Add BCL2/Ced9, CD47/P66 examples

seanome · Dec 6, 2024 · 104e6fa · 104e6fa
1 parent 0bd6db8
commit 104e6fa
Show file tree

Hide file tree

Showing 24 changed files with 5,644 additions and 2,000 deletions.
diff --git a/notebooks/05-scan-s3-csv-to-s3-parquet.ipynb b/notebooks/05-scan-s3-csv-to-s3-parquet.ipynb
diff --git a/notebooks/13-compute-all-sensitivity-to-first-fp.ipynb b/notebooks/13-compute-all-sensitivity-to-first-fp.ipynb
diff --git a/notebooks/14-plot-sensitivity-to-first-fp.ipynb b/notebooks/14-plot-sensitivity-to-first-fp.ipynb
diff --git a/notebooks/15-which-kmers-match.ipynb b/notebooks/15-which-kmers-match.ipynb
diff --git a/notebooks/16-ced9-bcl2-and-p66-cd47.ipynb b/notebooks/16-ced9-bcl2-and-p66-cd47.ipynb
diff --git a/notebooks/17-explore-hp-k10.ipynb b/notebooks/17-explore-hp-k10.ipynb
@@ -0,0 +1,206 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "103ccd5c-4285-4267-99c3-2110066a0661",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f4cd62d-9a46-405c-b38b-12df6d8158fc",
+   "metadata": {},
+   "source": [
+    "# Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "c32851e0-276d-483a-8d6c-15a42d5dab0e",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-07T21:58:24.482905Z",
+     "iopub.status.busy": "2024-11-07T21:58:24.482454Z",
+     "iopub.status.idle": "2024-11-07T21:58:24.497152Z",
+     "shell.execute_reply": "2024-11-07T21:58:24.496791Z",
+     "shell.execute_reply.started": "2024-11-07T21:58:24.482890Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "import os\n",
+    "import polars as pl\n",
+    "import seaborn as sns\n",
+    "\n",
+    "# Handwritten local modules\n",
+    "from sig2kmer import degenerate_protein_chatgpt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "a782a96b-cac4-4520-8e60-cd30de5272d3",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-07T21:58:24.846718Z",
+     "iopub.status.busy": "2024-11-07T21:58:24.846470Z",
+     "iopub.status.idle": "2024-11-07T21:59:09.700968Z",
+     "shell.execute_reply": "2024-11-07T21:59:09.700668Z",
+     "shell.execute_reply.started": "2024-11-07T21:58:24.846705Z"
+    },
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h4>NAIVE QUERY PLAN</h4><p>run <b>LazyFrame.show_graph()</b> to see the optimized version</p><?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
+       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
+       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
+       "<!-- Generated by graphviz version 2.44.0 (0)\n",
+       " -->\n",
+       "<!-- Title: polars_query Pages: 1 -->\n",
+       "<svg width=\"939pt\" height=\"46pt\"\n",
+       " viewBox=\"0.00 0.00 939.00 46.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
+       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 42)\">\n",
+       "<title>polars_query</title>\n",
+       "<polygon fill=\"white\" stroke=\"transparent\" points=\"-4,4 -4,-42 935,-42 935,4 -4,4\"/>\n",
+       "<!-- p1 -->\n",
+       "<g id=\"node1\" class=\"node\">\n",
+       "<title>p1</title>\n",
+       "<polygon fill=\"none\" stroke=\"black\" points=\"931,-38 0,-38 0,0 931,0 931,-38\"/>\n",
+       "<text text-anchor=\"middle\" x=\"465.5\" y=\"-22.8\" font-family=\"Times-Roman\" font-size=\"14.00\">Parquet SCAN [s3://seanome&#45;kmerseek/scope&#45;benchmark/analysis&#45;outputs/hp/00_cleaned_multisearch_results/scope40.multisearch.hp.k10.filtered.pq]</text>\n",
+       "<text text-anchor=\"middle\" x=\"465.5\" y=\"-7.8\" font-family=\"Times-Roman\" font-size=\"14.00\">π */38;</text>\n",
+       "</g>\n",
+       "</g>\n",
+       "</svg>\n"
+      ],
+      "text/plain": [
+       "<LazyFrame at 0x7FBEBCB57AA0>"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pq = \"s3://seanome-kmerseek/scope-benchmark/analysis-outputs/hp/00_cleaned_multisearch_results/scope40.multisearch.hp.k10.filtered.pq\"\n",
+    "multisearch = pl.scan_parquet(pq)\n",
+    "multisearch"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "053f1508-3e5b-4cf9-84cc-2d43c131d329",
+   "metadata": {},
+   "source": [
+    "# Read in data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "74c36a49-fcf4-4b37-8167-2da125057d4d",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-07T21:59:09.733249Z",
+     "iopub.status.busy": "2024-11-07T21:59:09.732985Z",
+     "iopub.status.idle": "2024-11-07T21:59:09.735189Z",
+     "shell.execute_reply": "2024-11-07T21:59:09.734951Z",
+     "shell.execute_reply.started": "2024-11-07T21:59:09.733238Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "ksize = 10\n",
+    "moltype = \"hp\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d7b46f44-ac7e-4449-aa6f-609e9b5787e0",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-07T21:59:09.735689Z",
+     "iopub.status.busy": "2024-11-07T21:59:09.735466Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "cleaned_multisearch_folder = \"/home/ec2-user/data/seanome-kmerseek/scope-benchmark/analysis-outputs/hp/00_cleaned_multisearch_results\"\n",
+    "\n",
+    "pq = os.path.join(\n",
+    "    cleaned_multisearch_folder, f\"scope40.multisearch.{moltype}.k{ksize}.filtered.pq\"\n",
+    ")\n",
+    "multisearch = pl.scan_parquet(pq)\n",
+    "multisearch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36fe4ff2-81c3-4581-85b0-4e431eff2641",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "multisearch.filter(pl.col(\"query_scop_id\") == \"d1ty4a_\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90495133-879b-4fab-b17c-3f3a16fd1a50",
+   "metadata": {},
+   "source": [
+    "### Filter on query family [\"Family f.1.4.1: Bcl-2 inhibitors of programmed cell death\"](https://scop.berkeley.edu/sunid=56855)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ddf848ee-a3f5-4510-b786-1fc935905854",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bcl2_family = \"f.1.4.1\"\n",
+    "\n",
+    "multisearch_bcl2 = multisearch.filter((pl.col(\"query_family\") == bcl2_family)).collect()\n",
+    "multisearch_bcl2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "455a4aa9-aaef-428c-81df-8977563d6389",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:2024-kmerseek-analysis-polars]",
+   "language": "python",
+   "name": "conda-env-2024-kmerseek-analysis-polars-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}