initial code move

.gitignore

@@ -0,0 +1,19 @@
+__pycache__/
+.hypothesis/
+.pytest_cache/
+.coverage
+SpatialOneHD.log
+ENACT.log
+cache/*
+.ipynb_checkpoints/
+src/.ipynb_checkpoints/
+templates/.ipynb_checkpoints/
+data/
+ENACT_supporting_files/
+ENACT_supporting_files.zip
+.idea/*
+.checkmarx/scan_results/*
+src/cache/*
+src/cache-pathologist/*
+src/binned_outputs/*
+src/binned_outputs-mouse/*

ENACT_demo.ipynb

@@ -0,0 +1,267 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "88dfe185-575f-484b-87a5-662d54a8aa14",
+   "metadata": {},
+   "source": [
+    "## ENACT Demo Notebook - Human Colorectal Cancer"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef3a94f5-4189-4c46-b4fa-570989cb78e9",
+   "metadata": {},
+   "source": [
+    "This notebook provides a demo for running ENACT on the Human Colorectal Cancer sample provided on 10X Genomics' website."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "31994db6-6997-4124-a4d5-bf09dbf64f69",
+   "metadata": {},
+   "source": [
+    "### Download VisiumHD data from the 10X Genomics website"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e56081b4-2eb0-45e4-9f46-7ed118b51551",
+   "metadata": {},
+   "source": [
+    "Whole slide image: full resolution tissue image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "712a9e76-d7e1-4cc1-b0ae-afad223a1713",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!curl -O https://cf.10xgenomics.com/samples/spatial-exp/3.0.0/Visium_HD_Human_Colon_Cancer/Visium_HD_Human_Colon_Cancer_tissue_image.btf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bfa4bd8e-4b4d-4593-b5f2-8cc881c1a2b1",
+   "metadata": {},
+   "source": [
+    "Visium HD output file. The transcript counts are provided in a .tar.gz file that needs to be extracted:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f7bc5a4-6f56-4ffa-8b1c-9c178d5c6022",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!curl -O https://cf.10xgenomics.com/samples/spatial-exp/3.0.0/Visium_HD_Human_Colon_Cancer/Visium_HD_Human_Colon_Cancer_binned_outputs.tar.gz\n",
+    "!tar -xvzf Visium_HD_Human_Colon_Cancer_binned_outputs.tar.gz"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c838e47e-0e91-4462-a099-ff061cd4f94f",
+   "metadata": {},
+   "source": [
+    "Locate the following two files from the extracted outputs file. These are the files we will use later as input to ENACT.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "08ea9a56-14c5-4ebc-bb09-e7535bbc1fee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    ".\n",
+    "└── binned_outputs/\n",
+    "    └── square_002um/\n",
+    "        ├── filtered_feature_bc_matrix.h5   <---- Transcript counts file (2um resolution)\n",
+    "        └── spatial/\n",
+    "            └── tissue_positions.parquet    <---- Bin locations relative to the full resolution image\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8d760ee8-f5a0-4a0f-ace6-c0b91176f4e1",
+   "metadata": {},
+   "source": [
+    "### Install ENACT\n",
+    "This will install the ENACT package and its dependencies.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d555ae41-0776-4047-bfe2-1ee3ebc475bb",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "!pip install enact"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39736162-ba27-435f-8dc6-876b2f507315",
+   "metadata": {},
+   "source": [
+    "### Access and update the `configs.yaml` file"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "56f81b7a-e58e-498b-8589-0fd9cfc82c08",
+   "metadata": {},
+   "source": [
+    "To run the ENACT pipeline, you will need a configuration file that specifies all the required settings. You can download the template configuration file from the GitHub repository.\n",
+    "\n",
+    "Refer to [Defining ENACT Configurations](https://github.com/Sanofi-OneAI/oneai-dda-spatialtr-enact/tree/release/ospo-new?tab=readme-ov-file#defining-enact-configurations) for a full list of parameters to configure."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19207eb1-f22a-48d7-80ba-08b6fc118872",
+   "metadata": {},
+   "source": [
+    "#### Step 1\n",
+    "Download the `configs.yaml` template from the `config` folder of [this repository](https://github.com/Sanofi-OneAI/oneai-dda-spatialtr-enact), and save it in your working directory."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8996161d-5164-4931-bfdc-ca0065686d44",
+   "metadata": {},
+   "source": [
+    "#### Step 2\n",
+    "Edit the input file locations in `configs.yaml` to the downloaded Visium HD files' location."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ff15bcbd-681e-4947-8277-cffc30f69df4",
+   "metadata": {},
+   "source": [
+    "```yaml\n",
+    "analysis_name: \"demo-colon\"                           \n",
+    "cache_dir: \"enact_output\"                   \n",
+    "paths:\n",
+    "    wsi_path: \"Visium_HD_Human_Colon_Cancer_tissue_image.btf\"      \n",
+    "    visiumhd_h5_path: \"binned_outputs/square_002um/filtered_feature_bc_matrix.h5\"         \n",
+    "    tissue_positions_path: \"binned_outputs/square_002um/spatial/tissue_positions.parquet\"      \n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81daa91f-e34e-4018-8a46-89ddb9b6cf99",
+   "metadata": {},
+   "source": [
+    "#### Step 3\n",
+    "Next, we set all the steps in the `configs.yaml` file to `True`, in order to run the whole ENACT pipeline later"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a4eb5a6-2436-4cf3-8b52-e06d431fc3a0",
+   "metadata": {},
+   "source": [
+    "```yaml\n",
+    "steps:\n",
+    "        segmentation: True                                   \n",
+    "        bin_to_geodataframes: True                             \n",
+    "        bin_to_cell_assignment: True                           \n",
+    "        cell_type_annotation: True         \n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4af04737-6ece-431f-b5d5-1eaefe63efca",
+   "metadata": {},
+   "source": [
+    "#### Step 4\n",
+    "Lastly, choose the `bin_to_cell_method` and `cell_annotation_method` we want to run with. In this demo, we will go with `\"weighted_by_area\"`, and `\"celltypist\"`.\n",
+    "\n",
+    "To run Celltypist as our cell annotation method, we also need to input the `cell_typist_model` parameter based on the type of sample we use."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9b495d82-cfce-4973-aed0-84aec7d2ac31",
+   "metadata": {},
+   "source": [
+    "```yaml\n",
+    " params:\n",
+    "      bin_to_cell_method: \"weighted_by_area\"                \n",
+    "      cell_annotation_method: \"celltypist\"                     \n",
+    "      cell_typist_model: \"Human_Colorectal_Cancer.pkl\"         \n",
+    "      seg_method: \"stardist\"                                    \n",
+    "      patch_size: 4000                                         \n",
+    "      use_hvg: True                                            \n",
+    "      n_hvg: 1000                                              \n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "13a165e4-7f63-4cfd-80ed-52a0823692f9",
+   "metadata": {},
+   "source": [
+    "### Run ENACT"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2aadbd97-ddf2-4252-9bb0-c59ba4600c4c",
+   "metadata": {},
+   "source": [
+    "Running ENACT on the whole sample image will take around 40 minutes. Output of the pipeline will be stored in the `\"enact_output\"` directory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "393087e7-9598-4ebe-a628-14cc0ac673a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from enact.pipeline import ENACT\n",
+    "import yaml\n",
+    "\n",
+    "configs_path = \"config/configs.yaml\" # Change this to the location of the configs.yaml file that you just edited\n",
+    "with open(configs_path, \"r\") as stream:\n",
+    "    configs = yaml.safe_load(stream)\n",
+    "\n",
+    "so_hd = ENACT(configs)\n",
+    "so_hd.run_enact()"
+   ]
+  }
+ ],
+ "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": "3.10.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

LICENSE.md

@@ -0,0 +1,7 @@
+**Copyright Sanofi 2024**
+
+Permission is hereby granted, free of charge, for academic research purposes only and for non-commercial uses only, to any person from academic research or non-profit organizations obtaining a copy of this software and associated documentation files (the "Software"), to use, copy, modify, or merge the Software, subject to the following conditions: this permission notice shall be included in all copies of the Software or of substantial portions of the Software.
+
+For purposes of this license, “non-commercial use” excludes uses foreseeably resulting in a commercial benefit. To use this software for other purposes (such as the development of a commercial product, including but not limited to software, service, or pharmaceuticals, or in a collaboration with a private company), please contact SANOFI at [email protected].
+
+All other rights are reserved. The Software is provided “as is”, without warranty of any kind, express or implied, including the warranties of noninfringement.

MANIFEST.in

@@ -0,0 +1,4 @@
+include README.md
+include LICENSE.md
+include config/configs.yaml
+

Makefile

@@ -0,0 +1,25 @@
+ENV_DIR := /home/oneai/envs/
+
+PY_ENV_NAME := enact_py_env
+
+PY_ENV_PATH := $(ENV_DIR)$(PY_ENV_NAME)
+
+CONFIG_PATH ?= config/configs.yaml
+
+create-env:
+	conda create --prefix $(PY_ENV_PATH) python=3.9
+
+run_enact:
+	bash setup_py_env.sh $(PY_ENV_PATH)
+	bash run_enact.sh $(PY_ENV_PATH) ${CONFIG_PATH}
+
+setup_py_env:
+	bash setup_py_env.sh $(PY_ENV_PATH)
+
+run_cell_ann_eval:
+	bash setup_py_env.sh $(PY_ENV_PATH)
+	bash run_cell_ann_eval.sh $(PY_ENV_PATH) 
+
+reproduce_results:
+	bash setup_py_env.sh $(PY_ENV_PATH)
+	bash reproduce_paper_results.sh $(PY_ENV_PATH)