# GSE61794 (H9-derived NSC x 2)
obj61794 = rnaseq_data.gse61794(source='star',
annotate_by='Ensembl Gene ID')
# combining replicates
rc = obj61794.meta.read_count.sum()
obj61794.meta = pd.DataFrame(data={
'cell_type': 'NSC',
'srr': 'SRR1586371-2',
'read_count': rc,
'sample': 'H9 NSC',
},
index=['SRR1586371-2'])
obj61794.data = pd.DataFrame(obj61794.data.sum(axis=1), columns=['H9 NSC'])
# WTCHG ALL samples
objwtchg_all = rnaseq_data.all_hgic_loader(annotate_by='Ensembl Gene ID',
include_derived=True)
to_keep_wtchg = (
'GIBCO_NSC_P4',
# 'DURA018_NSC_N2_P6',
# 'DURA018_NSC_N4_P4',
'DURA019_NSC_N8C_P2',
'DURA030_NSC_N16B6_P1',
'DURA031_NSC_N44B_P2')
# rRNA gene IDs
rrna_ensg = set(gtf_reader.get_rrna())
# MT gene_ids
mt_ensg = set(gtf_reader.get_mitochondrial())
# combine the data
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from scipy.stats import rankdata
from load_data import rnaseq_data
from stats import transformations
from utils.output import unique_output_dir
from utils.reference_genomes import ensembl_to_gene_symbol, gene_symbol_to_ensembl
if __name__ == "__main__":
outdir = unique_output_dir("tom_qpcr", reuse_empty=True)
ref = 'GIBCO_NSC_P4'
obj = rnaseq_data.all_hgic_loader(annotate_by="Ensembl Gene ID")
dat = obj.data.loc[obj.data.index.str.contains('ENSG')]
dat = dat.loc[:, ~obj.meta.index.str.contains('DURA')]
# normalised version (by number of aligned reads)
dat_n = dat.divide(dat.sum(axis=0), axis=1) * 1e6
# remove any absent / mostly absent genes
median_count = dat_n.median(axis=1).sort_values()
keep_idx = median_count.loc[median_count != 0].index
dat = dat.loc[keep_idx]
dat_n = dat_n.loc[keep_idx]
median_count = median_count.loc[keep_idx]
# remove any genes that are (mostly) absent in NSC
nsc_missing = dat.loc[:, ref] < 10.
import os
from load_data import rnaseq_data
import pandas as pd
from rnaseq import filter
from matplotlib import pyplot as plt
from plotting import clustering
from stats.transformations import median_absolute_deviation, variance_stabilizing_transform
import numpy as np
from utils.output import unique_output_dir
if __name__ == "__main__":
outdir = unique_output_dir("compare_gibco_h9")
loader_hgic = rnaseq_data.all_hgic_loader(annotate_by='Ensembl Gene ID')
loader_h9 = rnaseq_data.gse61794(annotate_by='Ensembl Gene ID')
genes = loader_hgic.data.index.intersection(loader_h9.data.index)
genes = genes[genes.str.contains('ENSG')]
# collapse H9 replicates
h9_data = loader_h9.data.sum(axis=1).loc[genes]
h9_data.name = 'H9_NSC'
h9_meta = pd.Series(
{
'type': 'NSC',
'read_count': sum(loader_h9.meta.read_count),
'sample': 'H9_NSC',
'disease_subgroup': 'control',
},
name='H9_NSC')
data = pd.concat((loader_hgic.data.loc[genes], h9_data), axis=1)