ind = (ds.counts > args.n_cpm_min_genes[0]).sum(
axis=1) >= args.n_cpm_min_genes[1]
ds.counts = ds.counts.loc[ind]
print('Ignore genes with multiple IDs')
from collections import Counter
genec = Counter(ds.featuresheet['GeneName'].values)
genes_multiple = [k for k, v in genec.items() if v > 1]
ds.featuresheet = ds.featuresheet.loc[~ds.featuresheet['GeneName'].
isin(genes_multiple)]
print('Translate to gene names')
ds.rename(axis='features', column='GeneName', inplace=True)
print('Restrict to virus genes')
dsv = ds.query_features_by_metadata('Organism == "mCMV"')
dsv.query_samples_by_metadata("moi in ('low', 'high')", inplace=True)
print('Log counts')
dsv.counts.log(inplace=True)
print('Plot double hierarchical clustering')
g = dsv.plot.clustermap(
cluster_samples=True,
cluster_features=True,
labels_samples=False,
annotate_samples={
'moi': 'Set1',
},
figsize=(12, 13),
#colorbars=True,
with open('../../data/mouse_mCMV_1/virus_gene_modules_1.json', 'rt') as f:
modules = json.load(f)
ds.featuresheet['module'] = ds.featuresheet['Organism']
ds.featuresheet.loc[ds.featuresheet['Organism'] == 'mCMV',
'module'] = 'other_virus'
ds.featuresheet.loc[modules['1'], 'module'] = 'early'
ds.featuresheet.loc[modules['2'], 'module'] = 'mid'
ds.featuresheet.loc[modules['3'], 'module'] = 'late'
print('Get average expression')
ds.featuresheet.loc[:, 'expression_geometric_mean'] = 10**(
(np.log10(0.1 + ds.counts)).mean(axis=1)) - 0.1
print('Restrict to genes within the modules')
dsg = ds.query_features_by_metadata(
'(module in ("early", "mid", "late")) | (expression_geometric_mean > 100)'
)
dsg.query_samples_by_metadata('moi in ("low", "high")', inplace=True)
dsg.query_samples_by_metadata('virus_reads_per_million >= 100',
inplace=True)
print('Make metadata for module expression')
dsg.samplesheet['exp_module_early'] = dsg.counts.loc[
ds.featuresheet['module'] == 'early'].sum(axis=0)
dsg.samplesheet['exp_module_mid'] = dsg.counts.loc[
ds.featuresheet['module'] == 'mid'].sum(axis=0)
dsg.samplesheet['exp_module_late'] = dsg.counts.loc[
ds.featuresheet['module'] == 'late'].sum(axis=0)
corrs = dsg.correlation.correlate_features_phenotypes(phenotypes=[
'exp_module_early', 'exp_module_mid', 'exp_module_late',
local_dict=locals(),
inplace=True)
if not args.keep2:
print('Filter out sample 2-uninfected (low quality)')
ds.query_samples_by_metadata('biosample != "2-uninfected"',
inplace=True)
print('Add normalized virus counts')
ds.samplesheet['virus_reads_per_million'] = 1e6 * ds.samplesheet[
'n_reads_virus'] / ds.samplesheet['n_reads']
ds.samplesheet['log_virus_reads_per_million'] = np.log10(
0.1 + ds.samplesheet['virus_reads_per_million'])
print('Limit to decently expressed genes')
ind = (ds.counts >= 10).sum(axis=1) >= 10
ds.featuresheet['detected_1010'] = ind.values
print('Ignore genes with multiple IDs')
from collections import Counter
genec = Counter(ds.featuresheet['GeneName'].values)
ind = [genec[gn] for gn in ds.featuresheet['GeneName'].values]
ds.featuresheet['nGenes'] = ind
ds.query_features_by_metadata(
'((Organism == "mCMV") | detected_1010) & (nGenes == 1)', inplace=True)
print('Translate to gene names')
ds.featuresheet['EnsemblID'] = ds.featuresheet.index
ds.rename(axis='features', column='GeneName', inplace=True)
with open('../../data/mouse_mCMV_1/virus_gene_modules_1.json', 'rt') as f:
modules = json.load(f)
ds.featuresheet['module'] = ds.featuresheet['Organism']
ds.featuresheet.loc[ds.featuresheet['Organism'] == 'mCMV',
'module'] = 'other_virus'
ds.featuresheet.loc[modules['1'], 'module'] = 'early'
ds.featuresheet.loc[modules['2'], 'module'] = 'mid'
ds.featuresheet.loc[modules['3'], 'module'] = 'late'
print('Get average expression')
ds.featuresheet.loc[:, 'expression_geometric_mean'] = 10**(
(np.log10(0.1 + ds.counts)).mean(axis=1)) - 0.1
print('Restrict to genes within the modules')
dsg = ds.query_features_by_metadata(
'(module in ("early", "mid", "late")) | ((Organism == "mCMV") & (expression_geometric_mean > 0.05)) | (expression_geometric_mean > 100)'
)
print('Export to TSV')
fdn = '../../data/mouse_mCMV_1/to_Paolo/'
co = (1e-6 * dsg.counts * samplesheet['n_reads']).fillna(0).astype(int)
co.to_csv(
fdn + 'counts_not_normalized_filtered.tsv',
sep='\t',
index=True,
)
dsg.samplesheet.to_csv(
fdn + 'samplesheet_filtered.tsv',
sep='\t',
index=True,
)
