{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e0d62664",
   "metadata": {},
   "source": [
    "# X-Set Enrichment Analysis (XSEA; c.f. ABAnnotate)\n",
    "\n",
    "So far, we've been computing colocalization values between a brain map and individual reference maps — one correlation per receptor or gene. But sometimes we don't care about individual maps; we want to know whether the brain pattern of interest is broadly associated with a *group* of maps — say, all serotonin receptors, or all genes expressed in excitatory neurons.\n",
    "\n",
    "This is the idea behind **X-Set Enrichment Analysis (XSEA)**. The concept is closely related to Gene Set Enrichment Analysis (GSEA) in transcriptomics, adapted for brain maps.\n",
    "\n",
    "The concept of XSEA used here was first implemented in the MATLAB toolbox [**ABAnnotate**](https://github.com/leondlotter/ABAnnotate), a predecessor of NiSpace. If you've used ABAnnotate, you'll find the concepts familiar.\n",
    "\n",
    "## The idea\n",
    "\n",
    "Given a brain map and a set of reference maps (e.g., all receptor maps for serotonin), XSEA computes:\n",
    "\n",
    "1. The mean colocalization between the brain map and all maps in the set.\n",
    "2. A p-value asking: is this mean colocalization higher than expected when the brain map is replaced by a spatially-constrained random map?\n",
    "\n",
    "The result is one statistic per *set*, not per individual map.\n",
    "\n",
    "## A note on null models\n",
    "\n",
    "There are two natural null hypotheses for XSEA:\n",
    "\n",
    "1. **Permute the input map** (default): generate surrogate maps of the brain map and recompute mean colocalizations. This tests whether the observed mean is higher than expected under spatial randomness.\n",
    "2. **Permute the sets**: randomly sample sets from a larger background population of maps and ask whether the observed set mean is higher than random sets.\n",
    "\n",
    "Ben Fulcher et al. (2021, *Nature Communications*) showed that random set sampling can inflate false positives when maps within a set are highly co-expressed (correlated). NiSpace therefore defaults to map permutation, following the approach of ABAnnotate. Pass `permute_sets=True` to switch to set permutation if needed. However, this is currently not recommended. In the future, we will implement within-set correlation-matched set resampling, which can address this issue."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6120975d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:06:41.215586Z",
     "iopub.status.busy": "2026-06-01T13:06:41.215454Z",
     "iopub.status.idle": "2026-06-01T13:06:41.628207Z",
     "shell.execute_reply": "2026-06-01T13:06:41.627893Z"
    }
   },
   "outputs": [],
   "source": [
    "import tqdm.notebook\n",
    "tqdm.notebook.tqdm = tqdm.tqdm\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5aab78c1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:06:41.629849Z",
     "iopub.status.busy": "2026-06-01T13:06:41.629701Z",
     "iopub.status.idle": "2026-06-01T13:06:43.536677Z",
     "shell.execute_reply": "2026-06-01T13:06:43.536382Z"
    }
   },
   "outputs": [],
   "source": [
    "from nispace.datasets import fetch_reference, fetch_example\n",
    "from nispace.io import load_img\n",
    "from nispace.api import NiSpace"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db130d48",
   "metadata": {},
   "source": [
    "## Dataset setup\n",
    "\n",
    "We'll run XSEA on the pain map against mRNA gene expression data, testing whether pain-related brain activation broadly aligns with the expression of particular cell types.\n",
    "\n",
    "The mRNA reference dataset is derived from the Allen Human Brain Atlas (AHBA) and provides mean gene expression per brain region for thousands of genes, organized into sets such as cell type markers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f6a4ef34",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:06:43.538369Z",
     "iopub.status.busy": "2026-06-01T13:06:43.538191Z",
     "iopub.status.idle": "2026-06-01T13:06:43.793287Z",
     "shell.execute_reply": "2026-06-01T13:06:43.792943Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.datasets: Loading mrna maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.datasets: Loading integrated collection 'CellTypesPsychEncodeTPM' for dataset 'mrna'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.datasets: Filtering maps by collection.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.datasets: Loading and inner-merging data parcellated with 'Schaefer100Parcels7Networks' and 'TianS1'\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mRNA data: 465 genes across 24 sets x 116 parcels\n",
      "Set names: ['Ex1 CortProject (L2/3)', 'Ex2 Granule (L3/4)', 'Ex3 Granule (L4)', 'Ex4 SubcortProject (L4)', 'Ex5 SubcortProject (L4-6)', 'Ex6 SubcortProject (L5-6)', 'Ex7 Corticothalamic', 'Ex8 Corticothalamic (L6)', 'In1 VIP+RELN+NDNF+ (L1/2)', 'In2 VIP+RELN-NDNF- (L6)', 'In3 VIP+RELN+NDNF- (L6)', 'In4 VIP-RELN+NDNF+ (L1-3)', 'In5 CCK+NOS1+CALB2+ (L2/3)', 'In6 PVALB+CRHBP+ (L4/5)', 'In7 SST+CALB1+NPY+ (L5/6)', 'In8 SST+NOS1+ (L6)', 'Astrocyte', 'Endothelial', 'Developing-quiescent', 'Developing-replicating', 'Microglia', 'Other Neurons', 'OPC', 'Oligodendrocyte']\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>hemi-L_div-Vis_lab-1</th>\n",
       "      <th>hemi-L_div-Vis_lab-2</th>\n",
       "      <th>hemi-L_div-Vis_lab-3</th>\n",
       "      <th>hemi-L_div-Vis_lab-4</th>\n",
       "      <th>hemi-L_div-Vis_lab-5</th>\n",
       "      <th>hemi-L_div-Vis_lab-6</th>\n",
       "      <th>hemi-L_div-Vis_lab-7</th>\n",
       "      <th>hemi-L_div-Vis_lab-8</th>\n",
       "      <th>hemi-L_div-Vis_lab-9</th>\n",
       "      <th>hemi-L_div-SomMot_lab-1</th>\n",
       "      <th>...</th>\n",
       "      <th>hemi-L_lab-PUT</th>\n",
       "      <th>hemi-L_lab-CAU</th>\n",
       "      <th>hemi-R_lab-HIP</th>\n",
       "      <th>hemi-R_lab-AMY</th>\n",
       "      <th>hemi-R_lab-pTHA</th>\n",
       "      <th>hemi-R_lab-aTHA</th>\n",
       "      <th>hemi-R_lab-NAc</th>\n",
       "      <th>hemi-R_lab-GP</th>\n",
       "      <th>hemi-R_lab-PUT</th>\n",
       "      <th>hemi-R_lab-CAU</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>set</th>\n",
       "      <th>map</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">Ex1 CortProject (L2/3)</th>\n",
       "      <th>CAMK2A</th>\n",
       "      <td>0.842136</td>\n",
       "      <td>0.826765</td>\n",
       "      <td>0.826967</td>\n",
       "      <td>0.827184</td>\n",
       "      <td>0.817241</td>\n",
       "      <td>0.822723</td>\n",
       "      <td>0.815382</td>\n",
       "      <td>0.818394</td>\n",
       "      <td>0.815004</td>\n",
       "      <td>0.819051</td>\n",
       "      <td>...</td>\n",
       "      <td>0.452723</td>\n",
       "      <td>0.571612</td>\n",
       "      <td>0.792884</td>\n",
       "      <td>0.710187</td>\n",
       "      <td>0.414296</td>\n",
       "      <td>0.366631</td>\n",
       "      <td>0.485376</td>\n",
       "      <td>0.288345</td>\n",
       "      <td>0.537562</td>\n",
       "      <td>0.596598</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CCDC88C</th>\n",
       "      <td>0.490978</td>\n",
       "      <td>0.415965</td>\n",
       "      <td>0.401705</td>\n",
       "      <td>0.323039</td>\n",
       "      <td>0.311288</td>\n",
       "      <td>0.341007</td>\n",
       "      <td>0.394077</td>\n",
       "      <td>0.361664</td>\n",
       "      <td>0.407064</td>\n",
       "      <td>0.432452</td>\n",
       "      <td>...</td>\n",
       "      <td>0.784354</td>\n",
       "      <td>0.905244</td>\n",
       "      <td>0.417680</td>\n",
       "      <td>0.772467</td>\n",
       "      <td>0.433421</td>\n",
       "      <td>0.556930</td>\n",
       "      <td>0.916510</td>\n",
       "      <td>0.728213</td>\n",
       "      <td>0.748571</td>\n",
       "      <td>0.981271</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CDH9</th>\n",
       "      <td>0.742186</td>\n",
       "      <td>0.618615</td>\n",
       "      <td>0.623595</td>\n",
       "      <td>0.567650</td>\n",
       "      <td>0.546706</td>\n",
       "      <td>0.577347</td>\n",
       "      <td>0.681953</td>\n",
       "      <td>0.648653</td>\n",
       "      <td>0.656170</td>\n",
       "      <td>0.708508</td>\n",
       "      <td>...</td>\n",
       "      <td>0.483765</td>\n",
       "      <td>0.509307</td>\n",
       "      <td>0.638481</td>\n",
       "      <td>0.786927</td>\n",
       "      <td>0.225884</td>\n",
       "      <td>0.266731</td>\n",
       "      <td>0.684596</td>\n",
       "      <td>0.402965</td>\n",
       "      <td>0.512751</td>\n",
       "      <td>0.539964</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3 rows × 116 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                hemi-L_div-Vis_lab-1  hemi-L_div-Vis_lab-2  \\\n",
       "set                    map                                                   \n",
       "Ex1 CortProject (L2/3) CAMK2A               0.842136              0.826765   \n",
       "                       CCDC88C              0.490978              0.415965   \n",
       "                       CDH9                 0.742186              0.618615   \n",
       "\n",
       "                                hemi-L_div-Vis_lab-3  hemi-L_div-Vis_lab-4  \\\n",
       "set                    map                                                   \n",
       "Ex1 CortProject (L2/3) CAMK2A               0.826967              0.827184   \n",
       "                       CCDC88C              0.401705              0.323039   \n",
       "                       CDH9                 0.623595              0.567650   \n",
       "\n",
       "                                hemi-L_div-Vis_lab-5  hemi-L_div-Vis_lab-6  \\\n",
       "set                    map                                                   \n",
       "Ex1 CortProject (L2/3) CAMK2A               0.817241              0.822723   \n",
       "                       CCDC88C              0.311288              0.341007   \n",
       "                       CDH9                 0.546706              0.577347   \n",
       "\n",
       "                                hemi-L_div-Vis_lab-7  hemi-L_div-Vis_lab-8  \\\n",
       "set                    map                                                   \n",
       "Ex1 CortProject (L2/3) CAMK2A               0.815382              0.818394   \n",
       "                       CCDC88C              0.394077              0.361664   \n",
       "                       CDH9                 0.681953              0.648653   \n",
       "\n",
       "                                hemi-L_div-Vis_lab-9  hemi-L_div-SomMot_lab-1  \\\n",
       "set                    map                                                      \n",
       "Ex1 CortProject (L2/3) CAMK2A               0.815004                 0.819051   \n",
       "                       CCDC88C              0.407064                 0.432452   \n",
       "                       CDH9                 0.656170                 0.708508   \n",
       "\n",
       "                                ...  hemi-L_lab-PUT  hemi-L_lab-CAU  \\\n",
       "set                    map      ...                                   \n",
       "Ex1 CortProject (L2/3) CAMK2A   ...        0.452723        0.571612   \n",
       "                       CCDC88C  ...        0.784354        0.905244   \n",
       "                       CDH9     ...        0.483765        0.509307   \n",
       "\n",
       "                                hemi-R_lab-HIP  hemi-R_lab-AMY  \\\n",
       "set                    map                                       \n",
       "Ex1 CortProject (L2/3) CAMK2A         0.792884        0.710187   \n",
       "                       CCDC88C        0.417680        0.772467   \n",
       "                       CDH9           0.638481        0.786927   \n",
       "\n",
       "                                hemi-R_lab-pTHA  hemi-R_lab-aTHA  \\\n",
       "set                    map                                         \n",
       "Ex1 CortProject (L2/3) CAMK2A          0.414296         0.366631   \n",
       "                       CCDC88C         0.433421         0.556930   \n",
       "                       CDH9            0.225884         0.266731   \n",
       "\n",
       "                                hemi-R_lab-NAc  hemi-R_lab-GP  hemi-R_lab-PUT  \\\n",
       "set                    map                                                      \n",
       "Ex1 CortProject (L2/3) CAMK2A         0.485376       0.288345        0.537562   \n",
       "                       CCDC88C        0.916510       0.728213        0.748571   \n",
       "                       CDH9           0.684596       0.402965        0.512751   \n",
       "\n",
       "                                hemi-R_lab-CAU  \n",
       "set                    map                      \n",
       "Ex1 CortProject (L2/3) CAMK2A         0.596598  \n",
       "                       CCDC88C        0.981271  \n",
       "                       CDH9           0.539964  \n",
       "\n",
       "[3 rows x 116 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# pain map (NeuroQuery meta-analytic z-map)\n",
    "pain_map = load_img(\"neuroquery/pain.nii.gz\")\n",
    "\n",
    "# mRNA reference: cell type marker sets (Lake et al 2016)\n",
    "# parcellation: Schaefer100+TianS1 (low resolution to match coarse ABA data sampling)\n",
    "mrna = fetch_reference(\n",
    "    \"mrna\",\n",
    "    parcellation=\"Schaefer100TianS1\",\n",
    "    collection=\"CellTypesPsychEncodeTPM\",\n",
    "    print_references=False\n",
    ")\n",
    "print(f\"mRNA data: {mrna.shape[0]} genes across {mrna.index.get_level_values('set').nunique()} sets x {mrna.shape[1]} parcels\")\n",
    "print(f\"Set names: {list(mrna.index.get_level_values('set').unique())}\")\n",
    "mrna.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2152ea4",
   "metadata": {},
   "source": [
    "Notice the two-level MultiIndex: the first level is the cell type group (\"set\"), the second is the individual gene. The set structure is what XSEA operates on.\n",
    "\n",
    "## Running XSEA step by step\n",
    "\n",
    "XSEA is triggered by passing `xsea=True` (or a specific aggregation method) to `colocalize()`. This computes colocalization with each individual map first, then averages within sets."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5b1f83d7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:06:43.794905Z",
     "iopub.status.busy": "2026-06-01T13:06:43.794729Z",
     "iopub.status.idle": "2026-06-01T13:06:50.756526Z",
     "shell.execute_reply": "2026-06-01T13:06:50.756233Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.api: *** NiSpace.fit() - Data extraction and preparation. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.core.parcellation: Building combined Parcellation 'Schaefer100Parcels7Networks+TianS1' from library.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.core.parcellation:   Common MNI space(s) for combined: ['MNI152NLin2009cAsym', 'MNI152NLin6Asym'].\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.core.parcellation:   Merging 'Schaefer100Parcels7Networks' and 'TianS1' for space 'MNI152NLin2009cAsym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:43 | nispace.core.parcellation:   Merging 'Schaefer100Parcels7Networks' and 'TianS1' for space 'MNI152NLin6Asym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.core.parcellation:   Fetching cx surface data for 'Schaefer100Parcels7Networks' in 'fsaverage' (for spin tests).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.core.parcellation:   Fetching cx surface data for 'Schaefer100Parcels7Networks' in 'fsLR' (for spin tests).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.core.parcellation: Combined parcellation 'Schaefer100Parcels7NetworksTianS1' ready. MNI space(s): ['MNI152NLin2009cAsym', 'MNI152NLin6Asym']. Cx surface space(s) for spins: ['fsaverage', 'fsLR'].\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.core.parcellation: Parcellation 'Schaefer100Parcels7NetworksTianS1': validation passed.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.core.parcellation: Parcellation 'Schaefer100Parcels7NetworksTianS1': active space set to 'MNI152NLin2009cAsym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.core.parcellation: Combined parcellation: cx-LH parcels = 58, cx-RH parcels = 58.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.api: Checking input data for 'x' (should be, e.g., PET data):\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.io: Input type: DataFrame, assuming parcellated data with shape (n_files/subjects/etc, n_parcels).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.api: Got 'x' data for 465 x 116 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.api: Checking input data for 'y' (should be, e.g., subject data):\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.io: Input type: list, assuming imaging data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.io: Background (bg) handling: ignoring bg: True (bg value: ['auto', 0.0]); dropping bg parcels: False\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:44 | nispace.io: Parcellating imaging data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Parcellating (4 proc):   0%|                                                                                                                                     | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Parcellating (4 proc): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 118.66it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: Got 'y' data for 1 x 116 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: Z-standardizing 'X' data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: *** NiSpace.colocalize() - Estimating X & Y colocalizations. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: Running 'spearman' colocalization.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: Will perform X-set enrichment analysis (XSEA).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: Using 24 sets with between 2 and 68 samples. Aggregating within-set colocalizations with: mean.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:48 | nispace.api: Pre-ranking X and Y data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc):   0%|                                                                                                                           | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2053.01it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "XSEA colocalizations: 24 sets\n",
      "                                Pain\n",
      "Microglia                   0.250146\n",
      "Astrocyte                   0.175766\n",
      "OPC                         0.168996\n",
      "In1 VIP+RELN+NDNF+ (L1/2)   0.142336\n",
      "Endothelial                 0.141804\n",
      "Ex6 SubcortProject (L5-6)   0.131066\n",
      "Ex8 Corticothalamic (L6)    0.127390\n",
      "Oligodendrocyte             0.118138\n",
      "Developing-replicating      0.105683\n",
      "Ex7 Corticothalamic         0.087049\n",
      "Developing-quiescent        0.059943\n",
      "In2 VIP+RELN-NDNF- (L6)     0.042509\n",
      "Other Neurons               0.017340\n",
      "Ex1 CortProject (L2/3)      0.017241\n",
      "In3 VIP+RELN+NDNF- (L6)     0.011462\n",
      "In8 SST+NOS1+ (L6)         -0.009339\n",
      "Ex5 SubcortProject (L4-6)  -0.018907\n",
      "In6 PVALB+CRHBP+ (L4/5)    -0.019250\n",
      "Ex2 Granule (L3/4)         -0.024170\n",
      "In7 SST+CALB1+NPY+ (L5/6)  -0.024495\n",
      "In5 CCK+NOS1+CALB2+ (L2/3) -0.031559\n",
      "Ex4 SubcortProject (L4)    -0.033283\n",
      "In4 VIP-RELN+NDNF+ (L1-3)  -0.036649\n",
      "Ex3 Granule (L4)           -0.215634\n"
     ]
    }
   ],
   "source": [
    "nsp = NiSpace(\n",
    "    x=mrna,\n",
    "    y=pain_map,\n",
    "    y_labels=\"Pain\",\n",
    "    parcellation=\"Schaefer100TianS1\",\n",
    "    seed=42,\n",
    "    n_proc=4\n",
    ")\n",
    "nsp.fit()\n",
    "\n",
    "# colocalize with XSEA aggregation\n",
    "# xsea=True computes the mean colocalization within each set\n",
    "nsp.colocalize(\"spearman\", xsea=True)\n",
    "\n",
    "# the result has one column per set (not per individual gene)\n",
    "colocs = nsp.get_colocalizations()\n",
    "print(f\"XSEA colocalizations: {colocs.shape[1]} sets\")\n",
    "print(colocs.T.sort_values(by=\"Pain\", ascending=False))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "34a7d767",
   "metadata": {},
   "source": [
    "## Permutation testing for XSEA\n",
    "\n",
    "Permutation testing works the same way as for individual maps: we call `permute(\"maps\")`, but now the null maps are used to compute null *set-level* colocalizations (after within-set averaging). The resulting p-value answers: is the observed set mean higher than expected under spatial randomness?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a2ccc357",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:06:50.758085Z",
     "iopub.status.busy": "2026-06-01T13:06:50.757950Z",
     "iopub.status.idle": "2026-06-01T13:07:08.728333Z",
     "shell.execute_reply": "2026-06-01T13:07:08.728014Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: *** NiSpace.permute() - Estimate exact non-parametric p values. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: Permutation of: Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: Using default null method 'moran' (parcellation null space: 'MNI152NLin2009cAsym').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: Loading observed colocalizations (method = 'spearman').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.api: Generating permuted Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:50 | nispace.nulls: Resampling volumetric parcellation from 1mm to 2mm for distance matrix generation.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:51 | nispace.nulls: Estimating euclidean distance matrix: 116 volumetric parcels, voxel-to-voxel mode, 4 proc.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   0%|                                                                                                                                | 0/116 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   7%|████████▎                                                                                                               | 8/116 [00:00<00:04, 25.13it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  10%|████████████▎                                                                                                          | 12/116 [00:00<00:08, 12.43it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  14%|████████████████▍                                                                                                      | 16/116 [00:01<00:08, 11.20it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  17%|████████████████████▌                                                                                                  | 20/116 [00:01<00:09, 10.53it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  21%|████████████████████████▌                                                                                              | 24/116 [00:02<00:10,  9.16it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  24%|████████████████████████████▋                                                                                          | 28/116 [00:02<00:08,  9.79it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  28%|████████████████████████████████▊                                                                                      | 32/116 [00:03<00:08,  9.52it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  31%|████████████████████████████████████▉                                                                                  | 36/116 [00:03<00:07, 10.18it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  34%|█████████████████████████████████████████                                                                              | 40/116 [00:03<00:07,  9.60it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  38%|█████████████████████████████████████████████▏                                                                         | 44/116 [00:04<00:07,  9.49it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  41%|█████████████████████████████████████████████████▏                                                                     | 48/116 [00:04<00:06, 10.82it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  45%|█████████████████████████████████████████████████████▎                                                                 | 52/116 [00:04<00:06, 10.45it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Applications/miniforge3/envs/nsp309/lib/python3.9/site-packages/joblib/externals/loky/process_executor.py:752: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  48%|█████████████████████████████████████████████████████████▍                                                             | 56/116 [00:05<00:06,  9.66it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  52%|█████████████████████████████████████████████████████████████▌                                                         | 60/116 [00:05<00:06,  9.09it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  55%|█████████████████████████████████████████████████████████████████▋                                                     | 64/116 [00:06<00:06,  8.03it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  59%|█████████████████████████████████████████████████████████████████████▊                                                 | 68/116 [00:06<00:05,  9.00it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  62%|█████████████████████████████████████████████████████████████████████████▊                                             | 72/116 [00:07<00:03, 11.24it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  66%|█████████████████████████████████████████████████████████████████████████████▉                                         | 76/116 [00:07<00:03, 12.93it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  69%|██████████████████████████████████████████████████████████████████████████████████                                     | 80/116 [00:07<00:02, 14.93it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  72%|██████████████████████████████████████████████████████████████████████████████████████▏                                | 84/116 [00:07<00:01, 16.56it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  76%|██████████████████████████████████████████████████████████████████████████████████████████▎                            | 88/116 [00:07<00:01, 19.08it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  79%|██████████████████████████████████████████████████████████████████████████████████████████████▍                        | 92/116 [00:07<00:01, 21.45it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  86%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋                | 100/116 [00:08<00:00, 29.63it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc): 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 116/116 [00:08<00:00, 14.33it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:59 | nispace.core.permute: No null maps found.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:59 | nispace.core.permute: Generating null maps (n = 1000, null_method = 'moran').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:59 | nispace.nulls: Null map generation: Assuming n = 1 data vector(s) for n = 116 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:06:59 | nispace.nulls: Using provided distance matrix/matrices.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Moran null maps (4 proc):   0%|                                                                                                                                  | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Moran null maps (4 proc): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1579.78it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:01 | nispace.nulls: Null data generation finished.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:01 | nispace.api: Running X Set Enrichment Analysis (XSEA) without set permutation.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:01 | nispace.api: Pre-ranking X and Y (null) data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   0%|                                                                                                                        | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   1%|▉                                                                                                               | 8/1000 [00:03<06:34,  2.52it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   8%|████████▍                                                                                                      | 76/1000 [00:03<00:35, 25.77it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:03<00:00, 256.19it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):   0%|                                                                                                                | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):   1%|▊                                                                                                       | 8/1000 [00:00<00:36, 27.37it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):  13%|████████████▉                                                                                        | 128/1000 [00:00<00:02, 404.43it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):  38%|██████████████████████████████████████▊                                                              | 384/1000 [00:00<00:00, 961.08it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):  51%|███████████████████████████████████████████████████▏                                                | 512/1000 [00:00<00:00, 1007.79it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):  77%|████████████████████████████████████████████████████████████████████████████▊                       | 768/1000 [00:00<00:00, 1402.87it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc): 100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:00<00:00, 1295.59it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.core.permute: Calculating exact p-values (tails = {'rho': 'two'}).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: *** NiSpace.correct_p() - Correct p values for multiple comparisons. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Correction method: 'meff_galwey', alpha: 0.05, dimension: 'array'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning X dataframe: \n",
      "| X_REDUCTION | \n",
      "| False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Meff_X (galwey) = 10.55 (from 24 maps).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD  | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | meffgalwey | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>mean_rho</th>\n",
       "      <th>p</th>\n",
       "      <th>p_corrected</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Ex7 Corticothalamic</th>\n",
       "      <td>0.087049</td>\n",
       "      <td>0.001</td>\n",
       "      <td>0.010495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex8 Corticothalamic (L6)</th>\n",
       "      <td>0.127390</td>\n",
       "      <td>0.001</td>\n",
       "      <td>0.010495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OPC</th>\n",
       "      <td>0.168996</td>\n",
       "      <td>0.002</td>\n",
       "      <td>0.020890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Microglia</th>\n",
       "      <td>0.250146</td>\n",
       "      <td>0.002</td>\n",
       "      <td>0.020890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Developing-replicating</th>\n",
       "      <td>0.105683</td>\n",
       "      <td>0.014</td>\n",
       "      <td>0.138153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex6 SubcortProject (L5-6)</th>\n",
       "      <td>0.131066</td>\n",
       "      <td>0.060</td>\n",
       "      <td>0.479255</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex3 Granule (L4)</th>\n",
       "      <td>-0.215634</td>\n",
       "      <td>0.068</td>\n",
       "      <td>0.524137</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Oligodendrocyte</th>\n",
       "      <td>0.118138</td>\n",
       "      <td>0.112</td>\n",
       "      <td>0.714241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Endothelial</th>\n",
       "      <td>0.141804</td>\n",
       "      <td>0.162</td>\n",
       "      <td>0.844909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Developing-quiescent</th>\n",
       "      <td>0.059943</td>\n",
       "      <td>0.170</td>\n",
       "      <td>0.859830</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In2 VIP+RELN-NDNF- (L6)</th>\n",
       "      <td>0.042509</td>\n",
       "      <td>0.194</td>\n",
       "      <td>0.897133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In1 VIP+RELN+NDNF+ (L1/2)</th>\n",
       "      <td>0.142336</td>\n",
       "      <td>0.202</td>\n",
       "      <td>0.907404</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Astrocyte</th>\n",
       "      <td>0.175766</td>\n",
       "      <td>0.242</td>\n",
       "      <td>0.946164</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In7 SST+CALB1+NPY+ (L5/6)</th>\n",
       "      <td>-0.024495</td>\n",
       "      <td>0.458</td>\n",
       "      <td>0.998433</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex2 Granule (L3/4)</th>\n",
       "      <td>-0.024170</td>\n",
       "      <td>0.672</td>\n",
       "      <td>0.999992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Other Neurons</th>\n",
       "      <td>0.017340</td>\n",
       "      <td>0.684</td>\n",
       "      <td>0.999995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In3 VIP+RELN+NDNF- (L6)</th>\n",
       "      <td>0.011462</td>\n",
       "      <td>0.688</td>\n",
       "      <td>0.999995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In5 CCK+NOS1+CALB2+ (L2/3)</th>\n",
       "      <td>-0.031559</td>\n",
       "      <td>0.750</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In4 VIP-RELN+NDNF+ (L1-3)</th>\n",
       "      <td>-0.036649</td>\n",
       "      <td>0.808</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex4 SubcortProject (L4)</th>\n",
       "      <td>-0.033283</td>\n",
       "      <td>0.830</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex1 CortProject (L2/3)</th>\n",
       "      <td>0.017241</td>\n",
       "      <td>0.844</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In8 SST+NOS1+ (L6)</th>\n",
       "      <td>-0.009339</td>\n",
       "      <td>0.878</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>In6 PVALB+CRHBP+ (L4/5)</th>\n",
       "      <td>-0.019250</td>\n",
       "      <td>0.882</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ex5 SubcortProject (L4-6)</th>\n",
       "      <td>-0.018907</td>\n",
       "      <td>0.916</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            mean_rho      p  p_corrected\n",
       "Ex7 Corticothalamic         0.087049  0.001     0.010495\n",
       "Ex8 Corticothalamic (L6)    0.127390  0.001     0.010495\n",
       "OPC                         0.168996  0.002     0.020890\n",
       "Microglia                   0.250146  0.002     0.020890\n",
       "Developing-replicating      0.105683  0.014     0.138153\n",
       "Ex6 SubcortProject (L5-6)   0.131066  0.060     0.479255\n",
       "Ex3 Granule (L4)           -0.215634  0.068     0.524137\n",
       "Oligodendrocyte             0.118138  0.112     0.714241\n",
       "Endothelial                 0.141804  0.162     0.844909\n",
       "Developing-quiescent        0.059943  0.170     0.859830\n",
       "In2 VIP+RELN-NDNF- (L6)     0.042509  0.194     0.897133\n",
       "In1 VIP+RELN+NDNF+ (L1/2)   0.142336  0.202     0.907404\n",
       "Astrocyte                   0.175766  0.242     0.946164\n",
       "In7 SST+CALB1+NPY+ (L5/6)  -0.024495  0.458     0.998433\n",
       "Ex2 Granule (L3/4)         -0.024170  0.672     0.999992\n",
       "Other Neurons               0.017340  0.684     0.999995\n",
       "In3 VIP+RELN+NDNF- (L6)     0.011462  0.688     0.999995\n",
       "In5 CCK+NOS1+CALB2+ (L2/3) -0.031559  0.750     1.000000\n",
       "In4 VIP-RELN+NDNF+ (L1-3)  -0.036649  0.808     1.000000\n",
       "Ex4 SubcortProject (L4)    -0.033283  0.830     1.000000\n",
       "Ex1 CortProject (L2/3)      0.017241  0.844     1.000000\n",
       "In8 SST+NOS1+ (L6)         -0.009339  0.878     1.000000\n",
       "In6 PVALB+CRHBP+ (L4/5)    -0.019250  0.882     1.000000\n",
       "Ex5 SubcortProject (L4-6)  -0.018907  0.916     1.000000"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# permute the input map (default for XSEA)\n",
    "nsp.permute(\n",
    "    \"maps\",\n",
    "    maps_which=\"Y\", # that's the input map\n",
    "    n_perm=1000,\n",
    "    p_tails=\"two\"  # two-tailed: no directional hypothesis for cell types\n",
    ")\n",
    "\n",
    "# correct p values\n",
    "nsp.correct_p()\n",
    "\n",
    "# get results\n",
    "p_values = nsp.get_p_values()\n",
    "pc_values = nsp.get_corrected_p_values()\n",
    "\n",
    "# show results sorted by p-value\n",
    "xsea_results = pd.DataFrame({\n",
    "    \"mean_rho\": colocs.T[\"Pain\"],\n",
    "    \"p\": p_values.T[\"Pain\"],\n",
    "    \"p_corrected\": pc_values.T[\"Pain\"]\n",
    "}).sort_values(\"p\")\n",
    "\n",
    "xsea_results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4d59c8de",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:07:08.730083Z",
     "iopub.status.busy": "2026-06-01T13:07:08.729957Z",
     "iopub.status.idle": "2026-06-01T13:07:09.136292Z",
     "shell.execute_reply": "2026-06-01T13:07:09.135886Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: *** NiSpace.plot() - Plot colocalization results. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD  | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | meffgalwey | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.api: Creating categorical plot for method spearman, colocalization stat rho.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:08 | nispace.plotting: Significance annotation: 5/24 p_uncorrected < 0.05, 4/24 p_meffgalwey < 0.05\u001b[0m\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x630 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(<Figure size 500x630 with 1 Axes>,\n",
       " <Axes: title={'center': \"$Spearman's\\\\ Rho$ colocalization\\n(permutation of $X\\\\ maps$)\"}, xlabel='$Rho$'>,\n",
       " <seaborn._core.plot.Plotter at 0x3154a61f0>)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nsp.plot(sort_by=\"coloc\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17aaa0f2",
   "metadata": {},
   "source": [
    "## XSEA with PET receptor sets\n",
    "\n",
    "XSEA isn't limited to gene expression — you can use any reference dataset with a set structure. The PET dataset, for example, has neurotransmitter systems as sets. Running XSEA on it asks: does the pain map align more with the overall *serotonin system* than with the overall *dopamine system*, beyond what spatial autocorrelation can explain?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "066690d2",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:07:09.137962Z",
     "iopub.status.busy": "2026-06-01T13:07:09.137823Z",
     "iopub.status.idle": "2026-06-01T13:07:19.919306Z",
     "shell.execute_reply": "2026-06-01T13:07:19.918959Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.datasets: Loading pet maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.datasets: Loading integrated collection 'UniqueTracers' for dataset 'pet'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.datasets: Filtering maps by collection.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.datasets: Filtered to 5 collection sets with between 3 and inf maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.datasets: Loading and inner-merging data parcellated with 'Schaefer200Parcels7Networks' and 'TianS1'\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.api: *** NiSpace.fit() - Data extraction and preparation. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation: Building combined Parcellation 'Schaefer200Parcels7Networks+TianS1' from library.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation:   Common MNI space(s) for combined: ['MNI152NLin2009cAsym', 'MNI152NLin6Asym'].\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation:   Merging 'Schaefer200Parcels7Networks' and 'TianS1' for space 'MNI152NLin2009cAsym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation:   Merging 'Schaefer200Parcels7Networks' and 'TianS1' for space 'MNI152NLin6Asym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation:   Fetching cx surface data for 'Schaefer200Parcels7Networks' in 'fsaverage' (for spin tests).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation:   Fetching cx surface data for 'Schaefer200Parcels7Networks' in 'fsLR' (for spin tests).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation: Combined parcellation 'Schaefer200Parcels7NetworksTianS1' ready. MNI space(s): ['MNI152NLin2009cAsym', 'MNI152NLin6Asym']. Cx surface space(s) for spins: ['fsaverage', 'fsLR'].\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation: Parcellation 'Schaefer200Parcels7NetworksTianS1': validation passed.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation: Parcellation 'Schaefer200Parcels7NetworksTianS1': active space set to 'MNI152NLin2009cAsym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.core.parcellation: Combined parcellation: cx-LH parcels = 108, cx-RH parcels = 108.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.api: Checking input data for 'x' (should be, e.g., PET data):\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.io: Input type: DataFrame, assuming parcellated data with shape (n_files/subjects/etc, n_parcels).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mWARNING | 01/06/26 15:07:09 | nispace.io: Parcellated data contains nan values!\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.api: Got 'x' data for 22 x 216 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.api: Checking input data for 'y' (should be, e.g., subject data):\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.io: Input type: list, assuming imaging data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.io: Background (bg) handling: ignoring bg: True (bg value: ['auto', 0.0]); dropping bg parcels: False\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:09 | nispace.io: Parcellating imaging data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Parcellating (4 proc):   0%|                                                                                                                                     | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Parcellating (4 proc): 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1784.81it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "/Applications/miniforge3/envs/nsp309/lib/python3.9/site-packages/neuromaps/transforms.py:254: FutureWarning: 'force_resample' will be set to 'True' by default in Nilearn 0.13.0.\n",
      "Use 'force_resample=True' to suppress this warning.\n",
      "  out = nimage.resample_to_img(load_nifti(img), load_nifti(target),\n",
      "/Applications/miniforge3/envs/nsp309/lib/python3.9/site-packages/neuromaps/transforms.py:254: FutureWarning: From release 0.13.0 onwards, this function will, by default, copy the header of the input image to the output. Currently, the header is reset to the default Nifti1Header. To suppress this warning and use the new behavior, set `copy_header=True`.\n",
      "  out = nimage.resample_to_img(load_nifti(img), load_nifti(target),\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Got 'y' data for 1 x 216 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Z-standardizing 'X' data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: *** NiSpace.colocalize() - Estimating X & Y colocalizations. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Running 'spearman' colocalization.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Will perform X-set enrichment analysis (XSEA).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Using 5 sets with between 3 and 6 samples. Aggregating within-set colocalizations with: mean.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Pre-ranking X and Y data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc):   0%|                                                                                                                           | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1805.55it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: *** NiSpace.permute() - Estimate exact non-parametric p values. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Permutation of: Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Using default null method 'moran' (parcellation null space: 'MNI152NLin2009cAsym').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Loading observed colocalizations (method = 'spearman').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.api: Generating permuted Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:10 | nispace.nulls: Resampling volumetric parcellation from 1mm to 2mm for distance matrix generation.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:11 | nispace.nulls: Estimating euclidean distance matrix: 216 volumetric parcels, voxel-to-voxel mode, 4 proc.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   0%|                                                                                                                                | 0/216 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   4%|████▍                                                                                                                   | 8/216 [00:00<00:06, 33.69it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   6%|██████▌                                                                                                                | 12/216 [00:00<00:07, 25.88it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   7%|████████▊                                                                                                              | 16/216 [00:00<00:10, 19.44it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   9%|███████████                                                                                                            | 20/216 [00:01<00:11, 16.63it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  11%|█████████████▏                                                                                                         | 24/216 [00:01<00:10, 17.70it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  13%|███████████████▍                                                                                                       | 28/216 [00:01<00:10, 17.17it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  15%|█████████████████▋                                                                                                     | 32/216 [00:01<00:09, 19.07it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  17%|███████████████████▊                                                                                                   | 36/216 [00:01<00:09, 19.59it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  19%|██████████████████████                                                                                                 | 40/216 [00:02<00:09, 18.03it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  20%|████████████████████████▏                                                                                              | 44/216 [00:02<00:08, 19.62it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  22%|██████████████████████████▍                                                                                            | 48/216 [00:02<00:09, 18.51it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  24%|████████████████████████████▋                                                                                          | 52/216 [00:02<00:08, 19.83it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  28%|█████████████████████████████████                                                                                      | 60/216 [00:03<00:07, 21.37it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  30%|███████████████████████████████████▎                                                                                   | 64/216 [00:03<00:08, 18.87it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  31%|█████████████████████████████████████▍                                                                                 | 68/216 [00:03<00:07, 20.87it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  33%|███████████████████████████████████████▋                                                                               | 72/216 [00:03<00:06, 21.89it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  35%|█████████████████████████████████████████▊                                                                             | 76/216 [00:03<00:07, 19.28it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  39%|██████████████████████████████████████████████▎                                                                        | 84/216 [00:04<00:06, 20.50it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  41%|████████████████████████████████████████████████▍                                                                      | 88/216 [00:04<00:05, 23.13it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  43%|██████████████████████████████████████████████████▋                                                                    | 92/216 [00:04<00:05, 21.36it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  44%|████████████████████████████████████████████████████▉                                                                  | 96/216 [00:04<00:06, 19.99it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  46%|██████████████████████████████████████████████████████▋                                                               | 100/216 [00:04<00:05, 21.81it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  48%|████████████████████████████████████████████████████████▊                                                             | 104/216 [00:05<00:04, 23.05it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  50%|███████████████████████████████████████████████████████████                                                           | 108/216 [00:05<00:04, 24.18it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  52%|█████████████████████████████████████████████████████████████▏                                                        | 112/216 [00:05<00:04, 24.72it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  54%|███████████████████████████████████████████████████████████████▎                                                      | 116/216 [00:05<00:03, 25.34it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  56%|█████████████████████████████████████████████████████████████████▌                                                    | 120/216 [00:05<00:03, 27.32it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  59%|█████████████████████████████████████████████████████████████████████▉                                                | 128/216 [00:05<00:02, 35.88it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  65%|████████████████████████████████████████████████████████████████████████████▍                                         | 140/216 [00:05<00:01, 49.65it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  69%|████████████████████████████████████████████████████████████████████████████████▊                                     | 148/216 [00:06<00:01, 51.91it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  72%|█████████████████████████████████████████████████████████████████████████████████████▏                                | 156/216 [00:06<00:01, 47.53it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  76%|█████████████████████████████████████████████████████████████████████████████████████████▌                            | 164/216 [00:06<00:01, 47.43it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  80%|█████████████████████████████████████████████████████████████████████████████████████████████▉                        | 172/216 [00:06<00:00, 47.77it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  83%|██████████████████████████████████████████████████████████████████████████████████████████████████▎                   | 180/216 [00:06<00:00, 48.72it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  87%|██████████████████████████████████████████████████████████████████████████████████████████████████████▋               | 188/216 [00:06<00:00, 54.01it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  91%|███████████████████████████████████████████████████████████████████████████████████████████████████████████           | 196/216 [00:06<00:00, 58.37it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  98%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 212/216 [00:07<00:00, 79.05it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc): 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 216/216 [00:07<00:00, 30.40it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.core.permute: No null maps found.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.core.permute: Generating null maps (n = 1000, null_method = 'moran').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.nulls: Null map generation: Assuming n = 1 data vector(s) for n = 216 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.nulls: Using provided distance matrix/matrices.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Moran null maps (4 proc):   0%|                                                                                                                                  | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Moran null maps (4 proc): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2193.67it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.nulls: Null data generation finished.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.api: Running X Set Enrichment Analysis (XSEA) without set permutation.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:18 | nispace.api: Pre-ranking X and Y (null) data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   0%|                                                                                                                        | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):  50%|██████████████████████████████████████████████████████▍                                                     | 504/1000 [00:00<00:00, 4697.46it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc): 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:00<00:00, 8452.87it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):   0%|                                                                                                                | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc): 100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:00<00:00, 10490.85it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.core.permute: Calculating exact p-values (tails = {'rho': 'upper'}).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: *** NiSpace.correct_p() - Correct p values for multiple comparisons. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Correction method: 'meff_galwey', alpha: 0.05, dimension: 'array'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Returning X dataframe: \n",
      "| X_REDUCTION | \n",
      "| False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Meff_X (galwey) = 3.97 (from 5 maps).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: *** NiSpace.plot() - Plot colocalization results. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD  | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | meffgalwey | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Creating categorical plot for method spearman, colocalization stat rho.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.plotting: Significance annotation: 0/5 p_uncorrected < 0.05, 0/5 p_meffgalwey < 0.05\u001b[0m\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x250 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(<Figure size 500x250 with 1 Axes>,\n",
       " <Axes: title={'center': \"$Spearman's\\\\ Rho$ colocalization\\n(permutation of $X\\\\ maps$)\"}, xlabel='$Rho$'>,\n",
       " <seaborn._core.plot.Plotter at 0x328c775b0>)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# For XSEA with PET, we need a collection with the set structure (neurotransmitter\n",
    "# systems as sets). UniqueTracers is a JSON-format collection that gives a two-level\n",
    "# ['set', 'map'] MultiIndex — exactly what XSEA needs to aggregate by system.\n",
    "pet_unique = fetch_reference(\n",
    "    \"pet\", parcellation=\"Schaefer200TianS1\", collection=\"UniqueTracers\", print_references=False,\n",
    "    set_size_range=(3, None) # when fetching set-based collections, some more parameters can be adjusted\n",
    ") \n",
    "\n",
    "nsp_pet = NiSpace(\n",
    "    x=pet_unique,\n",
    "    y=pain_map,\n",
    "    y_labels=\"Pain\",\n",
    "    parcellation=\"Schaefer200TianS1\",\n",
    "    seed=42,\n",
    "    n_proc=4\n",
    ")\n",
    "nsp_pet.fit()\n",
    "nsp_pet.colocalize(\"spearman\", xsea=True)\n",
    "nsp_pet.permute(\"maps\", maps_which=\"Y\", n_perm=1000, p_tails=\"upper\")\n",
    "nsp_pet.correct_p()\n",
    "\n",
    "nsp_pet.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "449f8ed7",
   "metadata": {},
   "source": [
    "## The `xsea_aggregation_method` parameter\n",
    "\n",
    "By default, XSEA aggregates individual map correlations by taking the mean. Alternatively, you can use `\"median\"` or `\"absmean\"`/`\"absmedian\"`, or even `\"weightedmean\"`. The latter only works when the input dataset does have a 3-level index with `set`, `map`, and `weight` as levels.  \n",
    "\n",
    "In practice, `\"mean\"` is the most common and interpretable choice, but `\"absmean\"` (absolute mean) can be reasonable based on the context."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e380d79f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:07:19.921018Z",
     "iopub.status.busy": "2026-06-01T13:07:19.920878Z",
     "iopub.status.idle": "2026-06-01T13:07:20.480996Z",
     "shell.execute_reply": "2026-06-01T13:07:20.480642Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: *** NiSpace.colocalize() - Estimating X & Y colocalizations. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Running 'spearman' colocalization.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Will perform X-set enrichment analysis (XSEA).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Using 5 sets with between 3 and 6 samples. Aggregating within-set colocalizations with: absmean.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Pre-ranking X and Y data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc):   0%|                                                                                                                           | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2839.75it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: *** NiSpace.permute() - Estimate exact non-parametric p values. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Permutation of: Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Using default null method 'moran' (parcellation null space: 'MNI152NLin2009cAsym').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Loading observed colocalizations (method = 'spearman').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Generating permuted Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.core.permute: Found existing null maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Running X Set Enrichment Analysis (XSEA) without set permutation.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:19 | nispace.api: Pre-ranking X and Y (null) data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   0%|                                                                                                                        | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):  76%|██████████████████████████████████████████████████████████████████████████████████                          | 760/1000 [00:00<00:00, 7087.12it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc): 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:00<00:00, 9039.47it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):   0%|                                                                                                                | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc): 100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:00<00:00, 10799.96it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.core.permute: Calculating exact p-values (tails = {'rho': 'upper'}).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: *** NiSpace.plot() - Plot colocalization results. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD  | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | meffgalwey | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: Creating categorical plot for method spearman, colocalization stat rho.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.plotting: Significance annotation: 1/5 p_uncorrected < 0.05, 0/5 p_meffgalwey < 0.05\u001b[0m\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x250 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(<Figure size 500x250 with 1 Axes>,\n",
       " <Axes: title={'center': \"$Spearman's\\\\ Rho$ colocalization\\n(permutation of $X\\\\ maps$)\"}, xlabel='$Rho$'>,\n",
       " <seaborn._core.plot.Plotter at 0x328e220a0>)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# absmean aggregation\n",
    "nsp_pet.colocalize(\"spearman\", xsea=True, xsea_aggregation_method=\"absmean\")\n",
    "nsp_pet.permute(\"maps\", maps_which=\"Y\", n_perm=1000, p_tails=\"upper\") # one-tailed p value in this case\n",
    "nsp_pet.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44607ed6",
   "metadata": {},
   "source": [
    "## XSEA via the workflow\n",
    "\n",
    "For a one-liner version:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5c745136",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-01T13:07:20.482469Z",
     "iopub.status.busy": "2026-06-01T13:07:20.482369Z",
     "iopub.status.idle": "2026-06-01T13:07:37.911015Z",
     "shell.execute_reply": "2026-06-01T13:07:37.910676Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.workflows: Loading integrated mrna dataset as X data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.datasets: Loading mrna maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.datasets: Loading integrated collection 'CellTypesPsychEncodeTPM' for dataset 'mrna'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.datasets: Filtering maps by collection.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.datasets: Loading and inner-merging data parcellated with 'Schaefer100Parcels7Networks' and 'TianS1'\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The NiSpace \"mRNA\" dataset is based on Allen Human Brain Atlas (AHBA) gene expression data published in Hawrylycz et al., \n",
      "2012 (https://doi.org/10.1038/nature11405). The dataset consists of mRNA expression data from postmortem brain tissue of \n",
      "six donors, mapped onto MNI or fsaverage parcels using the abagen toolbox (Markello et al., 2021, https://doi.org/10.7554/eLife.72129).\n",
      "The data was extracted using abagen.get_expression_data(..., lr_mirror=\"bidirectional\", norm_matched=False), considering\n",
      "parcel hemisphere and cortical vs. subcortical location. Gene stability was assessed independently of any specific\n",
      "parcellation using a voxel-level atlas constructed from Schaefer100 (cortex) and TianS1 (subcortex) at 8mm isotropic\n",
      "resolution (each voxel assigned a unique identifier; sample-to-voxel tolerance=8mm). Per-donor expression matrices were\n",
      "obtained via abagen and genes were retained if their mean donor-to-donor Spearman rank correlation exceeded 0.2\n",
      "(abagen.keep_stable_genes, rank=True, threshold=0.2). This stable gene set was applied uniformly across all parcellations.\n",
      "In addition to the two publications listed above, please cite publications associated with gene set collections as appropriate.\n",
      "To ensure reproducibility, note the NiSpace commit/version: 0.0.1b5.dev68+g20be93445.d20260520\n",
      "\n",
      "- CellTypesPsychEncodeTPM  Source: Lake2016      https://doi.org/10.1126/science.aaf1204\n",
      "- CellTypesPsychEncodeTPM  Source: Darmanis2015  https://doi.org/10.1073/pnas.1507125112\n",
      "- CellTypesPsychEncodeTPM  Source: Wang2018      https://doi.org/10.1126/science.aat8464\n",
      "\n",
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.api: *** NiSpace.fit() - Data extraction and preparation. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.core.parcellation: Building combined Parcellation 'Schaefer100Parcels7Networks+TianS1' from library.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.core.parcellation:   Common MNI space(s) for combined: ['MNI152NLin2009cAsym', 'MNI152NLin6Asym'].\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.core.parcellation:   Merging 'Schaefer100Parcels7Networks' and 'TianS1' for space 'MNI152NLin2009cAsym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:20 | nispace.core.parcellation:   Merging 'Schaefer100Parcels7Networks' and 'TianS1' for space 'MNI152NLin6Asym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.core.parcellation:   Fetching cx surface data for 'Schaefer100Parcels7Networks' in 'fsaverage' (for spin tests).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.core.parcellation:   Fetching cx surface data for 'Schaefer100Parcels7Networks' in 'fsLR' (for spin tests).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.core.parcellation: Combined parcellation 'Schaefer100Parcels7NetworksTianS1' ready. MNI space(s): ['MNI152NLin2009cAsym', 'MNI152NLin6Asym']. Cx surface space(s) for spins: ['fsaverage', 'fsLR'].\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.core.parcellation: Parcellation 'Schaefer100Parcels7NetworksTianS1': validation passed.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.core.parcellation: Parcellation 'Schaefer100Parcels7NetworksTianS1': active space set to 'MNI152NLin2009cAsym'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.core.parcellation: Combined parcellation: cx-LH parcels = 58, cx-RH parcels = 58.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.api: Checking input data for 'x' (should be, e.g., PET data):\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.io: Input type: DataFrame, assuming parcellated data with shape (n_files/subjects/etc, n_parcels).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.api: Got 'x' data for 465 x 116 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.api: Checking input data for 'y' (should be, e.g., subject data):\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.io: Input type: dict, assuming (img_name, img) pairs for imaging data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.io: Background (bg) handling: ignoring bg: True (bg value: ['auto', 0.0]); dropping bg parcels: False\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:21 | nispace.io: Parcellating imaging data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Parcellating (4 proc):   0%|                                                                                                                                     | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Parcellating (4 proc): 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2425.86it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Got 'y' data for 1 x 116 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Z-standardizing 'X' data.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: *** NiSpace.colocalize() - Estimating X & Y colocalizations. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Running 'spearman' colocalization.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Will perform X-set enrichment analysis (XSEA).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Using 24 sets with between 2 and 68 samples. Aggregating within-set colocalizations with: mean.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Pre-ranking X and Y data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc):   0%|                                                                                                                           | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Colocalizing (spearman, 4 proc): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2519.10it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: *** NiSpace.permute() - Estimate exact non-parametric p values. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Permutation of: Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Using default null method 'moran' (parcellation null space: 'MNI152NLin2009cAsym').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Loading observed colocalizations (method = 'spearman').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.api: Generating permuted Y maps.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.nulls: Resampling volumetric parcellation from 1mm to 2mm for distance matrix generation.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:22 | nispace.nulls: Estimating euclidean distance matrix: 116 volumetric parcels, voxel-to-voxel mode, 4 proc.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   0%|                                                                                                                                | 0/116 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):   7%|████████▎                                                                                                               | 8/116 [00:00<00:04, 24.14it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  10%|████████████▎                                                                                                          | 12/116 [00:00<00:06, 15.92it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Applications/miniforge3/envs/nsp309/lib/python3.9/site-packages/joblib/externals/loky/process_executor.py:752: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  14%|████████████████▍                                                                                                      | 16/116 [00:01<00:09, 10.23it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  17%|████████████████████▌                                                                                                  | 20/116 [00:02<00:13,  7.33it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  21%|████████████████████████▌                                                                                              | 24/116 [00:03<00:18,  5.05it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  24%|████████████████████████████▋                                                                                          | 28/116 [00:03<00:14,  6.27it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  28%|████████████████████████████████▊                                                                                      | 32/116 [00:04<00:12,  6.95it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  31%|████████████████████████████████████▉                                                                                  | 36/116 [00:04<00:09,  8.24it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  34%|█████████████████████████████████████████                                                                              | 40/116 [00:04<00:08,  8.60it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  38%|█████████████████████████████████████████████▏                                                                         | 44/116 [00:05<00:07,  9.10it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  41%|█████████████████████████████████████████████████▏                                                                     | 48/116 [00:05<00:06, 10.30it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  45%|█████████████████████████████████████████████████████▎                                                                 | 52/116 [00:05<00:06, 10.18it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  48%|█████████████████████████████████████████████████████████▍                                                             | 56/116 [00:06<00:05, 10.33it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  52%|█████████████████████████████████████████████████████████████▌                                                         | 60/116 [00:06<00:05, 10.26it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  55%|█████████████████████████████████████████████████████████████████▋                                                     | 64/116 [00:06<00:04, 11.83it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  59%|█████████████████████████████████████████████████████████████████████▊                                                 | 68/116 [00:07<00:03, 13.99it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  62%|█████████████████████████████████████████████████████████████████████████▊                                             | 72/116 [00:07<00:02, 16.25it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  66%|█████████████████████████████████████████████████████████████████████████████▉                                         | 76/116 [00:07<00:02, 18.45it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  69%|██████████████████████████████████████████████████████████████████████████████████                                     | 80/116 [00:07<00:02, 17.38it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  72%|██████████████████████████████████████████████████████████████████████████████████████▏                                | 84/116 [00:07<00:01, 18.70it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  76%|██████████████████████████████████████████████████████████████████████████████████████████▎                            | 88/116 [00:08<00:01, 19.72it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  79%|██████████████████████████████████████████████████████████████████████████████████████████████▍                        | 92/116 [00:08<00:01, 20.76it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc):  86%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋                | 100/116 [00:08<00:00, 27.71it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Distance matrix (4 proc): 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 116/116 [00:08<00:00, 13.69it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:31 | nispace.core.permute: No null maps found.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:31 | nispace.core.permute: Generating null maps (n = 1000, null_method = 'moran').\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:31 | nispace.nulls: Null map generation: Assuming n = 1 data vector(s) for n = 116 parcels.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:31 | nispace.nulls: Using provided distance matrix/matrices.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Moran null maps (4 proc):   0%|                                                                                                                                  | 0/1 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Moran null maps (4 proc): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1342.18it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:33 | nispace.nulls: Null data generation finished.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:33 | nispace.api: Running X Set Enrichment Analysis (XSEA) without set permutation.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:33 | nispace.api: Pre-ranking X and Y (null) data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   0%|                                                                                                                        | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):   1%|▉                                                                                                               | 8/1000 [00:01<02:21,  7.03it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc):  20%|█████████████████████▊                                                                                       | 200/1000 [00:01<00:03, 218.44it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Processing null arrays (4 proc): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:01<00:00, 775.37it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):   0%|                                                                                                                | 0/1000 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):   1%|▊                                                                                                       | 8/1000 [00:00<00:42, 23.38it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):  20%|███████████████████▊                                                                                 | 196/1000 [00:00<00:01, 546.43it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc):  52%|███████████████████████████████████████████████████▌                                                | 516/1000 [00:00<00:00, 1214.83it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      "Null colocalizations (spearman, 4 proc): 100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:00<00:00, 1530.12it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.core.permute: Calculating exact p-values (tails = {'rho': 'two'}).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: *** NiSpace.correct_p() - Correct p values for multiple comparisons. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Correction method: 'meff_galwey', alpha: 0.05, dimension: 'array'.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning X dataframe: \n",
      "| X_REDUCTION | \n",
      "| False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Meff_X (galwey) = 10.55 (from 24 maps).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: *** NiSpace.normalize_colocalizations() - Normalize colocalizations against null distribution. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Z-score method: robust (median/MAD).\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Stored normalized colocalizations: xdimred-false_ytrans-false_coloc-spearman_stat-rho_xsea-true_perm-ymaps\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: *** NiSpace.plot() - Plot colocalization results. ***\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD  | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | meffgalwey | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Creating categorical plot for method spearman, colocalization stat rho.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning z-scored colocalizations.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.plotting: Significance annotation: 5/24 p_uncorrected < 0.05, 4/24 p_meffgalwey < 0.05\u001b[0m\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x630 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning colocalizations: \n",
      "| METHOD   | XSEA | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | True | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | None      | False       | False       | \u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO | 01/06/26 15:07:37 | nispace.api: Returning p values: \n",
      "| METHOD   | PERMUTE_WHAT | XSEA | MC_METHOD  | X_REDUCTION | Y_TRANSFORM | \n",
      "| spearman | ymaps        | True | meffgalwey | False       | False       | \u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from nispace.workflows import xsea\n",
    "\n",
    "nsp_wf = xsea(\n",
    "    y={\"Pain\": pain_map},\n",
    "    x=\"mrna\",\n",
    "    x_collection=\"CellTypesPsychEncodeTPM\",\n",
    "    parcellation=\"Schaefer100TianS1\",\n",
    "    colocalization_method=\"spearman\",\n",
    "    n_perm=1000,\n",
    "    seed=42,\n",
    "    n_proc=4,\n",
    "    return_nispace_only=True\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee7d0c34",
   "metadata": {},
   "source": [
    "## Summary\n",
    "\n",
    "- XSEA aggregates individual map colocalizations within predefined sets and tests the set-level mean.\n",
    "- Enable it by passing `xsea=\"mean\"` (or `\"median\"`) to `colocalize()`.\n",
    "- Permutation testing works the same as for individual maps: `permute(\"maps\")`.\n",
    "- The default null model (map permutation) avoids inflation from within-set co-expression, following Fulcher et al. (2021).\n",
    "- ABAnnotate (the predecessor toolbox) used the same approach — XSEA in NiSpace is the generalized, multi-dataset version.\n",
    "- For the workflow version: `xsea()`.\n",
    "\n",
    "Next: [Notebook 11](intro11_advanced.ipynb) covers advanced topics: dimensionality reduction, multi-modal parcellations, alternative colocalization methods, and individual-level analyses."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "nsp309",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.20"
  },
  "nbsphinx": {
   "execute": "never"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}