Load data (TCR + counts)

Load the cellranger outputs and store them as h5ad.

import scanpy as sc
import scirpy as ir
import anndata
import pandas as pd
import os
import sys
from multiprocessing import Pool
import itertools

sample_sheet = "../tables/vanderburg_01_samples.csv"
output_file = "../results/01_process_data/adata.h5ad"
data_dir = "../data"
n_cpus = 16

# Parameters
sample_sheet = "sample_sheet.csv"
output_file = "adata.h5ad"
data_dir = "data"
n_cpus = "16"

obs = pd.read_csv(sample_sheet)

obs.set_index("samples")

	patient	origin	replicate	dataset	tumor_type	platform	age	sex	hpv_status	ir_status	facs_purity_cd3	facs_purity_cd56
samples
H143	H143	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.653	0.008
H149	H149	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.644	0.033
H160	H160	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.342	0.067
H176	H176	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.558	0.108
H182	H182	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.303	0.109
H185	H185	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.493	0.163
H188	H188	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.657	0.087
H205	H205	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.485	0.028
H211	H211	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.382	0.029
H197	H197	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.271	0.171
H208	H208	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.336	0.323
H68	H68	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.797	0.138
H141	H141	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.288	0.025

dataset_samples = obs["samples"].to_numpy(copy=True)

dataset_samples.sort()
dataset_samples

array(['H141', 'H143', 'H149', 'H160', 'H176', 'H182', 'H185', 'H188',
       'H197', 'H205', 'H208', 'H211', 'H68'], dtype=object)

def load_sample(sample_id, data_dir):
    filename_gex = os.path.join(
        data_dir, f"cellranger/{sample_id[1:]}_GEX/outs/raw_feature_bc_matrix.h5"
    )
    filename_tcr = os.path.join(
        data_dir, f"cellranger/{sample_id[1:]}_TCR/outs/filtered_contig_annotations.csv"
    )
    adata = sc.read_10x_h5(filename_gex, genome="GRCh38")
    adata_tcr = ir.io.read_10x_vdj(filename_tcr)
    adata.obs_names = [
        "{}_{}".format(sample_id, barcode) for barcode in adata.obs_names
    ]

    adata_tcr.obs_names = [
        "{}_{}".format(sample_id, barcode) for barcode in adata_tcr.obs_names
    ]
    duplicated = adata.var_names.duplicated()
    print(
        "Removing {} gene symbols because they are duplicated".format(sum(duplicated))
    )
    adata = adata[:, ~duplicated].copy()
    ir.pp.merge_with_ir(adata, adata_tcr)
    adata.obs["samples"] = sample_id
    return adata

with Pool(int(n_cpus)) as p:
    adatas = p.starmap(load_sample, zip(dataset_samples, itertools.repeat(data_dir)))

Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):
Variable names are not unique. To make them unique, call `.var_names_make_unique`.
/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical
/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated
Removing 24 gene symbols because they are duplicated
Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical
/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical

Removing 24 gene symbols because they are duplicated

... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical
/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical
/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical

Removing 24 gene symbols because they are duplicated

... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated
Removing 24 gene symbols because they are duplicated

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_junction_ins' as categorical
... storing 'IR_VJ_2_junction_ins' as categorical
... storing 'IR_VDJ_1_junction_ins' as categorical
... storing 'IR_VDJ_2_junction_ins' as categorical

Removing 24 gene symbols because they are duplicated

... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'multi_chain' as categorical
... storing 'genome' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical
... storing 'genome' as categorical
... storing 'multi_chain' as categorical
... storing 'feature_types' as categorical
... storing 'multi_chain' as categorical
... storing 'genome' as categorical
... storing 'feature_types' as categorical
... storing 'genome' as categorical

adata = anndata.concat(adatas)

# coarse filtering, proper QC is done later
sc.pp.filter_cells(adata, min_genes=100)

/opt/conda/lib/python3.8/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
  if not is_categorical(df_full[k]):

adata.obs["samples"]

H141_AAACCTGAGATAGCAT-1    H141
H141_AAACCTGAGATCCCAT-1    H141
H141_AAACCTGAGCGGCTTC-1    H141
H141_AAACCTGAGCTGTCTA-1    H141
H141_AAACCTGAGGCATTGG-1    H141
                           ... 
H68_TTTGTCAGTTGTTTGG-1      H68
H68_TTTGTCATCAGAGACG-1      H68
H68_TTTGTCATCAGGTAAA-1      H68
H68_TTTGTCATCGTCTGAA-1      H68
H68_TTTGTCATCTCCGGTT-1      H68
Name: samples, Length: 71401, dtype: object

obs

	samples	patient	origin	replicate	dataset	tumor_type	platform	age	sex	hpv_status	ir_status	facs_purity_cd3	facs_purity_cd56
0	H143	H143	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.653	0.008
1	H149	H149	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.644	0.033
2	H160	H160	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.342	0.067
3	H176	H176	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.558	0.108
4	H182	H182	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.303	0.109
5	H185	H185	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.493	0.163
6	H188	H188	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.657	0.087
7	H205	H205	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.485	0.028
8	H211	H211	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.382	0.029
9	H197	H197	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.271	0.171
10	H208	H208	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.336	0.323
11	H68	H68	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.797	0.138
12	H141	H141	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.288	0.025

obs.set_index("samples")

	patient	origin	replicate	dataset	tumor_type	platform	age	sex	hpv_status	ir_status	facs_purity_cd3	facs_purity_cd56
samples
H143	H143	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.653	0.008
H149	H149	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.644	0.033
H160	H160	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.342	0.067
H176	H176	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.558	0.108
H182	H182	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.303	0.109
H185	H185	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.493	0.163
H188	H188	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.657	0.087
H205	H205	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.485	0.028
H211	H211	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.382	0.029
H197	H197	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV-	NaN	0.271	0.171
H208	H208	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR-	0.336	0.323
H68	H68	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.797	0.138
H141	H141	tumor_primary	1	vanderburg_01	HNSC	10x_5p	NaN	NaN	HPV16+	IR+	0.288	0.025

tmp_obs = adata.obs.join(obs.set_index("samples"), on="samples", how="left", sort=True)

adata.obs = tmp_obs

adata.obs.loc[:, ["samples", "patient", "facs_purity_cd56"]].drop_duplicates()

	samples	patient	facs_purity_cd56
H141_AAACCTGAGATAGCAT-1	H141	H141	0.025
H143_AAACCTGAGCCGATTT-1	H143	H143	0.008
H149_AAACCTGAGACTGTAA-1	H149	H149	0.033
H160_AAACCTGAGAAACCAT-1	H160	H160	0.067
H176_AAACCTGAGAAGGTTT-1	H176	H176	0.108
H182_AAACCTGAGCCCAACC-1	H182	H182	0.109
H185_AAACCTGAGACGCACA-1	H185	H185	0.163
H188_AAACCTGAGAGACTAT-1	H188	H188	0.087
H197_AAACCTGAGGCTCTTA-1	H197	H197	0.171
H205_AAACCTGAGTTTAGGA-1	H205	H205	0.028
H208_AAACCTGAGAACTGTA-1	H208	H208	0.323
H211_AAACCTGAGGATATAC-1	H211	H211	0.029
H68_AAACCTGCACATTCGA-1	H68	H68	0.138

adata.shape

(71401, 33514)

Write output file

adata.write(output_file, compression="lzf")

/opt/conda/lib/python3.8/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
  if is_string_dtype(df[key]) and not is_categorical(df[key])
... storing 'IR_VJ_1_cdr3' as categorical
... storing 'IR_VJ_2_cdr3' as categorical
... storing 'IR_VDJ_1_cdr3' as categorical
... storing 'IR_VDJ_2_cdr3' as categorical
... storing 'IR_VJ_1_cdr3_nt' as categorical
... storing 'IR_VJ_2_cdr3_nt' as categorical
... storing 'IR_VDJ_1_cdr3_nt' as categorical
... storing 'IR_VDJ_2_cdr3_nt' as categorical
... storing 'IR_VJ_1_v_gene' as categorical
... storing 'IR_VJ_2_v_gene' as categorical
... storing 'IR_VDJ_1_v_gene' as categorical
... storing 'IR_VDJ_2_v_gene' as categorical
... storing 'IR_VJ_1_j_gene' as categorical
... storing 'IR_VJ_2_j_gene' as categorical
... storing 'IR_VJ_1_c_gene' as categorical
... storing 'IR_VJ_2_c_gene' as categorical
... storing 'IR_VDJ_1_c_gene' as categorical
... storing 'IR_VDJ_2_c_gene' as categorical
... storing 'samples' as categorical
... storing 'patient' as categorical
... storing 'origin' as categorical
... storing 'dataset' as categorical
... storing 'tumor_type' as categorical
... storing 'platform' as categorical
... storing 'hpv_status' as categorical
... storing 'ir_status' as categorical