{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import scanpy as sc\n", "import os\n", "from sklearn.cluster import KMeans\n", "from sklearn.cluster import AgglomerativeClustering\n", "from sklearn.metrics.cluster import adjusted_rand_score\n", "from sklearn.metrics.cluster import adjusted_mutual_info_score\n", "from sklearn.metrics.cluster import homogeneity_score\n", "import rpy2.robjects as robjects\n", "from rpy2.robjects import pandas2ri" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "df_metrics = pd.DataFrame(columns=['ARI_Louvain','ARI_kmeans','ARI_HC',\n", " 'AMI_Louvain','AMI_kmeans','AMI_HC',\n", " 'Homogeneity_Louvain','Homogeneity_kmeans','Homogeneity_HC'])" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "workdir = './output/'\n", "path_fm = os.path.join(workdir,'feature_matrices/')\n", "path_clusters = os.path.join(workdir,'clusters/')\n", "path_metrics = os.path.join(workdir,'metrics/')\n", "os.system('mkdir -p '+path_clusters)\n", "os.system('mkdir -p '+path_metrics)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "metadata = pd.read_csv('./input/metadata.tsv',sep='\\t',index_col=0)\n", "num_clusters = len(np.unique(metadata['label']))" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "17" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "files = [x for x in os.listdir(path_fm) if x.startswith('FM')]\n", "len(files)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['FM_Control_BMcov2500.rds',\n", " 'FM_BROCKMAN_BMcov2500.rds',\n", " 'FM_Cusanovich2018_BMcov2500.rds',\n", " 'FM_cisTopic_BMcov2500.rds',\n", " 'FM_chromVAR_BMcov2500_kmers.rds',\n", " 'FM_chromVAR_BMcov2500_motifs.rds',\n", " 'FM_chromVAR_BMcov2500_kmers_pca.rds',\n", " 'FM_chromVAR_BMcov2500_motifs_pca.rds',\n", " 'FM_GeneScoring_BMcov2500.rds',\n", " 'FM_GeneScoring_BMcov2500_pca.rds',\n", " 'FM_Cicero_BMcov2500.rds',\n", " 'FM_Cicero_BMcov2500_pca.rds',\n", " 'FM_SnapATAC_BMcov2500.rds',\n", " 'FM_Scasat_BMcov2500.rds',\n", " 'FM_scABC_BMcov2500.rds',\n", " 'FM_SCRAT_BMcov2500.rds',\n", " 'FM_SCRAT_BMcov2500_pca.rds']" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "files" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "def getNClusters(adata,n_cluster,range_min=0,range_max=3,max_steps=20):\n", " this_step = 0\n", " this_min = float(range_min)\n", " this_max = float(range_max)\n", " while this_step < max_steps:\n", " print('step ' + str(this_step))\n", " this_resolution = this_min + ((this_max-this_min)/2)\n", " sc.tl.louvain(adata,resolution=this_resolution)\n", " this_clusters = adata.obs['louvain'].nunique()\n", " \n", " print('got ' + str(this_clusters) + ' at resolution ' + str(this_resolution))\n", " \n", " if this_clusters > n_cluster:\n", " this_max = this_resolution\n", " elif this_clusters < n_cluster:\n", " this_min = this_resolution\n", " else:\n", " return(this_resolution, adata)\n", " this_step += 1\n", " \n", " print('Cannot find the number of clusters')\n", " print('Clustering solution from last iteration is used:' + str(this_clusters) + ' at resolution ' + str(this_resolution))" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Control\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "BROCKMAN\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 10 at resolution 1.5\n", "step 1\n", "got 6 at resolution 0.75\n", "Cusanovich2018\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "cisTopic\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "chromVAR_kmers\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 5 at resolution 1.5\n", "step 1\n", "got 10 at resolution 2.25\n", "step 2\n", "got 6 at resolution 1.875\n", "chromVAR_motifs\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "chromVAR_kmers_pca\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "chromVAR_motifs_pca\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "GeneScoring\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 31 at resolution 1.5\n", "step 1\n", "got 3 at resolution 0.75\n", "step 2\n", "got 12 at resolution 1.125\n", "step 3\n", "got 7 at resolution 0.9375\n", "step 4\n", "got 5 at resolution 0.84375\n", "step 5\n", "got 5 at resolution 0.890625\n", "step 6\n", "got 5 at resolution 0.9140625\n", "step 7\n", "got 7 at resolution 0.92578125\n", "step 8\n", "got 5 at resolution 0.919921875\n", "step 9\n", "got 7 at resolution 0.9228515625\n", "step 10\n", "got 7 at resolution 0.92138671875\n", "step 11\n", "got 7 at resolution 0.920654296875\n", "step 12\n", "got 5 at resolution 0.9202880859375\n", "step 13\n", "got 7 at resolution 0.92047119140625\n", "step 14\n", "got 5 at resolution 0.920379638671875\n", "step 15\n", "got 5 at resolution 0.9204254150390625\n", "step 16\n", "got 7 at resolution 0.9204483032226562\n", "step 17\n", "got 5 at resolution 0.9204368591308594\n", "step 18\n", "got 5 at resolution 0.9204425811767578\n", "step 19\n", "got 7 at resolution 0.920445442199707\n", "Cannot find the number of clusters\n", "Clustering solution from last iteration is used:7 at resolution 0.920445442199707\n", "GeneScoring_pca\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 14 at resolution 1.5\n", "step 1\n", "got 9 at resolution 0.75\n", "step 2\n", "got 7 at resolution 0.375\n", "step 3\n", "got 4 at resolution 0.1875\n", "step 4\n", "got 5 at resolution 0.28125\n", "step 5\n", "got 6 at resolution 0.328125\n", "Cicero\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 34 at resolution 1.5\n", "step 1\n", "got 2 at resolution 0.75\n", "step 2\n", "got 17 at resolution 1.125\n", "step 3\n", "got 5 at resolution 0.9375\n", "step 4\n", "got 11 at resolution 1.03125\n", "step 5\n", "got 8 at resolution 0.984375\n", "step 6\n", "got 4 at resolution 0.9609375\n", "step 7\n", "got 5 at resolution 0.97265625\n", "step 8\n", "got 7 at resolution 0.978515625\n", "step 9\n", "got 6 at resolution 0.9755859375\n", "Cicero_pca\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 10 at resolution 1.5\n", "step 1\n", "got 4 at resolution 0.75\n", "step 2\n", "got 6 at resolution 1.125\n", "SnapATAC\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "Scasat\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 6 at resolution 1.5\n", "scABC\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 14 at resolution 1.5\n", "step 1\n", "got 3 at resolution 0.75\n", "step 2\n", "got 4 at resolution 1.125\n", "step 3\n", "got 9 at resolution 1.3125\n", "step 4\n", "got 7 at resolution 1.21875\n", "step 5\n", "got 5 at resolution 1.171875\n", "step 6\n", "got 7 at resolution 1.1953125\n", "step 7\n", "got 5 at resolution 1.18359375\n", "step 8\n", "got 6 at resolution 1.189453125\n", "SCRAT\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 8 at resolution 1.5\n", "step 1\n", "got 6 at resolution 0.75\n", "SCRAT_pca\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/data/pinello/SHARED_SOFTWARE/anaconda3/envs/ATACseq_clustering/lib/python3.7/site-packages/rpy2/robjects/pandas2ri.py:191: FutureWarning: from_items is deprecated. Please use DataFrame.from_dict(dict(items), ...) instead. DataFrame.from_dict(OrderedDict(items)) may be used to preserve the key order.\n", " res = PandasDataFrame.from_items(items)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "step 0\n", "got 11 at resolution 1.5\n", "step 1\n", "got 6 at resolution 0.75\n" ] } ], "source": [ "for file in files:\n", " file_split = file.split('_')\n", " method = file_split[1]\n", " dataset = file_split[2].split('.')[0]\n", " if(len(file_split)>3):\n", " method = method + '_' + '_'.join(file_split[3:]).split('.')[0]\n", " print(method)\n", "\n", " pandas2ri.activate()\n", " readRDS = robjects.r['readRDS']\n", " df_rds = readRDS(os.path.join(path_fm,file))\n", " fm_mat = pandas2ri.ri2py(robjects.r['data.frame'](robjects.r['as.matrix'](df_rds)))\n", " fm_mat.columns = metadata.index\n", " \n", " adata = sc.AnnData(fm_mat.T)\n", " adata.var_names_make_unique()\n", " adata.obs = metadata.loc[adata.obs.index,]\n", " df_metrics.loc[method,] = \"\"\n", " #Louvain\n", " sc.pp.neighbors(adata, n_neighbors=15,use_rep='X')\n", "# sc.tl.louvain(adata)\n", " getNClusters(adata,n_cluster=num_clusters)\n", " #kmeans\n", " kmeans = KMeans(n_clusters=num_clusters, random_state=2019).fit(adata.X)\n", " adata.obs['kmeans'] = pd.Series(kmeans.labels_,index=adata.obs.index).astype('category')\n", " #hierachical clustering\n", " hc = AgglomerativeClustering(n_clusters=num_clusters).fit(adata.X)\n", " adata.obs['hc'] = pd.Series(hc.labels_,index=adata.obs.index).astype('category')\n", " #clustering metrics\n", " \n", " #adjusted rank index\n", " ari_louvain = adjusted_rand_score(adata.obs['label'], adata.obs['louvain'])\n", " ari_kmeans = adjusted_rand_score(adata.obs['label'], adata.obs['kmeans'])\n", " ari_hc = adjusted_rand_score(adata.obs['label'], adata.obs['hc'])\n", " #adjusted mutual information\n", " ami_louvain = adjusted_mutual_info_score(adata.obs['label'], adata.obs['louvain'],average_method='arithmetic')\n", " ami_kmeans = adjusted_mutual_info_score(adata.obs['label'], adata.obs['kmeans'],average_method='arithmetic') \n", " ami_hc = adjusted_mutual_info_score(adata.obs['label'], adata.obs['hc'],average_method='arithmetic')\n", " #homogeneity\n", " homo_louvain = homogeneity_score(adata.obs['label'], adata.obs['louvain'])\n", " homo_kmeans = homogeneity_score(adata.obs['label'], adata.obs['kmeans'])\n", " homo_hc = homogeneity_score(adata.obs['label'], adata.obs['hc'])\n", "\n", " df_metrics.loc[method,['ARI_Louvain','ARI_kmeans','ARI_HC']] = [ari_louvain,ari_kmeans,ari_hc]\n", " df_metrics.loc[method,['AMI_Louvain','AMI_kmeans','AMI_HC']] = [ami_louvain,ami_kmeans,ami_hc]\n", " df_metrics.loc[method,['Homogeneity_Louvain','Homogeneity_kmeans','Homogeneity_HC']] = [homo_louvain,homo_kmeans,homo_hc] \n", " adata.obs[['louvain','kmeans','hc']].to_csv(os.path.join(path_clusters ,method + '_clusters.tsv'),sep='\\t')" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "df_metrics.to_csv(path_metrics+'clustering_scores.csv')" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "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", "
ARI_LouvainARI_kmeansARI_HCAMI_LouvainAMI_kmeansAMI_HCHomogeneity_LouvainHomogeneity_kmeansHomogeneity_HC
Control0.9653150.7982180.7979010.9652790.8687540.8659260.965390.8682050.866151
BROCKMAN0.947240.6577680.7252510.9490480.752790.8042340.9492220.7526450.800707
Cusanovich201810.7732510.99799710.9000150.99705310.8710490.99707
cisTopic10.9979970.99799710.9970530.99705310.997070.99707
chromVAR_kmers0.768630.717030.6494660.824170.786710.7306110.822110.7873830.726742
chromVAR_motifs0.4646930.4595930.4210480.6121460.6145610.5798870.6108320.61640.579137
chromVAR_kmers_pca0.7416520.7505730.7021120.8039620.8095260.7684380.8042080.8104030.765538
chromVAR_motifs_pca0.4832010.4514050.4322680.6249370.6067740.6010310.6213480.6089640.588254
GeneScoring0.02142390.4483140.3621240.02638940.6015960.4478310.03406320.5213970.409118
GeneScoring_pca0.4015740.4037720.4004710.4994770.4922950.4982760.4901160.4814760.484532
Cicero0.1198780.4455140.4593460.1436040.6771570.6113320.1439220.5653380.600784
Cicero_pca0.5912840.5822760.5014410.7040680.7052550.6640970.6812980.6882950.634709
SnapATAC0.9979970.9979970.9979970.9970530.9970530.9970530.997070.997070.99707
Scasat0.9803290.8998490.8073840.9771480.92060.8739240.9772710.9210120.872492
scABC0.5415540.5234540.6963640.627560.6811820.7809810.5775480.6182570.76102
SCRAT0.5741040.552880.5383710.7062650.6869610.6844870.7026280.6866090.681563
SCRAT_pca0.6209990.5473430.5614410.7175250.6845130.6764010.7190680.6839290.673369
\n", "
" ], "text/plain": [ " ARI_Louvain ARI_kmeans ARI_HC AMI_Louvain AMI_kmeans \\\n", "Control 0.965315 0.798218 0.797901 0.965279 0.868754 \n", "BROCKMAN 0.94724 0.657768 0.725251 0.949048 0.75279 \n", "Cusanovich2018 1 0.773251 0.997997 1 0.900015 \n", "cisTopic 1 0.997997 0.997997 1 0.997053 \n", "chromVAR_kmers 0.76863 0.71703 0.649466 0.82417 0.78671 \n", "chromVAR_motifs 0.464693 0.459593 0.421048 0.612146 0.614561 \n", "chromVAR_kmers_pca 0.741652 0.750573 0.702112 0.803962 0.809526 \n", "chromVAR_motifs_pca 0.483201 0.451405 0.432268 0.624937 0.606774 \n", "GeneScoring 0.0214239 0.448314 0.362124 0.0263894 0.601596 \n", "GeneScoring_pca 0.401574 0.403772 0.400471 0.499477 0.492295 \n", "Cicero 0.119878 0.445514 0.459346 0.143604 0.677157 \n", "Cicero_pca 0.591284 0.582276 0.501441 0.704068 0.705255 \n", "SnapATAC 0.997997 0.997997 0.997997 0.997053 0.997053 \n", "Scasat 0.980329 0.899849 0.807384 0.977148 0.9206 \n", "scABC 0.541554 0.523454 0.696364 0.62756 0.681182 \n", "SCRAT 0.574104 0.55288 0.538371 0.706265 0.686961 \n", "SCRAT_pca 0.620999 0.547343 0.561441 0.717525 0.684513 \n", "\n", " AMI_HC Homogeneity_Louvain Homogeneity_kmeans \\\n", "Control 0.865926 0.96539 0.868205 \n", "BROCKMAN 0.804234 0.949222 0.752645 \n", "Cusanovich2018 0.997053 1 0.871049 \n", "cisTopic 0.997053 1 0.99707 \n", "chromVAR_kmers 0.730611 0.82211 0.787383 \n", "chromVAR_motifs 0.579887 0.610832 0.6164 \n", "chromVAR_kmers_pca 0.768438 0.804208 0.810403 \n", "chromVAR_motifs_pca 0.601031 0.621348 0.608964 \n", "GeneScoring 0.447831 0.0340632 0.521397 \n", "GeneScoring_pca 0.498276 0.490116 0.481476 \n", "Cicero 0.611332 0.143922 0.565338 \n", "Cicero_pca 0.664097 0.681298 0.688295 \n", "SnapATAC 0.997053 0.99707 0.99707 \n", "Scasat 0.873924 0.977271 0.921012 \n", "scABC 0.780981 0.577548 0.618257 \n", "SCRAT 0.684487 0.702628 0.686609 \n", "SCRAT_pca 0.676401 0.719068 0.683929 \n", "\n", " Homogeneity_HC \n", "Control 0.866151 \n", "BROCKMAN 0.800707 \n", "Cusanovich2018 0.99707 \n", "cisTopic 0.99707 \n", "chromVAR_kmers 0.726742 \n", "chromVAR_motifs 0.579137 \n", "chromVAR_kmers_pca 0.765538 \n", "chromVAR_motifs_pca 0.588254 \n", "GeneScoring 0.409118 \n", "GeneScoring_pca 0.484532 \n", "Cicero 0.600784 \n", "Cicero_pca 0.634709 \n", "SnapATAC 0.99707 \n", "Scasat 0.872492 \n", "scABC 0.76102 \n", "SCRAT 0.681563 \n", "SCRAT_pca 0.673369 " ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_metrics" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python [conda env:ATACseq_clustering]", "language": "python", "name": "conda-env-ATACseq_clustering-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }