import pandas as pd
import numpy as np
import scanpy as sc
import os
from sklearn.cluster import KMeans
from sklearn.cluster import AgglomerativeClustering
from sklearn.metrics.cluster import adjusted_rand_score
from sklearn.metrics.cluster import adjusted_mutual_info_score
from sklearn.metrics.cluster import homogeneity_score
import rpy2.robjects as robjects
from rpy2.robjects import pandas2ri
df_metrics = pd.DataFrame(columns=['ARI_Louvain','ARI_kmeans','ARI_HC',
'AMI_Louvain','AMI_kmeans','AMI_HC',
'Homogeneity_Louvain','Homogeneity_kmeans','Homogeneity_HC'])
workdir = './output/'
path_fm = os.path.join(workdir,'feature_matrices/')
path_clusters = os.path.join(workdir,'clusters/')
path_metrics = os.path.join(workdir,'metrics/')
os.system('mkdir -p '+path_clusters)
os.system('mkdir -p '+path_metrics)
0
metadata = pd.read_csv('./input/metadata.tsv',sep='\t',index_col=0)
num_clusters = len(np.unique(metadata['label']))
print(num_clusters)
10
files = [x for x in os.listdir(path_fm) if x.startswith('FM')]
len(files)
13
files
['FM_ChromVAR_buenrostro2018bulkpeaks_kmers.rds', 'FM_ChromVAR_buenrostro2018bulkpeaks_motifs.rds', 'FM_cisTopic_buenrostro2018bulkpeaks.rds', 'FM_Cusanovich2018_buenrostro2018bulkpeaks.rds', 'FM_Control_buenrostro2018bulkpeaks.rds', 'FM_GeneScoring_buenrostro2018bulkpeaks.rds', 'FM_Scasat_buenrostro2018bulkpeaks.rds', 'FM_scABC_buenrostro2018bulkpeaks.rds', 'FM_Cicero_buenrostro2018bulkpeaks.rds', 'FM_ChromVAR_buenrostro2018bulkpeaks_kmers_pca.rds', 'FM_ChromVAR_buenrostro2018bulkpeaks_motifs_pca.rds', 'FM_GeneScoring_buenrostro2018bulkpeaks_pca.rds', 'FM_Cicero_buenrostro2018bulkpeaks_pca.rds']
def getNClusters(adata,n_cluster,range_min=0,range_max=3,max_steps=20):
this_step = 0
this_min = float(range_min)
this_max = float(range_max)
while this_step < max_steps:
print('step ' + str(this_step))
this_resolution = this_min + ((this_max-this_min)/2)
sc.tl.louvain(adata,resolution=this_resolution)
this_clusters = adata.obs['louvain'].nunique()
print('got ' + str(this_clusters) + ' at resolution ' + str(this_resolution))
if this_clusters > n_cluster:
this_max = this_resolution
elif this_clusters < n_cluster:
this_min = this_resolution
else:
return(this_resolution, adata)
this_step += 1
print('Cannot find the number of clusters')
print('Clustering solution from last iteration is used:' + str(this_clusters) + ' at resolution ' + str(this_resolution))
for file in files:
file_split = file.split('_')
method = file_split[1]
dataset = file_split[2].split('.')[0]
if(len(file_split)>3):
method = method + '_' + '_'.join(file_split[3:]).split('.')[0]
print(method)
pandas2ri.activate()
readRDS = robjects.r['readRDS']
df_rds = readRDS(os.path.join(path_fm,file))
fm_mat = pandas2ri.ri2py(robjects.r['data.frame'](robjects.r['as.matrix'](df_rds)))
fm_mat.fillna(0,inplace=True)
fm_mat.columns = metadata.index
adata = sc.AnnData(fm_mat.T)
adata.var_names_make_unique()
adata.obs = metadata.loc[adata.obs.index,]
df_metrics.loc[method,] = ""
#Louvain
sc.pp.neighbors(adata, n_neighbors=15,use_rep='X')
# sc.tl.louvain(adata)
getNClusters(adata,n_cluster=num_clusters)
#kmeans
kmeans = KMeans(n_clusters=num_clusters, random_state=2019).fit(adata.X)
adata.obs['kmeans'] = pd.Series(kmeans.labels_,index=adata.obs.index).astype('category')
#hierachical clustering
hc = AgglomerativeClustering(n_clusters=num_clusters).fit(adata.X)
adata.obs['hc'] = pd.Series(hc.labels_,index=adata.obs.index).astype('category')
#clustering metrics
#adjusted rank index
ari_louvain = adjusted_rand_score(adata.obs['label'], adata.obs['louvain'])
ari_kmeans = adjusted_rand_score(adata.obs['label'], adata.obs['kmeans'])
ari_hc = adjusted_rand_score(adata.obs['label'], adata.obs['hc'])
#adjusted mutual information
ami_louvain = adjusted_mutual_info_score(adata.obs['label'], adata.obs['louvain'],average_method='arithmetic')
ami_kmeans = adjusted_mutual_info_score(adata.obs['label'], adata.obs['kmeans'],average_method='arithmetic')
ami_hc = adjusted_mutual_info_score(adata.obs['label'], adata.obs['hc'],average_method='arithmetic')
#homogeneity
homo_louvain = homogeneity_score(adata.obs['label'], adata.obs['louvain'])
homo_kmeans = homogeneity_score(adata.obs['label'], adata.obs['kmeans'])
homo_hc = homogeneity_score(adata.obs['label'], adata.obs['hc'])
df_metrics.loc[method,['ARI_Louvain','ARI_kmeans','ARI_HC']] = [ari_louvain,ari_kmeans,ari_hc]
df_metrics.loc[method,['AMI_Louvain','AMI_kmeans','AMI_HC']] = [ami_louvain,ami_kmeans,ami_hc]
df_metrics.loc[method,['Homogeneity_Louvain','Homogeneity_kmeans','Homogeneity_HC']] = [homo_louvain,homo_kmeans,homo_hc]
adata.obs[['louvain','kmeans','hc']].to_csv(os.path.join(path_clusters ,method + '_clusters.tsv'),sep='\t')
ChromVAR_kmers
/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. res = PandasDataFrame.from_items(items)
step 0 got 9 at resolution 1.5 step 1 got 14 at resolution 2.25 step 2 got 10 at resolution 1.875 ChromVAR_motifs
/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. res = PandasDataFrame.from_items(items)
step 0 got 10 at resolution 1.5 cisTopic
/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. res = PandasDataFrame.from_items(items)
step 0 got 18 at resolution 1.5 step 1 got 13 at resolution 0.75 step 2 got 9 at resolution 0.375 step 3 got 13 at resolution 0.5625 step 4 got 10 at resolution 0.46875 Cusanovich2018
/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. res = PandasDataFrame.from_items(items)
step 0 got 15 at resolution 1.5 step 1 got 11 at resolution 0.75 step 2 got 7 at resolution 0.375 step 3 got 10 at resolution 0.5625 Control
/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. res = PandasDataFrame.from_items(items)
step 0 got 19 at resolution 1.5 step 1 got 11 at resolution 0.75 step 2 got 8 at resolution 0.375 step 3 got 10 at resolution 0.5625 GeneScoring
/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. res = PandasDataFrame.from_items(items)
step 0 got 8 at resolution 1.5 step 1 got 33 at resolution 2.25 step 2 got 21 at resolution 1.875 step 3 got 13 at resolution 1.6875 step 4 got 13 at resolution 1.59375 step 5 got 11 at resolution 1.546875 step 6 got 9 at resolution 1.5234375 step 7 got 9 at resolution 1.53515625 step 8 got 10 at resolution 1.541015625 Scasat
/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. res = PandasDataFrame.from_items(items)
step 0 got 21 at resolution 1.5 step 1 got 14 at resolution 0.75 step 2 got 9 at resolution 0.375 step 3 got 11 at resolution 0.5625 step 4 got 11 at resolution 0.46875 step 5 got 10 at resolution 0.421875 scABC
/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. res = PandasDataFrame.from_items(items)
step 0 got 62 at resolution 1.5 step 1 got 2 at resolution 0.75 step 2 got 11 at resolution 1.125 step 3 got 4 at resolution 0.9375 step 4 got 7 at resolution 1.03125 step 5 got 10 at resolution 1.078125 Cicero
/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. res = PandasDataFrame.from_items(items)
step 0 got 89 at resolution 1.5 step 1 got 1 at resolution 0.75 step 2 got 15 at resolution 1.125 step 3 got 7 at resolution 0.9375 step 4 got 12 at resolution 1.03125 step 5 got 11 at resolution 0.984375 step 6 got 9 at resolution 0.9609375 step 7 got 8 at resolution 0.97265625 step 8 got 10 at resolution 0.978515625 ChromVAR_kmers_pca
/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. res = PandasDataFrame.from_items(items)
step 0 got 12 at resolution 1.5 step 1 got 7 at resolution 0.75 step 2 got 10 at resolution 1.125 ChromVAR_motifs_pca
/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. res = PandasDataFrame.from_items(items)
step 0 got 12 at resolution 1.5 step 1 got 7 at resolution 0.75 step 2 got 8 at resolution 1.125 step 3 got 9 at resolution 1.3125 step 4 got 10 at resolution 1.40625 GeneScoring_pca
/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. res = PandasDataFrame.from_items(items)
step 0 got 14 at resolution 1.5 step 1 got 8 at resolution 0.75 step 2 got 12 at resolution 1.125 step 3 got 9 at resolution 0.9375 step 4 got 10 at resolution 1.03125 Cicero_pca
/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. res = PandasDataFrame.from_items(items)
step 0 got 9 at resolution 1.5 step 1 got 19 at resolution 2.25 step 2 got 11 at resolution 1.875 step 3 got 9 at resolution 1.6875 step 4 got 12 at resolution 1.78125 step 5 got 12 at resolution 1.734375 step 6 got 11 at resolution 1.7109375 step 7 got 10 at resolution 1.69921875
df_metrics.to_csv(path_metrics+'clustering_scores.csv')
df_metrics
ARI_Louvain | ARI_kmeans | ARI_HC | AMI_Louvain | AMI_kmeans | AMI_HC | Homogeneity_Louvain | Homogeneity_kmeans | Homogeneity_HC | |
---|---|---|---|---|---|---|---|---|---|
ChromVAR_kmers | 0.393487 | 0.260785 | 0.225031 | 0.524566 | 0.413008 | 0.356731 | 0.543092 | 0.370503 | 0.301594 |
ChromVAR_motifs | 0.319824 | 0.209636 | 0.323051 | 0.510618 | 0.413654 | 0.464172 | 0.534893 | 0.429699 | 0.437689 |
cisTopic | 0.551506 | 0.351849 | 0.383048 | 0.661205 | 0.555908 | 0.573953 | 0.674538 | 0.585062 | 0.59729 |
Cusanovich2018 | 0.490138 | -0.00194164 | -0.00194164 | 0.636935 | -0.00278841 | -0.00278841 | 0.635598 | 0.00302188 | 0.00302188 |
Control | 0.183302 | 0.0229697 | 0.0397529 | 0.363688 | 0.0314137 | 0.0673721 | 0.377179 | 0.0328729 | 0.0616285 |
GeneScoring | 0.0403609 | 0.0179964 | 0.0255461 | 0.111789 | 0.0318159 | 0.0369079 | 0.11883 | 0.0346644 | 0.0399724 |
Scasat | 0.305007 | 0.161367 | 0.161388 | 0.517868 | 0.302171 | 0.378108 | 0.531279 | 0.320602 | 0.383529 |
scABC | 0.020894 | 0.0109238 | 0.0327437 | 0.0737247 | 0.0190839 | 0.0682762 | 0.0780852 | 0.0196556 | 0.0635191 |
Cicero | 0.033752 | -0.00369183 | -0.00194164 | 0.091265 | 0.0020334 | -0.00278841 | 0.095604 | 0.00611831 | 0.00302188 |
ChromVAR_kmers_pca | 0.431822 | 0.249719 | 0.238284 | 0.554208 | 0.413693 | 0.370762 | 0.57097 | 0.386348 | 0.313476 |
ChromVAR_motifs_pca | 0.278085 | 0.20965 | 0.277897 | 0.496071 | 0.392932 | 0.429734 | 0.516014 | 0.387038 | 0.41759 |
GeneScoring_pca | 0.0231933 | 0.0252487 | 0.0252567 | 0.0785274 | 0.0365736 | 0.0399461 | 0.0913253 | 0.0397867 | 0.0429546 |
Cicero_pca | 0.139162 | -0.00194164 | -0.00194164 | 0.243913 | -0.00278841 | -0.00278841 | 0.255627 | 0.00302188 | 0.00302188 |