{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import scanpy as sc\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "AnnData object with n_obs × n_vars = 149926 × 4000\n", " obs: 'nCount_ADT', 'nFeature_ADT', 'nCount_RNA', 'nFeature_RNA', 'orig.ident', 'lane', 'donor', 'time', 'celltype.l1', 'celltype.l2', 'celltype.l3', 'Phase', 'Batch', 'n_genes', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'total_counts_mt', 'log1p_total_counts_mt', 'pct_counts_mt'\n", " var: 'names', 'n_cells', 'mt', 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'highly_variable', 'means', 'dispersions', 'dispersions_norm'\n", " uns: 'Batch_colors', 'celltype.l1_colors', 'celltype.l2_colors', 'celltype.l3_colors', 'donor_colors', 'neighbors', 'pca', 'umap'\n", " obsm: 'X_pca', 'X_umap'\n", " varm: 'PCs'\n", " layers: 'count'\n", " obsp: 'connectivities', 'distances'" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scrna = sc.read('../data/hao-2020/expressions_hvg.h5ad')\n", "scrna" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "AnnData object with n_obs × n_vars = 149926 × 228\n", " obs: 'nCount_ADT', 'nFeature_ADT', 'nCount_RNA', 'nFeature_RNA', 'orig.ident', 'lane', 'donor', 'time', 'celltype.l1', 'celltype.l2', 'celltype.l3', 'Phase', 'Batch', 'n_genes'\n", " var: 'n_cells'\n", " uns: 'Batch_colors', 'celltype.l1_colors', 'celltype.l2_colors', 'celltype.l3_colors', 'donor_colors', 'neighbors', 'pca', 'umap'\n", " obsm: 'X_pca', 'X_umap'\n", " varm: 'PCs'\n", " layers: 'count'\n", " obsp: 'connectivities', 'distances'" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cite = sc.read('../data/hao-2020/protein.h5ad')\n", "cite" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "scrna.obs['cell_type'] = scrna.obs['celltype.l2'].astype('category')\n", "cite.obs['cell_type'] = cite.obs['celltype.l2'].astype('category')" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[66., 15., 37., ..., 8., 20., 50.],\n", " [ 4., 13., 9., ..., 7., 10., 22.],\n", " [ 6., 19., 8., ..., 7., 8., 13.],\n", " ...,\n", " [24., 5., 13., ..., 2., 2., 15.],\n", " [43., 4., 24., ..., 6., 7., 75.],\n", " [30., 7., 31., ..., 4., 2., 54.]], dtype=float32)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cite.layers['count']" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/anndata/_core/anndata.py:1094: FutureWarning: is_categorical is deprecated and will be removed in a future version. Use is_categorical_dtype instead\n", " if not is_categorical(df_full[k]):\n", "/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/pandas/core/arrays/categorical.py:2487: FutureWarning: The `inplace` parameter in pandas.Categorical.remove_unused_categories is deprecated and will be removed in a future version.\n", " res = method(*args, **kwargs)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "CD4\n", "CD4\n", "CD3\n", "CD56\n", "CD56\n", "CD11b\n", "CD11b\n", "CD38\n", "CD38\n", "CD44\n", "CD44\n", "CD26\n", "CD26\n", "CD275\n", "CD275\n", "CD45\n", "CD45\n", "CD133\n", "CD133\n", "CD3\n", "CD138\n", "CD138\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CD39Rat-IgG1-1CD107aCD62PTCR-2CD30CD31CD34CD35CD36...CD119CD169CD28CD161CD163CD138CD164CD144CD202bCD11c
L1_AAACCCAAGAAACTCA66.015.037.0142.04.03.0242.09.0752.014.0...28.05.031.03.013.014.05.08.020.050.0
L1_AAACCCAAGACATACA4.013.09.066.034.03.044.05.057.00.0...6.04.061.012.08.07.01.07.010.022.0
L1_AAACCCACAACTGGTT6.019.08.094.010.09.0103.04.060.02.0...2.05.037.00.06.018.01.07.08.013.0
L1_AAACCCACACGTACTA5.05.06.079.010.00.060.07.056.01.0...6.01.019.08.010.018.00.03.010.013.0
L1_AAACCCACAGCATACT4.010.014.0115.010.04.0169.06.073.05.0...2.04.046.00.01.016.01.05.013.012.0
..................................................................
E2L8_TTTGTTGGTCGTGATT1.02.011.059.017.01.052.06.024.01.0...6.00.026.00.02.06.03.05.010.07.0
E2L8_TTTGTTGGTGTGCCTG49.010.038.0256.011.01.0188.06.0519.014.0...18.026.016.00.013.016.011.05.06.090.0
E2L8_TTTGTTGGTTAGTTCG24.05.013.078.04.04.037.05.0851.04.0...12.01.014.01.05.09.023.02.02.015.0
E2L8_TTTGTTGGTTGGCTAT43.04.024.0287.08.03.0181.014.096.04.0...12.014.019.07.08.020.02.06.07.075.0
E2L8_TTTGTTGTCTCATGGA30.07.031.0146.010.01.0194.05.0274.06.0...9.07.021.02.07.012.06.04.02.054.0
\n", "

149926 rows × 217 columns

\n", "
" ], "text/plain": [ " CD39 Rat-IgG1-1 CD107a CD62P TCR-2 CD30 CD31 \\\n", "L1_AAACCCAAGAAACTCA 66.0 15.0 37.0 142.0 4.0 3.0 242.0 \n", "L1_AAACCCAAGACATACA 4.0 13.0 9.0 66.0 34.0 3.0 44.0 \n", "L1_AAACCCACAACTGGTT 6.0 19.0 8.0 94.0 10.0 9.0 103.0 \n", "L1_AAACCCACACGTACTA 5.0 5.0 6.0 79.0 10.0 0.0 60.0 \n", "L1_AAACCCACAGCATACT 4.0 10.0 14.0 115.0 10.0 4.0 169.0 \n", "... ... ... ... ... ... ... ... \n", "E2L8_TTTGTTGGTCGTGATT 1.0 2.0 11.0 59.0 17.0 1.0 52.0 \n", "E2L8_TTTGTTGGTGTGCCTG 49.0 10.0 38.0 256.0 11.0 1.0 188.0 \n", "E2L8_TTTGTTGGTTAGTTCG 24.0 5.0 13.0 78.0 4.0 4.0 37.0 \n", "E2L8_TTTGTTGGTTGGCTAT 43.0 4.0 24.0 287.0 8.0 3.0 181.0 \n", "E2L8_TTTGTTGTCTCATGGA 30.0 7.0 31.0 146.0 10.0 1.0 194.0 \n", "\n", " CD34 CD35 CD36 ... CD119 CD169 CD28 CD161 \\\n", "L1_AAACCCAAGAAACTCA 9.0 752.0 14.0 ... 28.0 5.0 31.0 3.0 \n", "L1_AAACCCAAGACATACA 5.0 57.0 0.0 ... 6.0 4.0 61.0 12.0 \n", "L1_AAACCCACAACTGGTT 4.0 60.0 2.0 ... 2.0 5.0 37.0 0.0 \n", "L1_AAACCCACACGTACTA 7.0 56.0 1.0 ... 6.0 1.0 19.0 8.0 \n", "L1_AAACCCACAGCATACT 6.0 73.0 5.0 ... 2.0 4.0 46.0 0.0 \n", "... ... ... ... ... ... ... ... ... \n", "E2L8_TTTGTTGGTCGTGATT 6.0 24.0 1.0 ... 6.0 0.0 26.0 0.0 \n", "E2L8_TTTGTTGGTGTGCCTG 6.0 519.0 14.0 ... 18.0 26.0 16.0 0.0 \n", "E2L8_TTTGTTGGTTAGTTCG 5.0 851.0 4.0 ... 12.0 1.0 14.0 1.0 \n", "E2L8_TTTGTTGGTTGGCTAT 14.0 96.0 4.0 ... 12.0 14.0 19.0 7.0 \n", "E2L8_TTTGTTGTCTCATGGA 5.0 274.0 6.0 ... 9.0 7.0 21.0 2.0 \n", "\n", " CD163 CD138 CD164 CD144 CD202b CD11c \n", "L1_AAACCCAAGAAACTCA 13.0 14.0 5.0 8.0 20.0 50.0 \n", "L1_AAACCCAAGACATACA 8.0 7.0 1.0 7.0 10.0 22.0 \n", "L1_AAACCCACAACTGGTT 6.0 18.0 1.0 7.0 8.0 13.0 \n", "L1_AAACCCACACGTACTA 10.0 18.0 0.0 3.0 10.0 13.0 \n", "L1_AAACCCACAGCATACT 1.0 16.0 1.0 5.0 13.0 12.0 \n", "... ... ... ... ... ... ... \n", "E2L8_TTTGTTGGTCGTGATT 2.0 6.0 3.0 5.0 10.0 7.0 \n", "E2L8_TTTGTTGGTGTGCCTG 13.0 16.0 11.0 5.0 6.0 90.0 \n", "E2L8_TTTGTTGGTTAGTTCG 5.0 9.0 23.0 2.0 2.0 15.0 \n", "E2L8_TTTGTTGGTTGGCTAT 8.0 20.0 2.0 6.0 7.0 75.0 \n", "E2L8_TTTGTTGTCTCATGGA 7.0 12.0 6.0 4.0 2.0 54.0 \n", "\n", "[149926 rows x 217 columns]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "protein_df = pd.DataFrame(index=cite.obs_names)\n", "ref_proteins = cite.var_names\n", "for p in ref_proteins:\n", " if p.split(\"-\")[-1] == \"1\" or p.split(\"-\")[-1] == \"2\":\n", " root = p.split(\"-\")[0]\n", " if root not in [\"Notch\", \"TCR\"]:\n", " try:\n", " protein_df[root] = (\n", " cite[:, root + \"-1\"].layers['count']\n", " + cite[:, root + \"-2\"].layers['count']\n", " )\n", " print(root)\n", " except:\n", " protein_df[p] = cite[:, p].layers['count']\n", " else:\n", " protein_df[p] = cite[:, p].layers['count']\n", " else:\n", " protein_df[p] = cite[:, p].layers['count']\n", "protein_df" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "AnnData object with n_obs × n_vars = 149926 × 217\n", " obs: 'nCount_ADT', 'nFeature_ADT', 'nCount_RNA', 'nFeature_RNA', 'orig.ident', 'lane', 'donor', 'time', 'celltype.l1', 'celltype.l2', 'celltype.l3', 'Phase', 'Batch', 'n_genes', 'cell_type'" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cite_new = sc.AnnData(protein_df.to_numpy())\n", "cite_new.obs = cite.obs.copy()\n", "cite_new" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "cite_new.layers['count'] = cite_new.X.copy()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "def clr_normalize_each_cell(adata, inplace=True):\n", " \"\"\"Normalize count vector for each cell, i.e. for each row of .X\"\"\"\n", "\n", " import numpy as np\n", " import scipy\n", "\n", " def seurat_clr(x):\n", " # TODO: support sparseness\n", " s = np.sum(np.log1p(x[x > 0]))\n", " exp = np.exp(s / len(x))\n", " return np.log1p(x / exp)\n", "\n", " if not inplace:\n", " adata = adata.copy()\n", "\n", " # apply to dense or sparse matrix, along axis. returns dense matrix\n", " adata.X = np.apply_along_axis(\n", " seurat_clr, 1, (adata.X.A if scipy.sparse.issparse(adata.X) else adata.X)\n", " )\n", " return adata" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "cite_new = clr_normalize_each_cell(cite_new)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/anndata/_core/anndata.py:1094: FutureWarning: is_categorical is deprecated and will be removed in a future version. Use is_categorical_dtype instead\n", " if not is_categorical(df_full[k]):\n", "/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/pandas/core/arrays/categorical.py:2487: FutureWarning: The `inplace` parameter in pandas.Categorical.remove_unused_categories is deprecated and will be removed in a future version.\n", " res = method(*args, **kwargs)\n" ] } ], "source": [ "adata1 = scrna[scrna.obs.Batch == 'Batch1']\n", "adata2 = scrna[scrna.obs.Batch == 'Batch2']" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "cite1 = cite_new[cite_new.obs.Batch == 'Batch1']\n", "cite2 = cite_new[cite_new.obs.Batch == 'Batch2']" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/anndata/_core/anndata.py:1192: FutureWarning: is_categorical is deprecated and will be removed in a future version. Use is_categorical_dtype instead\n", " if is_string_dtype(df[key]) and not is_categorical(df[key])\n" ] } ], "source": [ "adata1.write('../data/hao-2020/adata1.h5ad')\n", "adata2.write('../data/hao-2020/adata2.h5ad')\n", "cite1.write('../data/hao-2020/cite1.h5ad')\n", "cite2.write('../data/hao-2020/cite2.h5ad')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.9" } }, "nbformat": 4, "nbformat_minor": 5 }