICABLE, NOT_APPLICABLE'\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
+      "[ERROR] for blanks, ORGANISM_PART expected to be BLANK_SAMPLE, found {'NOT_APPLICABLE'}\n",
+      "[WARNING] for blanks, NOT_APPLICABLE expected, but not found in columns ['CATCH_LOT', 'BOTTLE_DIRECTION', 'HAZARD_GROUP', 'REGULATORY_COMPLIANCE', 'DATE_OF_COLLECTION', 'COLLECTION_LOCATION', 'DECIMAL_LATITUDE', 'DECIMAL_LONGITUDE', 'WHAT_3_WORDS']\n",
       "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: unexpected case for \"lepidoptera\", changing to \"Lepidoptera\" for validation\n",
       "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
       "[WARNING] ORDER: found unexpected rank for Acari (taxid 6933): subclass\n",
       "[WARNING] ORDER: found unexpected rank for Arachnida (taxid 6854): class\n",
       "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Staphyllinidae', 'Not_applicable', 'Ichneumonidade', 'Psilidade', 'Psycodidae'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Hellophilus', 'Not_applicable', 'Sullia'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['P3D' 'P6D' 'NOT_APPLICABLE' 'P1D' 'P7D']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n",
-      "[ERROR] invalid dates in 'DATE_OF_PRESERVATION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in ELEVATION: \"NOT_APPLICABLE\"\n"
+      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['P3D' 'P6D' 'P1D' 'P7D']\n",
+      "[ERROR] invalid dates in 'DATE_OF_PRESERVATION': ['NOT_APPLICABLE']\n"
      ]
     }
    ],
    "source": [
-    "df = validate('../results/20220322/BP_ST_changes_22.03.22_Sam_NHM-BIOSCAN-Manifest Jan 2022.xlsx', template_fn, verbose=False)"
+    "df = validate('../results/20220405/NHM-BIOSCAN-Manifest_05042022.xlsx', template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c238872a",
+   "id": "597705bb",
    "metadata": {},
    "outputs": [],
    "source": []
diff --git a/work/validate_partner_manifest_dev.ipynb b/work/validate_partner_manifest_dev.ipynb
index 3484fa6..3c40445 100644
--- a/work/validate_partner_manifest_dev.ipynb
+++ b/work/validate_partner_manifest_dev.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -30,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
@@ -60,7 +60,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -70,7 +70,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -82,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
@@ -124,7 +124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -141,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
@@ -169,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [
     {
@@ -196,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [
     {
@@ -224,7 +224,7 @@
        "Name: TIME_OF_COLLECTION, Length: 1009, dtype: object"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 35,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -243,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [
     {
@@ -281,7 +281,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [
     {
@@ -329,7 +329,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "NOT_COLLECTED           989\n",
+       "                         50\n",
+       "blank sample             10\n",
+       "Formica rufa              3\n",
+       "NOT_APPLICABLE            2\n",
+       "Syrphus ribesii           1\n",
+       "Episyrphus balteatus      1\n",
+       "Name: SCIENTIFIC_NAME, dtype: int64"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['SCIENTIFIC_NAME'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
@@ -337,8 +364,17 @@
      "output_type": "stream",
      "text": [
       "[INFO] Checking and excluding blank samples\n",
-      "[ERROR] last well H12 is not blank at SERIES [96]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE']. These samples will be included in further analysis.\n",
-      "[INFO] found 10 blank samples based on SCIENTIFIC_NAME\n"
+      "[INFO] found and excluded 12 blank samples based on SCIENTIFIC_NAME\n",
+      "[ERROR] for blanks, ORGANISM_PART expected to be BLANK_SAMPLE, found {'NOT_APPLICABLE'}\n",
+      "[WARNING] for blanks, NOT_APPLICABLE expected, but not found in columns ['COLLECTION_LOCATION']\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(1056, 38)\n",
+      "(1044, 38)\n"
      ]
     }
    ],
@@ -348,9 +384,12 @@
     "    \n",
     "    logging.info('Checking and excluding blank samples')\n",
     "    \n",
+    "    blank_sample_sci_names = ['blank sample','NOT_APPLICABLE']\n",
+    "    \n",
+    "    \n",
     "    # last well of plate expected to be blank\n",
     "    last_well = df[df['TUBE_OR_WELL_ID'] == 'H12']\n",
-    "    last_well_blanks = (last_well['SCIENTIFIC_NAME'] == 'blank sample')\n",
+    "    last_well_blanks = (last_well['SCIENTIFIC_NAME'].isin(blank_sample_sci_names))\n",
     "    if not last_well_blanks.all():\n",
     "        logging.error('last well H12 is not blank at SERIES {}: in SCIENTIFIC_NAME, '\n",
     "                      'expected \"blank sample\", found {}. '\n",
@@ -359,10 +398,11 @@
     "                        last_well[~last_well_blanks].SCIENTIFIC_NAME.to_list()\n",
     "        ))\n",
     "    \n",
-    "    is_blank = (df['SCIENTIFIC_NAME'] == 'blank sample')\n",
+    "    # also exclude blanks in non-last plate\n",
+    "    is_blank = df['SCIENTIFIC_NAME'].isin(blank_sample_sci_names)\n",
     "    blank_df = df[is_blank]\n",
     "    \n",
-    "    logging.info('found {} blank samples based on SCIENTIFIC_NAME'.format(blank_df.shape[0]))\n",
+    "    logging.info('found and excluded {} blank samples based on SCIENTIFIC_NAME'.format(blank_df.shape[0]))\n",
     "    \n",
     "    # check organism part\n",
     "    organism_part_pass = (blank_df['ORGANISM_PART'] == 'BLANK_SAMPLE')\n",
@@ -384,13 +424,14 @@
     "    # logging.info('{} samples of {} left for downstream analysis'.format(df_flt.shape[0], df.shape[0]))\n",
     "    \n",
     "    return df[~is_blank]\n",
-    "        \n",
-    "df = check_blanks(df)"
+    "print(df.shape)\n",
+    "df = check_blanks(df)\n",
+    "print(df.shape)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
@@ -443,7 +484,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [
     {
@@ -451,7 +492,7 @@
      "output_type": "stream",
      "text": [
       "[INFO] validating date column 'DATE_OF_COLLECTION'\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_COLLECTED' 'NOT_APPLICABLE' '']\n"
+      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_COLLECTED' '']\n"
      ]
     },
     {
@@ -472,7 +513,7 @@
        "Name: DATE_OF_COLLECTION, Length: 993, dtype: datetime64[ns]"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 42,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -515,7 +556,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [
     {
@@ -523,7 +564,7 @@
      "output_type": "stream",
      "text": [
       "[INFO] validating time column 'TIME_OF_COLLECTION'\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE' '']\n"
+      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['']\n"
      ]
     },
     {
@@ -544,7 +585,7 @@
        "Name: TIME_OF_COLLECTION, Length: 994, dtype: datetime64[ns]"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 43,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -575,7 +616,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [
     {
@@ -583,7 +624,7 @@
      "output_type": "stream",
      "text": [
       "[INFO] validating time period column 'DURATION_OF_COLLECTION'\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE' '']\n"
+      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['']\n"
      ]
     }
    ],
@@ -632,7 +673,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 45,
    "metadata": {},
    "outputs": [
     {
@@ -642,7 +683,7 @@
       "[INFO] validating country with coordinates\n",
       "[ERROR] no partner location found for coordinates '52.0236, 0.2389'\n",
       "[ERROR] no partner location found for coordinates '51.917197, -1.148376'\n",
-      "[ERROR] multiple partner countries for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE': ['UNITED KINGDOM' 'NOT_APPLICABLE']skipping coordinate validation\n",
+      "[ERROR] no partner location found for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE'\n",
       "[ERROR] multiple partner countries for coordinates '50.598618, -3.7209498': ['UNITED KINGDOM' '']skipping coordinate validation\n",
       "[WARNING] could not locate country for coordinates ', ', partner country ''\n"
      ]
@@ -787,7 +828,7 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1046 rows × 6 columns</p>\n",
+       "<p>1044 rows × 6 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -819,10 +860,10 @@
        "1054                                        ,                          UNKNOWN  \n",
        "1055                                        ,                          UNKNOWN  \n",
        "\n",
-       "[1046 rows x 6 columns]"
+       "[1044 rows x 6 columns]"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 45,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -931,7 +972,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -940,29 +981,25 @@
      "text": [
       "[INFO] validating taxonomy against NCBI\n",
       "[INFO] validating ORDER against NCBI\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
       "[ERROR] ORDER: unexpected case for \"NOT_COLLECTED\", changing to \"Not_collected\" for validation\n",
       "[ERROR] ORDER: unexpected case for \"diptera\", changing to \"Diptera\" for validation\n",
       "[ERROR] ORDER: unexpected case for \"Diptera and Arachnidae\", changing to \"Diptera and arachnidae\" for validation\n",
-      "[ERROR] ORDER: {'Acari (subclass)', '', 'Not_collected', 'Not_applicable', 'Tricoptera', 'Diptera and arachnidae', 'Symphyleona'} not found in NCBI Taxonomy\n",
+      "[ERROR] ORDER: {'', 'Acari (subclass)', 'Not_collected', 'Tricoptera', 'Diptera and arachnidae', 'Symphyleona'} not found in NCBI Taxonomy\n",
       "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
       "[INFO] ORDER: using only first matching rank for Plecoptera (taxid 50622): order\n",
       "[WARNING] ORDER: found unexpected rank for Protura (taxid 29999): class\n",
       "[INFO] validating FAMILY against NCBI\n",
       "[ERROR] FAMILY: unexpected case for \"NOT_COLLECTED\", changing to \"Not_collected\" for validation\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
       "[ERROR] FAMILY: unexpected case for \"Unkown and Acari\", changing to \"Unkown and acari\" for validation\n",
-      "[ERROR] FAMILY: {'', 'Aphidiodea', 'Not_collected', 'Not_applicable', 'Unkown and acari'} not found in NCBI Taxonomy\n",
+      "[ERROR] FAMILY: {'', 'Not_collected', 'Aphidiodea', 'Unkown and acari'} not found in NCBI Taxonomy\n",
       "[WARNING] FAMILY: found unexpected rank for Aphidoidea (taxid 33385): superfamily\n",
       "[INFO] validating GENUS against NCBI\n",
       "[ERROR] GENUS: unexpected case for \"NOT_COLLECTED\", changing to \"Not_collected\" for validation\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'', 'Not_collected', 'Not_applicable'} not found in NCBI Taxonomy\n",
+      "[ERROR] GENUS: {'', 'Not_collected'} not found in NCBI Taxonomy\n",
       "[INFO] GENUS: using only first matching rank for Bombus (taxid 28641): genus\n",
       "[INFO] validating SCIENTIFIC_NAME against NCBI\n",
       "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_COLLECTED\", changing to \"Not_collected\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'', 'Not_collected', 'Not_applicable'} not found in NCBI Taxonomy\n",
+      "[ERROR] SCIENTIFIC_NAME: {'', 'Not_collected'} not found in NCBI Taxonomy\n",
       "[INFO] cannot validate FAMILY for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate FAMILY for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate FAMILY for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
@@ -973,7 +1010,6 @@
       "[INFO] cannot validate FAMILY for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate FAMILY for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate ORDER for \"Acari (subclass)\", skipping taxonomy consistency check\n",
-      "[INFO] cannot validate ORDER for \"NOT_APPLICABLE\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate FAMILY for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate ORDER for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate GENUS for \"NOT_COLLECTED\", skipping taxonomy consistency check\n",
@@ -1335,7 +1371,7 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1046 rows × 42 columns</p>\n",
+       "<p>1044 rows × 42 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -1437,10 +1473,10 @@
        "1054                          \n",
        "1055                          \n",
        "\n",
-       "[1046 rows x 42 columns]"
+       "[1044 rows x 42 columns]"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1585,7 +1621,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -1593,7 +1629,6 @@
      "output_type": "stream",
      "text": [
       "[INFO] validating int format in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n",
       "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"\"\n"
      ]
     }
@@ -1619,7 +1654,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -1627,7 +1662,7 @@
      "output_type": "stream",
      "text": [
       "[INFO] validating date column 'DATE_OF_COLLECTION'\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_COLLECTED' 'NOT_APPLICABLE' '']\n",
+      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_COLLECTED' '']\n",
       "[INFO] validating date column 'DATE_OF_PRESERVATION'\n",
       "[ERROR] invalid dates in 'DATE_OF_PRESERVATION': ['' 'NOT_APPLICABLE']\n"
      ]
@@ -1640,7 +1675,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1649,7 +1684,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -1669,7 +1704,7 @@
        "Length: 993, dtype: bool"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1680,26 +1715,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
     "def compare_dates(before, after):\n",
-    "    \n",
-    "    ctdf = pd.concat([before.reset_index(), after.reset_index()], axis=1)\n",
+    "        \n",
+    "    logging.info(f'checking that {before.name} are earlier than {after.name}')\n",
+    "\n",
+    "    ctdf = pd.concat([before, after], axis=1)\n",
     "    date_conflict = ctdf[before.name] > ctdf[after.name]\n",
     "    \n",
-    "#     logging.info(date_conflict)\n",
     "    if date_conflict.any():\n",
     "        logging.error(f'{before.name} values are later than {after.name} for SERIES'\n",
-    "                      f' {ctdf[date_conflict].index.to_list()}')\n",
-    "    \n",
-    "compare_dates(bd, ad)"
+    "                      f' {ctdf[date_conflict].index.to_list()}')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -1720,48 +1754,44 @@
       "[ERROR] Found and excluded 240 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
       "[INFO] found 1056 samples across 11 plates\n",
       "[INFO] Checking and excluding blank samples\n",
-      "[ERROR] last well H12 is not blank at SERIES [96]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE']. These samples will be included in further analysis.\n",
-      "[INFO] found 10 blank samples based on SCIENTIFIC_NAME\n",
+      "[INFO] found and excluded 12 blank samples based on SCIENTIFIC_NAME\n",
+      "[ERROR] for blanks, ORGANISM_PART expected to be BLANK_SAMPLE, found {'NOT_APPLICABLE'}\n",
+      "[WARNING] for blanks, NOT_APPLICABLE expected, but not found in columns ['COLLECTION_LOCATION']\n",
       "[INFO] validating values in column 'PRESERVATIVE_SOLUTION'\n",
       "[INFO] validating values in column 'BOTTLE_DIRECTION'\n",
       "[ERROR] invalid values in 'BOTTLE_DIRECTION': {''}\n",
       "[INFO] validating values in column 'ORGANISM_PART'\n",
       "[ERROR] invalid values in 'ORGANISM_PART': {''}\n",
       "[INFO] validating values in column 'HAZARD_GROUP'\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE', ''}\n",
+      "[ERROR] invalid values in 'HAZARD_GROUP': {''}\n",
       "[INFO] validating values in column 'REGULATORY_COMPLIANCE'\n",
       "[ERROR] invalid values in 'REGULATORY_COMPLIANCE': {'', 'y'}\n",
       "[INFO] validating date column 'DATE_OF_COLLECTION'\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE' '']\n",
+      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['']\n",
       "[INFO] validating country with coordinates\n",
       "[ERROR] no partner location found for coordinates '52.0236, 0.2389'\n",
       "[ERROR] no partner location found for coordinates '51.917197, -1.148376'\n",
-      "[ERROR] multiple partner countries for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE': ['UNITED KINGDOM' 'NOT_APPLICABLE']skipping coordinate validation\n",
+      "[ERROR] no partner location found for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE'\n",
       "[ERROR] multiple partner countries for coordinates '50.598618, -3.7209498': ['UNITED KINGDOM' '']skipping coordinate validation\n",
       "[WARNING] could not locate country for coordinates ', ', partner country ''\n",
       "[INFO] validating taxonomy against NCBI\n",
       "[INFO] validating ORDER against NCBI\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
       "[ERROR] ORDER: unexpected case for \"diptera\", changing to \"Diptera\" for validation\n",
       "[ERROR] ORDER: unexpected case for \"Diptera and Arachnidae\", changing to \"Diptera and arachnidae\" for validation\n",
-      "[ERROR] ORDER: {'Acari (subclass)', '', 'Not_applicable', 'Tricoptera', 'Diptera and arachnidae', 'Symphyleona'} not found in NCBI Taxonomy\n",
+      "[ERROR] ORDER: {'', 'Acari (subclass)', 'Tricoptera', 'Diptera and arachnidae', 'Symphyleona'} not found in NCBI Taxonomy\n",
       "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
       "[INFO] ORDER: using only first matching rank for Plecoptera (taxid 50622): order\n",
       "[WARNING] ORDER: found unexpected rank for Protura (taxid 29999): class\n",
       "[INFO] validating FAMILY against NCBI\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
       "[ERROR] FAMILY: unexpected case for \"Unkown and Acari\", changing to \"Unkown and acari\" for validation\n",
-      "[ERROR] FAMILY: {'', 'Unkown and acari', 'Not_applicable', 'Aphidiodea'} not found in NCBI Taxonomy\n",
+      "[ERROR] FAMILY: {'', 'Aphidiodea', 'Unkown and acari'} not found in NCBI Taxonomy\n",
       "[WARNING] FAMILY: found unexpected rank for Aphidoidea (taxid 33385): superfamily\n",
       "[INFO] validating GENUS against NCBI\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'', 'Not_applicable'} not found in NCBI Taxonomy\n",
+      "[ERROR] GENUS: {''} not found in NCBI Taxonomy\n",
       "[INFO] GENUS: using only first matching rank for Bombus (taxid 28641): genus\n",
       "[INFO] validating SCIENTIFIC_NAME against NCBI\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'', 'Not_applicable'} not found in NCBI Taxonomy\n",
+      "[ERROR] SCIENTIFIC_NAME: {''} not found in NCBI Taxonomy\n",
       "[INFO] cannot validate ORDER for \"Acari (subclass)\", skipping taxonomy consistency check\n",
-      "[INFO] cannot validate ORDER for \"NOT_APPLICABLE\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate ORDER for \"diptera\", skipping taxonomy consistency check\n",
       "[INFO] cannot validate ORDER for \"Diptera and Arachnidae\", skipping taxonomy consistency check\n",
       "[ERROR] Family Syrphidae (taxid 34680) does not belong to Hymenoptera (taxid 7399)\n",
@@ -1775,19 +1805,19 @@
       "[INFO] validating values in column 'SEX'\n",
       "[ERROR] invalid values in 'SEX': {''}\n",
       "[INFO] validating time column 'TIME_OF_COLLECTION'\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE' '']\n",
+      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['']\n",
       "[INFO] validating time period column 'DURATION_OF_COLLECTION'\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE' '']\n",
+      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['']\n",
       "[INFO] validating values in column 'COLLECTION_METHOD'\n",
       "[ERROR] invalid values in 'COLLECTION_METHOD': {''}\n",
       "[INFO] validating int format in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING\n",
       "[INFO] excluding 50 [''] samples without data in 'TIME_ELAPSED_FROM_COLLECTION_TO_PLATING'\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n",
       "[INFO] validating date column 'DATE_OF_PRESERVATION'\n",
-      "[INFO] excluding 1044 [''] samples without data in 'DATE_OF_PRESERVATION'\n",
+      "[INFO] excluding 1042 [''] samples without data in 'DATE_OF_PRESERVATION'\n",
       "[ERROR] invalid dates in 'DATE_OF_PRESERVATION': ['NOT_APPLICABLE']\n",
+      "[INFO] checking that DATE_OF_COLLECTION are earlier than DATE_OF_PRESERVATION\n",
       "[INFO] validating int format in ELEVATION\n",
-      "[INFO] excluding 1046 [''] samples without data in 'ELEVATION'\n",
+      "[INFO] excluding 1044 [''] samples without data in 'ELEVATION'\n",
       "[INFO] # ended validate_partner_manifest_v.1.0\n"
      ]
     }
@@ -1815,10 +1845,11 @@
     "    valid_dict = get_valid_dict(template_fn)\n",
     "\n",
     "    # orange cols\n",
+    "    # exclude empty series\n",
     "    df = validate_series(df)\n",
     "    df = validate_plates_wells(df, 'RACK_OR_PLATE_ID', 'TUBE_OR_WELL_ID')\n",
     "    \n",
-    "    # check blanks\n",
+    "    # check and exclude blanks\n",
     "    df = check_blanks(df)\n",
     "    \n",
     "    validate_values('PRESERVATIVE_SOLUTION', df, valid_dict)\n",
@@ -1859,9 +1890,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 26,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "Exception",
+     "evalue": "Done for now",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mException\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m/var/folders/g7/vnlptw7d5pb544zsj_bypk44000h93/T/ipykernel_627/3693612858.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Done for now'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mException\u001b[0m: Done for now"
+     ]
+    }
+   ],
    "source": [
     "raise Exception('Done for now')"
    ]
@@ -1876,60 +1919,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220322/NBGW-[20210805]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 768 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[WARNING] ORDER: found unexpected rank for Acari (taxid 6933): subclass\n",
-      "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n"
-     ]
-    }
-   ],
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "df = validate('../results/20220322/NBGW-[20210805]-manifest.xlsx', template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220322/NBGW-[20220105]-manifest.xlsx\n",
-      "[ERROR] Found and excluded non-numeric SERIES: ['']\n",
-      "[ERROR] in TUBE_OR_WELL_ID for plate NBGW_003, wells {'E12'} are missing, wells set() are excessive\n",
-      "[ERROR] last well H12 is not blank at SERIES [95]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE']. These samples will be included in further analysis.\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] problem parsing coordinates 'NOT_APPLICABLE, NOT_APPLICABLE'\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate('../results/20220322/NBGW-[20220105]-manifest.xlsx', template_fn, verbose=False)"
    ]
@@ -1943,61 +1951,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220315/Sam_NHM-BIOSCAN-Manifest Jan 2022.xlsx\n",
-      "[WARNING] trailing spaces found in column 'FAMILY', SERIES [396]. Removing for validation\n",
-      "[WARNING] trailing spaces found in column 'GENUS', SERIES [294, 295, 394, 395, 397, 398, 409, 410, 411, 412, 635, 636, 639]. Removing for validation\n",
-      "[WARNING] extra columns in filled manifest compared to template: {'BAITED_TRAPS', 'Other/best taxon ID'}\n",
-      "[ERROR] template columns missing from filled manifest: {'MISC_METADATA'}\n",
-      "[ERROR] last well H12 is not blank at SERIES [192, 384, 480, 576, 672, 768, 864, 960, 1056, 288, 96]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']. These samples will be included in further analysis.\n",
-      "[ERROR] invalid values in 'BOTTLE_DIRECTION': {'East', 'West'}\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] problem parsing coordinates 'NOT_APPLICABLE, NOT_APPLICABLE'\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: unexpected case for \"lepidoptera\", changing to \"Lepidoptera\" for validation\n",
-      "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[WARNING] ORDER: found unexpected rank for Acari (taxid 6933): subclass\n",
-      "[WARNING] ORDER: found unexpected rank for Arachnida (taxid 6854): class\n",
-      "[WARNING] ORDER: found unexpected rank for Collembola (taxid 30001): class\n",
-      "[ERROR] FAMILY: unexpected case for \"UNKNOWN\", changing to \"Unknown\" for validation\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Psilidade', 'Not_applicable', 'Psycodidae', 'Ichneumonidade', 'Staphyllinidae'} not found in NCBI Taxonomy\n",
-      "[WARNING] FAMILY: found unexpected rank for Unknown (taxid 32644): species\n",
-      "[ERROR] GENUS: unexpected case for \"UNKNOWN\", changing to \"Unknown\" for validation\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Sullia', 'Hellophilus', 'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[WARNING] GENUS: found unexpected rank for Unknown (taxid 32644): species\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"UNKNOWN\", changing to \"Unknown\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"lacticolella\", changing to \"Lacticolella\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"equestris\", changing to \"Equestris\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"ocellare\", changing to \"Ocellare\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"marginata\", changing to \"Marginata\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"platypterus\", changing to \"Platypterus\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"vallata \", changing to \"Vallata \" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"rara \", changing to \"Rara \" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"balteatus\", changing to \"Balteatus\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"luteolata\", changing to \"Luteolata\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"pendulus\", changing to \"Pendulus\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Equestris', 'Lacticolella', 'Not_applicable', 'Marginata', 'Balteatus', 'Rara\\xa0', 'Ocellare', 'Pendulus', 'Luteolata', 'Vallata\\xa0'} not found in NCBI Taxonomy\n",
-      "[WARNING] SCIENTIFIC_NAME: found unexpected rank for Platypterus (taxid 484252): subgenus\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE' 'Not known']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['P2D23H' 'P5D23H30M' 'NOT_APPLICABLE' 'P1D0H0M' 'Not known' 'P1D4H20M'\n",
-      " 'P1D0H50M' 'unknown' '72hrs' '50hrs']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n",
-      "[ERROR] invalid dates in 'DATE_OF_PRESERVATION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in ELEVATION: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# test columns addition\n",
     "df = validate('../results/20220315/Sam_NHM-BIOSCAN-Manifest Jan 2022.xlsx', template_fn, verbose=False)"
@@ -2005,20 +1961,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220303_add_tax/final-CARR-20210727-manifestV1.xlsx\n",
-      "[WARNING] extra columns in filled manifest compared to template: {'PLATE_TEMPERATURE_STORAGE', 'SORTING_SOLUTION_USED', 'CATCH_BOTTLE_TEMPERATURE_STORAGE'}\n",
-      "[ERROR] for blanks, ORGANISM_PART expected to be BLANK_SAMPLE, found {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_PRESERVATION': ['NOT_APPLICABLE']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# test columns addition\n",
     "df = validate('../results/20220303_add_tax/final-CARR-20210727-manifestV1.xlsx', template_fn, verbose=False)\n",
@@ -2027,26 +1972,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['../results/20220304/NBGW-[20210527]-manifest.xlsx',\n",
-       " '../results/20220304/NBGW-[20210903]-manifest.xlsx',\n",
-       " '../results/20220304/NBGW-[20210930]-manifest.xlsx',\n",
-       " '../results/20220304/NBGW-[20211026]-manifest.xlsx',\n",
-       " '../results/20220304/NBGW-[20211130]-manifest.xlsx',\n",
-       " '../results/20220304/NBGW-[20220201]-manifest.xlsx',\n",
-       " '../results/20220304/NGBW-[20210629]-manifest.xlsx']"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "import glob\n",
     "fns = list(glob.glob('../results/20220304/*.xlsx'))\n",
@@ -2056,228 +1984,72 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NBGW-[20210527]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 576 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['9.04' '9.45']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[0], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NBGW-[20210903]-manifest.xlsx\n",
-      "[ERROR] last well H12 is not blank at SERIES [96, 192, 288, 384]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']\n",
-      "[ERROR] invalid values in 'ORGANISM_PART': {'Diptera placed in well, removed'}\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: unexpected case for \"NOT COLLECTED\", changing to \"Not collected\" for validation\n",
-      "[ERROR] ORDER: {'Not collected', 'Not_applicable', 'Opilones'} not found in NCBI Taxonomy\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[1], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NBGW-[20210930]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 672 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[ERROR] last well H12 is not blank at SERIES [96, 192, 288]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[2], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NBGW-[20211026]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 672 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[ERROR] last well H12 is not blank at SERIES [96, 192, 288]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid values in 'SEX': {'ADULT'}\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"0.5\"\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[3], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NBGW-[20211130]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 672 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[ERROR] last well H12 is not blank at SERIES [96, 192, 288]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[4], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NBGW-[20220201]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 672 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[ERROR] last well H12 is not blank at SERIES [96, 192, 288]: in SCIENTIFIC_NAME, expected \"blank sample\", found ['NOT_APPLICABLE', 'NOT_APPLICABLE', 'NOT_APPLICABLE']\n",
-      "[ERROR] invalid values in 'HAZARD_GROUP': {'NOT_APPLICABLE'}\n",
-      "[ERROR] invalid dates in 'DATE_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[WARNING] could not locate country for coordinates 'NOT_APPLICABLE, NOT_APPLICABLE', partner country 'NOT_APPLICABLE'\n",
-      "[ERROR] ORDER: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] ORDER: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] FAMILY: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] FAMILY: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] GENUS: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] GENUS: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] SCIENTIFIC_NAME: unexpected case for \"NOT_APPLICABLE\", changing to \"Not_applicable\" for validation\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Not_applicable'} not found in NCBI Taxonomy\n",
-      "[ERROR] invalid times in 'TIME_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] invalid times in 'DURATION_OF_COLLECTION': ['NOT_APPLICABLE']\n",
-      "[ERROR] found non-integer value in TIME_ELAPSED_FROM_COLLECTION_TO_PLATING: \"NOT_APPLICABLE\"\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[5], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[WARNING] # manifest ../results/20220304/NGBW-[20210629]-manifest.xlsx\n",
-      "[ERROR] Found and excluded 672 empty rows based on RACK_OR_PLATE_ID and TUBE_OR_WELL_ID\n",
-      "[WARNING] ORDER: found unexpected rank for Acari (taxid 6933): subclass\n",
-      "[ERROR] SCIENTIFIC_NAME: {'Bombus terrestris/lucorum'} not found in NCBI Taxonomy\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df = validate(fns[6], template_fn, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "Exception",
-     "evalue": "Done for now",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mException\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m/var/folders/g7/vnlptw7d5pb544zsj_bypk44000h93/T/ipykernel_46513/3693612858.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Done for now'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mException\u001b[0m: Done for now"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": []
   },
   {