The tf_class and tf_family in Bio.motifs.jaspar.db should be string array

Author: asntech

docs/changelog.rst

@@ -2,8 +2,8 @@
 Changelog
 =========
 
-Version 1.0.0
+Version 1.6.0
 -------------
-Released date:
+Released date: July 02, 2021
 
-Notes: 
+Notes: Both tf_family and tf_class are now string array.

docs/conf.py

@@ -22,7 +22,7 @@
 author = 'Aziz Khan'
 
 # The full version, including alpha/beta/rc tags
-release = 'v1.5.5'
+release = 'v1.6.0'
 
 
 # -- General configuration ---------------------------------------------------

docs/how_to_use.rst

@@ -67,8 +67,8 @@ Printing the motif will all the associated meta-information stored in the JASPAR
     	TF name	YY1
 	Matrix ID	MA0095.2
 	Collection	CORE
-	TF class	C2H2 zinc finger factors
-	TF family	More than 3 adjacent zinc finger factors
+	TF class	['C2H2 zinc finger factors']
+	TF family	['More than 3 adjacent zinc finger factors']
 	Species	9606
 	Taxonomic group	vertebrates
 	Accession	['P25490']
@@ -108,8 +108,8 @@ You can use the `fetch_motifs_by_name` function to find motifs by TF name. This
     	TF name	CTCF
 	Matrix ID	MA0139.1
 	Collection	CORE
-	TF class	C2H2 zinc finger factors
-	TF family	More than 3 adjacent zinc finger factors
+	TF class	['C2H2 zinc finger factors'
+	TF family	['More than 3 adjacent zinc finger factors']
 	Species	9606
 	Taxonomic group	vertebrates
 	Accession	['P49711']
@@ -126,8 +126,8 @@ You can use the `fetch_motifs_by_name` function to find motifs by TF name. This
 	TF name	CTCF
 	Matrix ID	MA0531.1
 	Collection	CORE
-	TF class	C2H2 zinc finger factors
-	TF family	More than 3 adjacent zinc finger factors
+	TF class	['C2H2 zinc finger factors']
+	TF family	['More than 3 adjacent zinc finger factors']
 	Species	7227
 	Taxonomic group	insects
 	Accession	['Q9VS55']

pyjaspar/__init__.py

@@ -17,8 +17,8 @@
     TF name YY1
     Matrix ID   MA0095.2
     Collection  CORE
-    TF class    C2H2 zinc finger factors
-    TF family   More than 3 adjacent zinc finger factors
+    TF class    ['C2H2 zinc finger factors']
+    TF family   ['More than 3 adjacent zinc finger factors']
     Species 9606
     Taxonomic group vertebrates
     Accession   ['P25490']
@@ -42,7 +42,7 @@
         for motif in motifs:
             pass # do something with the motif
 """
-__version__ = '1.5.5'
+__version__ = '1.6.0'
 
 
 import warnings
@@ -400,14 +400,18 @@ def _fetch_motif_by_internal_id(self, int_id):
 
         # fetch remaining annotation as tags from the ANNOTATION table
         cur.execute("select TAG, VAL from MATRIX_ANNOTATION where id = ?", (int_id,))
+
+        #Since jaspar 2018 tf_family and tf_class are return as array
+        tf_family = []
+        tf_class = []
         rows = cur.fetchall()
         for row in rows:
             attr = row[0]
             val = row[1]
             if attr == "class":
-                motif.tf_class = val
+                tf_class.append(val)
             elif attr == "family":
-                motif.tf_family = val
+                tf_family.append(val)
             elif attr == "tax_group":
                 motif.tax_group = val
             elif attr == "type":
@@ -425,6 +429,9 @@ def _fetch_motif_by_internal_id(self, int_id):
                 """
                 pass
 
+        motif.tf_family = tf_family
+        motif.tf_class = tf_class
+
         return motif
 
     def _fetch_counts_matrix(self, int_id):

pyjaspar_notebook.ipynb

@@ -33,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -49,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 3,
    "metadata": {
     "scrolled": true
    },
@@ -75,7 +75,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -130,7 +130,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "motif = jdb_obj.fetch_motif_by_id('MA0095.2')"
+    "motif = jdb_obj.fetch_motif_by_id('MA0006.1')"
    ]
   },
   {
@@ -142,29 +142,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "TF name\tYY1\n",
-      "Matrix ID\tMA0095.2\n",
+      "TF name\tAhr::Arnt\n",
+      "Matrix ID\tMA0006.1\n",
       "Collection\tCORE\n",
-      "TF class\tC2H2 zinc finger factors\n",
-      "TF family\tMore than 3 adjacent zinc finger factors\n",
-      "Species\t9606\n",
+      "TF class\t['Basic helix-loop-helix factors (bHLH)', 'Basic helix-loop-helix factors (bHLH)']\n",
+      "TF family\t['PAS domain factors', 'PAS domain factors']\n",
+      "Species\t10090\n",
       "Taxonomic group\tvertebrates\n",
-      "Accession\t['P25490']\n",
-      "Data type used\tChIP-seq\n",
-      "Medline\t18950698\n",
+      "Accession\t['P30561', 'P53762']\n",
+      "Data type used\tSELEX\n",
+      "Medline\t7592839\n",
+      "Comments\tdimer\n",
       "Matrix:\n",
-      "        0      1      2      3      4      5      6      7      8      9     10     11\n",
-      "A: 1126.00 6975.00 6741.00 2506.00 7171.00   0.00  11.00  13.00 812.00 867.00 899.00 1332.00\n",
-      "C: 4583.00   0.00  99.00 1117.00   0.00  12.00   0.00   0.00 5637.00 1681.00 875.00 4568.00\n",
-      "G: 801.00 181.00 268.00 3282.00   0.00   0.00 7160.00 7158.00  38.00 2765.00 4655.00 391.00\n",
-      "T: 661.00  15.00  63.00 266.00   0.00 7159.00   0.00   0.00 684.00 1858.00 742.00 880.00\n",
+      "        0      1      2      3      4      5\n",
+      "A:   3.00   0.00   0.00   0.00   0.00   0.00\n",
+      "C:   8.00   0.00  23.00   0.00   0.00   0.00\n",
+      "G:   2.00  23.00   0.00  23.00   0.00  24.00\n",
+      "T:  11.00   1.00   1.00   1.00  24.00   0.00\n",
       "\n",
       "\n",
       "\n"