0.1.15

GetPhenopackets.ipynb

@@ -628,7 +628,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "We found 390 cohorts\n",
+      "We found 391 cohorts\n",
       "Wrote phenopacket collection MarkDown file to docs/collections.md\n"
      ]
     }

docs/collections.md

@@ -251,6 +251,7 @@ Phenopacket store is a repository of [GA4GH phenopackets](https://pubmed.ncbi.nl
 |[WFS1](notebooks/WFS1/WFS1_Wolfram_syndrome_1_individuals.ipynb){:target="_blank"}|10 Phenopackets;[Wolfram syndrome 1](https://omim.org/entry/222300){:target="_blank"}|
 |[COL11A1](notebooks/COL11A1/COL11A1_STL2_individuals.ipynb){:target="_blank"}|2 Phenopackets;[Stickler syndrome, type II](https://omim.org/entry/604841){:target="_blank"}|
 |[SP7](notebooks/SP7/SP7_OI12_individuals.ipynb){:target="_blank"}|1 Phenopackets;[Osteogenesis imperfecta, type XII](https://omim.org/entry/613849){:target="_blank"}|
+|[DOCK11](notebooks/DOCK11/DOCK11_ADMIDX_individuals.ipynb){:target="_blank"}|12 Phenopackets;[Autoinflammatory disease, multisystem, with immune dysregulation, X-linked](https://omim.org/entry/301109){:target="_blank"}|
 |[TBX1](notebooks/TBX1/TBX1_Yagi_2003.ipynb){:target="_blank"}|5 Phenopackets;[DiGeorge syndrome](https://omim.org/entry/188400){:target="_blank"}|
 |[KCNT1](notebooks/KCNT1/KCNT1_DEE14_individuals.ipynb){:target="_blank"}|8 Phenopackets;[Developmental and epileptic encephalopathy 14](https://omim.org/entry/614959){:target="_blank"}|
 |[SKIC3](notebooks/SKIC3/SKIC3_THES1_individuals.ipynb){:target="_blank"}|2 Phenopackets;[Trichohepatoenteric syndrome 1](https://omim.org/entry/222470){:target="_blank"}|

src/ppktstore/stats/_ppkt_store_stats.py

@@ -41,6 +41,7 @@ def get_cohort_to_phenopacket_d(self):
 
     def _extract_all_phenopackets_df(self) -> pd.DataFrame:
         all_ppkt = None
+        column_names = ['disease', 'disease_id', 'patient_id', 'gene', 'allele_1', 'allele_2', 'PMID', 'cohort', 'filename']
         for info in self._archive.infolist():
             if info.is_dir():
                 continue
@@ -58,11 +59,11 @@ def _extract_all_phenopackets_df(self) -> pd.DataFrame:
                     continue
                 L = line.decode("utf-8")
                 fields = L.strip().split("\t")
-                if len(fields) != 8:
+                if len(fields) != len(column_names):
                     raise ValueError(f"Malformed line with {len(fields)} fields: {L}")
                 list_of_lists.append(fields)
-        columns = ['disease', 'disease_id', 'patient_id', 'gene', 'allele_1', 'allele_2', 'PMID','filename']
-        return pd.DataFrame(data=list_of_lists, columns=columns)
+
+        return pd.DataFrame(data=list_of_lists, columns=column_names)
 
     def _extract_all_cohort_phenopackets(self) -> typing.Dict:
         cohort_to_ppkt_d = defaultdict(list)