wip cleaning these up. Committing so can work on other branch

Author: alliblk

scripts/make-input-fastas.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -34,15 +34,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "738 sequences were available from Fauna.\n",
-      "568 sequences meet the geographic criteria.\n"
+      "819 sequences were available from Fauna.\n",
+      "649 sequences meet the geographic criteria.\n"
      ]
     }
    ],
@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -98,7 +98,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -115,14 +115,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "There are 476 sequences that are sampled from a relevant region and have over 70% informative bases\n"
+      "There are 552 sequences that are sampled from a relevant region and have over 70% informative bases\n"
      ]
     }
    ],
@@ -150,7 +150,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -164,14 +164,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "There are 394 genomes that we can include in published analyses.\n"
+      "There are 470 genomes that we can include in published analyses.\n"
      ]
     }
    ],
@@ -210,15 +210,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "There were 33 sequences from different culture passages of COL/FLR/2015 that should be removed.\n",
-      "There are now 361 sequences that should be included in the build.\n"
+      "There are now 437 sequences that should be included in the build.\n"
      ]
     }
    ],
@@ -253,13 +253,6 @@
     "        file.write(str(\">\" + key + \"\\n\" + publishable_seqs_no_cell_culture_passage_dict[key].lower() + \"\\n\" ))"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -3615,7 +3608,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.4"
+   "version": "3.6.12"
   }
  },
  "nbformat": 4,