def prepare_gct_files(outdir=None):
"""
Prepare the GCT files required to perform classification:
- Our GBM FFPE and cell culture samples
- TCGA RNA-Seq cohort
- Both combined
In all cases, use FPKM units and gene symbols, as these are used by Wang
"""
if outdir is None:
outdir = unique_output_dir("gct_files_for_wang")
infiles = []
# 1) Our data
obj_ffpe = rnaseq_data.load_by_patient('all', type='ffpe')
dat_ffpe = obj_ffpe.get_fpkm()
dat_ffpe.columns = ['%s_FFPE' % t for t in obj_ffpe.meta.reference_id]
obj_cc = rnaseq_data.load_by_patient(patient_ids='all')
dat_cc = obj_cc.get_fpkm()
dat_cc = dat_cc.loc[:, obj_cc.meta.type == 'GBM']
dat_all = pd.concat((dat_cc, dat_ffpe), axis=1)
idx = reference_genomes.ensembl_to_gene_symbol(dat_all.index).dropna()
dat_all = dat_all.loc[idx.index]
dat_all.index = idx
fn = os.path.join(outdir, "gbm_ffpe_cc_fpkm.gct")
gsea.data_to_gct(dat_all, fn)
infiles.append(fn)
# 2) TCGA (IDH1 WT only)
tcga_dat, tcga_meta = rnaseq_data.tcga_primary_gbm(units='fpkm')
tcga_dat = tcga_dat.loc[:, tcga_meta.idh1_status == 'WT']
idx = reference_genomes.ensembl_to_gene_symbol(tcga_dat.index).dropna()
idx = idx.loc[~idx.index.duplicated()]
tcga_dat = tcga_dat.loc[idx.index]
tcga_dat.index = idx
fn = os.path.join(outdir, "tcga_idh1_wt_fpkm.gct")
gsea.data_to_gct(tcga_dat, fn)
infiles.append(fn)
# 3) Combined
dat = gsea.combine_gct_files(*infiles)
fn = os.path.join(outdir, "tcga_idh1_wt_and_gbm_ffpe_cc_fpkm.gct")
gsea.data_to_gct(dat, fn)
de_params = {
'lfc': 1,
'fdr': 0.01,
'method': 'GLM'
}
subgroups = {
'RTK I': ['019', '030', '031'],
'RTK II': ['017', '050', '054'],
}
intersecter = lambda x, y: set(x).intersection(y)
unioner = lambda x, y: set(x).union(y)
# Load RNA-Seq from STAR
rnaseq_obj = rnaseq_data.load_by_patient(pids, annotate_by='Ensembl Gene ID')
# load additional references if required
h9_obj = rnaseq_data.gse61794(annotate_by='Ensembl Gene ID')
h1_obj = rnaseq_data.gse38993(annotate_by='Ensembl Gene ID')
rnaseq_obj = rnaseq_data.MultipleBatchLoader([rnaseq_obj, h1_obj, h9_obj])
# discard unmapped, etc
rnaseq_obj.data = rnaseq_obj.data.loc[rnaseq_obj.data.index.str.contains('ENSG')]
rnaseq_obj.meta = rnaseq_obj.meta.loc[~rnaseq_obj.meta.index.str.contains('PSC')]
rnaseq_obj.meta = rnaseq_obj.meta.loc[~rnaseq_obj.meta.index.str.contains('fibroblast')]
rnaseq_obj.data = rnaseq_obj.data.loc[:, rnaseq_obj.meta.index]
# load RNA-Seq from Salmon (for normalised comparison)
# disabled for now
if False:
unit = 'cpm'
type = 'cell_culture'
tax_id = 9606
if isinstance(cell_types, str):
cell_types = [cell_types]
if unit == 'tpm':
dat = rnaseq_data.load_salmon_by_patient_id(pids,
include_control=False,
type=type)
dat = general.ensembl_transcript_quant_to_gene(dat, tax_id=tax_id)
elif unit == 'cpm':
obj = rnaseq_data.load_by_patient(pids,
type=type,
source='star',
annotate_by='Ensembl Gene ID',
include_control=False)
dat = obj.data
dat = dat.divide(dat.sum(axis=0), axis=1) * 1e6
else:
raise NotImplementedError()
if cell_types is not None:
idx = reduce(
lambda x, y: x | y,
[dat.columns.str.contains(t) for t in cell_types],
)
dat = dat.loc[:, idx]
lookup = reference_genomes.gene_symbol_to_ensembl(gois, tax_id=tax_id)