Merge branch 'v5.0.0' of https://github.com/omics-datascience/multiomix…

… into fix/cgds_unlinkdataset

DEPLOYING.md

@@ -179,7 +179,7 @@ To integrate with [Modulector][modulector] and/or [BioAPI][bioapi] using `docker
                name: 'multiomix-network'
    ```
 3. The new versions of BioAPI and Modulector already come with service names suitable for integration with Multiomix. But **if you have any old version of those platforms**, change the Modulector and BioAPI configuration so that it does not conflict with the Multiomix configuration:
-   1. Rename all the services in the Modulector and BioAPI `docker-compose.yml` files with the suffix `_modulector` and `_bioapi`. And rename `web` service to `modulector` or `bioapi` respectively. **NOTE:** do not forget to rename the `depends_on` parameters, and the database connection parameters to point to the new services names.
+   1. Rename all the services in the Modulector and BioAPI `docker-compose.yml` files with the suffix `_modulector` and `_bioapi`. For example `mongo_bioapi`, `web_bioapi` and `nginx_bioapi` in the case of BioAPI. **NOTE:** do not forget to rename the `depends_on` parameters, and the database connection parameters to point to the new services names.
    2. Change the following block in the NGINX configuration files. In Modulector it's `config/nginx/conf.d/modulector.conf`, in BioAPI it's `/nginx/conf.d/default.conf`:
    ```
    # Old
@@ -191,7 +191,7 @@ To integrate with [Modulector][modulector] and/or [BioAPI][bioapi] using `docker
    # New
    upstream web {
      ip_hash;
-     server modulector:8000; # Or bioapi, dependening on which config file you're 
+     server web_modulector:8000; # Or web_bioapi, dependening on which config file you're editing
    }
    ```
 4. Set Multiomix parameters:

docker-compose_dist.yml

@@ -60,7 +60,7 @@ services:
 
     # Celery worker for correlation analysis
     correlation-analysis-worker:
-        image: omicsdatascience/multiomix:5.3.0-celery
+        image: omicsdatascience/multiomix:5.4.0-celery
         restart: 'always'
         depends_on:
             - db
@@ -77,7 +77,7 @@ services:
 
     # Celery worker for feature selection experiments
     fs-experiments-worker:
-        image: omicsdatascience/multiomix:5.3.0-celery
+        image: omicsdatascience/multiomix:5.4.0-celery
         restart: 'always'
         depends_on:
             - db
@@ -94,7 +94,7 @@ services:
 
     # Celery worker for statistical validations and trained models
     stats-worker:
-        image: omicsdatascience/multiomix:5.3.0-celery
+        image: omicsdatascience/multiomix:5.4.0-celery
         restart: 'always'
         depends_on:
             - db
@@ -111,7 +111,7 @@ services:
 
     # Celery worker for inference experiments
     inference-worker:
-        image: omicsdatascience/multiomix:5.3.0-celery
+        image: omicsdatascience/multiomix:5.4.0-celery
         restart: 'always'
         depends_on:
             - db
@@ -128,7 +128,7 @@ services:
 
     # Celery worker for sync CGDSStudies
     sync-datasets-worker:
-        image: omicsdatascience/multiomix:5.3.0-celery
+        image: omicsdatascience/multiomix:5.4.0-celery
         restart: 'always'
         depends_on:
             - db
@@ -145,7 +145,7 @@ services:
 
     # Django Backend Server
     multiomix:
-        image: omicsdatascience/multiomix:5.3.0
+        image: omicsdatascience/multiomix:5.4.0
         restart: 'always'
         # environment:
             # DJANGO_SETTINGS_MODULE: 'multiomics_intermediate.settings_prod'

src/biomarkers/models.py

@@ -60,6 +60,7 @@ class Biomarker(models.Model):
     cnas: QuerySet['CNAIdentifier']
     mirnas: QuerySet['MiRNAIdentifier']
     mrnas: QuerySet['MRNAIdentifier']
+
     name: str = models.CharField(max_length=300)
     description: Optional[str] = models.TextField(null=True, blank=True)
     tag: Optional[Tag] = models.ForeignKey(Tag, on_delete=models.SET_NULL, default=None, blank=True, null=True)

src/feature_selection/migrations/0055_alter_fsexperiment_app_name_and_more.py

@@ -0,0 +1,38 @@
+# Generated by Django 4.2.15 on 2024-10-03 21:02
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('feature_selection', '0054_alter_trainedmodel_state'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='fsexperiment',
+            name='app_name',
+            field=models.CharField(blank=True, help_text='Spark app name to get the results', max_length=100, null=True),
+        ),
+        migrations.AlterField(
+            model_name='fsexperiment',
+            name='attempt',
+            field=models.PositiveSmallIntegerField(default=0, help_text='Number of attempts to prevent a buggy experiment running forever'),
+        ),
+        migrations.AlterField(
+            model_name='fsexperiment',
+            name='emr_job_id',
+            field=models.CharField(blank=True, help_text='Job ID in the Spark cluster', max_length=100, null=True),
+        ),
+        migrations.AlterField(
+            model_name='fsexperiment',
+            name='execution_time',
+            field=models.PositiveIntegerField(default=0, help_text='Execution time in seconds'),
+        ),
+        migrations.AlterField(
+            model_name='fsexperiment',
+            name='task_id',
+            field=models.CharField(blank=True, help_text='Celery Task ID', max_length=100, null=True),
+        ),
+    ]

src/feature_selection/models.py

@@ -48,7 +48,7 @@ class ClusteringScoringMethod(models.IntegerChoices):
 
 
 class SVMKernel(models.IntegerChoices):
-    """SVM's kernel """
+    """SVM kernel """
     LINEAR = 1
     POLYNOMIAL = 2
     RBF = 3
@@ -102,10 +102,11 @@ class FSExperiment(models.Model):
     rf_times_records: QuerySet['RFTimesRecord']
     svm_times_records: QuerySet['SVMTimesRecord']
     best_model: 'TrainedModel'
+
     origin_biomarker = models.ForeignKey('biomarkers.Biomarker', on_delete=models.CASCADE,
                                          related_name='fs_experiments_as_origin')
     algorithm = models.IntegerField(choices=FeatureSelectionAlgorithm.choices)
-    execution_time = models.PositiveIntegerField(default=0)  # Execution time in seconds
+    execution_time = models.PositiveIntegerField(default=0, help_text='Execution time in seconds')
     created_biomarker = models.OneToOneField('biomarkers.Biomarker', on_delete=models.SET_NULL, null=True, blank=True,
                                              related_name='fs_experiment')
     user = models.ForeignKey(get_user_model(), on_delete=models.CASCADE)
@@ -122,14 +123,14 @@ class FSExperiment(models.Model):
     methylation_source = models.ForeignKey('api_service.ExperimentSource', on_delete=models.CASCADE, null=True,
                                            blank=True, related_name='fs_experiments_as_methylation')
 
-    task_id = models.CharField(max_length=100, blank=True, null=True)  # Celery Task ID
+    task_id = models.CharField(max_length=100, blank=True, null=True, help_text='Celery Task ID')
 
-    # Number of attempts to prevent a buggy experiment running forever
-    attempt = models.PositiveSmallIntegerField(default=0)
+    attempt = models.PositiveSmallIntegerField(default=0, help_text='Number of attempts to prevent a buggy experiment '
+                                                                    'running forever')
 
     # AWS-EMR fields
-    app_name = models.CharField(max_length=100, null=True, blank=True)  # Spark app name to get the results
-    emr_job_id = models.CharField(max_length=100, null=True, blank=True)  # Job ID in the Spark cluster
+    app_name = models.CharField(max_length=100, null=True, blank=True, help_text='Spark app name to get the results')
+    emr_job_id = models.CharField(max_length=100, null=True, blank=True, help_text='Job ID in the Spark cluster')
 
     def get_all_sources(self):
         """Returns a list with all the sources."""

src/multiomics_intermediate/settings.py

@@ -186,7 +186,7 @@
 # +++++ Custom settings +++++
 
 # Current Multiomix version
-VERSION: str = '5.3.0'
+VERSION: str = '5.4.0'
 
 # Default primary key field type
 # https://docs.djangoproject.com/en/4.0/ref/settings/#default-auto-field

src/statistical_properties/survival_functions.py

@@ -104,7 +104,7 @@ def generate_survival_groups_by_median_expression(
 def compute_c_index_and_log_likelihood(df: pd.DataFrame) -> Tuple[float, float]:
     """
     Computes the C-Index and the partial Log-Likelihood from a DataFrame.
-    @param df: Pandas DataFrame. IMPORTANT: has to have 3 colunms: 'E' (event), 'T' (time), and 'group' (group in which
+    @param df: Pandas DataFrame. IMPORTANT: has to have 3 columns: 'E' (event), 'T' (time), and 'group' (group in which
     the sample is).
     @return: A tuple with the C-Index and the partial Log-Likelihood.
     """

tools/k8s/multiomix-correlation-analysis-worker.yaml

@@ -36,7 +36,7 @@ spec:
       - name: logs-data
         emptyDir: {}
       containers:
-      - image: omicsdatascience/multiomix:5.1.2-celery
+      - image: omicsdatascience/multiomix:5.4.0-celery
         name: correlation-analysis-worker
         env:
         - name: QUEUE_NAME

tools/k8s/multiomix-fs-experiments-worker.yaml

@@ -36,7 +36,7 @@ spec:
       - name: logs-data
         emptyDir: {}
       containers:
-      - image: omicsdatascience/multiomix:5.1.2-celery
+      - image: omicsdatascience/multiomix:5.4.0-celery
         name: fs-experiments-worker
         env:
         - name: QUEUE_NAME

tools/k8s/multiomix-inference-worker.yaml

@@ -36,7 +36,7 @@ spec:
       - name: logs-data
         emptyDir: {}
       containers:
-      - image: omicsdatascience/multiomix:5.1.2-celery
+      - image: omicsdatascience/multiomix:5.4.0-celery
         name: inference-worker
         env:
         - name: QUEUE_NAME

tools/k8s/multiomix-stats-worker.yaml

@@ -36,7 +36,7 @@ spec:
       - name: logs-data
         emptyDir: {}
       containers:
-      - image: omicsdatascience/multiomix:5.1.2-celery
+      - image: omicsdatascience/multiomix:5.4.0-celery
         name: stats-worker
         env:
         - name: QUEUE_NAME

tools/k8s/multiomix-sync-datasets-worker.yaml

@@ -36,7 +36,7 @@ spec:
       - name: logs-data
         emptyDir: {}
       containers:
-      - image: omicsdatascience/multiomix:5.1.2-celery
+      - image: omicsdatascience/multiomix:5.4.0-celery
         name: sync-datasets-worker
         env:
         - name: QUEUE_NAME

tools/k8s/multiomix.yaml

@@ -126,7 +126,7 @@ spec:
           - key: "multiomics_intermediate.conf"
             path: "multiomics_intermediate.conf"          
       containers:
-      - image: omicsdatascience/multiomix:4.7.1
+      - image: omicsdatascience/multiomix:5.4.0
         name: multiomix
         env:
         - name: POSTGRES_USERNAME