Merge pull request #75 from gwaygenomics/rearrange-fig-names

[Response to Reviewers] Update all figure names

1.Data-exploration/gene_target_median_correlation.ipynb

@@ -198,12 +198,21 @@
    "execution_count": 3,
    "id": "4861408c-f0cd-4d9e-8b54-d52734e96f9d",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of unique targets: 720\n"
+     ]
+    }
+   ],
    "source": [
     "# Match compounds that target the same genes\n",
     "# Note the compound can also target _other_ genes as well\n",
     "all_targets = {x: list(set(x.split(\"|\"))) for x in cp_df.Metadata_target.unique().tolist()}\n",
     "\n",
+    "all_unique_targets = []\n",
     "cp_target_comparisons = {}\n",
     "for target in all_targets:\n",
     "    target_set = set(all_targets[target])\n",
@@ -216,7 +225,12 @@
     "            if target in cp_target_comparisons:\n",
     "                cp_target_comparisons[target].append(compare_target)\n",
     "            else:\n",
-    "                cp_target_comparisons[target] = [compare_target]"
+    "                cp_target_comparisons[target] = [compare_target]\n",
+    "    \n",
+    "    all_unique_targets += list(target_set)\n",
+    "\n",
+    "all_unique_targets = set(all_unique_targets)\n",
+    "print(f\"Number of unique targets: {len(all_unique_targets)}\")"
    ]
   },
   {

1.Data-exploration/scripts/nbconverted/gene_target_median_correlation.py

@@ -41,6 +41,7 @@
 # Note the compound can also target _other_ genes as well
 all_targets = {x: list(set(x.split("|"))) for x in cp_df.Metadata_target.unique().tolist()}
 
+all_unique_targets = []
 cp_target_comparisons = {}
 for target in all_targets:
     target_set = set(all_targets[target])
@@ -54,6 +55,11 @@
                 cp_target_comparisons[target].append(compare_target)
             else:
                 cp_target_comparisons[target] = [compare_target]
+
+    all_unique_targets += list(target_set)
+
+all_unique_targets = set(all_unique_targets)
+print(f"Number of unique targets: {len(all_unique_targets)}")
 
 
 # In[4]:

6.paper_figures/figure1.ipynb → 6.paper_figures/figure1_percentreplicating.ipynb

@@ -33,7 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "output_figure_base <- file.path(\"figures\", \"figure1\")\n",
+    "output_figure_base <- file.path(\"figures\", \"figure1_percentreplicating\")\n",
     "extensions <- c(\".png\", \".pdf\")"
    ]
   },
@@ -42,7 +42,9 @@
    "id": "013de854-d981-42c6-85d3-5f19edc32aef",
    "metadata": {},
    "source": [
-    "### Panel A - Within assay percent replicating non-parametric p values"
+    "### Panel B - Within assay percent replicating non-parametric p values\n",
+    "\n",
+    "Note, Panel A is a single cell example Cell Painting image"
    ]
   },
   {
@@ -367,7 +369,7 @@
     }
    ],
    "source": [
-    "panel_a_gg <- (\n",
+    "panel_b_gg <- (\n",
     "    ggplot(pr_pval_df, aes(x = median_score, y = neg_log_10_p_val))\n",
     "    + geom_point(aes(color = no_of_compounds), alpha = 0.05)\n",
     "    + geom_text(data = percent_replicating_df, aes(label = percent_replicating, x = 0.65, y = 2.5))\n",
@@ -384,15 +386,15 @@
     "    + guides(color = guide_legend(override.aes = list(alpha = 1, size = 2)))\n",
     ")\n",
     "\n",
-    "panel_a_gg"
+    "panel_b_gg"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "699ddb14-3066-4399-a329-3204eb40e614",
    "metadata": {},
    "source": [
-    "## Panel B - Comparing percent replicating scores\n",
+    "## Panel C - Comparing percent replicating scores\n",
     "\n",
     "At the perturbation level between the two assays."
    ]
@@ -556,7 +558,7 @@
     }
    ],
    "source": [
-    "panel_b_gg <- (\n",
+    "panel_c_gg <- (\n",
     "    ggplot(\n",
     "        pr_summary_df %>%\n",
     "            # Remove compounds measured in different wells inconsistently\n",
@@ -571,15 +573,15 @@
     "    + ylab(\"L1000: Median pairwise\\nreplicate Spearman correlation\")\n",
     ")\n",
     "\n",
-    "panel_b_gg"
+    "panel_c_gg"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "6e667e14-c5eb-4985-b586-7a687cb27792",
    "metadata": {},
    "source": [
-    "## Panel C - Percent replicating summary\n",
+    "## Panel D - Percent replicating summary\n",
     "\n",
     "Which compounds pass the null distribution threshold?"
    ]
@@ -869,7 +871,7 @@
    "source": [
     "updated_assay_colors <- c(assay_colors, \"Both\" = \"#DF74F0\")\n",
     "\n",
-    "panel_c_gg <- (\n",
+    "panel_d_gg <- (\n",
     "    ggplot(full_rect)\n",
     "    + geom_rect(\n",
     "        aes(\n",
@@ -899,7 +901,7 @@
     "\n",
     ")\n",
     "\n",
-    "panel_c_gg"
+    "panel_d_gg"
    ]
   },
   {
@@ -917,9 +919,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "panel_a_gg <- panel_a_gg + labs(tag = \"b\")\n",
-    "panel_b_gg <- panel_b_gg + labs(tag = \"c\")\n",
-    "panel_c_gg <- panel_c_gg + labs(tag = \"d\")"
+    "panel_b_gg <- panel_b_gg + labs(tag = \"b\")\n",
+    "panel_c_gg <- panel_c_gg + labs(tag = \"c\")\n",
+    "panel_d_gg <- panel_d_gg + labs(tag = \"d\")"
    ]
   },
   {
@@ -962,10 +964,10 @@
    ],
    "source": [
     "# We add an updated panel a in the resubmission, update tags here\n",
-    "left_panel <- (panel_a_gg / panel_b_gg) + plot_layout(heights = c(2, 1))\n",
+    "left_panel <- (panel_b_gg / panel_c_gg) + plot_layout(heights = c(2, 1))\n",
     "\n",
     "figure_1_gg <- (\n",
-    "    ( left_panel | panel_c_gg)\n",
+    "    ( left_panel | panel_d_gg)\n",
     "    + plot_layout(widths = c(2, 1))\n",
     ")\n",
     "\n",
@@ -980,7 +982,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "R [conda env:lincs-complimentarity-figures]",
+   "display_name": "R [conda env:lincs-complimentarity-figures] *",
    "language": "R",
    "name": "conda-env-lincs-complimentarity-figures-r"
   },

6.paper_figures/figure3.ipynb → 6.paper_figures/figure2_sampleanalysis.ipynb

@@ -5,7 +5,7 @@
    "id": "09a930c5-017c-4bc8-9bb6-eb6b31deba02",
    "metadata": {},
    "source": [
-    "## Figure 3\n",
+    "## Figure 2\n",
     "\n",
     "Perturbation sample diversity"
    ]
@@ -34,7 +34,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "output_figure_base <- file.path(\"figures\", \"figure3\")\n",
+    "output_figure_base <- file.path(\"figures\", \"figure2_sampleanalysis\")\n",
     "extensions <- c(\".png\", \".pdf\")"
    ]
   },
@@ -443,7 +443,7 @@
     "    labels = c(\"\", \"\")\n",
     ")\n",
     "\n",
-    "figure3_gg <- cowplot::plot_grid(\n",
+    "figure2_gg <- cowplot::plot_grid(\n",
     "    cowplot::plot_grid(\n",
     "        cp_umap_gg,\n",
     "        l1000_umap_gg,\n",
@@ -456,20 +456,12 @@
     "    labels = c(\"\", \"b\")\n",
     ")\n",
     "\n",
-    "figure3_gg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "b1044714-10fb-4a5b-ba16-49c44885e943",
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "for (extension in extensions) {\n",
     "    output_file <- paste0(output_figure_base, extension)\n",
-    "    cowplot::save_plot(output_file, figure3_gg, base_width = 12, base_height = 11, dpi = 500)\n",
-    "}"
+    "    cowplot::save_plot(output_file, figure2_gg, base_width = 12, base_height = 11, dpi = 500)\n",
+    "}\n",
+    "\n",
+    "figure2_gg"
    ]
   }
  ],