Merge branch 'enhancement/add_decriptor_tutorial' into 'dev'

Enhancement/add decriptor tutorial See merge request cdd/QSPRpred!171
CDDLeiden · Feb 9, 2024 · 597f9c0 · 597f9c0
2 parents 9904fc4 + 5614c70
commit 597f9c0
Show file tree

Hide file tree

Showing 8 changed files with 1,806 additions and 59 deletions.
diff --git a/docs/cli_usage.rst b/docs/cli_usage.rst
@@ -14,10 +14,7 @@ e.g. the help message for the :code:`QSPRpred.data_CLI` script can be shown as f
 A simple command-line workflow to prepare your dataset and train QSPR models is given below (see :ref:`CLI Example`).
 
 If you want more control over the inputs and outputs or want to customize QSPRpred for your purpose,
-you can also use the Python API directly (see `source code <https://github.com/CDDLeiden/QSPRpred/tree/main/tutorials>`_).
-Here you can find a tutorial with a Jupyter notebook illustrating some common use cases in the project source code.
-Make sure to download the tutorial folder to follow the examples in this CLI tutorial.
-
+you can also use the Python API directly (see `tutorials <https://github.com/CDDLeiden/QSPRpred/tree/main/tutorials>`_).
 
 CLI Example
 ***********

diff --git a/docs/features.rst b/docs/features.rst
@@ -52,7 +52,7 @@ Overview of available features
                     * :class:`~qsprpred.data.descriptors.fingerprints.AtomPairFP`: AtomPairFP
                     * :class:`~qsprpred.data.descriptors.fingerprints.AvalonFP`: AvalonFP
                     * :class:`~qsprpred.data.descriptors.fingerprints.LayeredFP`: LayeredFP
-                    * :class:`~qsprpred.data.descriptors.fingerprints.MACCsFP`: MACCsFP
+                    * :class:`~qsprpred.data.descriptors.fingerprints.MaccsFP`: MaccsFP
                     * :class:`~qsprpred.data.descriptors.fingerprints.MorganFP`: MorganFP
                     * :class:`~qsprpred.data.descriptors.fingerprints.PatternFP`: PatternFP
                     * :class:`~qsprpred.data.descriptors.fingerprints.RDKitFP`: RDKitFP
@@ -161,7 +161,7 @@ Overview of available features
 
     .. dropdown:: Model Assessors
 
-        :class:`~qsprpred.models.assessment_methods.ModelAssessor`: Base class for model assessors.
+        :class:`~qsprpred.models.assessment.methods.ModelAssessor`: Base class for model assessors.
 
         Model assessors are used to assess the performance of models.
         More information be found in the `model assessment tutorial <https://github.com/CDDLeiden/QSPRpred/blob/main/tutorials/basics/modelling/model_assessment.ipynb>`_.
@@ -170,8 +170,8 @@ Overview of available features
 
             .. tab-item:: Core
 
-                * :class:`~qsprpred.models.assessment_methods.CrossValAssessor`: CrossValAssessor
-                * :class:`~qsprpred.models.assessment_methods.TestSetAssessor`: TestSetAssessor
+                * :class:`~qsprpred.models.assessment.methods.CrossValAssessor`: CrossValAssessor
+                * :class:`~qsprpred.models.assessment.methods.TestSetAssessor`: TestSetAssessor
 
     .. dropdown:: Hyperparameter Optimizers
 
@@ -209,3 +209,50 @@ Overview of available features
                     * :class:`~qsprpred.plotting.classification.MetricsPlot`: MetricsPlot
                     * :class:`~qsprpred.plotting.classification.ConfusionMatrixPlot`: ConfusionMatrixPlot
 
+    .. dropdown:: Monitors
+
+        * :class:`~qsprpred.models.monitors.FitMonitor`: Base class for monitoring model fitting
+        * :class:`~qsprpred.models.monitors.AssessorMonitor`: Base class for monitoring model assessment (subclass of :class:`~qsprpred.models.monitors.FitMonitor`)
+        * :class:`~qsprpred.models.monitors.HyperparameterOptimizationMonitor`: Base class for monitoring hyperparameter optimization (subclass of :class:`~qsprpred.models.monitors.AssessorMonitor`)
+
+        Monitors are used to monitor the training of models.
+        More information can be found in the `model monitoring tutorial <https://github.com/CDDLeiden/QSPRpred/blob/main/tutorials/advanced/modelling/monitoring.ipynb>`_.
+
+        .. tab-set::
+
+            .. tab-item:: Core
+
+                * :class:`~qsprpred.models.monitors.NullMonitor`: NullMonitor
+                * :class:`~qsprpred.models.monitors.ListMonitor`: ListMonitor
+                * :class:`~qsprpred.models.monitors.BaseMonitor`: BaseMonitor
+                    * :class:`~qsprpred.models.monitors.FileMonitor`: FileMonitor
+                    * :class:`~qsprpred.models.monitors.WandBMonitor`: WandBMonitor
+
+    .. dropdown:: Scaffolds
+
+        :class:`~qsprpred.data.chem.scaffolds.Scaffold`: Base class for scaffolds.
+
+        Class for calculating molecular scaffolds of different kinds
+
+        .. tab-set::
+
+            .. tab-item:: Core
+
+                * :class:`~qsprpred.data.chem.scaffolds.Murcko`: Murcko
+                * :class:`~qsprpred.data.chem.scaffolds.BemisMurcko`: BemisMurcko
+
+    .. dropdown:: Clustering
+
+        :class:`~qsprpred.data.chem.clustering.MoleculeClusters`: Base class for clustering molecules.
+
+        Classes for clustering molecules
+
+        .. tab-set::
+
+            .. tab-item:: Core
+
+                * :class:`~qsprpred.data.chem.clustering.RandomClusters`: RandomClusters
+                * :class:`~qsprpred.data.chem.clustering.ScaffoldClusters`: ScaffoldClusters
+                * :class:`~qsprpred.data.chem.clustering.FPSimilarityClusters`: FPSimilarityClusters
+                    * :class:`~qsprpred.data.chem.clustering.FPSimilarityMaxMinClusters`: FPSimilarityMaxMinClusters
+                    * :class:`~qsprpred.data.chem.clustering.FPSimilarityLeaderPickerClusters`: FPSimilarityLeaderPickerClusters
diff --git a/qsprpred/data/descriptors/fingerprints.py b/qsprpred/data/descriptors/fingerprints.py
@@ -144,7 +144,7 @@ def __str__(self):
 
 class MaccsFP(Fingerprint):
     def __init__(self, nBits=167, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.nBits = nBits
         self.kwargs = kwargs
 
@@ -169,7 +169,7 @@ def __str__(self):
 
 class AvalonFP(Fingerprint):
     def __init__(self, nBits=1024, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.nBits = nBits
         self.kwargs = kwargs
 
@@ -194,7 +194,7 @@ def __str__(self):
 
 class TopologicalFP(Fingerprint):
     def __init__(self, nBits=2048, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.nBits = nBits
         self.kwargs = kwargs
 
@@ -221,7 +221,7 @@ def __str__(self):
 
 class AtomPairFP(Fingerprint):
     def __init__(self, nBits=2048, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.nBits = nBits
         self.kwargs = kwargs
 
@@ -248,7 +248,7 @@ def __str__(self):
 
 class RDKitFP(Fingerprint):
     def __init__(self, minPath=1, maxPath=7, nBits=2048, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.minPath = minPath
         self.maxPath = maxPath
         self.nBits = nBits
@@ -281,7 +281,7 @@ def __str__(self):
 
 class PatternFP(Fingerprint):
     def __init__(self, nBits=2048, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.nBits = nBits
         self.kwargs = kwargs
 
@@ -308,7 +308,7 @@ def __str__(self):
 
 class LayeredFP(Fingerprint):
     def __init__(self, minPath=1, maxPath=7, nBits=2048, **kwargs):
-        super().__init__()
+        super().__init__(used_bits=list(range(nBits)))
         self.minPath = minPath
         self.maxPath = maxPath
         self.nBits = nBits

diff --git a/qsprpred/data/descriptors/sets.py b/qsprpred/data/descriptors/sets.py
@@ -446,7 +446,7 @@ def __init__(self, model: Type["QSPRModel"] | str):
         Initialize the descriptorset with a `QSPRModel` object.
 
         Args:
-            model: a fitted model instance or a path to the model's meta file
+            model (QSPRModel): a fitted model instance or a path to the model's meta file
         """
         super().__init__()
         if isinstance(model, str):

diff --git a/qsprpred/data/descriptors/tests.py b/qsprpred/data/descriptors/tests.py
@@ -163,41 +163,14 @@ def setUp(self):
         super().setUp()
         self.setUpPaths()
 
-    @parameterized.expand(
-        [
-            (
-                f"{desc_set}_{TargetTasks.MULTICLASS}",
-                desc_set,
-                [
-                    {
-                        "name": "CL",
-                        "task": TargetTasks.MULTICLASS,
-                        "th": [0, 1, 10, 1200],
-                    }
-                ],
-            )
-            for desc_set in DataSetsPathMixIn.getAllDescriptors()
-        ]
-        + [
-            (
-                f"{desc_set}_{TargetTasks.REGRESSION}",
-                desc_set,
-                [{"name": "CL", "task": TargetTasks.REGRESSION}],
-            )
-            for desc_set in DataSetsPathMixIn.getAllDescriptors()
-        ]
-        + [
-            (
-                f"{desc_set}_Multitask",
-                desc_set,
-                [
-                    {"name": "CL", "task": TargetTasks.REGRESSION},
-                    {"name": "fu", "task": TargetTasks.SINGLECLASS, "th": [0.3]},
-                ],
-            )
-            for desc_set in DataSetsPathMixIn.getAllDescriptors()
-        ]
-    )
+    @parameterized.expand([
+        (
+            f"{desc_set}_{TargetTasks.REGRESSION}",
+            desc_set,
+            [{"name": "CL", "task": TargetTasks.REGRESSION}],
+        )
+        for desc_set in DataSetsPathMixIn.getAllDescriptors()
+    ])
     def testDescriptorsAll(self, _, desc_set, target_props):
         """Tests all available descriptor sets.
 

diff --git a/qsprpred/extra/data/descriptors/tests.py b/qsprpred/extra/data/descriptors/tests.py
@@ -267,10 +267,7 @@ def setUp(self):
             (
                 f"{desc_set}",
                 desc_set,
-                [
-                    {"name": "CL", "task": TargetTasks.REGRESSION},
-                    {"name": "fu", "task": TargetTasks.SINGLECLASS, "th": [0.3]},
-                ],
+                [{"name": "CL", "task": TargetTasks.REGRESSION}],
             )
             for desc_set in DataSetsMixInExtras.getAllDescriptors()
         ]

diff --git a/qsprpred/utils/testing/path_mixins.py b/qsprpred/utils/testing/path_mixins.py
@@ -10,12 +10,21 @@
 from sklearn.preprocessing import StandardScaler
 
 from ...data import RandomSplit, QSPRDataset
-from ...data.descriptors.fingerprints import MorganFP
+from ...data.descriptors.fingerprints import (
+    AtomPairFP,
+    AvalonFP,
+    LayeredFP,
+    MaccsFP,
+    MorganFP,
+    PatternFP,
+    RDKitFP,
+    RDKitMACCSFP,
+    TopologicalFP,
+)
 from ...data.descriptors.sets import (
     RDKitDescs,
     DrugExPhyschem,
     PredictorDesc,
-    RDKitDescs,
     TanimotoDistances,
 )
 from ...data.processing.data_filters import RepeatsFilter
@@ -101,7 +110,15 @@ def getAllDescriptors(cls):
                 radius=2,
                 nBits=128,
             ),
+            AtomPairFP(nBits=128),
+            AvalonFP(nBits=128),
+            LayeredFP(nBits=128),
+            MaccsFP(),
             MorganFP(radius=2, nBits=128),
+            PatternFP(nBits=128),
+            RDKitFP(nBits=128),
+            RDKitMACCSFP(),
+            TopologicalFP(nBits=128),
         ]
 
         return descriptor_sets