Adjusting fields for automated QC labelling

docs/interface/BindingAPI.md

@@ -1 +1 @@
-::: yeastdnnexplorer.interface.BindingAPI.BindingAPI
+::: yeastdnnexplorer.interface.BindingAPI.BindingAPI

docs/interface/BindingConcatenatedAPI.md

@@ -0,0 +1 @@
+::: yeastdnnexplorer.interface.BindingConcatenatedAPI.BindingConcatenatedAPI

docs/interface/DtoAPI.md

@@ -0,0 +1 @@
+::: yeastdnnexplorer.interface.DtoAPI.DtoAPI

docs/tutorials/database_interface.ipynb

@@ -144,12 +144,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "from yeastdnnexplorer.interface import *\n",
-    "import matplotlib.pyplot as plt"
+    "import matplotlib.pyplot as plt\n",
+    "import json\n",
+    "import pandas as pd"
    ]
   },
   {
@@ -2227,6 +2229,78 @@
     "plt.show()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## DTO API\n",
+    "\n",
+    "There is now an endpoint to submit jobs to run\n",
+    "[dual_threshold_optimization](https://github.com/BrentLab/Dual_Threshold_Optimization/tree/dev).\n",
+    "Submitting a job, and retrieving the result, can be achieved with `submit` and `retrieve`,\n",
+    "similar to rankresponse. `read()` will retrieve the records in the `metadata`. The DTO\n",
+    "results are in the `results` field, stored as a json.\n",
+    "\n",
+    "```python\n",
+    "dto_api = DtoAPI()\n",
+    "\n",
+    "# submit a DTO job like this. Note -- this can take ~30 minutes to run. It will fail\n",
+    "# if that promotersetsig_id and expression_id already exist in the DTO table\n",
+    "args = [\n",
+    "    {\n",
+    "        \"promotersetsig_id\": \"40\",\n",
+    "        \"expression_id\": \"77\",\n",
+    "        \"pss_rename_metric_columns\": False,\n",
+    "        \"pss_col1_ascending\": True,\n",
+    "        \"pss_col2_ascending\": False,\n",
+    "        \"pss_ranker_col1\": \"poisson_pval\",\n",
+    "        \"pss_ranker_col2\": \"callingcards_enrichment\",\n",
+    "        \"expression_col1_ascending\": False,\n",
+    "        \"expression_ranker_col1\": \"effect\",\n",
+    "        \"expression_ranker_col2\": None,\n",
+    "        \"expression_ranker_col1_abs\": True,\n",
+    "        \"n_permutations\": 1000,\n",
+    "        \"n_threads\": 28,\n",
+    "    }\n",
+    "]\n",
+    "\n",
+    "group_id = await dto_api.submit(post_dict=args)\n",
+    "\n",
+    "res = await dto_api.retrieve(group_id)\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# retrieve a DTO result with `read` to get records from the database\n",
+    "dto_api = DtoAPI()\n",
+    "dto_records = await dto_api.read()\n",
+    "\n",
+    "print(f'dto metadata results: {dto_records.get(\"metadata\")}')\n",
+    "\n",
+    "dto_results_list = []\n",
+    "\n",
+    "for i, row in dto_records.get(\"metadata\").iterrows():\n",
+    "    dto_results = json.loads(row.result.replace(\"'\", '\"'))\n",
+    "\n",
+    "    dto_results['id'] = row.id\n",
+    "    dto_results['promotersetsig_id'] = row.promotersetsig\n",
+    "    dto_results['expression_id'] = row.expression\n",
+    "    dto_results['regulator'] = row.regulator_symbol\n",
+    "    dto_results['binding_source'] = row.binding_source\n",
+    "    dto_results['expression_effect'] = row.expression_source\n",
+    "\n",
+    "    dto_results_list.append(dto_results)\n",
+    "\n",
+    "dto_results_df = pd.DataFrame(dto_results_list)\n",
+    "\n",
+    "print(f'dto results: {dto_results_df}')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

mkdocs.yml

@@ -51,6 +51,7 @@ nav:
   - Visualizing and Testing Data Generation Methods: tutorials/visualizing_and_testing_data_generation_methods.ipynb
   - Generalized Logistic Models: tutorials/generalized_logistic_models.ipynb
   - LassoCV: tutorials/lassoCV.ipynb
+  - Interactor Modeling Workflow: tutorials/interactor_modeling_workflow.ipynb
 - API:
   - Data Loaders:
     - Synthetic Data Loader: data_loaders/synthetic_data_loader.md
@@ -75,16 +76,18 @@ nav:
     - Records Only Classes:
       - interface/BindingManualQCAPI.md
       - interface/DataSourceAPI.md
+      - interface/DtoAPI.md
       - interface/ExpressionManualQCAPI.md
       - interface/FileFormatAPI.md
       - interface/GenomicFeatureAPI.md
       - interface/RegulatorAPI.md
     - Records and Files Classes:
-      - interface/BindingAPI.md
-      - interface/CallingCardsBackgroundAPI.md
-      - interface/ExpressionAPI.md
-      - interface/PromoterSetAPI.md
-      - interface/PromoterSetSigAPI.md
+      - BindingAPI: interface/BindingAPI.md
+      - BindingConcatenatedAPI: interface/BindingConcatenatedAPI.md
+      - CallingCardsBackgroundAPI: interface/CallingCardsBackgroundAPI.md
+      - ExpressionAPI: interface/ExpressionAPI.md
+      - PromoterSetAPI: interface/PromoterSetAPI.md
+      - PromoterSetSigAPI: interface/PromoterSetSigAPI.md
     - Developer Classes:
       - interface/AbstractAPI.md
       - interface/AbstractRecordsAndFilesAPI.md

yeastdnnexplorer/interface/AbstractRecordsAndFilesAPI.py

@@ -136,6 +136,9 @@ async def read(
         :param retrieve_files: Boolean. Whether to retrieve the files associated with
             the records. Defaults to False.
         :type retrieve_files: bool
+        :param kwargs: The following kwargs are used by the read() function. Any
+            others are passed onto the callback function
+            - timeout: The timeout for the GET request. Defaults to 120.
 
         :return: The result of the callback function.
         :rtype: Any
@@ -157,7 +160,8 @@ async def read(
         export_url = f"{self.url.rstrip('/')}/{self.export_url_suffix}"
         self.logger.debug("read() export_url: %s", export_url)
 
-        async with aiohttp.ClientSession() as session:
+        timeout = aiohttp.ClientTimeout(kwargs.pop("timeout", 120))
+        async with aiohttp.ClientSession(timeout=timeout) as session:
             try:
                 async with session.get(
                     export_url, headers=self.header, params=self.params

yeastdnnexplorer/interface/AbstractRecordsOnlyAPI.py

@@ -43,8 +43,9 @@ async def read(
             include `metadata`, `data`, and `cache` as parameters.
         :param export_url_suffix: The URL suffix for the export endpoint. This will
             return a response object with a csv file.
-        :param kwargs: Additional arguments to pass to the callback function.
-        :return: The result of the callback function.
+        :param kwargs: This can be used to pass "params" to the request to use in place
+            of `self.params`. If those are passed, they will be popped off and then
+            the remaining kwargs will be passed to the callback function
 
         """
         if not callable(callback) or {"metadata", "data", "cache"} - set(
@@ -66,7 +67,7 @@ async def read(
                 async with session.get(
                     export_url,
                     headers=self.header,
-                    params=self.params,
+                    params=kwargs.pop("params", self.params),
                 ) as response:
                     response.raise_for_status()
                     content = await response.content.read()

yeastdnnexplorer/interface/BindingConcatenatedAPI.py

@@ -0,0 +1,62 @@
+import os
+from typing import Any
+
+import pandas as pd
+
+from yeastdnnexplorer.interface.AbstractRecordsAndFilesAPI import (
+    AbstractRecordsAndFilesAPI,
+)
+
+
+class BindingConcatenatedAPI(AbstractRecordsAndFilesAPI):
+    """Class to interact with the BindingConcatenatedAPI endpoint."""
+
+    def __init__(self, **kwargs) -> None:
+        """
+        Initialize the BindingConcatenatedAPI object.
+
+        :param kwargs: parameters to pass through AbstractRecordsAndFilesAPI to
+            AbstractAPI.
+
+        """
+        valid_param_keys = kwargs.pop(
+            "valid_param_keys",
+            [
+                "id",
+                "regulator",
+                "regulator_locus_tag",
+                "regulator_symbol",
+                "batch",
+                "replicate",
+                "source",
+                "strain",
+                "condition",
+                "lab",
+                "assay",
+                "workflow",
+                "data_usable",
+            ],
+        )
+
+        url = kwargs.pop("url", os.getenv("BINDINGCONCATENATED_URL", None))
+
+        super().__init__(url=url, valid_keys=valid_param_keys, **kwargs)
+
+    def create(self, data: dict[str, Any], **kwargs) -> Any:
+        raise NotImplementedError("The BindingConcatenatedAPI does not support create.")
+
+    def update(self, df: pd.DataFrame, **kwargs) -> Any:
+        raise NotImplementedError("The BindingConcatenatedAPI does not support update.")
+
+    def delete(self, id: str, **kwargs) -> Any:
+        raise NotImplementedError("The BindingConcatenatedAPI does not support delete.")
+
+    def submit(self, post_dict: dict[str, Any], **kwargs) -> Any:
+        raise NotImplementedError("The BindingConcatenatedAPI does not support submit.")
+
+    def retrieve(
+        self, group_task_id: str, timeout: int, polling_interval: int, **kwargs
+    ) -> Any:
+        raise NotImplementedError(
+            "The BindingConcatenatedAPI does not support retrieve."
+        )