import gradio as gr import pandas as pd import umap import matplotlib.pyplot as plt import os import tempfile import scanpy as sc import argparse import subprocess import sys from io import BytesIO from huggingface_hub import hf_hub_download def main(input_file_path, species): # Get the current working directory current_working_directory = os.getcwd() # Print the current working directory print("Current Working Directory:", current_working_directory) # clone and cd into UCE repo os.system('git clone https://github.com/minwoosun/UCE.git') os.chdir('/home/user/app/UCE') # Get the current working directory current_working_directory = os.getcwd() # Print the current working directory print("Current Working Directory:", current_working_directory) # Specify the path to the directory you want to add new_directory = "/home/user/app/UCE" # Add the directory to the Python path sys.path.append(new_directory) ############## # UCE # ############## from evaluate import AnndataProcessor from accelerate import Accelerator # # python eval_single_anndata.py --adata_path "./data/10k_pbmcs_proc.h5ad" --dir "./" --model_loc "minwoosun/uce-100m" # script_name = "/home/user/app/UCE/eval_single_anndata.py" # args = ["--adata_path", input_file_path, "--dir", "/home/user/app/UCE/", "--model_loc", "minwoosun/uce-100m"] # command = ["python", script_name] + args dir_path = '/home/user/app/UCE/' model_loc = 'minwoosun/uce-100m' print(input_file_path) print(dir_path) print(model_loc) # Verify adata_path is not None if input_file_path is None or not os.path.exists(input_file_path): raise ValueError(f"Invalid adata_path: {input_file_path}. Please check if the file exists.") # Construct the command command = [ 'python', '/home/user/app/UCE/eval_single_anndata.py', '--adata_path', input_file_path, '--dir', dir_path, '--model_loc', model_loc ] # Print the command for debugging print("Running command:", command) print("---> RUNNING UCE") result = subprocess.run(command, capture_output=True, text=True, check=True) print(result.stdout) print(result.stderr) print("---> FINSIH UCE") ############## # UMAP # ############## UMAP = True if (UMAP): # Set output file path file_name_with_ext = os.path.basename(input_file_path) file_name = os.path.splitext(file_name_with_ext)[0] output_file = "/home/user/app/UCE/" + f"{file_name}_uce_adata.h5ad" adata = sc.read_h5ad(output_file) labels = pd.Categorical(adata.obs["cell_type"]) reducer = umap.UMAP(n_neighbors=15, min_dist=0.1, n_components=2, random_state=42) embedding = reducer.fit_transform(adata.obsm["X_uce"]) plt.figure(figsize=(10, 8)) # Create the scatter plot scatter = plt.scatter(embedding[:, 0], embedding[:, 1], c=labels.codes, cmap='Set1', s=50, alpha=0.6) # Create a legend handles = [] for i, cell_type in enumerate(labels.categories): handles.append(plt.Line2D([0], [0], marker='o', color='w', label=cell_type, markerfacecolor=plt.cm.Set1(i / len(labels.categories)), markersize=10)) plt.legend(handles=handles, title='Cell Type') plt.title('UMAP projection of the data') plt.xlabel('UMAP1') plt.ylabel('UMAP2') # Save plot to a BytesIO object buf = BytesIO() plt.savefig(buf, format='png') buf.seek(0) # Read the image from BytesIO object img = plt.imread(buf, format='png') else: img = None print("no image") return img, output_file if __name__ == "__main__": css = """ body {background-color: black; color: white;} .gradio-container {background-color: black; color: white;} input, button, select, textarea {background-color: #333; color: white;} """ with gr.Blocks(css=css) as demo: gr.Markdown( '''
UCE 100M Demo
Universal Cell Embeddings: Explore Single Cell Data
GitHub Paper
Upload a `.h5ad` single cell gene expression file and select the species (Human/Mouse). The demo will generate UMAP projections of the embeddings and allow you to download the embeddings for further analysis.
  1. 1. Upload your `.h5ad` file
  2. 2. Select the species
  3. 3. View the UMAP scatter plot
  4. 4. Download the UMAP coordinates
Please consider citing the following paper if you use this tool in your research:
Sun, M., et al. Universal Cell Embeddings: A tool for single-cell analysis. arXiv:2408.03322 (2024)
''' ) # Define Gradio inputs and outputs file_input = gr.File(label="Upload a .h5ad single cell gene expression file") species_input = gr.Dropdown(choices=["human", "mouse"], label="Select species") image_output = gr.Image(type="numpy", label="UMAP of UCE Embeddings") file_output = gr.File(label="Download embeddings") # Add the components and link to the function gr.Button("Run").click( fn=main, inputs=[file_input, species_input], outputs=[image_output, file_output] ) demo.launch()