ENACT: End-to-End Analysis and Cell Type Annotation for Visium High Definition (HD) Slides

Note

This is the official repo for ENACT. The manuscript can be accessed through BiorXiv.

Spatial transcriptomics (ST) enables the study of gene expression within its spatial context in histopathology samples. To date, a limiting factor has been the resolution of sequencing based ST products. The introduction of the Visium High Definition (HD) technology opens the door to cell resolution ST studies. However, challenges remain in the ability to accurately map transcripts to cells and in cell type assignment based on spot data.

ENACT is the first tissue-agnostic pipeline that integrates advanced cell segmentation with Visium HD transcriptomics data to infer cell types across whole tissue sections. Our pipeline incorporates novel bin-to-cell assignment methods, enhancing the accuracy of single-cell transcript estimates. Validated on diverse synthetic and real datasets, our approach demonstrates high effectiveness at predicting cell types and scalability, offering a robust solution for spatially resolved transcriptomics analysis.

This repository has the code for inferring cell types from the sub-cellular transcript counts provided by VisiumHD.

This can be achieved through the following steps:

Cell segmentation: segment high resolution image using NN-based image segmentation networks such as Stardist.
Bin-to-cell assignment: Obtain cell-wise transcript counts by aggregating the VisiumHD bins that are associated with each cell
Cell type inference: Use the cell-wise transcript counts to infer the cell labels/ phenotypes using methods used for single-cell RNA seq analysis (CellAsign or CellTypist or Sargent if installed) or novel approaches, and use comprehensive cell marker databases (Panglao or CellMarker can be used as reference).

Note

At this time, Sargent is currently not available in GitHub. For information on how to access Sargent (doi: https://doi.org/10.1016/j.mex.2023.102196), please contact the paper's corresponding authors (nima.nouri@sanofi.com). We provide the results obtained by Sargent in ENACT's Zenodo page under the following folders:

ENACT_supporting_files/public_data/human_colorectal/paper_results/chunks/naive/sargent_results/
ENACT_supporting_files/public_data/human_colorectal/paper_results/chunks/weighted_by_area/sargent_results/
ENACT_supporting_files/public_data/human_colorectal/paper_results/chunks/weighted_by_transcript/sargent_results/
ENACT_supporting_files/public_data/human_colorectal/paper_results/chunks/weighted_by_cluster/sargent_results/

Index of Instructions:

System Requirements
Install ENACT from Source
Install ENACT with Pip
Input Files for ENACT
Defining ENACT Configurations
Output Files for ENACT
Running ENACT from Notebook
Running ENACT from Terminal
Running Instructions
Reproducing Paper Results
Creating Synthetic VisiumHD Datasets
Citing ENACT

System Requirements

ENACT was tested with the following specifications:

Hardware Requirements: 32 CPU, 64GB RAM, 100 GB (harddisk and memory requirements may vary depending on whole slide image size; if the weight of the wsi is small the memory requirements can be significantly decreased)
Software: Python 3.9, (Optional) GPU (CUDA 11)

Install ENACT from Source

Step 1: Clone ENACT repository

git clone https://github.com/Sanofi-OneAI/oneai-dda-spatialtr-enact.git
cd oneai-dda-spatialtr-enact

Step 2: Setup Python environment

Start by defining the location and the name of the Conda environment in the Makefile:

ENV_DIR := /home/oneai/envs/   <---- Conda environment location
PY_ENV_NAME := enact_py_env    <---- Conda environment name

Next, run the following Make command to create a Conda environment with all of ENACT's dependencies

make setup_py_env

Install ENACT with Pip

ENACT can be installed from Pypi using:

pip install enact-SO

Input Files for ENACT

ENACT requires only three files, which can be obtained from SpaceRanger’s outputs for each experiment:

Whole resolution tissue image. This will be segmented to obtain the cell boundaries that will be used to aggregate the transcript counts.
tissue_positions.parquet. This is the file that specifies the 2um Visium HD bin locations relative to the full resolution image.
filtered_feature_bc_matrix.h5. This is the .h5 file with the 2um Visium HD bin counts.

Defining ENACT Configurations

ENACT users can choose to specify the configurations via one of two ways:

Passing them within the class constructor:

  from enact.pipeline import ENACT

  so_hd = ENACT(
      cache_dir="/home/oneai/test_cache",
      wsi_path="Visium_HD_Human_Colon_Cancer_tissue_image.btf",
      visiumhd_h5_path="binned_outputs/square_002um/filtered_feature_bc_matrix.h5",
      tissue_positions_path="binned_outputs/square_002um/spatial/tissue_positions.parquet",
      )

Full list of ENACT parameters (click to expand)

Parameters

cache_dir (str):
Directory to cache ENACT results. This must be specified by the user.
wsi_path (str):
Path to the Whole Slide Image (WSI) file. This must be provided by the user.
visiumhd_h5_path (str):
Path to the Visium HD h5 file containing spatial transcriptomics data. This must be provided by the user.
tissue_positions_path (str):
Path to the tissue positions file that contains spatial locations of barcodes. This must be provided by the user.
analysis_name (str):
Name of the analysis, used for output directories and results.
Default: "enact_demo".
seg_method (str):
Cell segmentation method.
Default: "stardist".
Options: ["stardist"].
patch_size (int):
Size of patches (in pixels) to process the image. Use a smaller patch size to reduce memory requirements.
Default: 4000.
use_hvg (bool):
Whether to use highly variable genes (HVG) during the analysis.
Default: True.
Options: [True].
n_hvg (int):
Number of highly variable genes to use if use_hvg is True.
Default: 1000.
n_clusters (int):
Number of clusters. Used only if bin_to_cell_method is "weighted_by_cluster".
Default: 4.
bin_representation (str):
Representation type for VisiumHD bins.
Default: "polygon".
Options: ["polygon"].
bin_to_cell_method (str):
Method to assign bins to cells.
Default: "weighted_by_cluster".
Options: ["naive", "weighted_by_area", "weighted_by_gene", "weighted_by_cluster"].
cell_annotation_method (str):
Method for annotating cell types.
Default: "celltypist".
Options: ["celltypist", "sargent" (if installed), "cellassign"].
cell_typist_model (str):
Path to the pre-trained CellTypist model for cell type annotation. Only used if cell_annotation_method is "celltypist".
Refer to CellTypist Models for a list of available models.
Default: "" (empty string).
run_synthetic (bool):
Whether to run synthetic data generation for testing purposes.
Default: False.
segmentation (bool):
Flag to run the image segmentation step.
Default: True.
bin_to_geodataframes (bool):
Flag to convert the bins to GeoDataFrames.
Default: True.
bin_to_cell_assignment (bool):
Flag to run bin-to-cell assignment.
Default: True.
cell_type_annotation (bool):
Flag to run cell type annotation.
Default: True.
cell_markers (dict):
A dictionary of cell markers used for annotation. Only used if cell_annotation_method is one of ["sargent", "cellassign"].
chunks_to_run (list):
Specific chunks of data to run the analysis on, typically for debugging.
Default: [] (runs all chunks).
configs_dict (dict):
Dictionary containing ENACT configuration parameters. If provided, the values in configs_dict will override any corresponding parameters passed directly to the class constructor. This is useful for running ENACT with a predefined configuration for convenience and consistency.
Default: {} (uses the parameters specified in the class constructor).

Specifying configurations in a yaml file: (sample file located under config/configs.yaml):

    analysis_name: <analysis-name>                              <---- custom name for analysis. Will create a folder with that name to store the results
    run_synthetic: False                                        <---- True if you want to run bin to cell assignment on synthetic dataset, False otherwise
    cache_dir: <path-to-store-enact-outputs>                    <---- path to store pipeline outputs
    paths:
        wsi_path: <path-to-whole-slide-image>                   <---- path to whole slide image
        visiumhd_h5_path: <path-to-counts-file>                 <---- location of the 2um x 2um gene by bin file (filtered_feature_bc_matrix.h5) from 10X Genomics 
        tissue_positions_path: <path-to-tissue-positions>       <---- location of the tissue of the tissue_positions.parquet file from 10X genomicsgenomics
    steps:
        segmentation: True                                      <---- True if you want to run segmentation
        bin_to_geodataframes: True                              <---- True to convert bin to geodataframes
        bin_to_cell_assignment: True                            <---- True to bin-to-cell assignment
        cell_type_annotation: True                              <---- True to run cell type annotation
    params:
      bin_to_cell_method: "weighted_by_cluster"                 <---- bin-to-cell assignment method. Pick one of ["naive", "weighted_by_area", "weighted_by_gene", "weighted_by_cluster"]
      cell_annotation_method: "celltypist"                      <---- cell annotation method. Pick one of ["cellassign", "celltypist"]
      cell_typist_model: "Human_Colorectal_Cancer.pkl"          <---- CellTypist model weights to use. Update based on organ of interest if using cell_annotation_method is set to "celltypist"
      seg_method: "stardist"                                    <---- cell segmentation method. Stardist is the only option for now
      patch_size: 4000                                          <---- defines the patch size. The whole resolution image will be broken into patches of this size. Reduce if you run into memory issues
      use_hvg: True                                             <---- True only run analysis on top n highly variable genes. Setting it to False runs ENACT on all genes in the counts file
      n_hvg: 1000                                               <---- number of highly variable genes to use 
      n_clusters: 4                                             <---- number of cell clusters to use for the "weighted_by_cluster" method. Default is 4.
  cell_markers:                                                 <---- cell-gene markers to use for cell annotation. Only applicable if params/cell_annotation_method is "cellassign" or "sargent"
      Epithelial: ["CDH1","EPCAM","CLDN1","CD2"]
      Enterocytes: ["CD55", "ELF3", "PLIN2", "GSTM3", "KLF5", "CBR1", "APOA1", "CA1", "PDHA1", "EHF"]
      Goblet cells: ["MANF", "KRT7", "AQP3", "AGR2", "BACE2", "TFF3", "PHGR1", "MUC4", "MUC13", "GUCA2A"]

Output Files for ENACT

ENACT outputs all its results under the cache directory which gets automatically created at run time:

.
└── cache/
    └── <anaylsis_name> /
        ├── chunks/
        │   ├── bins_gdf/
        │   │   └── patch_<patch_id>.csv
        │   ├── cells_gdf/
        │   │   └── patch_<patch_id>.csv
        │   └── <bin_to_cell_method>/
        │       ├── bin_to_cell_assign/
        │       │   └── patch_<patch_id>.csv
        │       ├── cell_ix_lookup/
        │       │   └── patch_<patch_id>.csv
        │       └── <cell_annotation_method>_results/
        │           ├── cells_adata.csv
        │           └── merged_results.csv
        └── cells_df.csv

ENACT breaks down the whole resolution image into "chunks" (or patches) of size patch_size. Results are provided per-chunk under the chunks directory.

bins_gdf:Folder containing GeoPandas dataframes representing the 2um Visium HD bins within a given patch
cells_gdf: Folder containing GeoPandas dataframes representing cells segmented in the tissue
<bin_to_cell_method>/bin_to_cell_assign: Folder contains dataframes with the transcripts assigned to each cells
<bin_to_cell_method>/cell_ix_lookup: Folder contains dataframes defining the indices and coordinates of the cells
<bin_to_cell_method>/<cell_annotation_method>_results/cells_adata.csv: Anndata object containing the results from ENACT (cell coordinates, cell types, transcript counts)
<bin_to_cell_method>/<cell_annotation_method>_results/merged_results.csv: Dataframe (.csv) containing the results from ENACT (cell coordinates, cell types)

Running ENACT from Notebook

The demo notebook provides a step-by-step guide on how to install and run ENACT on VisiumHD public data using notebook.

Running ENACT from Terminal

This section provides a guide for running ENACT on the Human Colorectal Cancer sample provided on 10X Genomics' website.

Step 1: Install ENACT from Source

Refer to Install ENACT from Source

Step 2: Download the necessary files from the 10X Genomics website:

Whole slide image: full resolution tissue image

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

Visium HD output file. The transcript counts are provided in a .tar.gz file that needs to be extracted:

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
tar -xvzf Visium_HD_Human_Colon_Cancer_binned_outputs.tar.gz

Locate the following two files from the extracted outputs file.

.
└── binned_outputs/
    └── square_002um/
        ├── filtered_feature_bc_matrix.h5   <---- Transcript counts file (2um resolution)
        └── spatial/
            └── tissue_positions.parquet    <---- Bin locations relative to the full resolution image

Step 3: Update input file locations and parameters under `config/configs.yaml`

Refer to Running Instructions for a full list of ENACT parameters to change.

Below is a sample configuration file to use to run ENACT on the Human Colorectal cancer sample:

analysis_name: "colon-demo"
run_synthetic: False # True if you want to run bin to cell assignment on synthetic dataset, False otherwise.
cache_dir: "cache/ENACT_outputs"                                                                          # Change according to your desired output location
paths:  
  wsi_path: "<path_to_data>/Visium_HD_Human_Colon_Cancer_tissue_image.btf"                                # whole slide image path
  visiumhd_h5_path: "<path_to_data>/binned_outputs/square_002um/filtered_feature_bc_matrix.h5"            # location of the 2um x 2um gene by bin file (filtered_feature_bc_matrix.h5) from 10X Genomics.   
  tissue_positions_path: "<path_to_data>/binned_outputs/square_002um/spatial/tissue_positions.parquet"    # location of the tissue of the tissue_positions.parquet file from 10X genomics
steps:
  segmentation: True # True if you want to run segmentation
  bin_to_geodataframes: True # True to convert bin to geodataframes
  bin_to_cell_assignment: True # True to assign cells to bins
  cell_type_annotation: True # True to run cell type annotation
params:
  seg_method: "stardist" # Stardist is the only option for now
  patch_size: 4000 # Defines the patch size. The whole resolution image will be broken into patches of this size
  bin_representation: "polygon"  # or point TODO: Remove support for anything else
  bin_to_cell_method: "weighted_by_cluster" # or naive
  cell_annotation_method: "celltypist"
  cell_typist_model: "Human_Colorectal_Cancer.pkl"
  use_hvg: True # Only run analysis on highly variable genes + cell markers specified
  n_hvg: 1000 # Number of highly variable genes to use
  n_clusters: 4 
  chunks_to_run: []
cell_markers:
  # Human Colon
  Epithelial: ["CDH1","EPCAM","CLDN1","CD2"]
  Enterocytes: ["CD55", "ELF3", "PLIN2", "GSTM3", "KLF5", "CBR1", "APOA1", "CA1", "PDHA1", "EHF"]
  Goblet cells: ["MANF", "KRT7", "AQP3", "AGR2", "BACE2", "TFF3", "PHGR1", "MUC4", "MUC13", "GUCA2A"]
  Enteroendocrine cells: ["NUCB2", "FABP5", "CPE", "ALCAM", "GCG", "SST", "CHGB", "IAPP", "CHGA", "ENPP2"]
  Crypt cells: ["HOPX", "SLC12A2", "MSI1", "SMOC2", "OLFM4", "ASCL2", "PROM1", "BMI1", "EPHB2", "LRIG1"]
  Endothelial: ["PECAM1","CD34","KDR","CDH5","PROM1","PDPN","TEK","FLT1","VCAM1","PTPRC","VWF","ENG","MCAM","ICAM1","FLT4"]     
  Fibroblast: ["COL1A1","COL3A1","COL5A2","PDGFRA","ACTA2","TCF21","FN"]
  Smooth muscle cell: ["BGN","MYL9","MYLK","FHL2","ITGA1","ACTA2","EHD2","OGN","SNCG","FABP4"]
  B cells: ["CD74", "HMGA1", "CD52", "PTPRC", "HLA-DRA", "CD24", "CXCR4", "SPCS3", "LTB", "IGKC"]
  T cells: ["JUNB", "S100A4", "CD52", "PFN1P1", "CD81", "EEF1B2P3", "CXCR4", "CREM", "IL32", "TGIF1"]
  NK cells: ["S100A4", "IL32", "CXCR4", "FHL2", "IL2RG", "CD69", "CD7", "NKG7", "CD2", "HOPX"]

Running Instructions

This section provides a guide on running ENACT on your own data

Step 1: Install ENACT from Source

Refer to Install ENACT from Source

Step 2: Define the Location of ENACT's Required Files

Define the locations of ENACT's required files in the config/configs.yaml file. Refer to Input Files for ENACT

    analysis_name: <analysis-name>                              <---- custom name for analysis. Will create a folder with that name to store the results
    cache_dir: <path-to-store-enact-outputs>                    <---- path to store pipeline outputs
    paths:
        wsi_path: <path-to-whole-slide-image>                   <---- path to whole slide image
        visiumhd_h5_path: <path-to-counts-file>                 <---- location of the 2um x 2um gene by bin file (filtered_feature_bc_matrix.h5) from 10X Genomics. 
        tissue_positions_path: <path-to-tissue-positions>       <---- location of the tissue of the tissue_positions.parquet file from 10X genomics

Step 3: Define ENACT configurations

Define the following core parameters in the config/configs.yaml file:

    params:
      bin_to_cell_method: "weighted_by_cluster"                 <---- bin-to-cell assignment method. Pick one of ["naive", "weighted_by_area", "weighted_by_gene", "weighted_by_cluster"]
      cell_annotation_method: "celltypist"                      <---- cell annotation method. Pick one of ["cellassign", "celltypist", "sargent" (if installed)]
      cell_typist_model: "Human_Colorectal_Cancer.pkl"          <---- CellTypist model weights to use. Update based on organ of interest if using cell_annotation_method is set to

Refer to Defining ENACT Configurations for a full list of parameters to configure. If using CellTypist, set cell_typist_model to one of the following models based on the organ and species under study: CellTypist models.

Step 4: Define Cell Gene Markers (Only applies for cell_annotation_method is "cellassign" or "sargent")

Define the cell gene markers in config/configs.yaml file. Those can be expert annotated or obtained from open-source databases such as Panglao or CellMarker. Example cell markers for human colorectal cancer samples:

  cell_markers:
    Epithelial: ["CDH1","EPCAM","CLDN1","CD2"]
    Enterocytes: ["CD55", "ELF3", "PLIN2", "GSTM3", "KLF5", "CBR1", "APOA1", "CA1", "PDHA1", "EHF"]
    Goblet cells: ["MANF", "KRT7", "AQP3", "AGR2", "BACE2", "TFF3", "PHGR1", "MUC4", "MUC13", "GUCA2A"]
    Enteroendocrine cells: ["NUCB2", "FABP5", "CPE", "ALCAM", "GCG", "SST", "CHGB", "IAPP", "CHGA", "ENPP2"]
    Crypt cells: ["HOPX", "SLC12A2", "MSI1", "SMOC2", "OLFM4", "ASCL2", "PROM1", "BMI1", "EPHB2", "LRIG1"]
    Endothelial: ["PECAM1","CD34","KDR","CDH5","PROM1","PDPN","TEK","FLT1","VCAM1","PTPRC","VWF","ENG","MCAM","ICAM1","FLT4"]     
    Fibroblast: ["COL1A1","COL3A1","COL5A2","PDGFRA","ACTA2","TCF21","FN"]
    Smooth muscle cell: ["BGN","MYL9","MYLK","FHL2","ITGA1","ACTA2","EHD2","OGN","SNCG","FABP4"]
    B cells: ["CD74", "HMGA1", "CD52", "PTPRC", "HLA-DRA", "CD24", "CXCR4", "SPCS3", "LTB", "IGKC"]
    T cells: ["JUNB", "S100A4", "CD52", "PFN1P1", "CD81", "EEF1B2P3", "CXCR4", "CREM", "IL32", "TGIF1"]
    NK cells: ["S100A4", "IL32", "CXCR4", "FHL2", "IL2RG", "CD69", "CD7", "NKG7", "CD2", "HOPX"]

Step 5: Run ENACT

make run_enact

Reproducing Paper Results

This section provides a guide on how to reproduce the ENACT paper results on the 10X Genomics Human Colorectal Cancer VisumHD sample. Here, ENACT is run on various combinations of bin-to-cell assignment methods and cell annotation algorithms.

Step 1: Install ENACT from Source

Refer to Install ENACT from Source

Step 2: Run ENACT on combinations of bin-to-cell assignment methods and cell annotation algorithms

Run the following command which will download all the supplementary file from ENACT's Zenodo page and programmatically run ENACT with various combinations of bin-to-cell assignment methods and cell annotation algorithms:

make reproduce_results

Creating Synthetic VisiumHD Datasets

To create synthetic VisiumHD dataset from Xenium or seqFISH+ data, run and follow the instructions of the notebooks in src/synthetic_data.
To run the ENACT pipeline with the synthetic data, set the following parameters in the config/configs.yaml file:

run_synthetic: True                                        <---- True if you want to run bin to cell assignment on synthetic dataset, False otherwise.

Run ENACT:

make run_enact

Citing ENACT

If you use this repository or its tools in your research, please cite the following:

@article {Kamel2024.10.17.618905,
	author = {Kamel, Mena and Song, Yiwen and Solbas, Ana and Villordo, Sergio and Sarangi, Amrut and Senin, Pavel and Mathew, Sunaal and Ayestas, Luis Cano and Wang, Seqian and Classe, Marion and Bar-Joseph, Ziv and Planas, Albert Pla},
	title = {ENACT: End-to-End Analysis of Visium High Definition (HD) Data},
	elocation-id = {2024.10.17.618905},
	year = {2024},
	doi = {10.1101/2024.10.17.618905},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Motivation: Spatial transcriptomics (ST) enables the study of gene expression within its spatial context in histopathology samples. To date, a limiting factor has been the resolution of sequencing based ST products. The introduction of the Visium High Definition (HD) technology opens the door to cell resolution ST studies. However, challenges remain in the ability to accurately map transcripts to cells and in assigning cell types based on the transcript data. Results: We developed ENACT, the first tissue-agnostic pipeline that integrates advanced cell segmentation with Visium HD transcriptomics data to infer cell types across whole tissue sections. Our pipeline incorporates novel bin-to-cell assignment methods, enhancing the accuracy of single-cell transcript estimates. Validated on diverse synthetic and real datasets, our approach is both scalable and effective offering a robust solution for spatially resolved transcriptomics analysis. Availability and implementation: ENACT source code is available at https://github.com/Sanofi-Public/enact-pipeline. Experimental data is available at https://zenodo.org/records/13887921. Supplementary information: Supplementary data are available at BiorXiv online.Competing Interest StatementThe authors have declared no competing interest.},
	URL = {https://www.biorxiv.org/content/early/2024/10/20/2024.10.17.618905},
	eprint = {https://www.biorxiv.org/content/early/2024/10/20/2024.10.17.618905.full.pdf},
	journal = {bioRxiv}
}

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

README.md

README.md

ENACT: End-to-End Analysis and Cell Type Annotation for Visium High Definition (HD) Slides

Index of Instructions:

System Requirements

Install ENACT from Source

Step 1: Clone ENACT repository

Step 2: Setup Python environment

Install ENACT with Pip

Input Files for ENACT

Defining ENACT Configurations

Parameters

Output Files for ENACT

Running ENACT from Notebook

Running ENACT from Terminal

Step 1: Install ENACT from Source

Step 2: Download the necessary files from the 10X Genomics website:

Step 3: Update input file locations and parameters under `config/configs.yaml`

Running Instructions

Step 1: Install ENACT from Source

Step 2: Define the Location of ENACT's Required Files

Step 3: Define ENACT configurations

Step 4: Define Cell Gene Markers (Only applies for cell_annotation_method is "cellassign" or "sargent")

Step 5: Run ENACT

Reproducing Paper Results

Step 1: Install ENACT from Source

Step 2: Run ENACT on combinations of bin-to-cell assignment methods and cell annotation algorithms

Creating Synthetic VisiumHD Datasets

Citing ENACT

Files

README.md

Latest commit

History

README.md

File metadata and controls

ENACT: End-to-End Analysis and Cell Type Annotation for Visium High Definition (HD) Slides

Index of Instructions:

System Requirements

Install ENACT from Source

Step 1: Clone ENACT repository

Step 2: Setup Python environment

Install ENACT with Pip

Input Files for ENACT

Defining ENACT Configurations

Parameters

Output Files for ENACT

Running ENACT from Notebook

Running ENACT from Terminal

Step 1: Install ENACT from Source

Step 2: Download the necessary files from the 10X Genomics website:

Step 3: Update input file locations and parameters under config/configs.yaml

Running Instructions

Step 1: Install ENACT from Source

Step 2: Define the Location of ENACT's Required Files

Step 3: Define ENACT configurations

Step 4: Define Cell Gene Markers (Only applies for cell_annotation_method is "cellassign" or "sargent")

Step 5: Run ENACT

Reproducing Paper Results

Step 1: Install ENACT from Source

Step 2: Run ENACT on combinations of bin-to-cell assignment methods and cell annotation algorithms

Creating Synthetic VisiumHD Datasets

Citing ENACT

Step 3: Update input file locations and parameters under `config/configs.yaml`