Add in silico perturbation example notebook.

examples/in_silico_perturbation.ipynb

@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e10ac0c9-40ce-41fb-b6fa-3d62b76f2e57",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from geneformer import InSilicoPerturber\n",
+    "from geneformer import InSilicoPerturberStats"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "67b44366-f255-4415-a865-6a27a8ffcce7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# in silico perturbation in deletion mode to determine genes whose \n",
+    "# deletion in the dilated cardiomyopathy (dcm) state significantly shifts\n",
+    "# the embedding towards non-failing (nf) state\n",
+    "isp = InSilicoPerturber(perturb_type=\"delete\",\n",
+    "                      perturb_rank_shift=None,\n",
+    "                      genes_to_perturb=\"all\",\n",
+    "                      combos=0,\n",
+    "                      anchor_gene=None,\n",
+    "                      model_type=\"CellClassifier\",\n",
+    "                      num_classes=3,\n",
+    "                      emb_mode=\"cell\",\n",
+    "                      cell_emb_style=\"mean_pool\",\n",
+    "                      filter_data={\"cell_type\":[\"Cardiomyocyte1\",\"Cardiomyocyte2\",\"Cardiomyocyte3\"]},\n",
+    "                      cell_states_to_model={\"disease\":([\"dcm\"],[\"nf\"],[\"hcm\"])},\n",
+    "                      max_ncells=2000,\n",
+    "                      emb_layer=0,\n",
+    "                      forward_batch_size=400,\n",
+    "                      nproc=16,\n",
+    "                      save_raw_data=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0525a663-871a-4ce0-a135-cc203817ffa9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# outputs intermediate files from in silico perturbation\n",
+    "isp.perturb_data(\"path/to/model\",\n",
+    "               \"path/to/input_data\",\n",
+    "               \"path/to/output_directory\",\n",
+    "               \"output_prefix\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f8aadabb-516a-4dc0-b307-6de880e64e26",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ispstats = InSilicoPerturberStats(mode=\"goal_state_shift\",\n",
+    "                                combos=0,\n",
+    "                                anchor_gene=None,\n",
+    "                                cell_states_to_model={\"disease\":([\"dcm\"],[\"nf\"],[\"hcm\"])})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ffecfae6-e737-43e3-99e9-fa37ff46610b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# extracts data from intermediate files and processes stats to output in final .csv\n",
+    "ispstats.get_stats(\"path/to/input_data\",\n",
+    "                   None,\n",
+    "                   \"path/to/output_directory\",\n",
+    "                   \"output_prefix\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}