Created
March 27, 2020 03:56
-
-
Save vals/7232c1ec808cd67eb67fe3cc99c87e18 to your computer and use it in GitHub Desktop.
Unpolished notebook resulting from making cell type dendrogram using Han et al HCL data
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Populating the interactive namespace from numpy and matplotlib\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "%pylab inline\n", | |
| "%config InlineBackend.figure_format = 'retina'\n", | |
| "\n", | |
| "import anndata\n", | |
| "import pandas as pd\n", | |
| "import plotnine as p\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "adata = anndata.read('HCL_comined.h5ad')" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 3, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "AnnData object with n_obs × n_vars = 599926 × 27341 \n", | |
| " obs: 'index', 'batch', 'tissue', 'n_genes', 'n_counts', 'sample', 'cluster', 'stage', 'donor', 'celltype'\n", | |
| " var: 'n_cells'" | |
| ] | |
| }, | |
| "execution_count": 3, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "adata" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 4, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "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>index</th>\n", | |
| " <th>batch</th>\n", | |
| " <th>tissue</th>\n", | |
| " <th>n_genes</th>\n", | |
| " <th>n_counts</th>\n", | |
| " <th>sample</th>\n", | |
| " <th>cluster</th>\n", | |
| " <th>stage</th>\n", | |
| " <th>donor</th>\n", | |
| " <th>celltype</th>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>barcode</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", | |
| " <td>AdultAdipose_1.TATGTAACACCCGCAGGA</td>\n", | |
| " <td>AdultAdipose_1.TATGTAACACCCGCAGGA-0</td>\n", | |
| " <td>AdultAdipose1</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>911</td>\n", | |
| " <td>1285.0</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Adult</td>\n", | |
| " <td>Donor20</td>\n", | |
| " <td>Macrophage</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>AdultAdipose_1.CTCGCAAATAAACATCCC</td>\n", | |
| " <td>AdultAdipose_1.CTCGCAAATAAACATCCC-0</td>\n", | |
| " <td>AdultAdipose1</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>1075</td>\n", | |
| " <td>1628.0</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Adult</td>\n", | |
| " <td>Donor20</td>\n", | |
| " <td>Macrophage</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>AdultAdipose_1.CGAGTATCGTAATACTTC</td>\n", | |
| " <td>AdultAdipose_1.CGAGTATCGTAATACTTC-0</td>\n", | |
| " <td>AdultAdipose1</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>730</td>\n", | |
| " <td>1018.0</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Adult</td>\n", | |
| " <td>Donor20</td>\n", | |
| " <td>Macrophage</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>AdultAdipose_1.CTCGCAGCGAATCGGCAG</td>\n", | |
| " <td>AdultAdipose_1.CTCGCAGCGAATCGGCAG-0</td>\n", | |
| " <td>AdultAdipose1</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>802</td>\n", | |
| " <td>1145.0</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Adult</td>\n", | |
| " <td>Donor20</td>\n", | |
| " <td>Macrophage</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>AdultAdipose_1.ACGTTGATCAACAGATGG</td>\n", | |
| " <td>AdultAdipose_1.ACGTTGATCAACAGATGG-0</td>\n", | |
| " <td>AdultAdipose1</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>622</td>\n", | |
| " <td>852.0</td>\n", | |
| " <td>AdultAdipose</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Adult</td>\n", | |
| " <td>Donor20</td>\n", | |
| " <td>Macrophage</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2</td>\n", | |
| " <td>NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2-1</td>\n", | |
| " <td>NeonatalAdrenalGland1</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>607</td>\n", | |
| " <td>849.0</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>12</td>\n", | |
| " <td>Fetus</td>\n", | |
| " <td>Donor19</td>\n", | |
| " <td>Erythroid progenitor cell (RP high)</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2</td>\n", | |
| " <td>NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2-1</td>\n", | |
| " <td>NeonatalAdrenalGland1</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>365</td>\n", | |
| " <td>463.0</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>63</td>\n", | |
| " <td>Fetus</td>\n", | |
| " <td>Donor19</td>\n", | |
| " <td>Fasciculata cell</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2</td>\n", | |
| " <td>NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2-1</td>\n", | |
| " <td>NeonatalAdrenalGland1</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>370</td>\n", | |
| " <td>459.0</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>63</td>\n", | |
| " <td>Fetus</td>\n", | |
| " <td>Donor19</td>\n", | |
| " <td>Fasciculata cell</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2</td>\n", | |
| " <td>NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2-1</td>\n", | |
| " <td>NeonatalAdrenalGland1</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>361</td>\n", | |
| " <td>435.0</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>63</td>\n", | |
| " <td>Fetus</td>\n", | |
| " <td>Donor19</td>\n", | |
| " <td>Fasciculata cell</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2</td>\n", | |
| " <td>NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2-1</td>\n", | |
| " <td>NeonatalAdrenalGland1</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>326</td>\n", | |
| " <td>453.0</td>\n", | |
| " <td>NeonatalAdrenalGland</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Fetus</td>\n", | |
| " <td>Donor19</td>\n", | |
| " <td>Macrophage</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "<p>599926 rows × 10 columns</p>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " index \\\n", | |
| "barcode \n", | |
| "AdultAdipose_1.TATGTAACACCCGCAGGA AdultAdipose_1.TATGTAACACCCGCAGGA-0 \n", | |
| "AdultAdipose_1.CTCGCAAATAAACATCCC AdultAdipose_1.CTCGCAAATAAACATCCC-0 \n", | |
| "AdultAdipose_1.CGAGTATCGTAATACTTC AdultAdipose_1.CGAGTATCGTAATACTTC-0 \n", | |
| "AdultAdipose_1.CTCGCAGCGAATCGGCAG AdultAdipose_1.CTCGCAGCGAATCGGCAG-0 \n", | |
| "AdultAdipose_1.ACGTTGATCAACAGATGG AdultAdipose_1.ACGTTGATCAACAGATGG-0 \n", | |
| "... ... \n", | |
| "NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2 NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2-1 \n", | |
| "NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2 NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2-1 \n", | |
| "NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2 NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2-1 \n", | |
| "NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2 NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2-1 \n", | |
| "NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2 NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2-1 \n", | |
| "\n", | |
| " batch \\\n", | |
| "barcode \n", | |
| "AdultAdipose_1.TATGTAACACCCGCAGGA AdultAdipose1 \n", | |
| "AdultAdipose_1.CTCGCAAATAAACATCCC AdultAdipose1 \n", | |
| "AdultAdipose_1.CGAGTATCGTAATACTTC AdultAdipose1 \n", | |
| "AdultAdipose_1.CTCGCAGCGAATCGGCAG AdultAdipose1 \n", | |
| "AdultAdipose_1.ACGTTGATCAACAGATGG AdultAdipose1 \n", | |
| "... ... \n", | |
| "NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2 NeonatalAdrenalGland1 \n", | |
| "NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2 NeonatalAdrenalGland1 \n", | |
| "NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2 NeonatalAdrenalGland1 \n", | |
| "NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2 NeonatalAdrenalGland1 \n", | |
| "NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2 NeonatalAdrenalGland1 \n", | |
| "\n", | |
| " tissue n_genes \\\n", | |
| "barcode \n", | |
| "AdultAdipose_1.TATGTAACACCCGCAGGA AdultAdipose 911 \n", | |
| "AdultAdipose_1.CTCGCAAATAAACATCCC AdultAdipose 1075 \n", | |
| "AdultAdipose_1.CGAGTATCGTAATACTTC AdultAdipose 730 \n", | |
| "AdultAdipose_1.CTCGCAGCGAATCGGCAG AdultAdipose 802 \n", | |
| "AdultAdipose_1.ACGTTGATCAACAGATGG AdultAdipose 622 \n", | |
| "... ... ... \n", | |
| "NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2 NeonatalAdrenalGland 607 \n", | |
| "NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2 NeonatalAdrenalGland 365 \n", | |
| "NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2 NeonatalAdrenalGland 370 \n", | |
| "NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2 NeonatalAdrenalGland 361 \n", | |
| "NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2 NeonatalAdrenalGland 326 \n", | |
| "\n", | |
| " n_counts sample \\\n", | |
| "barcode \n", | |
| "AdultAdipose_1.TATGTAACACCCGCAGGA 1285.0 AdultAdipose \n", | |
| "AdultAdipose_1.CTCGCAAATAAACATCCC 1628.0 AdultAdipose \n", | |
| "AdultAdipose_1.CGAGTATCGTAATACTTC 1018.0 AdultAdipose \n", | |
| "AdultAdipose_1.CTCGCAGCGAATCGGCAG 1145.0 AdultAdipose \n", | |
| "AdultAdipose_1.ACGTTGATCAACAGATGG 852.0 AdultAdipose \n", | |
| "... ... ... \n", | |
| "NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2 849.0 NeonatalAdrenalGland \n", | |
| "NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2 463.0 NeonatalAdrenalGland \n", | |
| "NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2 459.0 NeonatalAdrenalGland \n", | |
| "NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2 435.0 NeonatalAdrenalGland \n", | |
| "NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2 453.0 NeonatalAdrenalGland \n", | |
| "\n", | |
| " cluster stage donor \\\n", | |
| "barcode \n", | |
| "AdultAdipose_1.TATGTAACACCCGCAGGA 2 Adult Donor20 \n", | |
| "AdultAdipose_1.CTCGCAAATAAACATCCC 2 Adult Donor20 \n", | |
| "AdultAdipose_1.CGAGTATCGTAATACTTC 2 Adult Donor20 \n", | |
| "AdultAdipose_1.CTCGCAGCGAATCGGCAG 2 Adult Donor20 \n", | |
| "AdultAdipose_1.ACGTTGATCAACAGATGG 2 Adult Donor20 \n", | |
| "... ... ... ... \n", | |
| "NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2 12 Fetus Donor19 \n", | |
| "NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2 63 Fetus Donor19 \n", | |
| "NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2 63 Fetus Donor19 \n", | |
| "NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2 63 Fetus Donor19 \n", | |
| "NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2 2 Fetus Donor19 \n", | |
| "\n", | |
| " celltype \n", | |
| "barcode \n", | |
| "AdultAdipose_1.TATGTAACACCCGCAGGA Macrophage \n", | |
| "AdultAdipose_1.CTCGCAAATAAACATCCC Macrophage \n", | |
| "AdultAdipose_1.CGAGTATCGTAATACTTC Macrophage \n", | |
| "AdultAdipose_1.CTCGCAGCGAATCGGCAG Macrophage \n", | |
| "AdultAdipose_1.ACGTTGATCAACAGATGG Macrophage \n", | |
| "... ... \n", | |
| "NeonatalAdrenalGland_1.CCGCTAATTCCAGGACAT2 Erythroid progenitor cell (RP high) \n", | |
| "NeonatalAdrenalGland_1.TAGAGAGGGTTTTCGGGT2 Fasciculata cell \n", | |
| "NeonatalAdrenalGland_1.AAAACGTATGTACATGAT2 Fasciculata cell \n", | |
| "NeonatalAdrenalGland_1.ATGGCGTGCGGAATCAAC2 Fasciculata cell \n", | |
| "NeonatalAdrenalGland_1.CGCACCCTGTGTCCTTTC2 Macrophage \n", | |
| "\n", | |
| "[599926 rows x 10 columns]" | |
| ] | |
| }, | |
| "execution_count": 4, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "adata.obs" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 5, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "AdultPleura1 19695\n", | |
| "FetalMuscle1 18345\n", | |
| "FetalLiver1 17929\n", | |
| "AdultSpleen1 15806\n", | |
| "AdultAdrenalGland3 15083\n", | |
| " ... \n", | |
| "AdultOmentum3 1354\n", | |
| "FetalIntestine2 1338\n", | |
| "FetalStomach1 1322\n", | |
| "AdultHeart1 1308\n", | |
| "AdultBladder1 1267\n", | |
| "Name: batch, Length: 104, dtype: int64" | |
| ] | |
| }, | |
| "execution_count": 5, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "adata.obs['batch'].value_counts()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 6, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "Fibroblast 42587\n", | |
| "Macrophage 33241\n", | |
| "B cell (Plasmocyte) 27737\n", | |
| "Fetal mesenchymal progenitor 22915\n", | |
| "T cell 22780\n", | |
| " ... \n", | |
| "Fetal Neuron 644\n", | |
| "Intermediated cell 540\n", | |
| "Chondrocyte 421\n", | |
| "Kidney intercalated cell 138\n", | |
| "Adrenal gland inflammatory cell 91\n", | |
| "Name: celltype, Length: 63, dtype: int64" | |
| ] | |
| }, | |
| "execution_count": 6, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "adata.obs['celltype'].value_counts()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": null, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 15, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment