Feature/fs selection

src/api_service/migrations/0061_alter_experiment_shared_users.py

@@ -0,0 +1,20 @@
+# Generated by Django 4.2.15 on 2024-10-23 13:51
+
+from django.conf import settings
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+        ('api_service', '0060_experiment_shared_users'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='experiment',
+            name='shared_users',
+            field=models.ManyToManyField(blank=True, related_name='shared_users_correlation_analysis', to=settings.AUTH_USER_MODEL),
+        ),
+    ]

src/api_service/mrna_service.py

@@ -13,10 +13,28 @@ class MRNAService(object):
 
     def __init__(self):
         modulector_settings = settings.MODULECTOR_SETTINGS
-        self.url_modulector_prefix = f"http://{modulector_settings['host']}:{modulector_settings['port']}"
+        self.url_modulector_prefix = self.__build_url(modulector_settings)
 
         bioapi_settings = settings.BIOAPI_SETTINGS
-        self.url_bioapi_prefix = f"http://{bioapi_settings['host']}:{bioapi_settings['port']}"
+        self.url_bioapi_prefix = self.__build_url(bioapi_settings)
+
+    @staticmethod
+    def __build_url(settings: Dict[str, Any]) -> str:
+        """
+        Constructs the URL based on the settings provided.
+        If the port is the default for the protocol (80 for http, 443 for https), it is omitted.
+        Otherwise, the port is included in the URL.
+        @param settings: Dictionary containing protocol, host, and port information.
+        @return: Constructed URL as a string.
+        """
+        protocol = settings['protocol']
+        host = settings['host']
+        port = settings['port']
+
+        if (protocol == 'http' and port == 80) or (protocol == 'https' and port == 443):
+            return f"{protocol}://{host}"
+        else:
+            return f"{protocol}://{host}:{port}"
 
     @staticmethod
     def __generate_rest_query_params(get_request: QueryDict) -> str:

src/feature_selection/fs_algorithms_spark.py

@@ -32,6 +32,8 @@ def __get_clustering_algorithm_value(cluster_algorithm: ClusteringAlgorithm) ->
     """Gets the corresponding string value for the parameter 'clustering-algorithm' of the EMR integration."""
     if cluster_algorithm == ClusteringAlgorithm.SPECTRAL:
         return 'spectral'
+    if cluster_algorithm == ClusteringAlgorithm.BK_MEANS:
+        return 'bk_means'
     return 'k_means'  # Default is kmeans
 
 

src/feature_selection/fs_models.py

@@ -1,6 +1,6 @@
 from typing import Literal, Union, Optional
 from django.conf import settings
-from sklearn.cluster import KMeans, SpectralClustering
+from sklearn.cluster import KMeans, SpectralClustering, BisectingKMeans
 from sksurv.ensemble import RandomSurvivalForest
 from sksurv.svm import FastKernelSurvivalSVM
 from .models import ClusteringAlgorithm
@@ -12,7 +12,7 @@
 SVMOptimizerOptions = Literal["avltree", "rbtree"]
 
 # Available models for clustering
-ClusteringModels = Union[KMeans, SpectralClustering]
+ClusteringModels = Union[KMeans, SpectralClustering, BisectingKMeans]
 
 
 def get_clustering_model(clustering_algorithm: ClusteringAlgorithm,
@@ -28,6 +28,8 @@ def get_clustering_model(clustering_algorithm: ClusteringAlgorithm,
         return KMeans(n_clusters=number_of_clusters, random_state=random_state, n_init='auto')
     elif clustering_algorithm == ClusteringAlgorithm.SPECTRAL:
         return SpectralClustering(n_clusters=number_of_clusters, random_state=random_state)
+    elif clustering_algorithm == ClusteringAlgorithm.BK_MEANS:
+        return BisectingKMeans(n_clusters=number_of_clusters, random_state=random_state)
 
     raise Exception(f'Invalid clustering_algorithm parameter: {clustering_algorithm}')
 

src/feature_selection/migrations/0056_alter_clusteringparameters_algorithm_and_more.py

@@ -0,0 +1,23 @@
+# Generated by Django 4.2.15 on 2024-10-23 13:51
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('feature_selection', '0055_alter_fsexperiment_app_name_and_more'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='clusteringparameters',
+            name='algorithm',
+            field=models.IntegerField(choices=[(1, 'K Means'), (2, 'Spectral'), (3, 'Bk Means')], default=1),
+        ),
+        migrations.AlterField(
+            model_name='clusteringtimesrecord',
+            name='algorithm',
+            field=models.IntegerField(choices=[(1, 'K Means'), (2, 'Spectral'), (3, 'Bk Means')]),
+        ),
+    ]

src/feature_selection/models.py

@@ -33,6 +33,7 @@ class ClusteringAlgorithm(models.IntegerChoices):
     """Clustering algorithm."""
     K_MEANS = 1
     SPECTRAL = 2  # TODO: implement in backend
+    BK_MEANS = 3
 
 
 class ClusteringMetric(models.IntegerChoices):

src/feature_selection/views.py

@@ -209,7 +209,13 @@ def __get_clustering_parameters_columns(row: pd.Series) -> Tuple[int, Clustering
         parameters_desc = row['parameters']
         params = parameters_desc.split('_')
         number_of_clusters, algorithm_description, scoring_method = params[0], params[2], params[4]
-        algorithm = ClusteringAlgorithm.K_MEANS if algorithm_description == 'k-means' else ClusteringAlgorithm.SPECTRAL
+        # algorithm = ClusteringAlgorithm.K_MEANS if algorithm_description == 'k-means' else ClusteringAlgorithm.SPECTRAL
+        if algorithm_description == 'k-means':
+            algorithm = ClusteringAlgorithm.K_MEANS
+        elif algorithm_description == 'spectral':
+            algorithm = ClusteringAlgorithm.SPECTRAL
+        else:
+            algorithm = ClusteringAlgorithm.BK_MEANS
         scoring = ClusteringScoringMethod.C_INDEX if scoring_method == 'concordance-index' \
             else ClusteringScoringMethod.LOG_LIKELIHOOD
         return number_of_clusters, algorithm, scoring

src/frontend/static/frontend/src/components/biomarkers/labels/ClusteringAlgorithmLabel.tsx

@@ -28,6 +28,10 @@ export const ClusteringAlgorithmLabel = (props: ClusteringAlgorithmLabelProps) =
             color = 'blue'
             description = 'Spectral'
             break
+        case ClusteringAlgorithm.BK_MEANS:
+            color = 'blue'
+            description = 'Bisecting KMeans'
+            break
         default:
             color = 'blue'
             description = ''

src/frontend/static/frontend/src/components/biomarkers/types.ts

@@ -208,7 +208,8 @@ enum FitnessFunction {
 /** Clustering algorithm. */
 enum ClusteringAlgorithm {
     K_MEANS = 1,
-    SPECTRAL = 2
+    SPECTRAL = 2,
+    BK_MEANS = 3
 }
 
 /** Clustering metric to optimize. */

src/frontend/static/frontend/src/components/biomarkers/utils.ts

@@ -36,7 +36,8 @@ const SVMKernelOptions: DropdownItemProps[] = [
 /** Available options for a Clustering algorithm. */
 const clusteringAlgorithmOptions: DropdownItemProps[] = [
     { key: ClusteringAlgorithm.K_MEANS, text: 'K-Means', value: ClusteringAlgorithm.K_MEANS },
-    { key: ClusteringAlgorithm.SPECTRAL, text: 'Spectral', value: ClusteringAlgorithm.SPECTRAL }
+    { key: ClusteringAlgorithm.SPECTRAL, text: 'Spectral', value: ClusteringAlgorithm.SPECTRAL },
+    { key: ClusteringAlgorithm.BK_MEANS, text: 'BK-Means', value: ClusteringAlgorithm.BK_MEANS }
 ]
 
 /** Available options for a Clustering metric to optimize. */

src/multiomics_intermediate/settings.py

@@ -299,14 +299,16 @@
 
 # Modulector settings
 MODULECTOR_SETTINGS = {
-    'host': os.getenv('MODULECTOR_HOST', '127.0.0.1'),
-    'port': os.getenv('MODULECTOR_PORT', '8001')
+    'host': os.getenv('MODULECTOR_HOST', 'modulector.multiomix.org'),
+    'port': os.getenv('MODULECTOR_PORT', 443),
+    'protocol': os.getenv('BIOAPI_PROTOCOL', 'https')
 }
 
 # BioAPI settings
 BIOAPI_SETTINGS = {
-    'host': os.getenv('BIOAPI_HOST', '127.0.0.1'),
-    'port': os.getenv('BIOAPI_PORT', '8002')
+    'host': os.getenv('BIOAPI_HOST', 'bioapi.multiomix.org'),
+    'port': os.getenv('BIOAPI_PORT', 443),
+    'protocol': os.getenv('BIOAPI_PROTOCOL', 'https')
 }
 
 # Multiomix-aws-emr