Updated Mitocheck LOGO analysis plots

.pre-commit-config.yaml

@@ -14,7 +14,7 @@ repos:
 
   # Format TOML files early (before other tools might read config)
 -   repo: https://github.com/pappasam/toml-sort
-    rev: v0.24.3
+    rev: v0.24.4
     hooks:
     -   id: toml-sort
         args: ["--in-place"]

notebooks/3.mitocheck-analysis/1.buscar-analysis.ipynb

@@ -1222,6 +1222,101 @@
     "output_filename = f\"{'shuffled' if shuffle_flag else 'original'}_mitocheck_moa_analysis_results.parquet\"\n",
     "results_df.write_parquet(moa_analysis_output / output_filename)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "458fbd23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_df = pl.read_parquet(\n",
+    "    \"./results/moa_analysis/original_mitocheck_moa_analysis_results.parquet\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9d40b76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_df = (\n",
+    "    test_df.sort([\"ref_profile\", \"on_score\", \"off_score\", \"treatment\"], nulls_last=True)\n",
+    "    .with_row_index(\"_row_idx\")\n",
+    "    .with_columns(\n",
+    "        (pl.col(\"_row_idx\") - pl.col(\"_row_idx\").min().over(\"ref_profile\") + 1)\n",
+    "        .cast(pl.UInt32)\n",
+    "        .alias(\"rank\")\n",
+    "    )\n",
+    "    .drop(\"_row_idx\")\n",
+    ")\n",
+    "test_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f325f8aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr,\n",
+       ".dataframe > tbody > tr {\n",
+       "  text-align: right;\n",
+       "  white-space: pre-wrap;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (960, 6)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>rank</th><th>ref_profile</th><th>treatment</th><th>on_score</th><th>off_score</th><th>proportion</th></tr><tr><td>u32</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>f64</td></tr></thead><tbody><tr><td>null</td><td>&quot;ADCCM&quot;</td><td>&quot;BUB1B&quot;</td><td>null</td><td>null</td><td>null</td></tr><tr><td>null</td><td>&quot;ADCCM&quot;</td><td>&quot;KIF20A&quot;</td><td>null</td><td>null</td><td>null</td></tr><tr><td>null</td><td>&quot;ADCCM&quot;</td><td>&quot;MYST1&quot;</td><td>null</td><td>null</td><td>null</td></tr><tr><td>1</td><td>&quot;ADCCM&quot;</td><td>&quot;RGR&quot;</td><td>1.8337e-14</td><td>0.0</td><td>0.430556</td></tr><tr><td>2</td><td>&quot;ADCCM&quot;</td><td>&quot;OGG1&quot;</td><td>1.1369e-13</td><td>0.0</td><td>0.042553</td></tr><tr><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td></tr><tr><td>54</td><td>&quot;SmallIrregular&quot;</td><td>&quot;ENSG00000139974&quot;</td><td>463.140217</td><td>0.111111</td><td>0.0</td></tr><tr><td>55</td><td>&quot;SmallIrregular&quot;</td><td>&quot;CGI-63&quot;</td><td>497.549042</td><td>0.027778</td><td>0.0</td></tr><tr><td>56</td><td>&quot;SmallIrregular&quot;</td><td>&quot;VIPR1&quot;</td><td>541.199995</td><td>0.194444</td><td>0.0</td></tr><tr><td>57</td><td>&quot;SmallIrregular&quot;</td><td>&quot;ENSG00000198517&quot;</td><td>558.711878</td><td>0.0</td><td>0.0</td></tr><tr><td>58</td><td>&quot;SmallIrregular&quot;</td><td>&quot;ENSG00000180225&quot;</td><td>645.364835</td><td>0.138889</td><td>0.0</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (960, 6)\n",
+       "┌──────┬────────────────┬─────────────────┬────────────┬───────────┬────────────┐\n",
+       "│ rank ┆ ref_profile    ┆ treatment       ┆ on_score   ┆ off_score ┆ proportion │\n",
+       "│ ---  ┆ ---            ┆ ---             ┆ ---        ┆ ---       ┆ ---        │\n",
+       "│ u32  ┆ str            ┆ str             ┆ f64        ┆ f64       ┆ f64        │\n",
+       "╞══════╪════════════════╪═════════════════╪════════════╪═══════════╪════════════╡\n",
+       "│ null ┆ ADCCM          ┆ BUB1B           ┆ null       ┆ null      ┆ null       │\n",
+       "│ null ┆ ADCCM          ┆ KIF20A          ┆ null       ┆ null      ┆ null       │\n",
+       "│ null ┆ ADCCM          ┆ MYST1           ┆ null       ┆ null      ┆ null       │\n",
+       "│ 1    ┆ ADCCM          ┆ RGR             ┆ 1.8337e-14 ┆ 0.0       ┆ 0.430556   │\n",
+       "│ 2    ┆ ADCCM          ┆ OGG1            ┆ 1.1369e-13 ┆ 0.0       ┆ 0.042553   │\n",
+       "│ …    ┆ …              ┆ …               ┆ …          ┆ …         ┆ …          │\n",
+       "│ 54   ┆ SmallIrregular ┆ ENSG00000139974 ┆ 463.140217 ┆ 0.111111  ┆ 0.0        │\n",
+       "│ 55   ┆ SmallIrregular ┆ CGI-63          ┆ 497.549042 ┆ 0.027778  ┆ 0.0        │\n",
+       "│ 56   ┆ SmallIrregular ┆ VIPR1           ┆ 541.199995 ┆ 0.194444  ┆ 0.0        │\n",
+       "│ 57   ┆ SmallIrregular ┆ ENSG00000198517 ┆ 558.711878 ┆ 0.0       ┆ 0.0        │\n",
+       "│ 58   ┆ SmallIrregular ┆ ENSG00000180225 ┆ 645.364835 ┆ 0.138889  ┆ 0.0        │\n",
+       "└──────┴────────────────┴─────────────────┴────────────┴───────────┴────────────┘"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_df = test_df.with_columns(\n",
+    "    pl.col(\"on_score\")\n",
+    "    .rank(method=\"min\", descending=False)\n",
+    "    .over(\"ref_profile\")\n",
+    "    .cast(pl.UInt32)\n",
+    "    .alias(\"rank\")\n",
+    ").sort([\"ref_profile\", \"rank\"])\n",
+    "test_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9791894",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

notebooks/3.mitocheck-analysis/plots/all-plots/gene-ranking-relationships/kendall_w_real_permutation_summary.csv

@@ -1,6 +1,6 @@
 comparison,value
 real,0.3119730571847507
-perm_null_mean,0.06288665288214809
-perm_null_sd,0.015597630731234009
+perm_null_mean,0.06247271639021261
+perm_null_sd,0.015491729056433213
 empirical_p_real_vs_perm,0
-zscore_real_vs_perm,15.969502586300562
+zscore_real_vs_perm,16.105390165659312

notebooks/3.mitocheck-analysis/plots/all-plots/gene-ranking-relationships/profile_specificity_real_vs_shuffled.csv

@@ -1,17 +1,33 @@
-profile,mean_rho_real,mean_rho_shuffled,delta_real_minus_shuffled
-Anaphase,0.15650479608991533,0.5608964127385906,-0.4043916166486753
-Metaphase,0.13139922605215137,0.5093394174370867,-0.3779401913849353
-OutOfFocus,0.10073463266775773,0.4172842935847898,-0.31654966091703207
-Apoptosis,0.1762858259363896,0.478924334081411,-0.30263850814502136
-Large,0.1482367791371488,0.350562590707509,-0.2023258115703602
-Elongated,0.2712370916745004,0.47031707404217477,-0.19907998236767438
-Prometaphase,0.3473546385279508,0.5422565846807784,-0.19490194615282763
-Grape,0.327177791535563,0.5202688055905473,-0.19309101405498436
-MetaphaseAlignment,0.14517391794230394,0.3224625514621759,-0.17728863351987195
-Interphase,0.3424213985129714,0.5104889215703348,-0.1680675230573634
-Folded,0.2882696005225906,0.4517972552372199,-0.16352765471462932
-Hole,0.40691895860031285,0.5400238670665998,-0.13310490846628692
-ADCCM,0.42070576160986695,0.5503210383410524,-0.12961527673118545
-SmallIrregular,0.24237625897755977,0.3648440681218771,-0.12246780914431732
-Binuclear,0.3258004638947451,0.43975486734424585,-0.11395440344950075
-Polylobed,0.34938013645686744,0.39657308337490166,-0.04719294691803422
+profile,mean_rho,feature_space
+OutOfFocus,0.07750370900918473,original
+MetaphaseAlignment,0.09317750675662102,original
+Metaphase,0.09403146460384448,original
+Large,0.12395297721298071,original
+Anaphase,0.1295363284681192,original
+Apoptosis,0.1737850580597236,original
+SmallIrregular,0.21873523146467183,original
+Elongated,0.257222234180935,original
+Binuclear,0.27802463518368153,original
+Folded,0.2788073284358493,original
+Polylobed,0.31549516115662113,original
+Grape,0.31945239999258623,original
+Prometaphase,0.3258901426117646,original
+Interphase,0.3358363381673327,original
+Hole,0.3941905910241724,original
+ADCCM,0.4051700760604237,original
+MetaphaseAlignment,0.3370797217146052,shuffled
+Polylobed,0.36565797628873886,shuffled
+SmallIrregular,0.3732682342174917,shuffled
+Large,0.3761371957895286,shuffled
+Binuclear,0.429199932541633,shuffled
+OutOfFocus,0.44320772909259587,shuffled
+Elongated,0.4443778206808757,shuffled
+Apoptosis,0.4879658015481369,shuffled
+Metaphase,0.4921355483067866,shuffled
+Folded,0.5007048767989222,shuffled
+Grape,0.5014884633783497,shuffled
+ADCCM,0.5029203890851184,shuffled
+Hole,0.5112183719238499,shuffled
+Interphase,0.5257748638252964,shuffled
+Anaphase,0.5398174587901845,shuffled
+Prometaphase,0.585452476379703,shuffled

notebooks/3.mitocheck-analysis/plots/all-plots/gene-ranking-relationships/profile_specificity_real_vs_shuffled_wide.csv

@@ -0,0 +1,17 @@
+profile,original,shuffled,delta_real_minus_shuffled
+Anaphase,0.1295363284681192,0.5398174587901845,-0.4102811303220653
+Metaphase,0.09403146460384448,0.4921355483067866,-0.3981040837029421
+OutOfFocus,0.07750370900918473,0.44320772909259587,-0.36570402008341113
+Apoptosis,0.1737850580597236,0.4879658015481369,-0.3141807434884133
+Prometaphase,0.3258901426117646,0.585452476379703,-0.2595623337679384
+Large,0.12395297721298071,0.3761371957895286,-0.2521842185765479
+MetaphaseAlignment,0.09317750675662102,0.3370797217146052,-0.2439022149579842
+Folded,0.2788073284358493,0.5007048767989222,-0.22189754836307285
+Interphase,0.3358363381673327,0.5257748638252964,-0.18993852565796365
+Elongated,0.257222234180935,0.4443778206808757,-0.18715558649994074
+Grape,0.31945239999258623,0.5014884633783497,-0.1820360633857635
+SmallIrregular,0.21873523146467183,0.3732682342174917,-0.1545330027528199
+Binuclear,0.27802463518368153,0.429199932541633,-0.1511752973579515
+Hole,0.3941905910241724,0.5112183719238499,-0.11702778089967747
+ADCCM,0.4051700760604237,0.5029203890851184,-0.09775031302469467
+Polylobed,0.31549516115662113,0.36565797628873886,-0.05016281513211773