update core Data with number of random amino acids in PSPA

sky1ove · May 13, 2024 · 02387dc · 02387dc
1 parent c615cc1
commit 02387dc
Show file tree

Hide file tree

Showing 2 changed files with 36 additions and 6 deletions.
diff --git a/katlas/core.py b/katlas/core.py
@@ -99,6 +99,10 @@ class Data:
     # scoring via PSPA (all capital)
     OCHOA_PSPA_SCORE_URL = "https://github.com/sky1ove/katlas/raw/main/dataset/ochoa_pspa_score.parquet"
 
+    # PSPA number of random amino acids
+    PSPA_NUM_RANDOM_URL = "https://github.com/sky1ove/katlas/raw/main/dataset/pspa_divide_num.csv"
+
+
 
     @staticmethod
     def _fetch_data(url):
@@ -278,6 +282,17 @@ def get_combine_site_pplus_ochoa():
         #Convert the number in the column name into integer
         df.columns = [int(col) if col.lstrip('-').isdigit() else col for col in df.columns]
         return df
+
+
+    @staticmethod
+    def get_num_dict():
+        """
+        Fetches the data from the given URL and returns a DataFrame
+        """
+        num = pd.read_csv(Data.PSPA_NUM_RANDOM_URL)
+        num_dict = num.set_index('kinase')['num_random_aa'].to_dict()
+
+        return num_dict
 
 # %% ../nbs/00_core.ipynb 15
 class CPTAC:

diff --git a/nbs/00_core.ipynb b/nbs/00_core.ipynb
@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -27,7 +27,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -160,6 +160,10 @@
     "    # scoring via PSPA (all capital)\n",
     "    OCHOA_PSPA_SCORE_URL = \"https://github.com/sky1ove/katlas/raw/main/dataset/ochoa_pspa_score.parquet\"\n",
     "\n",
+    "    # PSPA number of random amino acids\n",
+    "    PSPA_NUM_RANDOM_URL = \"https://github.com/sky1ove/katlas/raw/main/dataset/pspa_divide_num.csv\"\n",
+    "    \n",
+    "\n",
     "    \n",
     "    @staticmethod\n",
     "    def _fetch_data(url):\n",
@@ -338,7 +342,18 @@
     "        \n",
     "        #Convert the number in the column name into integer\n",
     "        df.columns = [int(col) if col.lstrip('-').isdigit() else col for col in df.columns]\n",
-    "        return df"
+    "        return df\n",
+    "    \n",
+    "    \n",
+    "    @staticmethod\n",
+    "    def get_num_dict():\n",
+    "        \"\"\"\n",
+    "        Fetches the data from the given URL and returns a DataFrame\n",
+    "        \"\"\"\n",
+    "        num = pd.read_csv(Data.PSPA_NUM_RANDOM_URL)\n",
+    "        num_dict = num.set_index('kinase')['num_random_aa'].to_dict()\n",
+    "\n",
+    "        return num_dict"
    ]
   },
   {
@@ -4686,7 +4701,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [