reformatted cbioportal pipeline for nextflow compatibility

.gitignore

@@ -187,3 +187,4 @@ $RECYCLE.BIN/
 # Requests cache directory
 requests_cache/
 data_cache/
+*params.json

pyproject.toml

@@ -42,6 +42,9 @@ pytest-runner = "^6.0.1"
 [tool.pytest.ini_options]
 pythonpath = ["src"]
 
+[tool.poetry.scripts]
+process_cbioportal = "missense_kinase_toolkit.cli.process_cbioportal:main"
+
 [tool.poetry-dynamic-versioning]
 enable = true
 vcs = "git"

src/missense_kinase_toolkit/cbioportal.py

@@ -4,71 +4,15 @@
 
 import os
 import pandas as pd
-import sys
 
 from bravado.client import SwaggerClient
 from bravado.requests_client import RequestsClient
 
-
-CBIOPORTAL_TOKEN_VAR = "CBIOPORTAL_TOKEN"
-CBIOPORTAL_INSTANCE_VAR = "CBIOPORTAL_INSTANCE"
-DATA_CACHE_DIR = "DATA_CACHE"
-CBIOPORTAL_COHORT_VAR = "CBIOPORTAL_COHORT"
-
-
-def maybe_get_cbioportal_token_from_env(
-) -> str | None:
-    """Get the cBioPortal token from the environment
-
-    Returns
-    -------
-    str | None
-        cBioPortal token as string if exists, otherwise None
-    """
-    try:
-        token = os.environ[CBIOPORTAL_TOKEN_VAR]
-    except KeyError:
-        token = None
-
-    return token
-
-
-def maybe_get_cbioportal_instance_from_env(
-) -> str | None:
-    """Get the cBioPortal instance from the environment
-
-    Returns
-    -------
-    str | None
-        cBioPortal instance as string if exists, otherwise None
-    """
-    try:
-        instance = os.environ[CBIOPORTAL_INSTANCE_VAR]
-    except KeyError:
-        instance = None
-
-    return instance
-
-
-def maybe_get_cbioportal_cohort_from_env(
-) -> str | None:
-    """Get the cBioPortal instance from the environment
-
-    Returns
-    -------
-    str | None
-        cBioPortal instance as string if exists, otherwise None
-    """
-    try:
-        instance = os.environ[CBIOPORTAL_COHORT_VAR]
-    except KeyError:
-        print("Cohort not found in environment variables. This is necessary to run analysis. Exiting...")
-        sys.exit(1)
-
-    return instance
+from missense_kinase_toolkit import config
 
 
 def get_all_mutations_by_study(
+    study_id: str,
 ) -> list | None:
     """Get mutations  cBioPortal data
 
@@ -77,19 +21,11 @@ def get_all_mutations_by_study(
     list | None
         cBioPortal data of Abstract Base Classes objects if successful, otherwise None
     """
-    token = maybe_get_cbioportal_token_from_env()
-
-    instance = maybe_get_cbioportal_instance_from_env()
-    if instance is not None:
-        url = f"https://{instance}/api/v2/api-docs"
-    else:
-        url = "https://cbioportal.org/api/v2/api-docs"
+    instance = config.get_cbioportal_instance()
+    url = f"https://{instance}/api/v2/api-docs"
+    token = config.maybe_get_cbioportal_token()
 
-    # Zehir, 2017 MSKCC sequencing cohort is "msk_impact_2017"
-    # MSKCC clinical sequencing cohort is "mskimpact"
-    study_id = maybe_get_cbioportal_cohort_from_env()
-
-    if all(v is not None for v in (token, instance)):
+    if token is not None:
         http_client = RequestsClient()
         http_client.set_api_key(
             instance,
@@ -179,23 +115,23 @@ def save_cbioportal_data_to_csv(
     None
     """
     try:
-        path_data = os.environ[DATA_CACHE_DIR]
+        path_data = config.get_output_dir()
         if not os.path.exists(path_data):
             os.makedirs(path_data)
-        study_id = maybe_get_cbioportal_cohort_from_env()
+        study_id = config.get_cbioportal_cohort()
         df.to_csv(os.path.join(path_data, f"{study_id}_mutations.csv"), index=False)
     except KeyError:
-        print("DATA_CACHE not found in environment variables...")
+        print("OUTPUT_DIR not found in environment variables...")
+
 
+def get_and_save_cbioportal_cohort(
+    study_id: str,
+) -> None:
+    muts = get_all_mutations_by_study(study_id)
 
-def main():
-    muts = get_all_mutations_by_study()
     df_muts = parse_iterabc2dataframe(muts)
     df_genes = parse_iterabc2dataframe(df_muts["gene"])
     df_combo = pd.concat([df_muts, df_genes], axis=1)
     df_combo = df_combo.drop(['gene'], axis=1)
-    save_cbioportal_data_to_csv(df_combo)
-
 
-if __name__ == "__main__":
-    main()
+    save_cbioportal_data_to_csv(df_combo)

src/missense_kinase_toolkit/cli/process_cbioportal.py

@@ -0,0 +1,73 @@
+import argparse
+
+from missense_kinase_toolkit import config, cbioportal
+
+def parsearg_utils():
+    parser = argparse.ArgumentParser(
+        description="Get mutations from cBioPortal cohort and instance"
+    )
+
+    parser.add_argument(
+        "--cohort",
+        type=str,
+        help="Optional: cBioPortal cohort IDs separated by commas (e.g., `msk_impact_2017` for Zehir, 2017 and `mskimpact` for MSKCC clinical sequencing cohort)",
+        default="msk_impact_2017",
+    )
+
+    parser.add_argument(
+        "--outDir",
+        type=str,
+        help="Required: Output directory path (str)",
+    )
+
+    parser.add_argument(
+        "--instance",
+        type=str,
+        help="Optional: cBioPortal instance (e.g., `cbioportal.mskcc.org`). Default: `cbioportal.org` (str)",
+        default="cbioportal.org",
+    )
+
+    parser.add_argument(
+        "--token",
+        type=str,
+        default="",
+        help="Optional: cBioPortal API token (str)",
+    )
+
+    parser.add_argument(
+        "--requestsCache",
+        type=str,
+        default="",
+        help="Optional: Requests cache (str)",
+    )
+
+    # TODO: add logging functionality
+    return parser
+
+
+def main():
+    args = parsearg_utils().parse_args()
+
+    str_studies = args.cohort
+    list_studies = str_studies.split(",")
+    list_studies = [study.strip() for study in list_studies]
+
+    # required arguments
+    config.set_output_dir(args.outDir)
+    config.set_cbioportal_instance(args.instance)
+
+    # optional arguments
+    try:
+        if args.token != "":
+            config.set_cbioportal_instance(args.token)
+    except AttributeError:
+        pass
+
+    try:
+        if args.requestsCache != "":
+            config.set_cbioportal_instance(args.requestsCache)
+    except AttributeError:
+        pass
+
+    for study in list_studies:
+        cbioportal.get_and_save_cbioportal_cohort(study)

src/missense_kinase_toolkit/config.py

@@ -0,0 +1,138 @@
+import os
+import sys
+
+
+OUTPUT_DIR_VAR = "OUTPUT_DIR"
+CBIOPORTAL_INSTANCE_VAR = "CBIOPORTAL_INSTANCE"
+CBIOPORTAL_TOKEN_VAR = "CBIOPORTAL_TOKEN"
+REQUEST_CACHE_VAR = "REQUESTS_CACHE"
+
+
+def set_output_dir(
+    val: str
+) -> None:
+    """Set the output directory in environment variables
+    
+    Parameters
+    ----------
+    val : str
+        Output directory path
+
+    Returns
+    -------
+    None
+    """
+    os.environ[OUTPUT_DIR_VAR] = val
+
+
+def get_output_dir(
+) -> str | None:
+    """Get the output directory from the environment
+
+    Returns
+    -------
+    str | None
+        Output directory path if exists, otherwise None
+    """
+    try:
+        return os.environ[OUTPUT_DIR_VAR]
+    except KeyError:
+        print("Output directory not found in environment variables. This is necessary to run analysis. Exiting...")
+        sys.exit(1)
+
+
+def set_cbioportal_instance(
+    val: str
+) -> None:
+    """Set the cBioPortal instance in the environment variables
+
+    Parameters
+    ----------
+    val : str
+        cBioPortal instance; e.g., "cbioportal.mskcc.org" for MSKCC or 
+
+    Returns
+    -------
+    None
+    """
+    os.environ[CBIOPORTAL_INSTANCE_VAR] = val
+
+
+def get_cbioportal_instance(
+) -> str | None:
+    """Get the cBioPortal instance from the environment
+
+    Returns
+    -------
+    str | None
+        cBioPortal instance as string if exists, otherwise None
+    """
+    try:
+        return os.environ[CBIOPORTAL_INSTANCE_VAR]
+    except KeyError:
+        print("cBioPortal isntance not found in environment variables. This is necessary to run analysis. Exiting...")
+        sys.exit(1)
+
+
+def set_cbioportal_token(
+    val: str
+) -> None:
+    """Set the cBioPortal token in the environment variables
+
+    Parameters
+    ----------
+    val : str
+        cBioPortal token
+
+    Returns
+    -------
+    None
+    """
+    os.environ[CBIOPORTAL_TOKEN_VAR] = val
+
+
+def maybe_get_cbioportal_token(
+) -> str | None:
+    """Get the cBioPortal token from the environment
+
+    Returns
+    -------
+    str | None
+        cBioPortal token as string if exists, otherwise None
+    """
+    try:
+        return os.environ[CBIOPORTAL_TOKEN_VAR]
+    except KeyError:
+        return None
+
+
+def set_request_cache(
+    val: str
+) -> None:
+    """Set the request cache path in environment variables
+    
+    Parameters
+    ----------
+    val : str
+        Request cache path
+
+    Returns
+    -------
+    None
+    """
+    os.environ[REQUEST_CACHE_VAR] = val
+
+
+def maybe_get_request_cache(
+) -> str | None:
+    """Get the request cache path from the environment
+
+    Returns
+    -------
+    str | None
+        Request cache path as string if exists, otherwise None
+    """
+    try:
+        return os.environ[REQUEST_CACHE_VAR]
+    except KeyError:
+        return None

src/missense_kinase_toolkit/scrapers.py

@@ -1,7 +1,7 @@
 import pandas as pd
 
 def scrape_kinhub(
-    url: str ='http://www.kinhub.org/kinases.html'
+    url: str = "http://www.kinhub.org/kinases.html",
 ) -> pd.DataFrame:
     """Scrape the KinHub database for kinase information
 

src/nextflow/README.MD

@@ -0,0 +1,24 @@
+# NextFlow workflow to run pipeline
+
+To run: `nextflow run main.nf -params-file params.json`
+
+Generate own `params.json` file using the following parameters:
+```
+{
+    "CBIOPORTAL_COHORT"     : "TODO",
+    "OUTPUT_DIR"            : "TODO",
+    "CBIOPORTAL_INSTANCE"   : "TODO",
+    "CBIOPORTAL_TOKEN"      : "TODO",
+    "REQUESTS_CACHE"        : "TODO"
+}
+```
+
+Below is a description of what each variable should contain. If variable is optional and not in use, do not create any entry in the `json` file.
+
+| Variable             | Optional | Description |
+| :--------------------| :------: | :---------- |
+| 'CBIOPORTAL_COHORT'  |    No    | cBioPortal cohort to analyze |
+| 'OUTPUT_DIR'         |    No    | Path to outdir to save data |
+| 'CBIOPORTAL_INSTANCE'|    Yes   | `cbioportal.org` if none provided |
+| 'CBIOPORTAL_TOKEN'   |    Yes   | Data Access Token if using private instance|
+| 'REQUESTS_CACHE'     |    Yes   | Path to dir to cache requests data |