cellmaps-utils 0.10.0__py3-none-any.whl

cellmaps_utils/constants.py

@@ -0,0 +1,392 @@
+
+import argparse
+
+
+class ArgParseFormatter(argparse.ArgumentDefaultsHelpFormatter,
+                        argparse.RawDescriptionHelpFormatter):
+    """
+    Combine two :py:class:`argparse` Formatters to get help
+    and default values
+    displayed when showing help
+
+    """
+    pass
+
+
+LOG_FORMAT = "%(asctime)-15s %(levelname)s %(relativeCreated)dms " \
+             "%(filename)s::%(funcName)s():%(lineno)d %(message)s"
+"""
+Sets format of logging messages
+"""
+
+RO_CRATE_METADATA_FILE = 'ro-crate-metadata.json'
+"""
+`rocrate <https://www.researchobject.org/ro-crate>`__ metadata JSON file name
+"""
+
+PROVENANCE_ERRORS_FILE = 'provenance_errors.json'
+"""
+Contains log of any failed fairscape-cli calls
+"""
+
+TASK_FILE_PREFIX = 'task_'
+"""
+Prefix for task file
+"""
+
+TASK_START_FILE_SUFFIX = '_start.json'
+"""
+Suffix for task start file
+"""
+
+TASK_FINISH_FILE_SUFFIX = '_finish.json'
+"""
+Suffix for task finish file
+"""
+
+OUTPUT_LOG_FILE = 'output.log'
+"""
+Output log file name
+"""
+
+ERROR_LOG_FILE = 'error.log'
+"""
+Error log file name
+"""
+
+IMAGE_EMBEDDING_FILE = 'image_emd.tsv'
+"""
+Name of image embedding file
+"""
+
+IMAGE_LABELS_PROBABILITY_FILE = 'labels_prob.tsv'
+"""
+Name of image labels probability file
+"""
+
+PPI_EMBEDDING_FILE = 'ppi_emd.tsv'
+"""
+Name of Protein to Protein embedding file
+"""
+
+CO_EMBEDDING_FILE = 'coembedding_emd.tsv'
+"""
+Name of file containing coembedding
+"""
+
+IMAGE_GENE_NODE_ATTR_FILE = 'image_gene_node_attributes.tsv'
+"""
+Image gene node attributes filename
+"""
+
+IMAGE_GENE_NODE_ERRORS_FILE = 'image_gene_node_attributes.errors'
+"""
+Image gene node attributes errors filename
+"""
+
+PERTURBATION_FILE = 'perturbation.h5ad'
+"""
+Perturbation/CRISPRi h5ad file
+"""
+
+ANTIBODY_GENE_TABLE_FILE = 'antibody_gene_table.tsv'
+"""
+Antibody Gene Table file
+"""
+
+IMAGE_GENE_NODE_NAME_COL = 'name'
+"""
+Gene Symbol name column
+"""
+
+IMAGE_GENE_NODE_REPRESENTS_COL = 'represents'
+"""
+Ensembl ids column
+"""
+
+IMAGE_GENE_NODE_AMBIGUOUS_COL = 'ambiguous'
+"""
+Ambiguous column
+"""
+
+IMAGE_GENE_NODE_ANTIBODY_COL = 'antibody'
+"""
+Antibody name column
+"""
+
+IMAGE_GENE_NODE_FILENAME_COL = 'filename'
+"""
+File name column
+"""
+
+IMAGE_GENE_NODE_IMAGEURL_COL = 'imageurl'
+"""
+Image URL column
+"""
+
+
+IMAGE_GENE_NODE_COLS = [IMAGE_GENE_NODE_NAME_COL,
+                        IMAGE_GENE_NODE_REPRESENTS_COL,
+                        IMAGE_GENE_NODE_AMBIGUOUS_COL,
+                        IMAGE_GENE_NODE_ANTIBODY_COL,
+                        IMAGE_GENE_NODE_FILENAME_COL,
+                        IMAGE_GENE_NODE_IMAGEURL_COL]
+"""
+Columns in :py:const:`IMAGE_GENE_NODE_ATTR_FILE` file
+"""
+
+APMS_TSV_FILE = 'apms.tsv'
+"""
+AP-MS tsv file
+"""
+
+APMS_UNFILTERED_TSV_FILE = 'apms_unfiltered.tsv'
+"""
+AP-MS tsv file containing the complete pre-filter matrix. Same schema
+as :py:const:`APMS_TSV_FILE`
+"""
+
+APMS_DRUG_EFFECT_TSV_FILE = 'apms_drug_effect.tsv'
+"""
+MSstats drug effect tsv file. Only written for the treated RO-Crate.
+Joins to :py:const:`APMS_TSV_FILE` on Batch, Bait, Prey
+"""
+
+APMS_QC_FILE = 'apms_qc.json'
+"""
+AP-MS QC/summary statistics file
+"""
+
+SECMS_TSV_FILE = 'sec_ms.tsv'
+SECMS_REPLICATES_FILE = 'secms_replicates.tsv'
+SECMS_GROUPS_FILE = 'secms_protein_groups.tsv'
+SECMS_RUNS_FILE = 'secms_runs.tsv'
+SECMS_ROWS_FILE = 'secms_rows.tsv'
+SECMS_SOURCES_FILE = 'secms_sources.tsv'
+SECMS_QC_FILE = 'secms_qc.json'
+
+PPI_EDGELIST_FILE = 'ppi_edgelist.tsv'
+"""
+Protein to Protein interaction edgelist file name
+"""
+
+PPI_EDGELIST_GENEA_COL = 'geneA'
+"""
+First column name
+"""
+
+PPI_EDGELIST_GENEB_COL = 'geneB'
+"""
+Second column name
+"""
+
+PPI_EDGELIST_COLS = [PPI_EDGELIST_GENEA_COL,
+                     PPI_EDGELIST_GENEB_COL]
+"""
+Columns in :py:const:`PPI_EDGELIST_FILE`
+"""
+
+WEIGHTED_PPI_EDGELIST_WEIGHT_COL = 'Weight'
+"""
+weight column
+"""
+
+WEIGHTED_PPI_EDGELIST_COLS = [PPI_EDGELIST_GENEA_COL,
+                              PPI_EDGELIST_GENEB_COL,
+                              WEIGHTED_PPI_EDGELIST_WEIGHT_COL]
+
+PPI_GENE_NODE_ATTR_FILE = 'ppi_gene_node_attributes.tsv'
+"""
+Protein to Protein gene node attributes file
+"""
+
+PPI_GENE_NODE_COLS = ['name', 'represents', 'ambiguous', 'bait']
+"""
+Columns in :py:const:`PPI_GENE_NODE_ATTR_FILE`
+"""
+
+PPI_GENE_NODE_ERRORS_FILE = 'ppi_gene_node_attributes.errors'
+"""
+Protein to Protein gene node attributes error filename
+"""
+
+PPI_NETWORK_PREFIX = 'ppi'
+
+HIERARCHY_NETWORK_PREFIX = 'hierarchy'
+"""
+CX2 format hierarchy filename
+"""
+
+HIERARCHY_PARENT_NETWORK_PREFIX = 'hierarchy_parent'
+"""
+CX2 format hierarchy parent (interactome) filename
+"""
+
+HIERARCHY_NODES_FILE = 'hierarchy_node_attributes.tsv'
+"""
+Hierarchy node attributes file
+"""
+
+CX_SUFFIX = '.cx'
+"""
+Suffix for files in `CX <https://cytoscape.org/cx/specification/2022/01/11/cytoscape-exchange-format-specification-(version-1).html>`__ format
+"""
+
+CX2_SUFFIX = '.cx2'
+"""
+Suffix for files in `CX 2.0<https://cytoscape.org/cx/cx2/specification/2022/12/01/cytoscape-exchange-format-specification-(version-2).html>`__ format
+"""
+
+HCX_SUFFIX = '.hcx'
+"""
+Suffix for files in `HCX <https://cytoscape.org/cx>`__ format
+"""
+
+RED = 'red'
+"""
+Red color directory name and color name
+in red color files
+"""
+
+BLUE = 'blue'
+"""
+Blue color directory name and color name
+in blue color files
+"""
+GREEN = 'green'
+"""
+Green color directory name and color name
+in green color files
+"""
+
+YELLOW = 'yellow'
+"""
+Yellow color directory name and color name
+in yellow color files
+"""
+
+COLORS = [RED, BLUE, GREEN, YELLOW]
+"""
+List of colors
+"""
+
+COLOR_INDEXS = {
+            'red': 0,
+            'green': 1,
+            'blue': 2,
+            'yellow': 0,
+        }
+"""
+Indexes for colors in .jpeg image
+"""
+
+COLOR_LABELS_MAP = {
+    GREEN: 'protein of interest',
+    RED: 'Microtubules (Tubulin antibody)',
+    BLUE: 'Nucleus (DAPI)',
+    YELLOW: 'ER (Calreticulin antibody)',
+}
+"""
+Map of what each color refers to
+"""
+
+IMAGE_DOWNLOAD_STEP_DIR = '1.image_download'
+"""
+Name of directory where downloaded images are stored
+"""
+
+PPI_DOWNLOAD_STEP_DIR = '1.ppi_download'
+"""
+Name of directory where downloaded PPI edge and
+baitlist are stored
+"""
+
+PPI_EMBEDDING_STEP_DIR = '2.ppi_embedding'
+"""
+Name of directory where PPI embeddings are stored
+"""
+
+IMAGE_EMBEDDING_STEP_DIR = '2.image_embedding_fold'
+"""
+Name of directory where image embeddings are stored
+"""
+
+COEMBEDDING_STEP_DIR = '3.coembedding_fold'
+"""
+Name of directory where co-embeddings are stored
+"""
+
+HIERARCHY_STEP_DIR = '4.hierarchy'
+"""
+Name of directory where hierarchies are stored
+"""
+
+HIERARCHYEVAL_STEP_DIR = '5.hierarchyeval'
+"""
+Name of directory where hierarchy evaluations are stored
+"""
+
+DATASET_INFO_FILE = 'dataset_info.json'
+"""
+Name of file where information about a dataset is stored
+"""
+
+DATASET_NAME = 'name'
+"""
+Name of the dataset
+"""
+
+DATASET_ORGANIZATION_NAME = 'organization_name'
+"""
+Name of the organization
+"""
+
+DATASET_PROJECT_NAME = 'project_name'
+"""
+Name of the project
+"""
+
+DATASET_RELEASE = 'release'
+"""
+Release of the dataset
+"""
+
+DATASET_CELL_LINE = 'cell_line'
+"""
+Cell line
+"""
+
+DATASET_TREATMENT = 'treatment'
+"""
+Treatment
+"""
+
+DATASET_TISSUE = 'tissue'
+"""
+Tissue
+"""
+
+DATASET_AUTHOR = 'author'
+"""
+Author of the dataset
+"""
+
+DATASET_SLICE = 'slice'
+"""
+Slice
+"""
+
+DATASET_GENE_SET = 'gene_set'
+"""
+Gene set
+"""
+
+DATASET_COLLECTION_SET = 'collection_set'
+"""
+Collection set
+"""
+
+DATASET_REPLICATES = 'replicates'
+"""
+Replicates
+"""

cellmaps_utils/crispr_readme.txt

@@ -0,0 +1,19 @@
+@@H5AD@@ file
+-----------------------------------------------------------
+
+This file is a .h5ad file. Details about the data structure of this format
+can be found here: https://anndata.readthedocs.io/en/latest/. This data is
+a cell x gene matrix, with all preprocesing steps done in accordance to
+single cell best practices guide
+(https://www.sc-best-practices.org/conditions/perturbation_modeling.html#analysing-single-pooled-crispr-screens)
+up to section 19.4.5. The .X layer is set to the 'X_pert' output of the
+mixscape pipeline.
+
+cell line: @@CELL_LINE@@
+screening modality: perturb seq using CRISPR-dCas9-ZIM3
+screen targets: @@NUM_SCREEN_TARGETS_AND_GENE_SET@@ genes
+non-targeting controls: @@NUM_NON_TARGET_CTRLS@@
+number of guides per perturbation: @@NUM_PERTURB_GUIDES@@
+treatment: @@TREATMENT@@
+
+