From 2424d8855f8694b66ff0c64cbae8b0ad97e100e8 Mon Sep 17 00:00:00 2001
From: Chiara Rasi <rasi.chiara@gmail.com>
Date: Mon, 2 May 2022 08:17:38 +0200
Subject: [PATCH] Script to fix OMIM format for old cases (#3304)

* Script to fix OMIM format for old cases

* Added the --fix option

* Removed unused imports

* Same script as in test

Co-authored-by: Daniel Nilsson <daniel.k.nilsson@gmail.com>
---
 CHANGELOG.md                        |  1 +
 scout/models/case/case.py           | 10 +----
 scripts/convert_case_omim_format.py | 69 +++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+), 9 deletions(-)
 create mode 100644 scripts/convert_case_omim_format.py

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 24dab3a674..df716622b0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@ About changelog [here](https://keepachangelog.com/en/1.0.0/)
 - Rank score results now show the ranking range
 - cDNA and protein changes displayed on institute causatives pages
 - Optional SESSION_TIMEOUT_MINUTES configuration in app config files 
+- Script to convert old OMIM case format (list of integers) to new format (list of dictionaries)
 ### Changed
 - Verify user before redirecting to IGV alignments and sashimi plots
 - Build case IGV tracks starting from case and variant objects instead of passing all params in a form
diff --git a/scout/models/case/case.py b/scout/models/case/case.py
index 78097b86e5..a5b23890e4 100644
--- a/scout/models/case/case.py
+++ b/scout/models/case/case.py
@@ -1,16 +1,8 @@
 from __future__ import absolute_import
 
 import logging
-import os
 from datetime import datetime
 
-from scout.constants import ANALYSIS_TYPES
-from scout.models import PhenotypeTerm
-from scout.models.panel import GenePanel
-
-from . import STATUS
-from .individual import Individual
-
 logger = logging.getLogger(__name__)
 
 individual = dict(
@@ -59,7 +51,7 @@
     created_at=datetime,
     delivery_report=str,  # delivery report is a path to html file
     diagnosis_genes=list,  # List of references to genes
-    diagnosis_phenotypes=list,  # List of references to diseases
+    diagnosis_phenotypes=list,  # List of dictionaries with OMIM disease data
     display_name=str,  # required. This is the case name that will be shown in scout.
     dynamic_gene_list=list,  # List of genes
     gene_fusion_report=str,  # Path to the gene fusions report file
diff --git a/scripts/convert_case_omim_format.py b/scripts/convert_case_omim_format.py
new file mode 100644
index 0000000000..93c9b5df9c
--- /dev/null
+++ b/scripts/convert_case_omim_format.py
@@ -0,0 +1,69 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+
+import click
+from pymongo import MongoClient
+
+CASES_WITH_DIA = {
+    "diagnosis_phenotypes": {"$exists": True, "$ne": []}
+}  # MongoDB query to locate cases with any diagnosis
+
+SELECT_FIELDS = {
+    "owner": 1,
+    "display_name": 1,
+    "diagnosis_phenotypes": 1,
+}  # select only a few important fields using the query above
+
+
+@click.command()
+@click.option("--db-uri", required=True, help="mongodb://user:password@db_url:db_port")
+@click.option("--db-name", required=True, help="db name")
+@click.option("--fix", help="Use this flag to fix the OMIM format in old cases", is_flag=True)
+def omim_case_fix_format(db_uri, db_name, fix):
+    try:
+        client = MongoClient(db_uri)
+        db = client[db_name]
+        # test connection
+        click.echo("database connection info:{}".format(db))
+
+        cases_with_dia = list(db.case.find(CASES_WITH_DIA, SELECT_FIELDS))
+        click.echo(f"Total number of cases with diagnosis:{len(cases_with_dia)}")
+
+        # Display cases with old format of diagnosis (a list of integers)
+        cases_with_old_dia = [
+            case for case in cases_with_dia if isinstance(case["diagnosis_phenotypes"][0], int)
+        ]
+        click.echo(f"Total number of cases with old diagnosis format:{len(cases_with_old_dia)}")
+
+        for i, case in enumerate(cases_with_old_dia):
+            click.echo(f"n:{i}\t{case['owner']}\t{case['display_name']}")
+            old_dia = case["diagnosis_phenotypes"]
+            new_dia = []
+
+            for dia_nr in old_dia:
+                disease_term = db.disease_term.find_one({"disease_nr": dia_nr})
+                if disease_term is None:
+                    click.echo(f"Could not find a disease term with id:{dia_nr}")
+                    continue
+                new_dia.append(
+                    {
+                        "disease_nr": dia_nr,
+                        "disease_id": disease_term["disease_id"],
+                        "description": disease_term["description"],
+                    }
+                )
+
+            if fix is False:
+                new_dia = old_dia
+            else:
+                db.case.find_one_and_update(
+                    {"_id": case["_id"]}, {"$set": {"diagnosis_phenotypes": new_dia}}
+                )
+            click.echo(f"old dia:{old_dia}--->new dia:{new_dia}\n")
+
+    except Exception as err:
+        click.echo("Error {}".format(err))
+
+
+if __name__ == "__main__":
+    omim_case_fix_format()