Spotiflow - accurate and efficient spot detection with stereographic flow

Spotiflow is a deep learning-based, threshold-agnostic, and subpixel-accurate spot detection method for fluorescence microscopy. It is primarily developed for spatial transcriptomics workflows that require transcript detection in large, multiplexed FISH-images, although it can also be used to detect spot-like structures in general fluorescence microscopy images.

Installation

Create and activate a fresh conda environment (we currently support Python 3.9 to 3.11):

conda create -n spotiflow python=3.9
conda activate spotiflow

Then install PyTorch using conda/mamba (refer to the official installation instructions for more info depending on your system):

For MacOS:

conda install pytorch::pytorch torchvision -c pytorch # for MacOS

For Linux/Windows with a CUDA device (one might need to change the cuda version accordingly):

conda install pytorch torchvision pytorch-cuda=11.8 -c pytorch -c nvidia # Might need to change the cuda version accordingly

Note (only for Windows users): if using Windows, please install the latest Build Tools for Visual Studio (make sure to select the C++ build tools during installation) before proceeding to install Spotiflow.

Finally, install spotiflow:

pip install spotiflow

Usage

Training

See the example training script or the example notebook for an example of training. For finetuning an already pretrained model, please refer to the finetuning example notebook.

Inference

The API allows detecting spots in a new image in a few lines of code! Please check the corresponding example notebook and the documentation for a more in-depth explanation.

from spotiflow.model import Spotiflow
from spotiflow.sample_data import test_image_hybiss_2d

# Load sample image
img = test_image_hybiss_2d()
# Or any other image
# img = tifffile.imread("myimage.tif")

# Load a pretrained model
model = Spotiflow.from_pretrained("general", inference=True)
# Or load your own trained model from folder
# model = Spotiflow.from_folder("./mymodel", inference=True)

# Predict
points, details = model.predict(img) # points contains the coordinates of the detected spots, the attributes 'heatmap' and 'flow' of `details` contains the predicted full resolution heatmap and the prediction of the stereographic flow respectively (access them by `details.heatmap` or `details.flow`).

Napari plugin

Our napari plugin allows detecting spots directly with an easy-to-use UI. See napari-spotiflow for more information.

For developers

We are open to contributions, and we indeed very much encourage them! Make sure that existing tests pass before submitting a PR, as well as adding new tests/updating the documentation accordingly for new features.

Testing

First, clone the repository:

git clone git@github.com:weigertlab/spotiflow.git

Then install the testing extras:

cd spotiflow
pip install -e ".[testing]"

then run the tests:

pytest -v --color=yes --cov=spotiflow

Docs

Install the docs extras:

pip install -e ".[docs]"

and then cd into the docs folder of the cloned repository and build them:

cd spotiflow/docs
sphinx-build -M html source build

How to cite

If you use this code in your research, please cite the Spotiflow paper (currently preprint):

@inproceedings{dominguezmantes2024,
  author    = {},
  title     = {},
  ...
}