diff --git a/requirements.txt b/requirements.txt
index 8fbbc02..c8d6a96 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,5 +3,6 @@ matplotlib==3.10.3
 seaborn==0.13.2
 numpy==1.26.4
 git+https://github.com/pykale/pykale@main
-nilearn==0.11.1
+nilearn==0.10.4
 yacs==0.1.8
+gdown==5.2.0
diff --git a/tutorials/brain-disorder-diagnosis/config.py b/tutorials/brain-disorder-diagnosis/config.py
index 2ada3f1..8392c67 100644
--- a/tutorials/brain-disorder-diagnosis/config.py
+++ b/tutorials/brain-disorder-diagnosis/config.py
@@ -1,24 +1,34 @@
+import os
 from yacs.config import CfgNode
 
+DEFAULT_DIR = os.path.join(os.getcwd(), "data")
+
 _C = CfgNode()
 
 # Dataset configuration
 _C.DATASET = CfgNode()
 # Path to the dataset directory
-_C.DATASET.PATH = "nilearn_data"
+_C.DATASET.PATH = DEFAULT_DIR
 # Name of the brain atlas to use
+# Available options:
+# - "aal" (AAL)
+# - "cc200" (Cameron Craddock 200)
+# - "cc400" (Cameron Craddock 400)
+# - "difumo64" (DiFuMo 64)
+# - "dos160" (Dosenbach 160)
+# - "hcp-ica" (HCP-ICA)
+# - "ho" (Harvard-Oxford)
+# - "tt" (Talairach-Tournoux)
 _C.DATASET.ATLAS = "cc200"
-# Whether to apply bandpass filtering
-_C.DATASET.BANDPASS = False
-# Whether to apply global signal regression
-_C.DATASET.GLOBAL_SIGNAL_REGRESSION = False
-# Whether to use only quality-checked data
-_C.DATASET.QUALITY_CHECKED = False
-
-# Connectivity configuration
-_C.CONNECTIVITY = CfgNode()
-# List of connectivity measures to compute
-_C.CONNECTIVITY.MEASURES = ["pearson"]
+# Functional connectivity to use
+# Available options:
+# - "pearson"
+# - "partial"
+# - "tangent"
+# - "precision"
+# - "covariance"
+# - "tangent-pearson"
+_C.DATASET.FC = "tangent-pearson"
 
 # Phenotype configuration
 _C.PHENOTYPE = CfgNode()
@@ -27,37 +37,57 @@
 
 # Cross-validation configuration
 _C.CROSS_VALIDATION = CfgNode()
-# Cross-validation split method (e.g., leave-p-groups-out)
+# Cross-validation split method
+# Available options:
+# - "skf" (Stratified K-Folds)
+# - "lpgo" (Leave-P-Groups-Out)
 _C.CROSS_VALIDATION.SPLIT = "skf"
 # Number of folds for cross-validation
+# or number of groups for Leave-P-Groups-Out
 _C.CROSS_VALIDATION.NUM_FOLDS = 10
 # Number of repeats for cross-validation
-_C.CROSS_VALIDATION.NUM_REPEATS = 1
+_C.CROSS_VALIDATION.NUM_REPEATS = 5
 
 # Trainer configuration
 _C.TRAINER = CfgNode()
-# Classifier to use (e.g., auto-select)
+# Classifier to use
+# Available options:
+# - "lda"
+# - "lr"
+# - "linear_svm"
+# - "svm"
+# - "ridge"
+# - "auto"
 _C.TRAINER.CLASSIFIER = "lr"
-# Use non-linear transformations
+# Use non-linear transformations (no interpretability)
 _C.TRAINER.NONLINEAR = False
 # Search strategy for hyperparameter tuning
 _C.TRAINER.SEARCH_STRATEGY = "random"
 # Number of iterations for hyperparameter search
-_C.TRAINER.NUM_SEARCH_ITER = 100
+_C.TRAINER.NUM_SEARCH_ITER = int(1e3)
 # Number of iterations for solver
 _C.TRAINER.NUM_SOLVER_ITER = int(1e6)
 # List of scoring metrics
+# Available options:
+# - "accuracy"
+# - "precision"
+# - "recall"
+# - "f1"
+# - "roc_auc"
+# - "matthews_corrcoef"
 _C.TRAINER.SCORING = ["accuracy", "roc_auc"]
 # Refit based on the best hyperparameters on a scoring metric
 _C.TRAINER.REFIT = "accuracy"
 # Number of parallel jobs (-1: all CPUs, -4: all but 4 CPUs)
-_C.TRAINER.N_JOBS = -4
+_C.TRAINER.N_JOBS = 1
+# Pre-dispatch of jobs for parallel processing
+_C.TRAINER.PRE_DISPATCH = "2*n_jobs"
 # Verbosity level
 _C.TRAINER.VERBOSE = 0
 
 # Random state for reproducibility
 # Seed for random number generators
-_C.RANDOM_STATE = 0
+_C.RANDOM_STATE = None
 
 
 def get_cfg_defaults():
diff --git a/tutorials/brain-disorder-diagnosis/data.py b/tutorials/brain-disorder-diagnosis/data.py
new file mode 100644
index 0000000..e563eac
--- /dev/null
+++ b/tutorials/brain-disorder-diagnosis/data.py
@@ -0,0 +1,160 @@
+import os
+import json
+import numpy as np
+import pandas as pd
+import gdown
+
+from sklearn.utils._param_validation import StrOptions, validate_params
+
+
+@validate_params(
+    {
+        "data_dir": [str],
+        "atlas": [
+            StrOptions(
+                {"aal", "cc200", "cc400", "difumo64", "dos160", "hcp-ica", "ho", "tt"}
+            )
+        ],
+        "fc": [
+            StrOptions(
+                {
+                    "pearson",
+                    "partial",
+                    "tangent",
+                    "precision",
+                    "covariance",
+                    "tangent-pearson",
+                }
+            )
+        ],
+        "vectorize": [bool],
+        "verbose": [bool],
+    },
+    prefer_skip_nested_validation=False,
+)
+def load_data(
+    data_dir="data", atlas="cc200", fc="tangent-pearson", vectorize=True, verbose=True
+):
+    """
+    Load functional connectivity data and phenotypic data with gdown support.
+
+    This function uses manifest files to download the required files from Google Drive if not present locally.
+    It automatically downloads files listed in manifests/abide.json and folders listed in manifests/atlas.json.
+
+    Parameters
+    ----------
+    data_dir : str, optional (default="data")
+        Local directory to store the dataset.
+
+    atlas : str, optional (default="cc200")
+        Atlas name (subfolder inside fc/).
+
+    fc : str, optional (default="tangent-pearson")
+        Functional connectivity file name (without extension).
+
+    vectorize : bool, optional (default=True)
+        Whether to vectorize the upper triangle of the connectivity matrices.
+
+    verbose : bool, optional (default=True)
+        Whether to print download and progress messages.
+
+    Returns
+    -------
+    fc_data : np.ndarray
+        Functional connectivity data (vectorized if requested).
+
+    phenotypes : pd.DataFrame
+        Loaded phenotypic data.
+
+    rois : np.ndarray
+        ROI labels.
+
+    coords : np.ndarray
+        ROI coordinates.
+
+    Raises
+    ------
+    FileNotFoundError
+        If the required file paths are not found after attempted download.
+    """
+    # Paths
+    fc_path = os.path.join(data_dir, "abide", "fc", atlas, f"{fc}.npy")
+    is_proba = atlas in {"difumo64"}
+    atlas_type = "probabilistic" if is_proba else "deterministic"
+    atlas_path = os.path.join(data_dir, "atlas", atlas_type, atlas)
+    phenotypes_path = os.path.join(data_dir, "abide", "phenotypes.csv")
+
+    # Ensure all files exist (download if needed)
+    _ensure_abide_file(data_dir, fc_path, verbose)
+    _ensure_abide_file(data_dir, phenotypes_path, verbose)
+    _ensure_atlas_folder(data_dir, atlas_path, verbose)
+
+    # Load connectivity data
+    fc_data = np.load(fc_path)
+    if vectorize:
+        row, col = np.triu_indices(fc_data.shape[1], 1)
+        fc_data = fc_data[..., row, col]
+
+    phenotypes = pd.read_csv(phenotypes_path)
+
+    with open(os.path.join(atlas_path, "labels.txt"), "r") as f:
+        rois = np.array(f.read().strip().split("\n"))
+    coords = np.load(os.path.join(atlas_path, "coords.npy"))
+
+    return fc_data, phenotypes, rois, coords
+
+
+def _ensure_abide_file(data_dir, target_path, verbose):
+    """Ensure abide file exists locally; download from manifest if missing."""
+    if os.path.exists(target_path):
+        if verbose:
+            print(f"✔ File found: {target_path}")
+        return
+
+    manifest_path = os.path.join(os.path.dirname(__file__), "manifests", "abide.json")
+    with open(manifest_path, "r") as f:
+        manifest = json.load(f)
+
+    rel_path = os.path.relpath(target_path, data_dir).replace("\\", "/")
+    for file_entry in manifest:
+        if file_entry["path"] == rel_path:
+            if verbose:
+                print(f"⬇ Downloading {rel_path} ...")
+            os.makedirs(os.path.dirname(target_path), exist_ok=True)
+            gdown.download(file_entry["url"], output=target_path, quiet=not verbose)
+            if os.path.exists(target_path):
+                return
+            else:
+                break
+
+    raise FileNotFoundError(f"File not found and not found in manifest: {target_path}")
+
+
+def _ensure_atlas_folder(data_dir, atlas_path, verbose):
+    """Ensure atlas folder exists locally; download using gdown.download_folder if missing."""
+    if os.path.exists(atlas_path):
+        if verbose:
+            print(f"✔ Atlas folder found: {atlas_path}")
+        return
+
+    manifest_path = os.path.join(os.path.dirname(__file__), "manifests", "atlas.json")
+    with open(manifest_path, "r") as f:
+        manifest = json.load(f)
+
+    rel_path = os.path.relpath(atlas_path, data_dir).replace("\\", "/")
+    for folder_entry in manifest:
+        if folder_entry["path"] == rel_path:
+            if verbose:
+                print(f"⬇ Downloading atlas folder {rel_path} ...")
+            os.makedirs(os.path.dirname(atlas_path), exist_ok=True)
+            gdown.download_folder(
+                id=folder_entry["id"], output=atlas_path, quiet=not verbose
+            )
+            if os.path.exists(atlas_path):
+                return
+            else:
+                break
+
+    raise FileNotFoundError(
+        f"Atlas folder not found and not found in manifest: {atlas_path}"
+    )
diff --git a/tutorials/brain-disorder-diagnosis/experiments/base.yml b/tutorials/brain-disorder-diagnosis/experiments/base.yml
index 26e5ec5..3658c80 100644
--- a/tutorials/brain-disorder-diagnosis/experiments/base.yml
+++ b/tutorials/brain-disorder-diagnosis/experiments/base.yml
@@ -1,6 +1,11 @@
 DATASET:
-  ATLAS: aal
+  ATLAS: hcp-ica
+
+CROSS_VALIDATION:
+  NUM_REPEATS: 1
 
 TRAINER:
-  NUM_SEARCH_ITER: 50
+  NUM_SEARCH_ITER: 20
   NUM_SOLVER_ITER: 100
+
+RANDOM_STATE: 0
diff --git a/tutorials/brain-disorder-diagnosis/manifests/abide.json b/tutorials/brain-disorder-diagnosis/manifests/abide.json
new file mode 100644
index 0000000..61fde12
--- /dev/null
+++ b/tutorials/brain-disorder-diagnosis/manifests/abide.json
@@ -0,0 +1,296 @@
+[
+    {
+        "id": "1DHoQOInWgZlYiCATzPVHfolAhF1WLfFN",
+        "name": "phenotypes.csv",
+        "path": "abide/phenotypes.csv",
+        "url": "https://drive.google.com/uc?id=1DHoQOInWgZlYiCATzPVHfolAhF1WLfFN"
+    },
+    {
+        "id": "19pydQA5n6nNko6fUL-AWOtzZE3s_ZFKo",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/hcp-ica/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=19pydQA5n6nNko6fUL-AWOtzZE3s_ZFKo"
+    },
+    {
+        "id": "13VsKOnKhhPhzgA1PLHxu8zBPPVg20oT-",
+        "name": "covariance.npy",
+        "path": "abide/fc/hcp-ica/covariance.npy",
+        "url": "https://drive.google.com/uc?id=13VsKOnKhhPhzgA1PLHxu8zBPPVg20oT-"
+    },
+    {
+        "id": "1XqdZcrPIzUvmyDZYga0CsB-Cz_1bnyhW",
+        "name": "precision.npy",
+        "path": "abide/fc/hcp-ica/precision.npy",
+        "url": "https://drive.google.com/uc?id=1XqdZcrPIzUvmyDZYga0CsB-Cz_1bnyhW"
+    },
+    {
+        "id": "1zAOgfoTBeLUHXok0GOEuDnqZ-5Ome1sd",
+        "name": "tangent.npy",
+        "path": "abide/fc/hcp-ica/tangent.npy",
+        "url": "https://drive.google.com/uc?id=1zAOgfoTBeLUHXok0GOEuDnqZ-5Ome1sd"
+    },
+    {
+        "id": "1-CUiUrzZb2nZhdlua_EMIpAroysra392",
+        "name": "pearson.npy",
+        "path": "abide/fc/hcp-ica/pearson.npy",
+        "url": "https://drive.google.com/uc?id=1-CUiUrzZb2nZhdlua_EMIpAroysra392"
+    },
+    {
+        "id": "1nupIrwbVw-UFrvaLmjKShgVdNtwXYsSP",
+        "name": "partial.npy",
+        "path": "abide/fc/hcp-ica/partial.npy",
+        "url": "https://drive.google.com/uc?id=1nupIrwbVw-UFrvaLmjKShgVdNtwXYsSP"
+    },
+    {
+        "id": "1f8QPkO3n9uW6eDualnrKXyQJv-D-Z5Ao",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/aal/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1f8QPkO3n9uW6eDualnrKXyQJv-D-Z5Ao"
+    },
+    {
+        "id": "1nT9dWeQOM8sXhQkX-e97ExhGZOrPkpBh",
+        "name": "precision.npy",
+        "path": "abide/fc/aal/precision.npy",
+        "url": "https://drive.google.com/uc?id=1nT9dWeQOM8sXhQkX-e97ExhGZOrPkpBh"
+    },
+    {
+        "id": "1YZhjow-OSydrcq9EC7Hggp6RGPHz_jXP",
+        "name": "covariance.npy",
+        "path": "abide/fc/aal/covariance.npy",
+        "url": "https://drive.google.com/uc?id=1YZhjow-OSydrcq9EC7Hggp6RGPHz_jXP"
+    },
+    {
+        "id": "1V47WxQgHZpkMtEmqljdbCfVhGQBICnaV",
+        "name": "tangent.npy",
+        "path": "abide/fc/aal/tangent.npy",
+        "url": "https://drive.google.com/uc?id=1V47WxQgHZpkMtEmqljdbCfVhGQBICnaV"
+    },
+    {
+        "id": "1xHIelH5a_K-KOmnC-Ovhm4h7y0UOChp5",
+        "name": "partial.npy",
+        "path": "abide/fc/aal/partial.npy",
+        "url": "https://drive.google.com/uc?id=1xHIelH5a_K-KOmnC-Ovhm4h7y0UOChp5"
+    },
+    {
+        "id": "1IDyUNIKo6Oi5RSdQ6h4BSwpx-MzjBzqP",
+        "name": "pearson.npy",
+        "path": "abide/fc/aal/pearson.npy",
+        "url": "https://drive.google.com/uc?id=1IDyUNIKo6Oi5RSdQ6h4BSwpx-MzjBzqP"
+    },
+    {
+        "id": "1oPEeGWeZMJcodr_1O_hjg_I5CojSOQHA",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/cc200/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1oPEeGWeZMJcodr_1O_hjg_I5CojSOQHA"
+    },
+    {
+        "id": "1ZmIIN6hRijJJfk-_UibxSBGzLraB-4Yx",
+        "name": "precision.npy",
+        "path": "abide/fc/cc200/precision.npy",
+        "url": "https://drive.google.com/uc?id=1ZmIIN6hRijJJfk-_UibxSBGzLraB-4Yx"
+    },
+    {
+        "id": "138lGGR3_tskE-BxweEZ_hXt8NK-Q0F-h",
+        "name": "covariance.npy",
+        "path": "abide/fc/cc200/covariance.npy",
+        "url": "https://drive.google.com/uc?id=138lGGR3_tskE-BxweEZ_hXt8NK-Q0F-h"
+    },
+    {
+        "id": "1aRLyCqEnRGrhpWVagXnADs5caLH_muEp",
+        "name": "tangent.npy",
+        "path": "abide/fc/cc200/tangent.npy",
+        "url": "https://drive.google.com/uc?id=1aRLyCqEnRGrhpWVagXnADs5caLH_muEp"
+    },
+    {
+        "id": "1Bq2jD0F8gh7gB8JYxxqrNQa48Iw-mODo",
+        "name": "partial.npy",
+        "path": "abide/fc/cc200/partial.npy",
+        "url": "https://drive.google.com/uc?id=1Bq2jD0F8gh7gB8JYxxqrNQa48Iw-mODo"
+    },
+    {
+        "id": "1ko1GXeqOQvSTCjHk6ePo93jTMdPJYIyM",
+        "name": "pearson.npy",
+        "path": "abide/fc/cc200/pearson.npy",
+        "url": "https://drive.google.com/uc?id=1ko1GXeqOQvSTCjHk6ePo93jTMdPJYIyM"
+    },
+    {
+        "id": "1rdBd8tm-G4GFwsYYfG5V9fN13D9XxSV4",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/difumo64/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1rdBd8tm-G4GFwsYYfG5V9fN13D9XxSV4"
+    },
+    {
+        "id": "10hrnAIRTnwlk-b5XD3Q7-rRwkHFo_r-3",
+        "name": "covariance.npy",
+        "path": "abide/fc/difumo64/covariance.npy",
+        "url": "https://drive.google.com/uc?id=10hrnAIRTnwlk-b5XD3Q7-rRwkHFo_r-3"
+    },
+    {
+        "id": "19po8WQP6OonrL-6TsSBZW4X-qhpZbg8d",
+        "name": "tangent.npy",
+        "path": "abide/fc/difumo64/tangent.npy",
+        "url": "https://drive.google.com/uc?id=19po8WQP6OonrL-6TsSBZW4X-qhpZbg8d"
+    },
+    {
+        "id": "1N0RVZ4IkPNL7BjEXjuQ7H1nfe3RRE7es",
+        "name": "precision.npy",
+        "path": "abide/fc/difumo64/precision.npy",
+        "url": "https://drive.google.com/uc?id=1N0RVZ4IkPNL7BjEXjuQ7H1nfe3RRE7es"
+    },
+    {
+        "id": "1pDTTpWw8u09NNShOpqriIwGxVuwQ2Gmq",
+        "name": "partial.npy",
+        "path": "abide/fc/difumo64/partial.npy",
+        "url": "https://drive.google.com/uc?id=1pDTTpWw8u09NNShOpqriIwGxVuwQ2Gmq"
+    },
+    {
+        "id": "1qWtrsIQIEC662pNAy2QW-7btOp3WS5LE",
+        "name": "pearson.npy",
+        "path": "abide/fc/difumo64/pearson.npy",
+        "url": "https://drive.google.com/uc?id=1qWtrsIQIEC662pNAy2QW-7btOp3WS5LE"
+    },
+    {
+        "id": "1CTCjMwiRumJ3wTMo9Eht4SXpCeSKoJtE",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/tt/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1CTCjMwiRumJ3wTMo9Eht4SXpCeSKoJtE"
+    },
+    {
+        "id": "1aMMw2S01oW2hPdml3dzgxGUdUdKzCFWh",
+        "name": "precision.npy",
+        "path": "abide/fc/tt/precision.npy",
+        "url": "https://drive.google.com/uc?id=1aMMw2S01oW2hPdml3dzgxGUdUdKzCFWh"
+    },
+    {
+        "id": "12LxphE-5Z0JylVlD73mrEkTKyWsEPGYF",
+        "name": "tangent.npy",
+        "path": "abide/fc/tt/tangent.npy",
+        "url": "https://drive.google.com/uc?id=12LxphE-5Z0JylVlD73mrEkTKyWsEPGYF"
+    },
+    {
+        "id": "1vjlHpBpz-mrifp74QPXrWjtotz_pwzJW",
+        "name": "covariance.npy",
+        "path": "abide/fc/tt/covariance.npy",
+        "url": "https://drive.google.com/uc?id=1vjlHpBpz-mrifp74QPXrWjtotz_pwzJW"
+    },
+    {
+        "id": "1OqsfrAg6pTWi_TGrlyQpw9jNCVFUKdCK",
+        "name": "partial.npy",
+        "path": "abide/fc/tt/partial.npy",
+        "url": "https://drive.google.com/uc?id=1OqsfrAg6pTWi_TGrlyQpw9jNCVFUKdCK"
+    },
+    {
+        "id": "14sOs6AUmnyj3-U9Z1DOjk_wtBAcGfkLU",
+        "name": "pearson.npy",
+        "path": "abide/fc/tt/pearson.npy",
+        "url": "https://drive.google.com/uc?id=14sOs6AUmnyj3-U9Z1DOjk_wtBAcGfkLU"
+    },
+    {
+        "id": "1CVSQiCDM0dfa0HCCZRuHYRY7uc67DAhd",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/cc400/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1CVSQiCDM0dfa0HCCZRuHYRY7uc67DAhd"
+    },
+    {
+        "id": "1UDjNd6wAyX2lxAY8-ZXUgT520mcjlEm6",
+        "name": "precision.npy",
+        "path": "abide/fc/cc400/precision.npy",
+        "url": "https://drive.google.com/uc?id=1UDjNd6wAyX2lxAY8-ZXUgT520mcjlEm6"
+    },
+    {
+        "id": "1ybIrLrheCLjHWrIsZVhVsCAOo1Z6pDAp",
+        "name": "covariance.npy",
+        "path": "abide/fc/cc400/covariance.npy",
+        "url": "https://drive.google.com/uc?id=1ybIrLrheCLjHWrIsZVhVsCAOo1Z6pDAp"
+    },
+    {
+        "id": "1gtf8957rXkfS1e1Z7YeFzGs12dH9duZy",
+        "name": "tangent.npy",
+        "path": "abide/fc/cc400/tangent.npy",
+        "url": "https://drive.google.com/uc?id=1gtf8957rXkfS1e1Z7YeFzGs12dH9duZy"
+    },
+    {
+        "id": "1JCMjsWVbgjOVESpnWs8Cn6tkCn4ialZ1",
+        "name": "partial.npy",
+        "path": "abide/fc/cc400/partial.npy",
+        "url": "https://drive.google.com/uc?id=1JCMjsWVbgjOVESpnWs8Cn6tkCn4ialZ1"
+    },
+    {
+        "id": "1ofQOemsme9bhHobSXMY5g-0CDXqUqlzE",
+        "name": "pearson.npy",
+        "path": "abide/fc/cc400/pearson.npy",
+        "url": "https://drive.google.com/uc?id=1ofQOemsme9bhHobSXMY5g-0CDXqUqlzE"
+    },
+    {
+        "id": "1XZCSo_TkTaI26qkSA2XBNtI8Qx8uIIFh",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/ho/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1XZCSo_TkTaI26qkSA2XBNtI8Qx8uIIFh"
+    },
+    {
+        "id": "1yf-x0gKKknfYNqX9WXx-cfbWeUpe2zP6",
+        "name": "precision.npy",
+        "path": "abide/fc/ho/precision.npy",
+        "url": "https://drive.google.com/uc?id=1yf-x0gKKknfYNqX9WXx-cfbWeUpe2zP6"
+    },
+    {
+        "id": "17CQYW2RIg6i9uyo0J91M4kLEuIaGkVQi",
+        "name": "tangent.npy",
+        "path": "abide/fc/ho/tangent.npy",
+        "url": "https://drive.google.com/uc?id=17CQYW2RIg6i9uyo0J91M4kLEuIaGkVQi"
+    },
+    {
+        "id": "1S5Rufop8sz-5UjvNl_IH9pxKBbbAOuxj",
+        "name": "covariance.npy",
+        "path": "abide/fc/ho/covariance.npy",
+        "url": "https://drive.google.com/uc?id=1S5Rufop8sz-5UjvNl_IH9pxKBbbAOuxj"
+    },
+    {
+        "id": "1KoTmVgCkhq_zV7HyqR7yLb_yyWR2PbQG",
+        "name": "partial.npy",
+        "path": "abide/fc/ho/partial.npy",
+        "url": "https://drive.google.com/uc?id=1KoTmVgCkhq_zV7HyqR7yLb_yyWR2PbQG"
+    },
+    {
+        "id": "19C9VSIq1XmPL0S7LPuFmAWvKQ0fbUJ0V",
+        "name": "pearson.npy",
+        "path": "abide/fc/ho/pearson.npy",
+        "url": "https://drive.google.com/uc?id=19C9VSIq1XmPL0S7LPuFmAWvKQ0fbUJ0V"
+    },
+    {
+        "id": "1h0moD1Uopvm-7BOVzxlBPoFS1-Vt9euz",
+        "name": "tangent-pearson.npy",
+        "path": "abide/fc/dos160/tangent-pearson.npy",
+        "url": "https://drive.google.com/uc?id=1h0moD1Uopvm-7BOVzxlBPoFS1-Vt9euz"
+    },
+    {
+        "id": "1-kd7qPSDHyi_K6O_pK-kbwdSIkEBjvnC",
+        "name": "precision.npy",
+        "path": "abide/fc/dos160/precision.npy",
+        "url": "https://drive.google.com/uc?id=1-kd7qPSDHyi_K6O_pK-kbwdSIkEBjvnC"
+    },
+    {
+        "id": "1N-rOxLFsEWw3h7x2XLZPwQ9syb7Rxhb9",
+        "name": "covariance.npy",
+        "path": "abide/fc/dos160/covariance.npy",
+        "url": "https://drive.google.com/uc?id=1N-rOxLFsEWw3h7x2XLZPwQ9syb7Rxhb9"
+    },
+    {
+        "id": "1Q8CJEW4HQlTNOtLLFBUhlHvm11LH5Deu",
+        "name": "tangent.npy",
+        "path": "abide/fc/dos160/tangent.npy",
+        "url": "https://drive.google.com/uc?id=1Q8CJEW4HQlTNOtLLFBUhlHvm11LH5Deu"
+    },
+    {
+        "id": "10K8JeSi0oaA9gNzzL7h8_Mwydpn0O2Wu",
+        "name": "partial.npy",
+        "path": "abide/fc/dos160/partial.npy",
+        "url": "https://drive.google.com/uc?id=10K8JeSi0oaA9gNzzL7h8_Mwydpn0O2Wu"
+    },
+    {
+        "id": "1dkj6i-zo1ZO6IbN87IAPLvJRNQ8X_KYM",
+        "name": "pearson.npy",
+        "path": "abide/fc/dos160/pearson.npy",
+        "url": "https://drive.google.com/uc?id=1dkj6i-zo1ZO6IbN87IAPLvJRNQ8X_KYM"
+    }
+]
diff --git a/tutorials/brain-disorder-diagnosis/manifests/atlas.json b/tutorials/brain-disorder-diagnosis/manifests/atlas.json
new file mode 100644
index 0000000..78f97fd
--- /dev/null
+++ b/tutorials/brain-disorder-diagnosis/manifests/atlas.json
@@ -0,0 +1,46 @@
+[
+    {
+        "id": "1BSpl4xBbIsQ709b5_QRcy-Uh0hNEfSBe",
+        "path": "atlas"
+    },
+    {
+        "id": "1cGEKgOM1sT_JZnV4GKa8j0H8oh_z3K9a",
+        "path": "atlas/deterministic"
+    },
+    {
+        "id": "1Er9eoLqSY6KYgYd516XHNbQole1pok6-",
+        "path": "atlas/deterministic/tt"
+    },
+    {
+        "id": "1b7EhBoAr_cany3GAYmGRbNtBvValq107",
+        "path": "atlas/deterministic/cc200"
+    },
+    {
+        "id": "1dy3ACTD5_0CJ7BIy2lPBye1ep_Kvw-Py",
+        "path": "atlas/deterministic/ho"
+    },
+    {
+        "id": "1gUpE8tSFjlmACFiDzGYGbqAuY4yUtyKd",
+        "path": "atlas/deterministic/aal"
+    },
+    {
+        "id": "1kZmHdVfZQh_prqzc5LdIpAg1bITzwIh2",
+        "path": "atlas/deterministic/dos160"
+    },
+    {
+        "id": "1P90qp_z0A05bgFrKWN_L4W0RAdEp0HXE",
+        "path": "atlas/deterministic/hcp-ica"
+    },
+    {
+        "id": "17WoiOgQGIq00SLzMQaItJDvmUEUTP9bn",
+        "path": "atlas/deterministic/cc400"
+    },
+    {
+        "id": "1jNzbR3UhNxcavEs7PqusPDeadiUx4FfY",
+        "path": "atlas/probabilistic"
+    },
+    {
+        "id": "18dAJp1gcxEQ8qRnp5tdZJiI_PaLVGqwv",
+        "path": "atlas/probabilistic/difumo64"
+    }
+]
diff --git a/tutorials/brain-disorder-diagnosis/notebook.ipynb b/tutorials/brain-disorder-diagnosis/notebook.ipynb
index ee9039d..8947f59 100644
--- a/tutorials/brain-disorder-diagnosis/notebook.ipynb
+++ b/tutorials/brain-disorder-diagnosis/notebook.ipynb
@@ -1,15 +1,7 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 5,
-  "metadata": {
-    "kernelspec": {
-      "display_name": "embc25",
-      "language": "python",
-      "name": "python3"
-    }
-  },
   "cells": [
     {
+      "cell_type": "markdown",
       "metadata": {},
       "source": [
         "# Brain Disorder Diagnosis\n",
@@ -29,10 +21,10 @@
         "3.\t**Extract** functional connectivity **embedding** from ROI-based time series.\n",
         "4.\t**Build** a **training** and **evaluation** pipeline to assess classification performance under various domain adaptation strategies.\n",
         "5.\t**Interpret** the learned model by extracting weights for pairwise ROI feature importance and visualizing them using a connectome plot."
-      ],
-      "cell_type": "markdown"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -41,138 +33,126 @@
         "\n",
         "As a starting point, we will install the required packages and load a set of helper functions to assist throughout this tutorial. To keep the output clean and focused on interpretation, we will also suppress warnings.\n",
         "\n",
-        "Moreover, we provide helper functions that can be inspected directly in the `.py` files located in the notebook\u2019s current directory. The three additional helper scripts are:\n",
-        "- `config.py`: Defines the base configuration settings, which can be overridden using a custom `.yml` file.\n",
-        "- `parsing.py`: Contains utilities to compile evaluation results from the training process.\n",
-        "- `preprocess.py`: Handles phenotype preprocessing (e.g., imputing missing values and encoding categorical variables) and feature extraction from the fMRI time series.\n",
+        "In addition, several helper scripts are provided to modularize the code and simplify the workflow. These can be inspected directly as `.py` files in the notebook’s current directory. The helper scripts include:\n",
         "\n",
-        "For Google Colab, these helper scripts are found in `embc-mmai25/tutorials/brain-disorder-diagnosis`."
-      ],
-      "cell_type": "markdown"
+        "- **`config.py`**: Defines the base configuration settings, which can be customized and overridden using external `.yml` files.\n",
+        "- **`data.py`**: Provides data loading functions and utilities to automatically download any required datasets.\n",
+        "- **`parsing.py`**: Contains utilities to compile and summarize evaluation results from the training process.\n",
+        "- **`preprocess.py`**: Handles phenotype preprocessing, including missing value imputation, categorical variable encoding, and feature extraction from fMRI time series data."
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": [
           "hide-input"
         ]
       },
+      "outputs": [],
       "source": [
         "import os\n",
+        "import site\n",
+        "import sys\n",
         "import warnings\n",
         "\n",
         "warnings.filterwarnings(\"ignore\")\n",
         "os.environ[\"PYTHONWARNINGS\"] = \"ignore\"\n",
         "\n",
-        "# Test if running in Colab\n",
-        "data_dir = None\n",
         "if \"google.colab\" in str(get_ipython()):\n",
-        "    from google.colab import drive\n",
-        "\n",
-        "    mount_dir = os.path.join(\"/content\", \"drive\")\n",
-        "    drive.mount(mount_dir)\n",
-        "    # Assign it to your dataset's location\n",
-        "    data_dir = os.path.join(mount_dir, \"MyDrive\", \"data\")\n",
-        "    %cd /content\n",
+        "    sys.path.insert(0, site.getusersitepackages())\n",
         "    !git clone -b brain-decoding https://github.com/pykale/embc-mmai25.git\n",
-        "    %cd /content/embc-mmai25/tutorials/brain-disorder-diagnosis"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
+        "    %cp -r /content/embc-mmai25/tutorials/brain-disorder-diagnosis/* /content/\n",
+        "    %rm -r /content/embc-mmai25"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
       "source": [
         "## Packages\n",
         "\n",
-        "The main packages required for this tutorial are `pykale`, `nilearn`, `pandas`, and `yacs`.\n",
+        "The main packages required for this tutorial are:\n",
         "\n",
-        "`pykale` is an open-source interdisciplinary machine learning library developed at the University of Sheffield, with a focus on applications in biomedical and scientific domains.\n",
+        "- **pykale**: An open-source interdisciplinary machine learning library developed at the University of Sheffield. It focuses on applications in biomedical and scientific domains, providing tools for multimodal learning, domain adaptation, and model interpretability.\n",
         "\n",
-        "`nilearn` is a Python library for neuroimaging analysis, widely used for processing and visualizing functional MRI (fMRI) data.\n",
+        "- **gdown**: A utility package that simplifies downloading files and folders directly from Google Drive.\n",
         "\n",
-        "`pandas` is a popular data wrangling library.\n",
+        "- **nilearn**: A Python library for neuroimaging analysis. It offers convenient tools for processing, analyzing, and visualizing functional MRI (fMRI) data.\n",
         "\n",
-        "`yacs` is a configuration management used to store experiment settings."
-      ],
-      "cell_type": "markdown"
+        "- **yacs**: A lightweight configuration management library used to store and organize experiment settings in a hierarchical and human-readable format."
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": [
           "hide-input"
         ]
       },
-      "source": [
-        "!pip install --quiet git+https://github.com/pykale/pykale@main \\\n",
-        "    nilearn==0.11.1 yacs==0.1.8 \\\n",
-        "    && echo \"pykale, nilearn, and yacs installed successfully \u2705\" \\\n",
-        "    || echo \"Failed to install pykale, nilearn, and yacs \u274c\""
-      ],
-      "cell_type": "code",
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
-            "pykale, nilearn, and yacs installed successfully \u2705\n"
+            "pykale, gdown, nilearn, and yacs installed successfully ✅\n"
           ]
         }
       ],
-      "execution_count": null
+      "source": [
+        "!pip install --quiet --user \\\n",
+        "    git+https://github.com/pykale/pykale@main \\\n",
+        "    gdown==5.2.0 nilearn==0.10.4 yacs==0.1.8 \\\n",
+        "    && echo \"pykale, gdown, nilearn, and yacs installed successfully ✅\" \\\n",
+        "    || echo \"Failed to install pykale, gdown, nilearn, and yacs ❌\""
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {},
       "source": [
         "## Configuration\n",
         "\n",
-        "To minimize the footprint of the notebook when specifying configurations, we provide a `config.py` file that defines default parameters. These can be customized by supplying a `.yml` configuration file, such as `experiments/base.yml` as an example."
-      ],
-      "cell_type": "markdown"
+        "To minimize the footprint of the notebook when specifying configurations, we provide a `config.py` file that defines default parameters. These can be customized by supplying a `.yml` configuration file, such as `experiments/base.yml` as an example.\n",
+        "\n",
+        "Please refer to these files for detailed instructions on how to customize the experiment settings.  \n",
+        "We provide detailed descriptions of each configurable option in the following sections."
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": [
           "hide-input"
         ]
       },
-      "source": [
-        "from config import get_cfg_defaults\n",
-        "\n",
-        "cfg = get_cfg_defaults()\n",
-        "cfg.merge_from_file(\"experiments/base.yml\")\n",
-        "cfg.freeze()\n",
-        "print(cfg)"
-      ],
-      "cell_type": "code",
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
-            "CONNECTIVITY:\n",
-            "  MEASURES: ['pearson']\n",
             "CROSS_VALIDATION:\n",
             "  NUM_FOLDS: 10\n",
             "  NUM_REPEATS: 1\n",
             "  SPLIT: skf\n",
             "DATASET:\n",
-            "  ATLAS: aal\n",
-            "  BANDPASS: False\n",
-            "  GLOBAL_SIGNAL_REGRESSION: False\n",
-            "  PATH: nilearn_data\n",
-            "  QUALITY_CHECKED: False\n",
+            "  ATLAS: hcp-ica\n",
+            "  FC: tangent-pearson\n",
+            "  PATH: /home/zarizky/projects/embc-mmai25/tutorials/brain-disorder-diagnosis/data\n",
             "PHENOTYPE:\n",
             "  STANDARDIZE: site\n",
             "RANDOM_STATE: 0\n",
             "TRAINER:\n",
             "  CLASSIFIER: lr\n",
             "  NONLINEAR: False\n",
-            "  NUM_SEARCH_ITER: 50\n",
+            "  NUM_SEARCH_ITER: 20\n",
             "  NUM_SOLVER_ITER: 100\n",
-            "  N_JOBS: -4\n",
+            "  N_JOBS: -1\n",
+            "  PRE_DISPATCH: 2*n_jobs\n",
             "  REFIT: accuracy\n",
             "  SCORING: ['accuracy', 'roc_auc']\n",
             "  SEARCH_STRATEGY: random\n",
@@ -180,9 +160,17 @@
           ]
         }
       ],
-      "execution_count": null
+      "source": [
+        "from config import get_cfg_defaults\n",
+        "\n",
+        "cfg = get_cfg_defaults()\n",
+        "cfg.merge_from_file(\"experiments/base.yml\")\n",
+        "cfg.freeze()\n",
+        "print(cfg)"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -191,150 +179,129 @@
         "\n",
         "Typically, raw fMRI scans require extensive preprocessing before they can be used in a machine learning pipeline. However, the **ABIDE** dataset provides several preprocessed derivatives, which can be downloaded directly from the [Preprocessed Connectomes Project (PCP)](https://preprocessed-connectomes-project.org/abide/), eliminating the need for manual preprocessing.\n",
         "\n",
+        "Given the long runtime required to extract the functional connectivity embedding, we will omit this step from this notebook and provide pre-computed embeddings through the provided `load_data` function with the associated atlas.\n",
+        "\n",
+        "For users interested in computing the time series and functional connectivity embeddings from scratch, assuming preprocessed images are available, please refer to:\n",
+        "\n",
+        "- [`NiftiLabelsMasker` (Deterministic / 3D Atlas)](https://nilearn.github.io/stable/modules/generated/nilearn.maskers.NiftiLabelsMasker.html)\n",
+        "- [`NiftiMapsMasker` (Probabilistic / 4D Atlas)](https://nilearn.github.io/stable/modules/generated/nilearn.maskers.NiftiMapsMasker.html)\n",
+        "- `extract_functional_connectivity` function implemented in `preprocess.py`.\n",
+        "\n",
         "In this tutorial, we focus on the following preprocessing options:\n",
-        "- `atlas`: The **brain atlas** used to **extract ROI time series**. Available options include: `\"aal\"`, `\"cc200\"`, `\"cc400\"`, `\"dosenbach160\"`, `\"ez\"`, `\"ho\"`, and `\"tt\"`. Default: `\"aal\"`\n",
-        "- `bp`: Whether to apply **band-pass filter** to the time series between [0.01, 0.1] Hz. Default: `False`\n",
-        "- `gsr`: Whether to apply **global signal regression** to remove shared global noise from the signals. Default: `False`\n",
-        "- `qc`: Whether to include **only scans that passed all quality checks** provided by the dataset curators. Default: `True`"
-      ],
-      "cell_type": "markdown"
+        "\n",
+        "- **`path`** (or `data_dir`): Directory where the preprocessed dataset is located.\n",
+        "  - *Default:* Current working directory + `/data`\n",
+        "\n",
+        "- **`atlas`**: The brain atlas used to extract ROI time series.\n",
+        "  - Available options:\n",
+        "    - `\"aal\"`: AAL Atlas\n",
+        "    - `\"cc200\"`: Cameron Craddock 200\n",
+        "    - `\"cc400\"`: Cameron Craddock 400\n",
+        "    - `\"difumo64\"`: DiFuMo 64\n",
+        "    - `\"dos160\"`: Dosenbach 160\n",
+        "    - `\"hcp-ica\"`: HCP-ICA\n",
+        "    - `\"ho\"`: Harvard-Oxford\n",
+        "    - `\"tt\"`: Talairach-Tournoux  \n",
+        "  - *Default:* `\"cc200\"`\n",
+        "\n",
+        "- **`fc`**: The functional connectivity measure used to compute pairwise associations between ROIs.\n",
+        "  - Available options:\n",
+        "    - `\"pearson\"`: Pearson correlation\n",
+        "    - `\"partial\"`: Partial correlation\n",
+        "    - `\"tangent\"`: Tangent embedding\n",
+        "    - `\"precision\"`: Precision (inverse covariance)\n",
+        "    - `\"covariance\"`: Covariance\n",
+        "    - `\"tangent-pearson\"`: Tangent-Pearson hybrid connectivity  \n",
+        "  - *Default:* `\"tangent-pearson\"`"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
-      "source": [
-        "from nilearn.datasets import fetch_abide_pcp\n",
-        "\n",
-        "# Fetch the preprocessed ABIDE dataset using the specified preprocessing options\n",
-        "# This returns a dictionary containing region-wise time series and associated metadata\n",
-        "dataset = fetch_abide_pcp(\n",
-        "    data_dir=data_dir,\n",
-        "    # Select the atlas-specific ROI time series (e.g., 'rois_aal')\n",
-        "    derivatives=[f\"rois_{cfg.DATASET.ATLAS}\"],\n",
-        "    # Whether to apply band-pass filtering\n",
-        "    band_pass_filtering=cfg.DATASET.BANDPASS,\n",
-        "    # Whether to apply global signal regression\n",
-        "    global_signal_regression=cfg.DATASET.GLOBAL_SIGNAL_REGRESSION,\n",
-        "    # Whether to include only subjects that passed QC\n",
-        "    quality_checked=cfg.DATASET.QUALITY_CHECKED,\n",
-        ")\n",
-        "\n",
-        "time_series = dataset[f\"rois_{cfg.DATASET.ATLAS}\"]"
-      ],
-      "cell_type": "code",
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
-            "[get_dataset_dir] Dataset found in /home/zarizky/nilearn_data/ABIDE_pcp\n"
+            "✔ File found: /home/zarizky/projects/embc-mmai25/tutorials/brain-disorder-diagnosis/data/abide/fc/hcp-ica/tangent-pearson.npy\n",
+            "✔ File found: /home/zarizky/projects/embc-mmai25/tutorials/brain-disorder-diagnosis/data/abide/phenotypes.csv\n",
+            "✔ Atlas folder found: /home/zarizky/projects/embc-mmai25/tutorials/brain-disorder-diagnosis/data/atlas/deterministic/hcp-ica\n"
           ]
         }
       ],
-      "execution_count": null
+      "source": [
+        "from data import load_data\n",
+        "\n",
+        "fc, phenotypes, rois, coords = load_data(\n",
+        "    cfg.DATASET.PATH, cfg.DATASET.ATLAS, cfg.DATASET.FC\n",
+        ")"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
       "source": [
-        "## Phenotype Preprocessing \n",
+        "## Phenotype Preprocessing\n",
         "\n",
-        "The phenotypic information in the dataset contains several missing values. We impute and encode it to make it suitable for modeling.\n",
+        "The phenotypic information in the dataset contains several missing values. We impute and encode these variables to make them suitable for modeling. The `preprocess_phenotypic_data` function handles this functionality for us.\n",
         "\n",
-        "**Categorical Variables**\n",
+        "### Categorical Variables\n",
         "\n",
         "The following categorical phenotypes are used and will be **one-hot encoded**:\n",
+        "\n",
         "- `SITE_ID`\n",
         "- `SEX`\n",
         "- `HANDEDNESS_CATEGORY`\n",
         "- `EYE_STATUS_AT_SCAN`\n",
         "\n",
-        "**Continuous Variables**\n",
+        "### Continuous Variables\n",
         "\n",
         "The following continuous phenotypes will optionally be **standardized**:\n",
+        "\n",
         "- `AGE_AT_SCAN`\n",
         "- `FIQ`\n",
         "\n",
-        "Possible options to `standardize` the continuous phenotypes includes:\n",
-        "- `\"all\"` or `True`: Standardize across all subjects\n",
-        "- `\"site\"`: Standardize within each site\n",
-        "- `False`: No standardization\n",
+        "Standardization options for continuous phenotypes (`standardize` argument):\n",
+        "\n",
+        "- `\"all\"` or `True`: Standardize across all subjects.\n",
+        "- `\"site\"`: Standardize within each site.\n",
+        "- `False`: No standardization.\n",
+        "\n",
+        "### Handling Missing Values\n",
         "\n",
-        "**Handling Missing Values**\n",
         "- `HANDEDNESS_CATEGORY`: Missing values are assumed to correspond to `right-handed` subjects.\n",
         "- `FIQ`: Missing values are imputed with a default score of `100`.\n",
         "\n",
-        "**Label Encoding**\n",
+        "### Label Encoding\n",
         "\n",
         "The diagnostic label `DX_GROUP` is used to assign the target class:\n",
-        "- `CONTROL` \u2192 `0`\n",
-        "- `ASD` \u2192 `1`"
-      ],
-      "cell_type": "markdown"
-    },
-    {
-      "metadata": {
-        "tags": []
-      },
-      "source": [
-        "from preprocess import process_phenotypic_data\n",
-        "\n",
-        "# Process the phenotypic metadata from the ABIDE dataset\n",
-        "# This function handles:\n",
-        "# - Imputation of missing values (e.g., assuming right-handed for missing handedness)\n",
-        "# - One-hot encoding of categorical variables (e.g., sex, site, eye status)\n",
-        "# - Standardization of continuous variables based on the chosen strategy ('site' or 'all')\n",
-        "\n",
-        "# Returns:\n",
-        "# - `labels`: Binary class labels (0 = control, 1 = ASD)\n",
-        "# - `sites`: Site identifiers for domain adaptation\n",
-        "# - `phenotypes`: Feature matrix containing encoded and standardized phenotypic variables\n",
-        "labels, sites, phenotypes = process_phenotypic_data(\n",
-        "    dataset[\"phenotypic\"], cfg.PHENOTYPE.STANDARDIZE\n",
-        ")"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
-    },
-    {
-      "metadata": {
-        "tags": []
-      },
-      "source": [
-        "## Embedding Extraction\n",
-        "\n",
-        "Functional MRI (fMRI) time series data often vary in temporal length. However, many machine learning models, including those used in this study require fixed-size input. To address this, a common approach in fMRI analysis is to compute the functional connectivity (e.g., correlation) between regions of interest (ROIs), resulting in a fixed-size feature representation.\n",
-        "\n",
-        "Specifically, we compute a connectivity matrix for each subject, and extract the upper or lower triangular part (excluding the diagonal) to obtain a feature vector suitable for model training.\n",
         "\n",
-        "The available arguments for embedding extraction are:\n",
-        "- `measures`: A sequence of connectivity transformations applied to the ROI time series. Supported options include: `\"pearson\"`, `\"partial\"`, `\"tangent\"`, `\"covariance\"`, and `\"precision\"`. Default: `[\"pearson\"]`.\n",
-        "\n",
-        "Multiple transformations can be chained to compute composite connectivity representations. For example, the **Tangent-Pearson** method proposed by *Kunda et al.* can be specified via `measures = [\"tangent\", \"pearson\"]`. This design also allows for future extensions to support higher-order connectivity features.\n",
-        "\n",
-        "```{warning}\n",
-        "Given the long runtime needed for Tangent-Pearson, we opt to use `\"pearson\"` by default.\n",
-        "```"
-      ],
-      "cell_type": "markdown"
+        "- `CONTROL` → `0`\n",
+        "- `ASD` → `1`"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
+      "outputs": [],
       "source": [
-        "from preprocess import extract_functional_connectivity\n",
+        "from preprocess import preprocess_phenotypic_data\n",
         "\n",
-        "features = extract_functional_connectivity(time_series, cfg.CONNECTIVITY.MEASURES)"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
+        "labels, sites, phenotypes = preprocess_phenotypic_data(\n",
+        "    phenotypes, cfg.PHENOTYPE.STANDARDIZE\n",
+        ")"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -346,36 +313,10 @@
         "We explore different configurations including a baseline model, domain adaptation using site information, and an extended approach that incorporates additional phenotypic variables.\n",
         "\n",
         "Each model is evaluated using cross-validation, and we analyze the impact of domain adaptation on classification performance."
-      ],
-      "cell_type": "markdown"
-    },
-    {
-      "metadata": {
-        "tags": []
-      },
-      "source": [
-        "### Random Seed\n",
-        "\n",
-        "To ensure reproducibility across runs, we define a fixed random seed. This guarantees that all operations involving randomness, such as cross-validation splits, model initialization, and hyperparameter search to produce consistent results."
-      ],
-      "cell_type": "markdown"
-    },
-    {
-      "metadata": {
-        "tags": []
-      },
-      "source": [
-        "from sklearn.utils.validation import check_random_state\n",
-        "\n",
-        "# Convert the seed into a numpy-compatible RandomState instance\n",
-        "# This ensures consistent behavior across scikit-learn functions that rely on randomness\n",
-        "random_state = check_random_state(cfg.RANDOM_STATE)"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -386,17 +327,31 @@
         "\n",
         "Alternatively, we can also use **Leave-P-Groups-Out (LPGO)** cross-validation. This strategy is particularly useful in multi-site studies, as it ensures that data from the same group (e.g., imaging site) are not shared between training and test sets, enabling more realistic generalization assessment under domain shift.\n",
         "\n",
-        "For this tutorial we will specify several arguments:\n",
-        "- `split`: Defines the cross-validation strategy. `\"skf\"` for stratified k-fold to maintain label balance in each fold or use `\"lpgo\"` to evaluate generalization across sites by holding out entire groups (e.g., imaging sites). Default: `\"lpgo\"`\n",
-        "- `num_folds`: Sets how many folds to use for stratified k-fold or how many groups to leave out in LPGO. Default: `1`\n",
-        "- `num_cv_repeats`: Determines how many times the k-fold procedure is repeated to obtain more stable estimates (ignored when using LPGO). Default: `1`"
-      ],
-      "cell_type": "markdown"
+        "In this tutorial, we specify the following arguments:\n",
+        "\n",
+        "- **`split`**: Defines the cross-validation strategy.\n",
+        "  - Available options: \n",
+        "    - `\"skf\"`: Stratified K-Fold to maintain label balance in each fold.\n",
+        "    - `\"lpgo\"`: Leave-P-Groups-Out to evaluate generalization across sites by holding out entire groups (e.g., imaging sites).\n",
+        "  - *Default:* `\"skf\"`\n",
+        "\n",
+        "- **`num_folds`**: The number of folds for Stratified K-Fold or the number of groups to leave out in LPGO.\n",
+        "  - *Default:* `10`\n",
+        "\n",
+        "- **`num_repeats`**: The number of times the k-fold procedure is repeated to obtain more stable estimates (ignored when using LPGO).\n",
+        "  - *Default:* `5`\n",
+        "\n",
+        "- **`random_state`**: Seed for random number generators for reproducibility.\n",
+        "  - *Default:* `None`"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
+      "outputs": [],
       "source": [
         "from sklearn.model_selection import LeavePGroupsOut, RepeatedStratifiedKFold\n",
         "\n",
@@ -407,8 +362,8 @@
         "    n_splits=cfg.CROSS_VALIDATION.NUM_FOLDS,\n",
         "    # Number of repeat rounds\n",
         "    n_repeats=cfg.CROSS_VALIDATION.NUM_REPEATS,\n",
-        "    # Ensures reproducibility\n",
-        "    random_state=random_state,\n",
+        "    # Ensures reproducibility, intentionally set to the seed to have the same splits across runs\n",
+        "    random_state=cfg.RANDOM_STATE,\n",
         ")\n",
         "\n",
         "# Override with leave-p-proups-out if specified\n",
@@ -416,43 +371,91 @@
         "if cfg.CROSS_VALIDATION.SPLIT == \"lpgo\":\n",
         "    # Use group-based CV for domain adaptation or site bias evaluation\n",
         "    cv = LeavePGroupsOut(cfg.CROSS_VALIDATION.NUM_FOLDS)"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
       "source": [
         "### Model Definition\n",
-        "We define different model configurations used for classification. Each model shares the same base classifier (e.g., logistic regression), but differs in how domain adaptation is applied:\n",
+        "\n",
+        "We define several model configurations used for classification. Each model shares the same base classifier but differs in how domain adaptation is applied:\n",
+        "\n",
         "- **Baseline**: A standard model trained directly on functional connectivity features without domain adaptation.\n",
-        "- **Site Only**: A domain-adapted model that uses site labels as the adaptation factor, reducing site-specific bias.\n",
+        "- **Site Only**: A domain-adapted model that uses site labels as the adaptation factor to reduce site-specific bias.\n",
         "- **All Phenotypes**: An extended domain-adapted model that incorporates multiple phenotypic variables (e.g., age, sex, handedness) to further reduce inter-site variability.\n",
         "\n",
         "We also specify the hyperparameter search strategy and other training parameters for each configuration, including:\n",
-        "- `classifier`: The base model to use for classification. Available options include `\"logistic\"` for logistic regression, `\"ridge\"` for ridge classifier, and `\"svm\"` for support vector machines. Default: `\"logistic\"`\n",
-        "- `scoring`: A list of performance metrics (e.g., accuracy, F1, AUROC) used during cross-validation.\n",
-        "- `num_solver_iterations`: Maximum number of iterations allowed for the solver to converge during model fitting.\n",
-        "- `num_search_iterations`: Number of hyperparameter combinations to evaluate in a randomized search.\n",
-        "- `num_jobs`: Number of CPU cores used in parallel for hyperparameter tuning and model training. Set to `-1` to use all of the available CPU cores or `-k` to use all but `k` CPU cores.\n",
-        "- `verbose`: Controls the verbosity of the training output. Higher values provide more detailed logs."
-      ],
-      "cell_type": "markdown"
+        "\n",
+        "- **`classifier`**: The base model used for classification.\n",
+        "  - Available options:\n",
+        "    - `\"lda\"`: Linear Discriminant Analysis\n",
+        "    - `\"lr\"`: Logistic Regression\n",
+        "    - `\"linear_svm\"`: Linear Support Vector Machine\n",
+        "    - `\"svm\"`: Kernel Support Vector Machine\n",
+        "    - `\"ridge\"`: Ridge Classifier (L2-regularized linear model)\n",
+        "    - `\"auto\"`: Automatically selects an appropriate model based on data characteristics.\n",
+        "  - *Default:* `\"lr\"`\n",
+        "\n",
+        "- **`nonlinear`**: Whether to apply non-linear transformations (non-interpretable).\n",
+        "  - *Type:* `boolean`\n",
+        "  - *Default:* `False`\n",
+        "\n",
+        "- **`search_strategy`**: The hyperparameter search method.\n",
+        "  - Available options:\n",
+        "    - `\"random\"`: Randomly search over finite iterations.\n",
+        "    - `\"grid\"`: Search over all possible combinations.\n",
+        "  - *Default:* `\"random\"`\n",
+        "\n",
+        "- **`num_search_iterations`**: The number of hyperparameter combinations to evaluate in randomized search.\n",
+        "  - *Default:* `1,000`\n",
+        "\n",
+        "- **`num_solver_iterations`**: The maximum number of iterations allowed for solver convergence.\n",
+        "  - *Default:* `1,000,000`\n",
+        "\n",
+        "- **`scoring`**: A list of performance metrics used during cross-validation.\n",
+        "  - Available options:\n",
+        "    - `\"accuracy\"`: Accuracy\n",
+        "    - `\"precision\"`: Precision\n",
+        "    - `\"recall\"`: Recall\n",
+        "    - `\"f1\"`: F1-Score\n",
+        "    - `\"roc_auc\"`: Area Under ROC Curve (AUROC)\n",
+        "    - `\"matthews_corrcoef\"`: Matthews Correlation Coefficient (MCC)\n",
+        "  - *Default:* `[\"accuracy\", \"roc_auc\"]`\n",
+        "\n",
+        "- **`refit`**: The metric used to refit the best model after hyperparameter tuning.\n",
+        "  - *Default:* `\"accuracy\"`\n",
+        "\n",
+        "- **`num_jobs`**: The number of CPU cores used for training and hyperparameter search.\n",
+        "  - Set to `-1` for all CPUs, `-k` for all but `k` CPUs.\n",
+        "  - *Default:* `-1`\n",
+        "\n",
+        "- **`pre_dispatch`**: Controls job pre-dispatching for parallel execution.\n",
+        "  - *Default:* `\"2*n_jobs\"`\n",
+        "\n",
+        "- **`verbose`**: Controls verbosity of training output.\n",
+        "  - *Default:* `0`\n",
+        "\n",
+        "- **`random_state`**: Seed for random number generators for reproducibility.\n",
+        "  - *Default:* `None`"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
+      "outputs": [],
       "source": [
         "from sklearn.base import clone\n",
         "from kale.pipeline.multi_domain_adapter import AutoMIDAClassificationTrainer as Trainer\n",
         "\n",
-        "# Configuration with cv included\n",
+        "# Configuration with cv and random_state/seed included\n",
         "trainer_cfg = {k.lower(): v for k, v in cfg.TRAINER.items()}\n",
-        "trainer_cfg = {**trainer_cfg, \"cv\": cv}\n",
+        "trainer_cfg = {**trainer_cfg, \"cv\": cv, \"random_state\": cfg.RANDOM_STATE}\n",
         "\n",
         "# Initialize dictionary for different trainers\n",
         "trainers = {}\n",
@@ -466,12 +469,10 @@
         "# Clone the 'site_only' trainer to create 'all_phenotypes' trainer\n",
         "# This enables reusing the same training configuration, while modifying only the input domain factors\n",
         "trainers[\"all_phenotypes\"] = clone(trainers[\"site_only\"])"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -481,19 +482,29 @@
         "We train each model configuration using the previously defined cross-validation strategy. The training process involves fitting the model on functional connectivity features and evaluating its performance using multiple scoring metrics (e.g., accuracy, F1-score, AUROC).\n",
         "\n",
         "For models with domain adaptation, we pass additional domain factors (such as site or phenotypic variables) to guide the alignment of embedding. Cross-validation is performed to ensure robust performance estimates and to select the best hyperparameter configuration for each model."
-      ],
-      "cell_type": "markdown"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Fitting all_phenotypes model: 100%|██████████| 3/3 [00:21<00:00,  7.23s/it]\n"
+          ]
+        }
+      ],
       "source": [
         "import pandas as pd\n",
         "from tqdm import tqdm\n",
         "\n",
         "# Define common training arguments for all models: features (X), labels (y), and group info (sites)\n",
-        "fit_args = {\"x\": features, \"y\": labels, \"groups\": sites}\n",
+        "fit_args = {\"x\": fc, \"y\": labels, \"groups\": sites}\n",
         "\n",
         "cv_results = {}\n",
         "for model in (pbar := tqdm(trainers)):\n",
@@ -506,20 +517,10 @@
         "    pbar.set_description(f\"Fitting {model} model\")\n",
         "    trainers[model].fit(**args)\n",
         "    cv_results[model] = pd.DataFrame(trainers[model].cv_results_)"
-      ],
-      "cell_type": "code",
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "Fitting all_phenotypes model: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 3/3 [02:14<00:00, 44.96s/it]\n"
-          ]
-        }
-      ],
-      "execution_count": null
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -529,27 +530,16 @@
         "We evaluate and compare the performance of different model configurations using cross-validation results. We aggregate the top-performing scores for each model based on a specified evaluation metric (e.g., accuracy), allowing us to assess the effectiveness of domain adaptation strategies.\n",
         "\n",
         "By comparing models with and without domain adaptation, we can determine the impact of incorporating site and phenotypic information on multi-site autism classification performance. This analysis helps identify which configurations generalize best across heterogeneous imaging sites."
-      ],
-      "cell_type": "markdown"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
-      "source": [
-        "from parsing import compile_results\n",
-        "\n",
-        "# Compile the cross-validation results into a summary table,\n",
-        "# sorting by the model with the highest test accuracy across CV folds\n",
-        "compiled_results = compile_results(cv_results, \"accuracy\")\n",
-        "\n",
-        "# Display the compiled results DataFrame (models as rows, metrics as formatted strings)\n",
-        "display(compiled_results)"
-      ],
-      "cell_type": "code",
       "outputs": [
         {
-          "output_type": "display_data",
           "data": {
             "text/html": [
               "<div>\n",
@@ -582,18 +572,18 @@
               "  <tbody>\n",
               "    <tr>\n",
               "      <th>Baseline</th>\n",
-              "      <td>0.6736 \u00b1 0.0489</td>\n",
-              "      <td>0.7329 \u00b1 0.0480</td>\n",
+              "      <td>0.6629 ± 0.0523</td>\n",
+              "      <td>0.7105 ± 0.0556</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <th>Site Only</th>\n",
-              "      <td>0.6860 \u00b1 0.0304</td>\n",
-              "      <td>0.7307 \u00b1 0.0273</td>\n",
+              "      <td>0.6609 ± 0.0509</td>\n",
+              "      <td>0.7127 ± 0.0596</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <th>All Phenotypes</th>\n",
-              "      <td>0.6794 \u00b1 0.0554</td>\n",
-              "      <td>0.7319 \u00b1 0.0517</td>\n",
+              "      <td>0.6474 ± 0.0597</td>\n",
+              "      <td>0.7057 ± 0.0514</td>\n",
               "    </tr>\n",
               "  </tbody>\n",
               "</table>\n",
@@ -602,26 +592,37 @@
             "text/plain": [
               "                       Accuracy            AUROC\n",
               "Model                                           \n",
-              "Baseline        0.6736 \u00b1 0.0489  0.7329 \u00b1 0.0480\n",
-              "Site Only       0.6860 \u00b1 0.0304  0.7307 \u00b1 0.0273\n",
-              "All Phenotypes  0.6794 \u00b1 0.0554  0.7319 \u00b1 0.0517"
+              "Baseline        0.6629 ± 0.0523  0.7105 ± 0.0556\n",
+              "Site Only       0.6609 ± 0.0509  0.7127 ± 0.0596\n",
+              "All Phenotypes  0.6474 ± 0.0597  0.7057 ± 0.0514"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
-      "execution_count": null
+      "source": [
+        "from parsing import compile_results\n",
+        "\n",
+        "# Compile the cross-validation results into a summary table,\n",
+        "# sorting by the model with the highest test accuracy across CV folds\n",
+        "compiled_results = compile_results(cv_results, \"accuracy\")\n",
+        "\n",
+        "# Display the compiled results DataFrame (models as rows, metrics as formatted strings)\n",
+        "display(compiled_results)"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
       "source": [
         "# Interpretation"
-      ],
-      "cell_type": "markdown"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
@@ -629,103 +630,113 @@
         "We interpret the trained models by analyzing the learned weights associated with functional connectivity features. Specifically, we extract the top-weighted ROI pairs that contributed most to the classification decision.\n",
         "\n",
         "These weights are visualized as a **connectome plot**, allowing us to examine which brain region interactions are most informative for distinguishing individuals with autism from controls. This not only enhances the interpretability of the model but also provides potential insights into neurobiological patterns relevant to autism."
-      ],
-      "cell_type": "markdown"
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "tags": []
       },
-      "source": [
-        "import seaborn as sns\n",
-        "from nilearn.plotting import find_parcellation_cut_coords\n",
-        "from kale.interpret.visualize import visualize_connectome\n",
-        "from nilearn.datasets import fetch_atlas_aal\n",
-        "\n",
-        "aal = fetch_atlas_aal()\n",
-        "coords = find_parcellation_cut_coords(aal.maps)\n",
-        "labels = aal.labels\n",
-        "\n",
-        "proj = visualize_connectome(\n",
-        "    trainers[\"baseline\"].coef_.ravel(),\n",
-        "    labels,\n",
-        "    coords,\n",
-        "    0.002,  # Take top 0.2% of connections\n",
-        "    legend_params={\n",
-        "        \"bbox_to_anchor\": (2.75, -0.1),  # Align legend outside the plot\n",
-        "        \"ncol\": 2,\n",
-        "    },\n",
-        ")\n",
-        "\n",
-        "# Display the resulting connectome plot\n",
-        "display(proj)"
-      ],
-      "cell_type": "code",
       "outputs": [
         {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "[get_dataset_dir] Dataset found in /home/zarizky/nilearn_data/aal_SPM12\n"
-          ]
-        },
-        {
-          "output_type": "display_data",
           "data": {
             "text/plain": [
-              "<nilearn.plotting.displays._projectors.OrthoProjector at 0x79dd265e3e80>"
+              "<nilearn.plotting.displays._projectors.OrthoProjector at 0x751dbdeaf640>"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         },
         {
-          "output_type": "display_data",
           "data": {
-            "image/png": "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",
+            "image/png": "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",
             "text/plain": [
               "<Figure size 660x350 with 5 Axes>"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
-      "execution_count": null
+      "source": [
+        "import numpy as np\n",
+        "from kale.interpret.visualize import visualize_connectome\n",
+        "\n",
+        "# Fetch coefficients to visualize feature importance\n",
+        "coef = trainers[\"site_only\"].coef_.ravel()\n",
+        "# check if coef != features, assumes augmented features with phenotypes/sites\n",
+        "if coef.shape[0] != fc.shape[1]:\n",
+        "    coef, _ = np.split(coef, [fc.shape[1]])\n",
+        "\n",
+        "# Visualize the coefficients as a connectome plot\n",
+        "proj = visualize_connectome(\n",
+        "    trainers[\"baseline\"].coef_.ravel(),\n",
+        "    rois,\n",
+        "    coords,\n",
+        "    0.015,  # Take top 1.5% of connections\n",
+        "    legend_params={\n",
+        "        \"bbox_to_anchor\": (2.75, -0.1),  # Align legend outside the plot\n",
+        "        \"ncol\": 2,\n",
+        "    },\n",
+        ")\n",
+        "\n",
+        "# Display the resulting connectome plot\n",
+        "display(proj)"
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
         "tags": []
       },
       "source": [
+        "### Interpretation of Discriminative Connectivity Patterns\n",
+        "\n",
         "This plot shows the **most discriminative ROI connections** for classifying ASD vs Control subjects.\n",
         "- **Red edges** indicate connections **stronger in ASD**.\n",
         "- **Blue edges** indicate connections **stronger in Control**.\n",
-        "- Color intensity reflects the **magnitude of contribution** to the model\u2019s decision.\n",
+        "- Color intensity reflects the **magnitude of contribution** to the model’s decision.\n",
         "\n",
         "---\n",
         "\n",
         "**Key Patterns**:\n",
-        "- **Cingulate Cortex**:\n",
-        "    - *Cingulum_Ant_L*, *Cingulum_Mid_L*\n",
-        "    - Central to **emotional regulation** and default mode network (DMN) activity, often disrupted in ASD.\n",
-        "- **Temporal Poles**:\n",
-        "    - *Temporal_Pole_Mid_L*, *Temporal_Pole_Mid_R*, *Temporal_Pole_Sup_R*\n",
-        "    - Involved in **social cognition**, **language**, and **emotion processing**, key deficits in ASD.\n",
-        "- **Cerebellum Subregions**:\n",
-        "    - *Cerebellum_7b_R*, *Cerebellum_9_L*, *Cerebellum_Crus1_R*\n",
-        "    - Linked to **motor control**, **timing**, and increasingly, to **higher-order cognition** in ASD studies.\n",
-        "- **Limbic and Memory-related Areas**:\n",
-        "    - *Hippocampus_R*, *ParaHippocampal_L/R*, *Amygdala_R*\n",
-        "    - Frequently show **altered volume and connectivity** in ASD, affecting memory, learning, and emotion.\n",
-        "- **Sensory and Integration Regions**:\n",
-        "    - *Heschl_L*, *Rolandic_Oper_R*, *Supramarginal_R*\n",
-        "    - Implicated in **auditory** and **sensorimotor integration**, which are commonly atypical in ASD.\n",
-        "- **Occipital and Parietal Areas**:\n",
-        "    - *Occipital_Inf_L*, *Parietal_Inf_R*\n",
-        "    - Linked to **visual processing** and **attention control**, where ASD differences have been reported.\n",
-        "\n",
-        "The interpretability analysis of the trained model reveals that **functional connectivity differences across key brain regions** contribute meaningfully to distinguishing **ASD** from **Control** subjects."
-      ],
-      "cell_type": "markdown"
+        "\n",
+        "- **Default Mode Network (DMN)**:\n",
+        "    - *DefaultMode.MPFC*, *DefaultMode.PCC*, *DefaultMode.LP (L/R)*\n",
+        "    - Core hubs of the DMN, associated with **self-referential processing**, **social cognition**, and often disrupted in ASD.\n",
+        "\n",
+        "- **Fronto-Parietal Network**:\n",
+        "    - *FrontoParietal.PPC (L)*\n",
+        "    - Involved in **executive function** and **cognitive flexibility**, domains typically impaired in ASD.\n",
+        "\n",
+        "- **Dorsal Attention Network**:\n",
+        "    - *DorsalAttention.IPS (L)*\n",
+        "    - Associated with **goal-directed attention**, potentially altered in ASD subjects.\n",
+        "\n",
+        "- **Salience Network**:\n",
+        "    - *Salience.SMG (R)*\n",
+        "    - Plays a role in **interoception** and **social-emotional processing**, relevant for ASD symptoms.\n",
+        "\n",
+        "- **Language Network**:\n",
+        "    - *Language.pSTG (R)*\n",
+        "    - Critical for **language comprehension** and **social communication**, often affected in ASD.\n",
+        "\n",
+        "- **Sensorimotor and Cerebellar Regions**:\n",
+        "    - *SensoriMotor.Lateral (L)*, *Cerebellar.Posterior*\n",
+        "    - Linked to **motor coordination** and **sensorimotor integration**, commonly atypical in ASD.\n",
+        "\n",
+        "The interpretability analysis of the trained model highlights that **functional connectivity alterations across DMN, attention, salience, language, and sensorimotor systems** are key discriminative factors for distinguishing **ASD** from **Control** subjects."
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "embc25",
+      "language": "python",
+      "name": "python3"
     }
-  ]
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
 }
diff --git a/tutorials/brain-disorder-diagnosis/parsing.py b/tutorials/brain-disorder-diagnosis/parsing.py
index 33f2733..dc6fba4 100644
--- a/tutorials/brain-disorder-diagnosis/parsing.py
+++ b/tutorials/brain-disorder-diagnosis/parsing.py
@@ -2,6 +2,8 @@
 from collections import defaultdict
 from sklearn.utils._param_validation import validate_params, StrOptions
 
+__all__ = ["compile_results"]
+
 # Mapping for model and score display names
 MODEL = ["baseline", "site_only", "all_phenotypes"]
 MODEL = {model: " ".join(model.split("_")).title() for model in MODEL}
@@ -25,6 +27,7 @@ def compile_results(cv_results, sort_by):
     cv_results : dict of str -> pd.DataFrame or dict of str -> dict of str -> list
         Dictionary mapping model names to cross-validation results.
         Each entry should either be a DataFrame or a dictionary of dictionary of list.
+
     sort_by : str
         Metric to use for selecting the best-performing model variant.
         Available ones include: "accuracy", "precision", "recall", "f1", "roc_auc",
diff --git a/tutorials/brain-disorder-diagnosis/preprocess.py b/tutorials/brain-disorder-diagnosis/preprocess.py
index 2c02204..57779f5 100644
--- a/tutorials/brain-disorder-diagnosis/preprocess.py
+++ b/tutorials/brain-disorder-diagnosis/preprocess.py
@@ -11,6 +11,8 @@
     validate_params,
 )
 
+__all__ = ["preprocess_phenotypic_data", "extract_functional_connectivity"]
+
 SELECTED_PHENOTYPES = [
     "SUB_ID",
     "SITE_ID",
@@ -51,7 +53,7 @@
     {"data": [pd.DataFrame], "standardize": [StrOptions({"site", "all"}), "boolean"]},
     prefer_skip_nested_validation=False,
 )
-def process_phenotypic_data(data, standardize=False):
+def preprocess_phenotypic_data(data, standardize=False):
     """Process phenotypic data to impute missing values and and encode categorical
     variables including sex, handedness, eye status at scan, and diagnostic group.
 
@@ -60,22 +62,20 @@ def process_phenotypic_data(data, standardize=False):
     data : pd.DataFrame of shape (n_subjects, n_phenotypes)
         The phenotypes data to be processed.
 
-    standardize: boolean or str of ("site", "all")
-                Standardize FIQ and age. The default is 0.
-                Setting to True or "all" standardizes the
-                values over all subjects while "site"
+    standardize : boolean or str of ("site", "all"), (default=False)
+                Standardize FIQ and age. Setting to True or "all"
+                standardizes the values over all subjects while "site"
                 standardizes according to the site.
 
-    verbose : int, optional
-            The verbosity level. The default is 0.
-            verbose > 0 will log the current processing step.
-
     Returns
     -------
-    labels : pd.Series of shape (n_subjects)
+    labels : array-like of shape (n_subjects)
             The encoded classification group. 0 is "CONTROL" and
             1 is "ASD"
 
+    sites : array-like of shape (n_subjects)
+            The site IDs for each subject.
+
     phenotypes : pd.DataFrame of shape (n_subjects, n_selected_phenotypes)
                 The processed selected phenotype data with imputed values.
     """
@@ -113,7 +113,7 @@ def process_phenotypic_data(data, standardize=False):
     data = data[SELECTED_PHENOTYPES].set_index("SUB_ID")
 
     # Separate the class labels, sites, and phenotypes
-    labels = data["DX_GROUP"].map({"CONTROL": 0, "ASD": 1})
+    labels = data["DX_GROUP"].map({"CONTROL": 0, "ASD": 1}).to_numpy()
     sites = data["SITE_ID"].to_numpy()
     phenotypes = data.drop(columns=["DX_GROUP"])
     # One-hot encode categorical valued phenotypes
@@ -134,9 +134,8 @@ def extract_functional_connectivity(data, measures=["pearson"]):
         An array of numpy arrays, where each array is a time series of shape (t, n_rois).
         The time series data for each subject.
 
-    measures : list[str], optional
+    measures : list[str], optional (default=["pearson"])
         A list of connectivity measures to use for feature extraction.
-        The default is ["pearson"].
         Supported measures are "pearson", "partial", "tangent", "covariance", and "precision".
         Multiple measures can be specified as a list to compose a higher-order measure.