Merge pull request #2 from vanallenlab/2021-08-11

2021 July 7 release

analyses/knowledge-bases/civic-oncokb/create-source-data.ipynb

@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import openpyxl\n",
+    "\n",
+    "folder = \"../../../extended-data/extended-data-fig-4/\"\n",
+    "filename = \"source-data-extended-data-fig-4.xlsx\"\n",
+    "writer = pd.ExcelWriter(f'{folder}/{filename}', engine='xlsxwriter')\n",
+    "\n",
+    "tuples = [('pmid', 'a'), ('drug', 'b'), ('gene', 'c')]\n",
+    "for handle, label in tuples:\n",
+    "    df = pd.read_csv(f\"{handle}-comparison.txt\", sep='\\t')\n",
+    "    df.to_excel(writer, sheet_name=f\"Extended Data Fig. 4{label}\", index=False)\n",
+    "writer.save()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "moalmanac-paper",
+   "language": "python",
+   "name": "moalmanac-paper"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

analyses/knowledge-bases/civic-oncokb/upset.R

@@ -8,17 +8,35 @@ drugs <- read.csv('drug-comparison.txt', sep='\t', header=T)
 genes <- read.csv('gene-comparison.txt', sep='\t', header=T)
 pmids <- read.csv('pmid-comparison.txt', sep='\t', header=T)
 
-png('~/Github/moalmanac-paper/figures/supplementary-figure-13/supplementary-figure-13.png', width=800, height=600)
-upset(pmids, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=2)
-grid.text("Comparison of PubMed IDs catalogued by\nCIViC, MOAlmanac, and OncoKB",x = 0.65, y=0.95, gp=gpar(fontsize=20))
+## PDF
+pdf("~/Github/moalmanac-paper/extended-data-figures/extended-data-fig-4/extended-data-fig-4a.pdf", paper='a4')
+upset(pmids, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=1.5,
+      mainbar.y.label="PubMed IDs\nintersection size")
 dev.off()
 
-png('~/Github/moalmanac-paper/figures/supplementary-figure-14/supplementary-figure-14.png', width=800, height=600)
-upset(drugs, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=2)
-grid.text("Comparison of therapies catalogued by\nCIViC, MOAlmanac, and OncoKB",x = 0.65, y=0.95, gp=gpar(fontsize=20))
+pdf("~/Github/moalmanac-paper/extended-data-figures/extended-data-fig-4/extended-data-fig-4b.pdf", paper='a4')
+upset(drugs, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=1.5,
+      mainbar.y.label="Therapies\nintersection size")
 dev.off()
 
-png('~/Github/moalmanac-paper/figures/supplementary-figure-15/supplementary-figure-15.png', width=800, height=600)
-upset(genes, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=2)
-grid.text("Comparison of genes catalogued by\nCIViC, MOAlmanac, and OncoKB",x = 0.65, y=0.95, gp=gpar(fontsize=20))
+pdf("~/Github/moalmanac-paper/extended-data-figures/extended-data-fig-4/extended-data-fig-4c.pdf", paper='a4')
+upset(genes, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=1.5,
+      mainbar.y.label="Genes\nintersection size")
 dev.off()
+
+## PNG
+png("~/Github/moalmanac-paper/extended-data-figures/extended-data-fig-4/extended-data-fig-4a.png", res=300, width=1000, height=750)
+upset(pmids, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=1,
+      mainbar.y.label="PubMed IDs\nintersection size")
+dev.off()
+
+png("~/Github/moalmanac-paper/extended-data-figures/extended-data-fig-4/extended-data-fig-4b.png", res=300, width=1000, height=750)
+upset(drugs, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=1,
+      mainbar.y.label="Therapies\nintersection size")
+dev.off()
+
+png("~/Github/moalmanac-paper/extended-data-figures/extended-data-fig-4/extended-data-fig-4c.png", res=300, width=1000, height=750)
+upset(genes, sets = c("CIViC", "MOAlmanac", "OncoKB"), sets.bar.color = "#56B4E9", order.by = "freq", text.scale=1,
+      mainbar.y.label="Genes\nintersection size")
+dev.off()
+

analyses/knowledge-bases/molecular-oncology-almanac/README.md

@@ -1,5 +1,5 @@
 # Molecular Oncology Almanac
 These notebooks perform calculations and generate a few figures.
 - `count-combination-therapies.ipynb` counts the combination therapies present in the database
-- `create-supplementary-table.ipynb` creates supplementary table 1, which lists an TARGET annotated version of TARGET and all catalogued entries in MOAlmanac
-- `illustrate-moalmanac-breakdown.ipynb` creates a figure, Figure 1c
+- `create-supplementary-table.ipynb` creates supplementary table 2, which lists an TARGET annotated version of TARGET and all catalogued entries in MOAlmanac
+- `illustrate-moalmanac-breakdown.ipynb` creates a figure, Fig. 1c

analyses/knowledge-bases/molecular-oncology-almanac/create-supplementary-table.ipynb

@@ -29,32 +29,110 @@
     "import pandas as pd\n",
     "import glob \n",
     "\n",
-    "filename = 'supplementary-table-2'\n",
-    "folder = f'../../../tables/supplementary-table-02'\n",
-    "!mkdir -p $folder\n",
-    "outname = f'{folder}/{filename}.xlsx'\n",
-    "\n",
     "options = {}\n",
     "options['strings_to_formulas'] = False\n",
     "options['strings_to_urls'] = False\n",
     "\n",
-    "writer = pd.ExcelWriter(outname)\n",
+    "column_order = ['disease', \n",
+    "                'context', \n",
+    "                'oncotree_term', \n",
+    "                'oncotree_code', \n",
+    "                'therapy_name', \n",
+    "                'therapy_strategy', \n",
+    "                'therapy_type', \n",
+    "                'therapy_sensitivity',\n",
+    "                'therapy_resistance', \n",
+    "                'favorable_prognosis', \n",
+    "                'predictive_implication',\n",
+    "                'description', \n",
+    "                'preferred_assertion', \n",
+    "                'source_type', \n",
+    "                'citation', \n",
+    "                'url', \n",
+    "                'doi',\n",
+    "                'pmid', \n",
+    "                'nct', \n",
+    "                'last_updated', \n",
+    "                'adverse_event_risk', \n",
+    "                'feature_type', \n",
+    "                'gene', \n",
+    "                'chromosome', \n",
+    "                'start_position', \n",
+    "                'end_position', \n",
+    "                'reference_allele', \n",
+    "                'alternate_allele', \n",
+    "                'cdna_change', \n",
+    "                'protein_change', \n",
+    "                'variant_annotation', \n",
+    "                'exon', \n",
+    "                'rsid', \n",
+    "                'pathogenic', \n",
+    "                'direction', \n",
+    "                'cytoband',\n",
+    "                'gene1', \n",
+    "                'gene2', \n",
+    "                'rearrangement_type', \n",
+    "                'classification', \n",
+    "                'minimum_mutations', \n",
+    "                'mutations_per_mb',\n",
+    "                #'minimum_neoantigens',\n",
+    "                'cosmic_signature_number',\n",
+    "                'cosmic_signature_version',\n",
+    "                'event', \n",
+    "                'locus', \n",
+    "                'status', \n",
+    "                'technique'\n",
+    "]\n",
     "\n",
-    "target = pd.read_excel('../target/almanac-comparison.xlsx')\n",
-    "target.to_excel(writer, sheet_name='TARGET')\n",
+    "dtype_map = {\n",
+    "    'aneuploidy': 'Aneuploidy',\n",
+    "    'copy_number': 'Copy Number',\n",
+    "    'germline_variant': 'Germline variant',\n",
+    "    'knockdown': 'Knockdown',\n",
+    "    'microsatellite_stability': 'Microsatellite stability',\n",
+    "    'mutational_burden': 'Mutational burden',\n",
+    "    'mutational_signature': 'Mutational signature',\n",
+    "    'neoantigen_burden': 'Neoantigen burden',\n",
+    "    'rearrangement': 'Rearrangement',\n",
+    "    'silencing': 'Silencing',\n",
+    "    'somatic_variant': 'Somatic variant'\n",
+    "}\n",
     "\n",
-    "sheet_names = []\n",
+    "sheets = []\n",
     "handles = glob.glob('../moalmanac-db/content/*')\n",
     "for handle in sorted(handles):\n",
     "    dtype = handle.split('/')[-1].split('.tsv')[0]\n",
-    "    if dtype == 'microsatellite_stability':\n",
-    "        dtype = 'msi'\n",
-    "    sheet_name = f'moalmanac-{dtype}'\n",
-    "    sheet_names.append(sheet_name)\n",
-    "    \n",
+    "    feature_type = dtype_map[dtype]  \n",
     "    tmp = pd.read_csv(handle, sep='\\t')\n",
-    "    tmp.to_excel(writer, sheet_name=sheet_name, index=False)\n",
-    "    \n",
+    "    tmp['feature_type'] = feature_type\n",
+    "    sheets.append(tmp)\n",
+    "\n",
+    "\n",
+    "sort_columns = ['gene', 'gene1', 'gene2', 'therapy_sensitivity', 'therapy_resistance', 'favorable_prognosis', 'disease', 'therapy_name']\n",
+    "df = (pd\n",
+    "      .concat(sheets, ignore_index=True)\n",
+    "      .loc[:, column_order]\n",
+    "      .sort_values(sort_columns, ascending=True)\n",
+    "     )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "filename = 'supplementary-table-2'\n",
+    "folder = f'../../../tables/supplementary-table-02'\n",
+    "!mkdir -p $folder\n",
+    "outname = f'{folder}/{filename}.xlsx'\n",
+    "\n",
+    "writer = pd.ExcelWriter(outname)\n",
+    "\n",
+    "target = pd.read_excel('../target/almanac-comparison.xlsx')\n",
+    "target.to_excel(writer, sheet_name='TableS2-TARGET', index=False)\n",
+    "df.to_excel(writer, sheet_name='TableS2-MOAlmanac', index=False)\n",
+    "\n",
     "writer.save()"
    ]
   },