dmr_hash_dict)
filename = 'dmr_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DMR_LOAD_DIR, filename)
if os.path.isfile(fn):
logger.info("Loading pre-computed DMR results from %s", fn)
dmr_res_s1 = dmr.DmrResultCollection.from_pickle(fn, anno=anno)
else:
raise Exception("Unable to locate pre-existing results.")
# load DE results
rnaseq_obj = rnaseq_loader.load_by_patient(consts.PIDS,
include_control=False)
rnaseq_obj.filter_by_sample_name(consts.S1_RNASEQ_SAMPLES)
the_hash = tsgd.de_results_hash(rnaseq_obj.meta.index.tolist(), de_params)
filename = 'de_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DE_LOAD_DIR, filename)
if os.path.isfile(fn):
logger.info("Reading S1 DE results from %s", fn)
with open(fn, 'rb') as f:
de_res_s1 = pickle.load(f)
else:
raise Exception("Unable to locate pre-existing DE results.")
the_hash = tsgd.dmr_results_hash(meth_obj.meta.index.tolist(),
dmr_hash_dict)
filename = 'dmr_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DMR_LOAD_DIR, filename)
rna_cc_obj.meta.index.isin(consts.S1_RNASEQ_SAMPLES_INSC))
# FIXME: this is a bug in the loader?
rna_ff_obj.batch_id = rna_ff_obj.meta.batch
rna_cc_obj.batch_id = rna_cc_obj.meta.batch
# store the sample list now for hash dict
rna_sample_names = rna_ff_obj.meta.index.tolist(
) + rna_cc_obj.meta.index.tolist()
# combine
rna_obj = rnaseq_loader.loader.MultipleBatchLoader([rna_cc_obj, rna_ff_obj])
# a few of the type entries in meta are missing
rna_obj.meta['type'] = rna_obj.meta['type'].fillna('GBM')
# load or run DE
the_hash = tsgd.de_results_hash(rna_sample_names, de_params)
filename = 'de_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DE_LOAD_DIR, filename)
if os.path.isfile(fn):
logger.info("Reading S1 DE results from %s", fn)
with open(fn, 'rb') as f:
de_res_full_s1 = pickle.load(f)
else:
groups_s1 = pd.Series(index=rna_obj.meta.index)
comparisons_s1 = {}
for pid in pids:
groups_s1[(rna_obj.meta.patient_id.fillna('') == pid)
& (rna_obj.meta['type'] == 'GBM')] = "GBM%s" % pid
groups_s1[groups_s1.index.str.contains('NSC')
& groups_s1.index.str.contains(pid)] = "iNSC%s" % pid
import statsmodels.formula.api as sm
logger = log.get_console_logger()
if __name__ == '__main__':
outdir = output.unique_output_dir()
DMR_LOAD_DIR = os.path.join(INTERMEDIATE_DIR, 'dmr')
DE_LOAD_DIR = os.path.join(INTERMEDIATE_DIR, 'de')
rnaseq_obj = loader.load_by_patient(consts.PIDS)
rnaseq_obj.filter_by_sample_name(consts.S1_RNASEQ_SAMPLES)
dat_s1 = rnaseq_obj.data
meta_s1 = rnaseq_obj.meta.loc[dat_s1.columns]
the_hash = tsgd.de_results_hash(meta_s1.index.tolist(), consts.DE_PARAMS)
filename = 'de_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DE_LOAD_DIR, filename)
if os.path.isfile(fn):
logger.info("Reading S1 DE results from %s", fn)
with open(fn, 'rb') as f:
de_res_full_s1 = pickle.load(f)
else:
raise NotImplementedError(
"We require a precomputed DE results file (expected this at %s)" %
fn)
basedir = os.path.join(INTERMEDIATE_DIR, "assess_reprog_alt1")
indir = os.path.join(basedir, "results")
names = [t.replace('.csv', '') for t in os.listdir(indir) if '.csv' in t]
#######################################################
# DE
#######################################################
# data
rnaseq_obj = rnaseq_loader.load_by_patient(pids,
include_control=False,
source='star')
rnaseq_obj.filter_by_sample_name(consts.S1_RNASEQ_SAMPLES)
dat_s1 = rnaseq_obj.data
meta_s1 = rnaseq_obj.meta
cpm = dat_s1.divide(dat_s1.sum(axis=0), axis=1) * 1e6
# DE results
the_hash = tsgd.de_results_hash(meta_s1.index.tolist(), de_params)
filename = 'de_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DE_LOAD_DIR, filename)
if os.path.isfile(fn):
logger.info("Reading S1 DE results from %s", fn)
with open(fn, 'rb') as f:
de_res_full_s1 = pickle.load(f)
else:
raise AttributeError(
"Unable to find pre-computed S1 comparison results.")
de_res_s1 = dict([(k, v.loc[v.FDR < de_params['fdr']])
for k, v in de_res_full_s1.items()])
vs, vc = setops.venn_from_arrays(*[de_res_s1[pid].index for pid in pids])
de_res_wide = setops.venn_set_to_wide_dataframe(
obj_ff = loader.load_by_patient(pids, source='salmon', type='ffpe')
obj_ff.filter_by_sample_name(consts.FFPE_RNASEQ_SAMPLES)
# add PID to FFPE metadata
nh_id = obj_ff.meta.index.str.replace(r'(_?)(DEF|SP).*', '')
p_id = [NH_ID_TO_PATIENT_ID_MAP[t.replace('_', '-')] for t in nh_id]
obj_ff.meta.insert(0, 'nh_id', nh_id)
obj_ff.meta.insert(0, 'patient_id', p_id)
# pull out logged TPM
log2_tpm_cc = np.log2(obj_cc.data + eps)
log2_tpm_ff = np.log2(obj_ff.data + eps)
# load DE results
the_hash = tsgd.de_results_hash(obj_cc.meta.index.tolist(),
consts.DE_PARAMS)
filename = 'de_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DE_LOAD_DIR, filename)
if os.path.isfile(fn):
with open(fn, 'rb') as f:
de_res_full_s1 = pickle.load(f)
else:
raise IOError("No pre-computed results file found: %s" % fn)
# load genes in GAG-related IPA pathways
pathways = [
'Chondroitin Sulfate Biosynthesis',
'Dermatan Sulfate Biosynthesis',
'Dermatan Sulfate Biosynthesis (Late Stages)',
'Chondroitin Sulfate Biosynthesis (Late Stages)',
# load RNA-Seq data
rna_obj = rnaseq_loader.load_by_patient(pids,
type='cell_culture',
source='star',
include_control=False)
# filter CC to include only HIC and iAPC
rna_obj.filter_samples(
rna_obj.meta.index.isin(consts.S1_RNASEQ_SAMPLES_IAPC +
consts.S1_RNASEQ_SAMPLES_GIC))
# FIXME: this is a bug in the loader?
rna_obj.batch_id = rna_obj.meta.batch
# load or run DE
the_hash = tsgd.de_results_hash(rna_obj.meta.index, de_params)
filename = 'de_results_paired_comparison.%d.pkl' % the_hash
fn = os.path.join(DE_LOAD_DIR, filename)
if os.path.isfile(fn):
logger.info("Reading S1 DE results from %s", fn)
with open(fn, 'rb') as f:
de_res_full_s1 = pickle.load(f)
else:
groups_s1 = pd.Series(index=rna_obj.meta.index)
comparisons_s1 = {}
for pid in pids:
groups_s1[rna_obj.meta.index.str.contains(pid)
& (rna_obj.meta['type'] == 'GBM')] = "GBM%s" % pid
groups_s1[groups_s1.index.str.contains(pid)
& (rna_obj.meta['type'] == 'iAPC')] = "iAPC%s" % pid