UCD-BDLab · ramosv · Dec 30, 2025 · Dec 30, 2025
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,18 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/).
 
+## [1.2.2] - 2025-12-29
+
+### Documentation
+- **Updated Index**: index now includes tables with examples for feature selection.
+- **Getting Started for Biologists**: An updated page which leverages google colab for a more user friendly walkthrough of BioNeuralNet.
+
+### Ray Tune Patch
+- **Ray tune**: Updated from `ray[tune,train]>=2.46.0` to `ray[tune,train]>=2.46.0, <2.53.0` due to an recent release on December 20, 2025 which breaks some functionality. This temporately fixes the issue.
+
+### New DPMON param: `tune_trails`
+- This parameter gives users the ability to dictate how many ray tune trials to run. This works alongside the Dynamic Sampling from `v1.2.1`.
+
 ## [1.2.1] - 2025-11-30
 
 ### Dependencies
@@ -227,4 +239,4 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 - **Bug Fixes**:
   - Resolved incorrect handling of `tune=True` in Hybrid Louvain.
   - Addressed inconsistencies in `GraphEmbedding` parameter parsing.
-  - Fixed dataset loading issues in example scripts.
+  - Fixed dataset loading issues in example scripts.
diff --git a/README.md b/README.md
@@ -8,7 +8,7 @@
 [![Documentation](https://img.shields.io/badge/docs-read%20the%20docs-blue.svg)](https://bioneuralnet.readthedocs.io/en/latest/)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17503083.svg)](https://doi.org/10.5281/zenodo.17503083)
 
-## Welcome to BioNeuralNet 1.2.1
+## Welcome to BioNeuralNet 1.2.2
 
 ![BioNeuralNet Logo](assets/LOGO_TB.png)
 

diff --git a/bioneuralnet/__init__.py b/bioneuralnet/__init__.py
@@ -23,7 +23,7 @@
 * `utils`: Utilities for logging, reproducibility, graph generation, and data processing.
 """
 
-__version__ = "1.2.1"
+__version__ = "1.2.2"
 
 # submodules to enable direct imports such as `from bioneuralnet import utils`
 from . import utils

diff --git a/bioneuralnet/downstream_task/dpmon.py b/bioneuralnet/downstream_task/dpmon.py
@@ -69,6 +69,7 @@ class DPMON:
         lr (float): Learning rate for the optimizer.
         weight_decay (float): L2 weight decay (regularization) coefficient.
         tune (bool): If True, perform hyperparameter tuning before final training.
+        tune_trails (int): Number of trials to perform if tune=True.
         gpu (bool): If True, use GPU if available.
         cv (bool): If True, use K-fold cross-validation; otherwise use repeated train/test splits.
         cuda (int): CUDA device index to use when gpu=True.
@@ -98,6 +99,7 @@ def __init__(
         lr: float = 1e-1,
         weight_decay: float = 1e-4,
         tune: bool = False,
+        tune_trails: int = 10,
         gpu: bool = False,
         cv: bool = False,
         cuda: int = 0,
@@ -156,6 +158,7 @@ def __init__(
         self.lr = lr
         self.weight_decay = weight_decay
         self.tune = tune
+        self.tune_trails = tune_trails
         self.gpu = gpu
         self.cuda = cuda
         self.seed = seed
@@ -205,6 +208,7 @@ def run(self) -> Tuple[pd.DataFrame, object, torch.Tensor | None]:
             "gpu": self.gpu,
             "cuda": self.cuda,
             "tune": self.tune,
+            "tune_trials": self.tune_trails,
             "seed": self.seed,
             "seed_trials": self.seed_trials,
             "cv": self.cv,
@@ -892,8 +896,8 @@ def short_dirname_creator(trial):
 
     gpu_per_trial = 0.05 if use_gpu else 0.0
 
-    num_samples = 50
-    max_retries = 5
+    num_samples = dpmon_params['tune_trials']
+    max_retries = 4
 
     seed_trials = dpmon_params.get("seed_trials", False)
 
@@ -916,6 +920,7 @@ def short_dirname_creator(trial):
                 config=pipeline_configs,
                 num_samples=num_samples,
                 verbose=0,
+                log_to_file=True,
                 scheduler=scheduler,
                 stop=stopper,
                 name="tune_dp",

diff --git a/docs/source/Quick_Start.ipynb b/docs/source/Quick_Start.ipynb
diff --git a/docs/source/_autosummary/bioneuralnet.clustering.correlated_louvain.rst b/docs/source/_autosummary/bioneuralnet.clustering.correlated_louvain.rst
@@ -19,7 +19,6 @@ bioneuralnet.clustering.correlated\_louvain
    .. autosummary::
 
       ASHAScheduler
-      Any
       CLIReporter
       CorrelatedLouvain
       PCA

diff --git a/docs/source/_autosummary/bioneuralnet.clustering.correlated_pagerank.rst b/docs/source/_autosummary/bioneuralnet.clustering.correlated_pagerank.rst
@@ -17,7 +17,6 @@ bioneuralnet.clustering.correlated\_pagerank
    .. autosummary::
 
       ASHAScheduler
-      Any
       CLIReporter
       CorrelatedPageRank
       PCA

diff --git a/docs/source/_autosummary/bioneuralnet.downstream_task.subject_representation.rst b/docs/source/_autosummary/bioneuralnet.downstream_task.subject_representation.rst
@@ -21,7 +21,6 @@ bioneuralnet.downstream\_task.subject\_representation
    .. autosummary::
 
       ASHAScheduler
-      Any
       AutoEncoder
       CLIReporter
       PCA

diff --git a/docs/source/_autosummary/bioneuralnet.external_tools.smccnet.rst b/docs/source/_autosummary/bioneuralnet.external_tools.smccnet.rst
@@ -15,7 +15,6 @@ bioneuralnet.external\_tools.smccnet
 
    .. autosummary::
 
-      Any
       Path
       SmCCNet
 
diff --git a/docs/source/_static/getting_started_bio1.png b/docs/source/_static/getting_started_bio1.png
diff --git a/docs/source/_static/getting_started_bio10.png b/docs/source/_static/getting_started_bio10.png
diff --git a/docs/source/_static/getting_started_bio2.png b/docs/source/_static/getting_started_bio2.png
diff --git a/docs/source/_static/getting_started_bio3.png b/docs/source/_static/getting_started_bio3.png
diff --git a/docs/source/_static/getting_started_bio4.png b/docs/source/_static/getting_started_bio4.png
diff --git a/docs/source/_static/getting_started_bio5.png b/docs/source/_static/getting_started_bio5.png
diff --git a/docs/source/_static/getting_started_bio6.png b/docs/source/_static/getting_started_bio6.png
diff --git a/docs/source/_static/getting_started_bio7.png b/docs/source/_static/getting_started_bio7.png
diff --git a/docs/source/_static/getting_started_bio8.png b/docs/source/_static/getting_started_bio8.png
diff --git a/docs/source/_static/getting_started_bio9.png b/docs/source/_static/getting_started_bio9.png
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -12,7 +12,7 @@
 try:
     release = metadata.version("bioneuralnet")
 except metadata.PackageNotFoundError:
-    release = "1.2.1"
+    release = "1.2.2"
 
 project = "BioNeuralNet"
 version = release

diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -38,6 +38,7 @@ Quick Start Examples
 Get started quickly with these end-to-end examples demonstrating the BioNeuralNet workflow:
 
 - :doc:`Quick_Start`
+- :doc:`quick_start_bio`
 - :doc:`notebooks/index`
 
 **BioNeuralNet Workflow Overview**
@@ -57,9 +58,9 @@ BioNeuralNet is a flexible and modular Python framework tailored for **end-to-en
 
 **Core Analytical Modules:**
 
-- **Network Construction**: Build informative networks from raw tabular data using strategies like **Similarity**, **Correlation**, **Neighborhood-based**, or **Phenotype-driven** (e.g., SmCCNet) approaches.
+- **Network Construction**: Build informative networks from raw tabular data using strategies like **Similarity**, **Correlation**, **Neighborhood-based**, or **Phenotype-driven** (e.g., SmCCNet) approaches. [1]_
 - **Biomarker Discovery**: Identify biological modules and key molecular interactions that drive disease phenotypes.
-- **Disease Prediction**: Implement end-to-end supervised disease classification using the **DPMON** (Disease Prediction using Multi-Omics Networks) module.
+- **Disease Prediction**: Implement end-to-end supervised disease classification using the **DPMON** (Disease Prediction using Multi-Omics Networks) module. [2]_
 - **Subject Representation**: Generate enhanced subject-level embeddings for stratification and clustering.
 
 **Visualizing Multi-Omics Networks**
@@ -71,7 +72,7 @@ BioNeuralNet allows you to inspect the topology of your constructed networks. Th
    :alt: Multi-Omics Network Visualization
    :width: 100%
 
-   *Network visualization of a highly connected gene module identified in the KIPAN dataset.* `Full Size Image <https://bioneuralnet.readthedocs.io/en/latest/_images/kipan_net.png>`_
+   *Network visualization of a highly connected gene module identified in the KIPAN dataset.* `See Network Full Size <https://bioneuralnet.readthedocs.io/en/latest/_images/kipan_net.png>`_
 
 **Top Identified Biomarkers (Hub Omics)**
 
@@ -133,7 +134,7 @@ By projecting high-dimensional omics networks into latent spaces, BioNeuralNet d
    :alt: t-SNE visualization of Network Embeddings
    :width: 100%
 
-   *2D projection of Network Embeddings showing distinct separation between omics modalities.* `Full Size Image <https://bioneuralnet.readthedocs.io/en/latest/_images/emb_kipan.png>`_
+   *2D projection of Network Embeddings showing distinct separation between omics modalities.* `See Embeddings Full Size <https://bioneuralnet.readthedocs.io/en/latest/_images/emb_kipan.png>`_
 
 For detailed explanations of BioNeuralNet's supported GNN architectures, see :doc:`gnns`.
 
@@ -148,12 +149,63 @@ To ensure scientific rigor and optimal performance when using BioNeuralNet, user
 * **Computational Scalability**: While optimized for standard omics datasets, extremely large networks may require aggressive feature reduction or subgraph detection strategies to maintain computational efficiency.
 * **Interpretability Scope**: BioNeuralNet provides network-level interpretability (identifying key modules and hub features). However, full node-level explainability remains an active area of research.
 
+**Feature Selection Examples**
+
+The following feature set were determined by the intersection of features identified via the **ANOVA F-test** and **Random Forest Importance**. This approach offers comprehensive filtering by balancing class-based relevance (ANOVA) with non-linear model importance (Random Forest).
+
+.. list-table:: TCGA-BRCA Feature Selection
+   :widths: 25 20 20 20 15
+   :header-rows: 1
+   :align: center
+
+   * - Omics Data Type
+     - ANOVA-F & Variance
+     - RF & Variance
+     - ANOVA-F & Random Forest (Selected)
+     - All Three Agree
+   * - **Methylation**
+     - 2,092 features
+     - 1,870 features
+     - **2,203 features**
+     - 814 features
+   * - **RNA**
+     - 2,359 features
+     - 2,191 features
+     - **2,500 features**
+     - 1,124 features
+
+.. list-table:: TCGA-LGG Feature Selection
+   :widths: 25 20 20 20 15
+   :header-rows: 1
+   :align: center
+
+   * - Omics Data Type
+     - ANOVA-F & Variance
+     - RF & Variance
+     - ANOVA-F & Random Forest (Selected)
+     - All Three Agree
+   * - **Methylation**
+     - 2,704 features
+     - 1,768 features
+     - **1,823 features**
+     - 809 features
+   * - **RNA**
+     - 2,183 features
+     - 1,977 features
+     - **2,127 features**
+     - 763 features
+
+For a full list of *BioNeuralNet* preprocessing utilties see: `Preprocessing Utilities <https://bioneuralnet.readthedocs.io/en/latest/utils.html#preprocessing-utilities>`_.
+
+The full analysis and implementation details for the tables above can be found in the :doc:`notebooks/index`.
+
 Explore BioNeuralNet's Documentation
 ------------------------------------
 
 For detailed examples and tutorials, visit:
 
 - :doc:`Quick_Start`: A quick walkthrough demonstrating the BioNeuralNet workflow from start to finish.
+- :doc:`quick_start_bio`: A user-frienfly walkthrough for members of the community without a developer background.
 - :doc:`notebooks/index`: A collection of demonstration notebooks showcasing end-to-end analyses on TCGA datasets.
 
 **Documentation Sections:**

diff --git a/docs/source/notebooks/TCGA-Biomarkers.ipynb b/docs/source/notebooks/TCGA-Biomarkers.ipynb
@@ -21,7 +21,7 @@
     "\n",
     "**Data Source:** [Broad Institute FireHose](http://firebrowse.org/?cohort=KIPAN)\n",
     "\n",
-    "*For the end-to-end analysis see TCGA-KIPAN Analysis*"
+    "*For the end-to-end analysis inclusind data preprocessing*: [TCGA-KIPAN Full Notebook](https://github.com/UCD-BDLab/BioNeuralNet/blob/main/TCGA-Notebooks/TCGA-KIPAN.ipynb)"
    ]
   },
   {
-Original file line number
+Diff line change
@@ Expand Up / @@ -15,7 +15,6 @@ bioneuralnet.external\_tools.smccnet @@
        .. autosummary::
-          Any
           Path
           SmCCNet