cellmaps_coembedding package

Subpackages

• cellmaps_coembedding.muse_sc package
  • Submodules
  • cellmaps_coembedding.muse_sc.architecture module
    • Protein_Dataset
    • ToTensor
    • init_weights()
    • init_weights_d()
    • structured_embedding
      • structured_embedding.forward()
  • cellmaps_coembedding.muse_sc.df_utils module
    • canberra_similarity()
    • check_symmetric()
    • cosine_similarity_scaled()
    • euclidean_similarity()
    • kendall_scaled()
    • manhattan_similarity()
    • pearson_scaled()
    • spearman_scaled()
    • upper_tri_values()
    • znorm()
  • cellmaps_coembedding.muse_sc.file_utils module
    • load_obj()
    • save_obj()
  • cellmaps_coembedding.muse_sc.triplet_loss module
    • batch_all_triplet_loss()
    • batch_hard_triplet_loss()
    • fraction_triplets()
  • Module contents
    • make_matrix_from_labels()
    • muse_fit_predict()
    • train_model()
    • write_result_to_file()

• cellmaps_coembedding.autoembed_sc package
  • Submodules
  • cellmaps_coembedding.autoembed_sc.architecture module
  • Module contents

Submodules

cellmaps_coembedding.cellmaps_coembeddingcmd module

cellmaps_coembedding.cellmaps_coembeddingcmd.main(args)

Main entry point for program

Parameters:

args (list) – arguments passed to command line usually sys.argv[1:]()

Returns:

return value of cellmaps_coembedding.runner.CellmapsCoEmbedder.run() or 2 if an exception is raised

Return type:

int

cellmaps_coembedding.exceptions module

exception cellmaps_coembedding.exceptions.CellmapsCoEmbeddingError

Bases: Exception

Base exception for cellmaps_coembedding

cellmaps_coembedding.runner module

class cellmaps_coembedding.runner.AutoCoEmbeddingGenerator(dimensions=128, outdir=None, embeddings=None, ppi_embeddingdir=None, image_embeddingdir=None, embedding_names=None, jackknife_percent=0.0, n_epochs=100, save_update_epochs=True, batch_size=16, triplet_margin=0.2, dropout=0.5, l2_norm=False, mean_losses=False)

Bases: ProteinGPSCoEmbeddingGenerator

Generates co-embedding using proteingps

Deprecated since version 1.0.0: The embedding was renamed to proteingps. This class is now called ProteinGPSCoEmbeddingGenerator.

Initializes the ProteinGPSCoEmbeddingGenerator.

Parameters:

• dimensions – The dimensionality of the embedding space (default: 128).

• outdir – The output directory where embeddings should be saved.

• embeddings – Embedding data.

• ppi_embeddingdir – Directory containing protein-protein interaction embeddings.

• image_embeddingdir – Directory containing image embeddings.

• embedding_names – List of names corresponding to each type of embedding provided.

• jackknife_percent – Percentage of data to withhold from training as a method of resampling (default: 0).

• n_epochs – Number of epochs for which the model trains (default: 250).

• save_update_epochs – Boolean indicating whether to save embeddings at regular epoch intervals.

• batch_size – Number of samples per batch during training (default: 16).

• triplet_margin – The margin value for the triplet loss during training (default: 1.0).

• dropout – The dropout rate between layers in the neural network (default: 0).

• l2_norm – If true, L2 normalize coembeddings

class cellmaps_coembedding.runner.CellmapsCoEmbedder(outdir=None, inputdirs=None, embedding_generator=None, name=None, organization_name=None, project_name=None, provenance_utils=<cellmaps_utils.provenance.ProvenanceUtil object>, skip_logging=True, input_data_dict=None, provenance=None)

Bases: object

Class to run algorithm

Constructor

Parameters:

• outdir (str) – Directory to write the results of this tool

• inputdir (str) – Output directory where embeddings to be coembedded are located (output of cellmaps_image_embedding and cellmaps_ppi_embedding)

• embedding_generator

• skip_logging (bool) – If True skip logging, if None or False do NOT skip logging

• name (str)

• organization_name (str)

• project_name (str)

• input_data_dict (dict)

generate_readme()

get_coembedding_file()

Gets image embedding file :return:

run()

Runs CM4AI Generate COEMBEDDINGS

Returns:

class cellmaps_coembedding.runner.EmbeddingGenerator(dimensions=128, ppi_embeddingdir=None, image_embeddingdir=None, embeddings=None, embedding_names=None)

Bases: object

Base class for implementations that generate network embeddings

Constructor

DROPOUT = 0.5

JACKKNIFE_PERCENT = 0.0

LATENT_DIMENSIONS = 128

N_EPOCHS = 100

get_dimensions()

Gets number of dimensions this embedding will generate

Returns:

number of dimensions aka vector length

Return type:

int

get_embedding_inputdirs()

Determines the input directories for embeddings by extracting the directory path from each embedding file path. If the path is already a directory, it’s returned as is.

Returns:

A list of directory paths for each embedding, derived from the embedding file paths.

Return type:

list

get_next_embedding()

Generator method for getting next embedding. Caller should implement with yield operator

Raises:

NotImplementedError: Subclasses should implement this

Returns:

Embedding

Return type:

list

class cellmaps_coembedding.runner.FakeCoEmbeddingGenerator(dimensions=128, ppi_embeddingdir=None, image_embeddingdir=None, embeddings=None, embedding_names=None)

Bases: EmbeddingGenerator

Generates a fake coembedding for intersection of embedding dirs

Constructor :param dimensions:

get_next_embedding()

Gets next embedding

Returns:

class cellmaps_coembedding.runner.MuseCoEmbeddingGenerator(dimensions=128, k=10, triplet_margin=0.1, dropout=0.5, n_epochs=100, n_epochs_init=100, outdir=None, embeddings=None, ppi_embeddingdir=None, image_embeddingdir=None, embedding_names=None, jackknife_percent=0.0)

Bases: EmbeddingGenerator

Generats co-embedding using MUSE

Parameters:

• dimensions

• k – k nearest neighbors value used for clustering - clustering used for triplet loss

• triplet_margin – margin for triplet loss

• dropout – dropout between neural net layers

• n_epochs – training epochs

• n_epochs_init – initialization training epochs

• outdir

• ppi_embeddingdir

• image_embeddingdir

• jackknife_percent – percent of data to withhold from training

N_EPOCHS_INIT = 100

get_next_embedding()

Returns:

class cellmaps_coembedding.runner.ProteinGPSCoEmbeddingGenerator(dimensions=128, outdir=None, embeddings=None, ppi_embeddingdir=None, image_embeddingdir=None, embedding_names=None, jackknife_percent=0.0, n_epochs=100, save_update_epochs=True, batch_size=16, triplet_margin=0.2, dropout=0.5, l2_norm=False, mean_losses=False)

Bases: EmbeddingGenerator

Generates co-embedding using proteingps

Initializes the ProteinGPSCoEmbeddingGenerator.

Parameters:

• dimensions – The dimensionality of the embedding space (default: 128).

• outdir – The output directory where embeddings should be saved.

• embeddings – Embedding data.

• ppi_embeddingdir – Directory containing protein-protein interaction embeddings.

• image_embeddingdir – Directory containing image embeddings.

• embedding_names – List of names corresponding to each type of embedding provided.

• jackknife_percent – Percentage of data to withhold from training as a method of resampling (default: 0).

• n_epochs – Number of epochs for which the model trains (default: 250).

• save_update_epochs – Boolean indicating whether to save embeddings at regular epoch intervals.

• batch_size – Number of samples per batch during training (default: 16).

• triplet_margin – The margin value for the triplet loss during training (default: 1.0).

• dropout – The dropout rate between layers in the neural network (default: 0).

• l2_norm – If true, L2 normalize coembeddings

get_next_embedding()

Iteratively generates embeddings by fitting the proteingps to the current data set.

Returns:

Yields the next embedding, produced by the proteingps embedder’s fit_predict method.

cellmaps_coembedding.utils module

Module contents

Top-level package for CM4AI Generate PPI.