jupyter-scatter + citeseq example

jsscatter-citeseq.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "54dd22df",
   "metadata": {},
   "source": [
    "# Setup (from muon tutorial)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "18ddfce4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import scanpy as sc\n",
    "import muon as mu\n",
    "from muon import prot as pt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "56a327af",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/isaac/github/anndata/anndata/_core/anndata.py:1830: UserWarning: Variable names are not unique. To make them unique, call `.var_names_make_unique`.\n",
      "  utils.warn_names_duplicates(\"var\")\n",
      "/Users/isaac/github/mudata/mudata/_core/mudata.py:405: UserWarning: var_names are not unique. To make them unique, call `.var_names_make_unique`.\n",
      "  warnings.warn(\n",
      "/Users/isaac/github/anndata/anndata/_core/anndata.py:1830: UserWarning: Variable names are not unique. To make them unique, call `.var_names_make_unique`.\n",
      "  utils.warn_names_duplicates(\"var\")\n",
      "/Users/isaac/github/mudata/mudata/_core/mudata.py:405: UserWarning: var_names are not unique. To make them unique, call `.var_names_make_unique`.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "mdata = mu.read_10x_h5(\"/Users/isaac/data/5k_pbmc_protein_v3/filtered_feature_bc_matrix.h5\")\n",
    "mdata_raw = mu.read_10x_h5(\"/Users/isaac/data/5k_pbmc_protein_v3/raw_feature_bc_matrix.h5\")  # This can be quite slow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "da777194",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre>MuData object with n_obs × n_vars = 5247 × 33570\n",
       "  var:\t&#x27;gene_ids&#x27;, &#x27;feature_types&#x27;, &#x27;genome&#x27;\n",
       "  2 modalities\n",
       "    rna:\t5247 x 33538\n",
       "      var:\t&#x27;gene_ids&#x27;, &#x27;feature_types&#x27;, &#x27;genome&#x27;\n",
       "    prot:\t5247 x 32\n",
       "      var:\t&#x27;gene_ids&#x27;, &#x27;feature_types&#x27;, &#x27;genome&#x27;</pre>"
      ],
      "text/plain": [
       "MuData object with n_obs × n_vars = 5247 × 33570\n",
       "  var:\t'gene_ids', 'feature_types', 'genome'\n",
       "  2 modalities\n",
       "    rna:\t5247 x 33538\n",
       "      var:\t'gene_ids', 'feature_types', 'genome'\n",
       "    prot:\t5247 x 32\n",
       "      var:\t'gene_ids', 'feature_types', 'genome'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mdata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "986a7409",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.9/site-packages/muon/_prot/preproc.py:109: UserWarning: empty_counts_range values are not provided, treating all the non-cells as empty droplets\n",
      "  warn(\n"
     ]
    }
   ],
   "source": [
    "pt.pp.dsb(mdata, data_raw=mdata_raw)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "b3002231",
   "metadata": {},
   "outputs": [],
   "source": [
    "prot = mdata.mod[\"prot\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "8a71793f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[11.682451 , 25.302616 ,  8.956743 , ...,  3.5722427,  1.2447473,\n",
       "         4.7979374],\n",
       "       [41.978897 , 39.361183 ,  6.458017 , ...,  4.1822805,  3.488111 ,\n",
       "         2.703628 ],\n",
       "       [41.68785  , 46.374855 , 11.26968  , ...,  2.5616493,  0.8283367,\n",
       "         3.9854221],\n",
       "       ...,\n",
       "       [34.96165  ,  3.4794345, 31.56558  , ...,  1.8609884,  1.9400594,\n",
       "         1.8395486],\n",
       "       [ 5.713143 , 17.781412 ,  4.512927 , ...,  3.4425242,  4.967757 ,\n",
       "         3.4117422],\n",
       "       [47.315876 , 47.650482 ,  6.7013407, ...,  4.0108767,  2.5449634,\n",
       "         4.6269016]], dtype=float32)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prot.X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "63d07e93",
   "metadata": {},
   "outputs": [],
   "source": [
    "sc.tl.pca(prot)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "049494e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "sc.pp.neighbors(prot)\n",
    "sc.tl.umap(prot, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "04aecf9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "sc.tl.leiden(prot, resolution=0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "450ba97f",
   "metadata": {},
   "outputs": [],
   "source": [
    "rna = mdata.mod[\"rna\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "c169081c",
   "metadata": {},
   "outputs": [],
   "source": [
    "sc.pp.normalize_total(rna)\n",
    "sc.pp.log1p(rna)\n",
    "sc.pp.pca(rna)\n",
    "sc.pp.neighbors(rna, n_neighbors=30)\n",
    "sc.tl.leiden(rna, resolution=0.5)\n",
    "sc.tl.umap(rna)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "1d52c5ae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AnnData object with n_obs × n_vars = 5247 × 33538\n",
       "    obs: 'leiden'\n",
       "    var: 'gene_ids', 'feature_types', 'genome'\n",
       "    uns: 'log1p', 'pca', 'neighbors', 'leiden', 'umap'\n",
       "    obsm: 'X_pca', 'X_umap'\n",
       "    varm: 'PCs'\n",
       "    obsp: 'distances', 'connectivities'"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rna"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "82ed7edf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['CD1A',\n",
       " 'CD1B',\n",
       " 'CD1C',\n",
       " 'CD1D',\n",
       " 'CD1E',\n",
       " 'CD2',\n",
       " 'CD2AP',\n",
       " 'CD2BP2',\n",
       " 'CD3D',\n",
       " 'CD3E',\n",
       " 'CD3EAP',\n",
       " 'CD3G',\n",
       " 'CD4',\n",
       " 'CD5',\n",
       " 'CD5L',\n",
       " 'CD6',\n",
       " 'CD7',\n",
       " 'CD8A',\n",
       " 'CD8B',\n",
       " 'CD8B2',\n",
       " 'CD9',\n",
       " 'CD14',\n",
       " 'CD19',\n",
       " 'CD22',\n",
       " 'CD24',\n",
       " 'CD27',\n",
       " 'CD28',\n",
       " 'CD33',\n",
       " 'CD34',\n",
       " 'CD36',\n",
       " 'CD37',\n",
       " 'CD38',\n",
       " 'CD40',\n",
       " 'CD40LG',\n",
       " 'CD44',\n",
       " 'CD44-AS1',\n",
       " 'CD46',\n",
       " 'CD47',\n",
       " 'CD48',\n",
       " 'CD52',\n",
       " 'CD53',\n",
       " 'CD55',\n",
       " 'CD58',\n",
       " 'CD59',\n",
       " 'CD63',\n",
       " 'CD68',\n",
       " 'CD69',\n",
       " 'CD70',\n",
       " 'CD72',\n",
       " 'CD74',\n",
       " 'CD79A',\n",
       " 'CD79B',\n",
       " 'CD80',\n",
       " 'CD81',\n",
       " 'CD81-AS1',\n",
       " 'CD82',\n",
       " 'CD83',\n",
       " 'CD84',\n",
       " 'CD86',\n",
       " 'CD93',\n",
       " 'CD96',\n",
       " 'CD99',\n",
       " 'CD99L2',\n",
       " 'CD101',\n",
       " 'CD109',\n",
       " 'CD151',\n",
       " 'CD160',\n",
       " 'CD163',\n",
       " 'CD163L1',\n",
       " 'CD164',\n",
       " 'CD164L2',\n",
       " 'CD177',\n",
       " 'CD180',\n",
       " 'CD200',\n",
       " 'CD200R1',\n",
       " 'CD200R1L',\n",
       " 'CD207',\n",
       " 'CD209',\n",
       " 'CD226',\n",
       " 'CD244',\n",
       " 'CD247',\n",
       " 'CD248',\n",
       " 'CD274',\n",
       " 'CD276',\n",
       " 'CD300A',\n",
       " 'CD300C',\n",
       " 'CD300E',\n",
       " 'CD300LB',\n",
       " 'CD300LD',\n",
       " 'CD300LF',\n",
       " 'CD300LG',\n",
       " 'CD302',\n",
       " 'CD320']"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "natsorted(rna.var_names[rna.var_names.str.match(r\"CD[0-9]\")])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "b12a2a39",
   "metadata": {},
   "outputs": [],
   "source": [
    "rna.var_names_make_unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c4221be",
   "metadata": {},
   "source": [
    "# Plotting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "07e2c5e9",
   "metadata": {},
   "outputs": [],
   "source": [
    "rna_plot_df = sc.get.obs_df(rna, [\"leiden\", \"CD4\", \"CD19\"], obsm_keys=[(\"X_umap\", 0), (\"X_umap\", 1)])\n",
    "prot_plot_df = sc.get.obs_df(prot, [\"leiden\", \"CD4_TotalSeqB\", \"CD19_TotalSeqB\"], obsm_keys=[(\"X_umap\", 0), (\"X_umap\", 1)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "62e49783",
   "metadata": {},
   "outputs": [],
   "source": [
    "import jscatter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "cb1ec00c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f8869d3dd0fd4cba92a68e7f24753612",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "GridBox(children=(HBox(children=(VBox(children=(Button(button_style='primary', icon='arrows', layout=Layout(wi…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "jscatter.link(\n",
    "    [\n",
    "        jscatter.Scatter(data=rna_plot_df, x=\"X_umap-0\", y=\"X_umap-1\", color_by=\"CD4\"),\n",
    "        jscatter.Scatter(data=rna_plot_df, x=\"X_umap-0\", y=\"X_umap-1\", color_by=\"leiden\"),\n",
    "        jscatter.Scatter(data=prot_plot_df, x=\"X_umap-0\", y=\"X_umap-1\", color_by=\"CD4_TotalSeqB\"),\n",
    "        jscatter.Scatter(data=prot_plot_df, x=\"X_umap-0\", y=\"X_umap-1\", color_by=\"leiden\"),\n",
    "    ],\n",
    "    rows=2\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3.bak"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}