hubioinfo / cytocommunity Goto Github PK

A spatial omics data analysis tool that enables both unsupervised and supervised discovery of complex tissue cellular neighborhoods from cell phenotypes.

License: MIT License

Python 88.71% R 11.29%

multiplexed-imaging-analysis single-cell-analysis spatial-data-analysis

cytocommunity's People

Contributors

Stargazers

Watchers

Forkers

tanlabcode zhaohh52 rimanb hyacinthmeng

cytocommunity's Issues

[CytoCommunity] Using visium data

Dear authors,

Hi, all! Thank you so much sharing great tool to community.
I happen to come across you used DLPFC 10x visium data on CytoCommunity as well but can't find any toy example how you converted raw spaceranger output into current cytocommunity input files. Can you guide us with tutorial or explanation how one can do this?

many thanks in advance,
J

supervised method

I would like to generate the heatmap as in your paper
Could you please share the code or ideas?

Also, I cannot find where to get the file '..._GraphLabel.txt.'

Thank you!

Get Node _NodeAttr.txt and _GraphIndex.txt files

Hello,

Thank you for providing this interesting tool,

I surely missed something, but I did not understand from the tutorial how I can create the Node Attribute.txt and Graph Index.txt files.

Could you give me hints on how to generate those files ?

Thank you,
Pacôme

Run CytoCommunity on MacOS

Hello, Yuxuan

Thank you for developing the tool!

I can run Cytocommunity very smoothly on Linux but have a hard time running it on my Mac. I wonder if you could please also provide the installation file for MacOS (the yml file for MacOS) so that Mac Users, like me, can install it with pip on Mac. I tried to install it on my Mac PC but ran into a segmentation error when running the Python scripts. I guess the package versions are different.

Thank you!

Best,
Xiyu

Conda Package Installation Failure on Windows Using requirements.txt

Hello Authors,

Thanks for creating this tool.

I'm having trouble installing the Python environment from requirements.txt using Conda. It can't find some packages:

Collecting package metadata (current_repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.

PackagesNotFoundError: The following packages are not available from current channels:

  - libuv==1.44.2=h8ffe710_0
  - cffi==1.15.1=py310hcbf9ad4_0
  - yaml==0.2.5=h8ffe710_2
  - typing_extensions==4.4.0=pyha770c72_0
  - numpy==1.23.3=py310h4a8f9c9_0
  - six==1.16.0=pyh6c4a22f_0
  - setuptools==65.4.1=pyhd8ed1ab_0
  - vc==14.2=hac3ee0b_8
  - vs2015_runtime==14.29.30139=h890b9b1_8
  - contourpy==1.0.5=py310h232114e_0
  - xorg-libxau==1.0.9=hcd874cb_0
  - libbrotlidec==1.0.9=h8ffe710_7
  - libtiff==4.4.0=h8e97e67_4
  - tqdm==4.64.1=pyhd8ed1ab_0
  - lerc==4.0.0=h63175ca_0
  - jpeg==9e=h8ffe710_2
  - requests==2.28.1=pyhd8ed1ab_1
  - pytorch-mutex==1.0=cpu
  - brotli==1.0.9=h8ffe710_7
  - pip==22.2.2=pyhd8ed1ab_0
  - pcre2==10.37=hdfff0fc_1
  - xorg-libxdmcp==1.1.3=hcd874cb_0
  - intel-openmp==2022.1.0=h57928b3_3787
  - libwebp-base==1.2.4=h8ffe710_0
  - win_inet_pton==1.1.0=py310h5588dad_4
  - matplotlib-base==3.6.0=py310h51140c5_0
  - xz==5.2.6=h8d14728_0
  - yacs==0.1.8=pyhd8ed1ab_0
  - ï»¿
  - colorama==0.4.5=pyhd8ed1ab_0
  - liblapack==3.9.0=16_win64_mkl
  - urllib3==1.26.11=pyhd8ed1ab_0
  - pytorch-spline-conv==1.2.1=py310_torch_1.11.0_cpu
  - libiconv==1.17=h8ffe710_0
  - libvorbis==1.3.7=h0e60522_0
  - ply==3.11=py_1
  - pandas==1.5.0=py310h1c4a608_0
  - pyopenssl==22.0.0=pyhd8ed1ab_1
  - scikit-learn==1.1.2=py310h3a564e9_0
  - python==3.10.6=h9a09f29_0_cpython
  - libdeflate==1.14=hcfcfb64_0
  - zstd==1.5.2=h7755175_4
  - tzdata==2022d=h191b570_0
  - python-louvain==0.15=pyhd8ed1ab_1
  - mkl-devel==2022.1.0=h57928b3_875
  - glib==2.74.0=h12be248_0
  - blas==2.116=mkl
  - matplotlib==3.6.0=py310h5588dad_0
  - toml==0.10.2=pyhd8ed1ab_0
  - sip==6.6.2=py310h8a704f9_0
  - pyg==2.0.4=py310_torch_1.11.0_cpu
  - ucrt==10.0.20348.0=h57928b3_0
  - mkl==2022.1.0=h6a75c08_874
  - mkl-include==2022.1.0=h6a75c08_874
  - statsmodels==0.13.2=py310h2873277_0
  - unicodedata2==14.0.0=py310he2412df_1
  - m2w64-pcre2==10.34=0
  - tk==8.6.12=h8ffe710_0
  - libogg==1.3.4=h8ffe710_1
  - qt-main==5.15.6=hf0cf448_0
  - networkx==2.8.7=pyhd8ed1ab_0
  - libglib==2.74.0=h79619a9_0
  - python_abi==3.10=2_cp310
  - jinja2==3.1.2=pyhd8ed1ab_1
  - freetype==2.12.1=h546665d_0
  - wheel==0.37.1=pyhd8ed1ab_0
  - icu==70.1=h0e60522_0
  - pytorch-scatter==2.0.9=py310_torch_1.11.0_cpu
  - pillow==9.2.0=py310h52929f7_2
  - libzlib==1.2.12=hcfcfb64_4
  - pytorch==1.11.0=py3.10_cpu_0
  - zlib==1.2.12=hcfcfb64_4
  - libpng==1.6.38=h19919ed_0
  - markupsafe==2.1.1=py310he2412df_1
  - brotlipy==0.7.0=py310he2412df_1004
  - pyqt==5.15.7=py310hbabf5d4_0
  - pyqt5-sip==12.11.0=py310h8a704f9_0
  - gstreamer==1.20.3=h6b5321d_2
  - pytorch-sparse==0.6.15=py310_torch_1.11.0_cpu
  - tornado==6.2=py310he2412df_0
  - pytorch-cluster==1.6.0=py310_torch_1.11.0_cpu
  - cpuonly==2.0=0
  - bzip2==1.0.8=h8ffe710_4
  - patsy==0.5.3=pyhd8ed1ab_0
  - kiwisolver==1.4.4=py310h476a331_0
  - blas-devel==3.9.0=16_win64_mkl
  - pysocks==1.7.1=pyh0701188_6
  - rpy2==3.5.1=py310r41h3c8b411_1
  - libbrotlicommon==1.0.9=h8ffe710_7
  - tbb==2021.6.0=h91493d7_0
  - pytz==2022.4=pyhd8ed1ab_0
  - pyparsing==3.0.9=pyhd8ed1ab_0
  - r-base==4.1.3=hddad469_1
  - cycler==0.11.0=pyhd8ed1ab_0
  - python-dateutil==2.8.2=pyhd8ed1ab_0
  - charset-normalizer==2.1.1=pyhd8ed1ab_0
  - munkres==1.1.4=pyh9f0ad1d_0
  - libbrotlienc==1.0.9=h8ffe710_7
  - libxcb==1.13=hcd874cb_1004
  - brotli-bin==1.0.9=h8ffe710_7
  - fonttools==4.37.4=py310h8d17308_0
  - liblapacke==3.9.0=16_win64_mkl
  - scipy==1.9.1=py310h578b7cb_0
  - packaging==21.3=pyhd8ed1ab_0
  - glib-tools==2.74.0=h12be248_0
  - pthread-stubs==0.4=hcd874cb_1001
  - gst-plugins-base==1.20.3=h001b923_2
  - lcms2==2.12=h2a16943_0
  - krb5==1.19.3=h1176d77_0
  - openjpeg==2.5.0=hc9384bd_1
  - libcblas==3.9.0=16_win64_mkl
  - joblib==1.2.0=pyhd8ed1ab_0
  - libsqlite==3.39.4=hcfcfb64_0
  - threadpoolctl==3.1.0=pyh8a188c0_0
  - libblas==3.9.0=16_win64_mkl
  - pycparser==2.21=pyhd8ed1ab_0
  - pyyaml==6.0=py310he2412df_4
  - seaborn-base==0.12.0=pyhd8ed1ab_0
  - seaborn==0.12.0=hd8ed1ab_0
  - libffi==3.4.2=h8ffe710_5
  - gettext==0.19.8.1=h5728263_1009
  - idna==3.4=pyhd8ed1ab_0

Current channels:

  - https://repo.anaconda.com/pkgs/main/win-64
  - https://repo.anaconda.com/pkgs/main/noarch
  - https://repo.anaconda.com/pkgs/r/win-64
  - https://repo.anaconda.com/pkgs/r/noarch
  - https://repo.anaconda.com/pkgs/msys2/win-64
  - https://repo.anaconda.com/pkgs/msys2/noarch

To search for alternate channels that may provide the conda package you're
looking for, navigate to

    https://anaconda.org

and use the search bar at the top of the page.

Do you have any advice for fixing this? Should I use specific channels to get these packages?

Thanks!

Dataset for reproducing results

Hi there,

really cool package and congratulations on the publication.

Some people in my team are really interested in trying to reproduce some of your results, especially on the CODEX spleen dataset. Looking through your "Data Availability Statement" in the publication I noticed how you refer to the original data repository, however, I could not find the compartment annotations here (e.g., "Red Pulp", "Marginal Zone" etc.).

Would it be possible for you to share the data with the cell type and compartment annotations, perhaps as an .h5ad object or something similar. I'm assuming you used something like this to run your method and evaluate your results.

Best,
Alma

Error dimension specified as 0 but tensor has no dimensions in Step 2 - SoftTCNLearning_Supervised.py

Hello,

Now that I have the input in the right place, I manage to run Step 0 and 1 successfully.

Now, in the Step 2 - SoftTCNLearning_Supervised.py when running this line :
model = Net(dataset.num_features, dataset.num_classes).to(device)

I get :

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
Cell In[57], line 2
      1 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
----> 2 model = Net(dataset.num_features, dataset.num_classes).to(device)  #Initialize model for each fold.
      3 optimizer = torch.optim.Adam(model.parameters(), lr=LearningRate)
      5 FoldFolderName = TimeFolderName + "/Fold" + str(num_fold)

File ~/anaconda3/envs/CytoCommunity/lib/python3.10/site-packages/torch_geometric/data/dataset.py:114, in Dataset.num_features(self)
    110 @property
    111 def num_features(self) -> int:
    112     r"""Returns the number of features per node in the dataset.
    113     Alias for :py:attr:`~num_node_features`."""
--> 114     return self.num_node_features

File ~/anaconda3/envs/CytoCommunity/lib/python3.10/site-packages/torch_geometric/data/dataset.py:103, in Dataset.num_node_features(self)
    100 @property
    101 def num_node_features(self) -> int:
    102     r"""Returns the number of features per node in the dataset."""
--> 103     data = self[0]
    104     data = data[0] if isinstance(data, tuple) else data
    105     if hasattr(data, 'num_node_features'):

File ~/anaconda3/envs/CytoCommunity/lib/python3.10/site-packages/torch_geometric/data/dataset.py:198, in Dataset.__getitem__(self, idx)
    193 if (isinstance(idx, (int, np.integer))
    194         or (isinstance(idx, Tensor) and idx.dim() == 0)
    195         or (isinstance(idx, np.ndarray) and np.isscalar(idx))):
    197     data = self.get(self.indices()[idx])
--> 198     data = data if self.transform is None else self.transform(data)
    199     return data
    201 else:

File ~/anaconda3/envs/CytoCommunity/lib/python3.10/site-packages/torch_geometric/transforms/to_dense.py:51, in ToDense.__call__(self, data)
     48     size = [num_nodes - data.pos.size(0)] + list(data.pos.size())[1:]
     49     data.pos = torch.cat([data.pos, data.pos.new_zeros(size)], dim=0)
---> 51 if data.y is not None and (data.y.size(0) == orig_num_nodes):
     52     size = [num_nodes - data.y.size(0)] + list(data.y.size())[1:]
     53     data.y = torch.cat([data.y, data.y.new_zeros(size)], dim=0)

IndexError: dimension specified as 0 but tensor has no dimensions

It seems that accessing any of the attributes: dataset.num_classes, dataset.num_features, dataset.num_node_features or dataset.num_edge_features produces the same error and it seems to be related to accessing data.y.size(0)

Best,
Pacôme

hubioinfo / cytocommunity Goto Github PK

cytocommunity's People

Contributors

Stargazers

Watchers

Forkers

cytocommunity's Issues

[CytoCommunity] Using visium data

supervised method

Get Node _NodeAttr.txt and _GraphIndex.txt files

Run CytoCommunity on MacOS

Conda Package Installation Failure on Windows Using requirements.txt

Dataset for reproducing results

Error dimension specified as 0 but tensor has no dimensions in Step 2 - SoftTCNLearning_Supervised.py

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent