scout-browser 4.90.1__py3-none-any.whl → 4.91__py3-none-any.whl

scout/demo/panelapp_panel.json

@@ -0,0 +1,463 @@
+{
+  "id": 522,
+  "hash_id": null,
+  "name": "Familial melanoma",
+  "disease_group": "",
+  "disease_sub_group": "",
+  "status": "public",
+  "version": "2.4",
+  "version_created": "2024-01-09T11:31:08.965539Z",
+  "relevant_disorders": [
+    "R254"
+  ],
+  "stats": {
+    "number_of_genes": 8,
+    "number_of_strs": 0,
+    "number_of_regions": 0
+  },
+  "types": [
+    {
+      "name": "GMS Rare Disease",
+      "slug": "gms-rare-disease",
+      "description": "This panel type is used for GMS panels that are not virtual (i.e. could be a wet lab test)"
+    },
+    {
+      "name": "GMS signed-off",
+      "slug": "gms-signed-off",
+      "description": "This panel has undergone review by a NHSE GMS disease specialist group and processes to be signed-off for use within the GMS."
+    }
+  ],
+  "genes": [
+    {
+      "gene_data": {
+        "alias": [
+          "hucep-6",
+          "KIAA0272",
+          "UCHL2"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:950",
+        "gene_name": "BRCA1 associated protein 1",
+        "omim_gene": [
+          "603089"
+        ],
+        "alias_name": [
+          "ubiquitin carboxy-terminal hydrolase"
+        ],
+        "gene_symbol": "BAP1",
+        "hgnc_symbol": "BAP1",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "3:52435029-52444366",
+              "ensembl_id": "ENSG00000163930"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "3:52401013-52410350",
+              "ensembl_id": "ENSG00000163930"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "1998-09-17"
+      },
+      "entity_type": "gene",
+      "entity_name": "BAP1",
+      "confidence_level": "3",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [],
+      "evidence": [
+        "Expert Review Green",
+        "NHS GMS",
+        "Expert List"
+      ],
+      "phenotypes": [
+        "Tumor predisposition syndrome 1, OMIM:614327",
+        "{Uveal melanoma, susceptibility to, 2}, OMIM:606661"
+      ],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "PSK-J3"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:1773",
+        "gene_name": "cyclin dependent kinase 4",
+        "omim_gene": [
+          "123829"
+        ],
+        "alias_name": null,
+        "gene_symbol": "CDK4",
+        "hgnc_symbol": "CDK4",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "12:58141510-58149796",
+              "ensembl_id": "ENSG00000135446"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "12:57747727-57756013",
+              "ensembl_id": "ENSG00000135446"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "1993-07-28"
+      },
+      "entity_type": "gene",
+      "entity_name": "CDK4",
+      "confidence_level": "3",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [],
+      "evidence": [
+        "Expert Review Green",
+        "NHS GMS",
+        "Expert List"
+      ],
+      "phenotypes": [],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "CDK4I",
+          "p16",
+          "INK4a",
+          "MTS1",
+          "CMM2",
+          "ARF",
+          "p19",
+          "p14",
+          "INK4",
+          "p16INK4a",
+          "p19Arf",
+          "p14ARF"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:1787",
+        "gene_name": "cyclin dependent kinase inhibitor 2A",
+        "omim_gene": [
+          "600160"
+        ],
+        "alias_name": null,
+        "gene_symbol": "CDKN2A",
+        "hgnc_symbol": "CDKN2A",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "9:21967751-21995300",
+              "ensembl_id": "ENSG00000147889"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "9:21967753-21995301",
+              "ensembl_id": "ENSG00000147889"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "1994-05-19"
+      },
+      "entity_type": "gene",
+      "entity_name": "CDKN2A",
+      "confidence_level": "3",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [],
+      "evidence": [
+        "Expert Review Green",
+        "NHS GMS",
+        "Expert List"
+      ],
+      "phenotypes": [
+        "{Melanoma, cutaneous malignant, 2}, OMIM:155601",
+        "{Melanoma and neural system tumor syndrome}, OMIM:155755",
+        "{Melanoma-pancreatic cancer syndrome}, OMIM:606719"
+      ],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "hPot1",
+          "DKFZp586D211"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:17284",
+        "gene_name": "protection of telomeres 1",
+        "omim_gene": [
+          "606478"
+        ],
+        "alias_name": null,
+        "gene_symbol": "POT1",
+        "hgnc_symbol": "POT1",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "7:124462440-124570037",
+              "ensembl_id": "ENSG00000128513"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "7:124822386-124929983",
+              "ensembl_id": "ENSG00000128513"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "2004-08-20"
+      },
+      "entity_type": "gene",
+      "entity_name": "POT1",
+      "confidence_level": "3",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [
+        "24686849",
+        "24686846",
+        "29523635",
+        "30451293",
+        "30586141",
+        "32325837",
+        "32907878"
+      ],
+      "evidence": [
+        "Expert Review Green",
+        "NHS GMS",
+        "Expert List"
+      ],
+      "phenotypes": [
+        "Melanoma, cutaneous malignant, susceptibility to, 10, OMIM:615848"
+      ],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "Ptop",
+          "Pip1",
+          "Tpp1",
+          "Tint1"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:25070",
+        "gene_name": "ACD, shelterin complex subunit and telomerase recruitment factor",
+        "omim_gene": [
+          "609377"
+        ],
+        "alias_name": [
+          "TIN2 interacting protein 1",
+          "POT1 and TIN2 organizing protein"
+        ],
+        "gene_symbol": "ACD",
+        "hgnc_symbol": "ACD",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "16:67691415-67694713",
+              "ensembl_id": "ENSG00000102977"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "16:67657512-67660815",
+              "ensembl_id": "ENSG00000102977"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "2005-01-04"
+      },
+      "entity_type": "gene",
+      "entity_name": "ACD",
+      "confidence_level": "2",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [],
+      "evidence": [
+        "Expert Review Amber",
+        "NHS GMS"
+      ],
+      "phenotypes": [],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "FAD",
+          "FAD1",
+          "BRCC2",
+          "XRCC11"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:1101",
+        "gene_name": "BRCA2, DNA repair associated",
+        "omim_gene": [
+          "600185"
+        ],
+        "alias_name": [
+          "BRCA1/BRCA2-containing complex, subunit 2"
+        ],
+        "gene_symbol": "BRCA2",
+        "hgnc_symbol": "BRCA2",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "13:32889611-32973805",
+              "ensembl_id": "ENSG00000139618"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "13:32315474-32400266",
+              "ensembl_id": "ENSG00000139618"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "1994-10-17"
+      },
+      "entity_type": "gene",
+      "entity_name": "BRCA2",
+      "confidence_level": "2",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [],
+      "evidence": [
+        "Expert Review Amber",
+        "NHS GMS"
+      ],
+      "phenotypes": [],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "RAP1"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:19246",
+        "gene_name": "TERF2 interacting protein",
+        "omim_gene": [
+          "605061"
+        ],
+        "alias_name": null,
+        "gene_symbol": "TERF2IP",
+        "hgnc_symbol": "TERF2IP",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "16:75681684-75795770",
+              "ensembl_id": "ENSG00000166848"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "16:75647786-75761872",
+              "ensembl_id": "ENSG00000166848"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "2002-09-18"
+      },
+      "entity_type": "gene",
+      "entity_name": "TERF2IP",
+      "confidence_level": "2",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [],
+      "evidence": [
+        "Expert Review Amber",
+        "NHS GMS"
+      ],
+      "phenotypes": [],
+      "mode_of_inheritance": "",
+      "tags": [],
+      "transcript": null
+    },
+    {
+      "gene_data": {
+        "alias": [
+          "TRT",
+          "TP2",
+          "TCS1",
+          "hEST2",
+          "EST2"
+        ],
+        "biotype": "protein_coding",
+        "hgnc_id": "HGNC:11730",
+        "gene_name": "telomerase reverse transcriptase",
+        "omim_gene": [
+          "187270"
+        ],
+        "alias_name": null,
+        "gene_symbol": "TERT",
+        "hgnc_symbol": "TERT",
+        "hgnc_release": "2017-11-03",
+        "ensembl_genes": {
+          "GRch37": {
+            "82": {
+              "location": "5:1253262-1295184",
+              "ensembl_id": "ENSG00000164362"
+            }
+          },
+          "GRch38": {
+            "90": {
+              "location": "5:1253147-1295069",
+              "ensembl_id": "ENSG00000164362"
+            }
+          }
+        },
+        "hgnc_date_symbol_changed": "1998-01-21"
+      },
+      "entity_type": "gene",
+      "entity_name": "TERT",
+      "confidence_level": "2",
+      "penetrance": null,
+      "mode_of_pathogenicity": "",
+      "publications": [
+        "23348503",
+        "23348506",
+        "35912549"
+      ],
+      "evidence": [
+        "Expert Review Amber",
+        "NHS GMS",
+        "Expert List"
+      ],
+      "phenotypes": [
+        "{Melanoma, cutaneous malignant, 9}, OMIM:615134"
+      ],
+      "mode_of_inheritance": "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown",
+      "tags": [
+        "watchlist"
+      ],
+      "transcript": null
+    }
+  ],
+  "strs": [],
+  "regions": []
+}

scout/demo/panelapp_panels_reduced.json

@@ -0,0 +1,37 @@
+{
+  "count": 1,
+  "next": null,
+  "previous": null,
+  "results": [
+    {
+		"id": 522,
+		"hash_id": null,
+		"name": "Familial melanoma",
+		"disease_group": "",
+		"disease_sub_group": "",
+		"status": "public",
+		"version": "2.4",
+		"version_created": "2024-01-09T11:31:08.965539Z",
+		"relevant_disorders": [
+			"R254"
+		],
+		"stats": {
+			"number_of_genes": 8,
+			"number_of_strs": 0,
+			"number_of_regions": 0
+		},
+		"types": [
+			{
+				"name": "GMS Rare Disease",
+				"slug": "gms-rare-disease",
+				"description": "This panel type is used for GMS panels that are not virtual (i.e. could be a wet lab test)"
+			},
+			{
+				"name": "GMS signed-off",
+				"slug": "gms-signed-off",
+				"description": "This panel has undergone review by a NHSE GMS disease specialist group and processes to be signed-off for use within the GMS."
+			}
+		]
+	}
+  ]
+}

scout/load/panel.py

@@ -5,20 +5,15 @@ functions to load panels into the database
 """
 
 import logging
-import math
-from datetime import datetime
-from typing import Dict, List
 
-from click import Abort
+from click import Abort, progressbar
 from flask.cli import current_app
 
-from scout.parse.panel import get_panel_info, parse_gene_panel, parse_panel_app_panel
+from scout.parse.panel import get_panel_info, parse_gene_panel
 from scout.utils.handle import get_file_handle
-from scout.utils.scout_requests import fetch_mim_files, fetch_resource
+from scout.utils.scout_requests import fetch_mim_files
 
 LOG = logging.getLogger(__name__)
-PANELAPP_BASE_URL = "https://panelapp.genomicsengland.co.uk/WebServices/{0}/"
-PANEL_NAME = "PANELAPP-GREEN"
 
 
 def load_panel(panel_path, adapter, **kwargs):
@@ -111,140 +106,6 @@ def load_panel(panel_path, adapter, **kwargs):
         raise err
 
 
-def _panelapp_panel_ids() -> List[str]:
-    """Fetch all PanelApp panel IDs"""
-    json_lines = fetch_resource(PANELAPP_BASE_URL.format("list_panels"), json=True)
-    return [panel_info["Panel_Id"] for panel_info in json_lines.get("result", [])]
-
-
-def _parse_panelapp_panel(
-    panel_id: str,
-    institute: str,
-    confidence: str,
-    ensembl_id_to_hgnc_id_map: Dict[str, int],
-    hgnc_symbol_to_ensembl_id_map: Dict[str, str],
-):
-    """fetch and parse lines from a PanelApp panel, given its ID
-
-    Args:
-        adapter(scout.adapter.MongoAdapter)
-        panel_id(str): The panel app panel id
-        confidence(str enum green|amber|red): traffic light-style PanelApp level of confidence
-        ensembl_to_hgnc_map: dict[str, int]
-        hgnc_to_ensembl_map: [int, str]
-
-
-    Returns:
-        parsed_panel(dict). Example:
-            {'version': 3.3, 'date': datetime.datetime(2023, 1, 31, 16, 43, 37, 521719), 'display_name': 'Diabetes - neonatal onset - [GREEN]', 'institute': 'cust000', 'panel_type': 'clinical', 'genes': [list of genes], 'panel_id': '55a9041e22c1fc6711b0c6c0'}
-
-    """
-    json_lines = fetch_resource(PANELAPP_BASE_URL.format("get_panel") + panel_id, json=True)
-    parsed_panel = parse_panel_app_panel(
-        panel_info=json_lines["result"],
-        ensembl_gene_hgnc_id_map=ensembl_id_to_hgnc_id_map,
-        hgnc_symbol_ensembl_gene_map=hgnc_symbol_to_ensembl_id_map,
-        institute=institute,
-        confidence=confidence,
-    )
-    if confidence != "green":
-        parsed_panel["panel_id"] = "_".join([panel_id, confidence])
-    else:  # This way the old green panels will be overwritten, instead of creating 2 sets of green panels, old and new
-        parsed_panel["panel_id"] = panel_id
-
-    return parsed_panel
-
-
-def load_panelapp_panel(adapter, panel_id=None, institute="cust000", confidence="green"):
-    """Load PanelApp panels into scout database
-
-    If no panel_id load all PanelApp panels
-
-    Args:
-        adapter(scout.adapter.MongoAdapter)
-        panel_id(str): The panel app panel id
-        institute(str): _id of an institute
-        confidence(str enum green|amber|red): traffic light-style PanelApp level of confidence
-    """
-    panel_ids = [panel_id]
-
-    if not panel_id:
-        LOG.info("Fetching all panel app panels")
-        panel_ids: List[str] = _panelapp_panel_ids()
-
-    ensembl_id_to_hgnc_id_map: Dict[str, int] = adapter.ensembl_to_hgnc_id_mapping()
-    hgnc_symbol_to_ensembl_id_map: Dict[int, str] = adapter.hgnc_symbol_ensembl_id_mapping()
-
-    for _ in panel_ids:
-        parsed_panel = _parse_panelapp_panel(
-            panel_id=_,
-            institute=institute,
-            confidence=confidence,
-            ensembl_id_to_hgnc_id_map=ensembl_id_to_hgnc_id_map,
-            hgnc_symbol_to_ensembl_id_map=hgnc_symbol_to_ensembl_id_map,
-        )
-
-        if len(parsed_panel["genes"]) == 0:
-            LOG.warning("Panel %s is missing genes. Skipping.", parsed_panel["display_name"])
-            continue
-
-        try:
-            adapter.load_panel(parsed_panel=parsed_panel, replace=True)
-        except Exception as err:
-            raise err
-
-
-def load_panelapp_green_panel(adapter, institute, force):
-    """Load/Update the panel containing all Panelapp Green genes
-
-    Args:
-        adapter(scout.adapter.MongoAdapter)
-        institute(str): _id of an institute
-        force(bool): force update panel even if it has fewer genes than previous version
-    """
-    LOG.info("Fetching all panel app panels")
-    panel_ids = _panelapp_panel_ids()
-
-    # check and set panel version
-    old_panel = adapter.gene_panel(panel_id=PANEL_NAME)
-    green_panel = {
-        "panel_name": PANEL_NAME,
-        "display_name": "PanelApp Green Genes",
-        "institute": institute,
-        "version": float(math.floor(old_panel["version"]) + 1) if old_panel else 1.0,
-        "date": datetime.now(),
-    }
-    genes = set()  # avoid duplicate genes from different panels
-    # Loop over all PanelApp panels
-
-    ensembl_id_to_hgnc_id_map: Dict[str, int] = adapter.ensembl_to_hgnc_id_mapping()
-    hgnc_symbol_to_ensembl_id_map: Dict[int, str] = adapter.hgnc_symbol_ensembl_id_mapping()
-
-    for _ in panel_ids:
-        # And collect their green genes
-        parsed_panel = _parse_panelapp_panel(
-            panel_id=_,
-            institute=institute,
-            confidence="green",
-            ensembl_id_to_hgnc_id_map=ensembl_id_to_hgnc_id_map,
-            hgnc_symbol_to_ensembl_id_map=hgnc_symbol_to_ensembl_id_map,
-        )
-        genes.update({(gene["hgnc_id"], gene["hgnc_symbol"]) for gene in parsed_panel.get("genes")})
-
-    green_panel["genes"] = [{"hgnc_id": tup[0], "hgnc_symbol": tup[1]} for tup in genes]
-
-    # Do not update panel if new version contains less genes and force flag is False
-    if old_panel and len(old_panel.get("genes", [])) > len(green_panel["genes"]):
-        LOG.warning(
-            f"This new version of PANELAPP-GREEN contains less genes (n={len(green_panel['genes'])}) than the previous one (n={len(old_panel['genes'])})"
-        )
-        if force is False:
-            LOG.error("Aborting. Please use the force flag -f to update the panel anyway")
-            return
-
-    adapter.load_panel(parsed_panel=green_panel, replace=True)
-
-
 def load_omim_panel(adapter, genemap2, mim2genes, api_key, institute):
     """Add OMIM panel to the database.
     Args: