}
#Create the X reference (in the correct order)
x_reference = {
'X1': np.array([eval(x_ref[x]['X1']) for x in meta[:, 0]]),
'X2': np.array([eval(x_ref[x]['X2']) for x in meta[:, 0]])
}
#Run all samples against the control
print('Running JACKS inference')
ctrldata = data[:, sample_ids.index(ctrl_sample), :]
testdata = data[:, [
i for i, x in enumerate(sample_ids) if ctrl_sample not in x
], :]
jacks_results = infer_JACKS(gene_index,
testdata,
ctrldata,
fixed_x=x_reference)
#Write out the results
print('Writing JACKS results')
sample_ids_without_ctrl = [x for x in sample_ids if x != ctrl_sample]
writeJacksWResults(outfile_w, jacks_results, sample_ids_without_ctrl)
writeJacksWResults(outfile_w2,
jacks_results,
sample_ids_without_ctrl,
write_w2=True)
writeJacksXResults(outfile_x, jacks_results, gene_grnas)
pickleJacksFullResults(outfile_pickle, jacks_results,
sample_ids_without_ctrl, gene_grnas)
print 'Loading sample specification'
sample_spec = createSampleSpec(countfile, replicatefile, rep_hdr, sample_hdr)
#Load the mappings from guides to genes
print 'Loading gene mappings'
gene_spec = createGeneSpec(guidemappingfile, sgrna_hdr, gene_hdr)
#Load the data and preprocess (or just load from pickle if we did this already)
print 'Loading data and pre-processing'
data, meta, sample_ids, genes, gene_index = load_data_and_preprocess(sample_spec, gene_spec)
gene_grnas = {gene: [x for x in meta[gene_index[gene],0]] for gene in gene_index}
#Run each sample against the control
ctrldata = data[:,sample_ids.index(ctrl_sample),:]
for sample_id in sample_ids:
if sample_id == ctrl_sample: continue
outfile_w = outprefix + '_' + sample_id + '_gene_JACKS_results.txt'
outfile_x = outprefix + '_' + sample_id + '_grna_JACKS_results.txt'
outfile_pickle = outprefix + '_' + sample_id +'_JACKS_results_full.pickle'
print 'Running JACKS inference for', sample_id
testdata = data[:,[sample_ids.index(sample_id)],:]
jacks_results = infer_JACKS(gene_index, testdata, ctrldata)
#Write out the results
print 'Writing JACKS results for', sample_id
writeJacksWResults( outfile_w, jacks_results, [sample_id])
writeJacksXResults( outfile_x, jacks_results, gene_grnas )
pickleJacksFullResults( outfile_pickle, jacks_results, [sample_id], gene_grnas )
def run(countfile,
replicatefile,
guidemappingfile,
rep_hdr,
sample_hdr,
ctrl_sample_or_hdr,
sgrna_hdr,
gene_hdr,
outprefix,
sgrna_reference_file=None,
apply_w_hp=False,
boot_strap=False):
LOG.setLevel(logging.WARNING)
print('Loading sample specification')
sample_spec, ctrl_per_sample, ctrl_spec = createSampleSpec(
countfile, replicatefile, rep_hdr, sample_hdr, ctrl_sample_or_hdr)
outfile_w = outprefix + '_gene_JACKS_results.txt'
outfile_w2 = outprefix + '_genestd_JACKS_results.txt'
outfile_x = outprefix + '_grna_JACKS_results.txt'
outfile_lfc = outprefix + '_logfoldchange_means.txt'
outfile_lfc_std = outprefix + '_logfoldchange_std.txt'
outfile_pickle = outprefix + '_JACKS_results_full.pickle'
# Load the mappings from guides to genes
print('Loading gene mappings')
gene_spec = createGeneSpec(guidemappingfile, sgrna_hdr, gene_hdr)
# Load the data and preprocess
print('Loading data and pre-processing')
data, meta, sample_ids, genes, gene_index = load_data_and_preprocess(
sample_spec, gene_spec)
gene_grnas = {
gene: [x for x in meta[gene_index[gene], 0]]
for gene in gene_index
}
writeFoldChanges(outfile_lfc, data, meta, sample_ids)
writeFoldChanges(outfile_lfc_std, data, meta, sample_ids, write_std=True)
if sgrna_reference_file:
print('Loading sgrna reference values')
x_ref = loadSgrnaReference(sgrna_reference_file)
print('Checking sgrna reference identifiers against gene mappings')
for guide in gene_spec:
if guide not in x_ref:
raise Exception('%s has no sgrna reference in %s' %
(guide, sgrna_reference_file))
x_reference = {
'X1': np.array([eval(x_ref[x]['X1']) for x in meta[:, 0]]),
'X2': np.array([eval(x_ref[x]['X2']) for x in meta[:, 0]])
}
else:
x_reference = None
# Run all samples against their controls
print('Running JACKS_ inference')
if ctrl_per_sample: # Different control samples specified per test sample
test_sample_idxs = [
i for i, x in enumerate(sample_ids) if ctrl_spec[x] != x
]
testdata = data[:, test_sample_idxs, :]
ctrldata = data[:, [
sample_ids.index(ctrl_spec[sample_ids[idx]])
for idx in test_sample_idxs
], :]
else: # Same control sample for all tests
ctrldata = data[:, sample_ids.index(ctrl_sample_or_hdr), :]
test_sample_idxs = [
i for i, x in enumerate(sample_ids) if x != ctrl_sample_or_hdr
]
testdata = data[:, test_sample_idxs, :]
if not boot_strap:
jacks_results = infer_JACKS(gene_index,
testdata,
ctrldata,
fixed_x=x_reference,
apply_w_hp=apply_w_hp)
# Write out the results
print('Writing JACKS_ results')
sample_ids_without_ctrl = [sample_ids[idx] for idx in test_sample_idxs]
writeJacksWResults(outfile_w, jacks_results, sample_ids_without_ctrl)
writeJacksWResults(outfile_w2,
jacks_results,
sample_ids_without_ctrl,
write_w2=True)
writeJacksXResults(outfile_x, jacks_results, gene_grnas)
pickleJacksFullResults(outfile_pickle, jacks_results,
sample_ids_without_ctrl, gene_grnas)
else:
[sample_ids[idx] for idx in test_sample_idxs]
boots_x_w = bootstrap(
gene_index,
testdata,
ctrldata,
gene_grnas,
fixed_x=x_reference,
apply_w_hp=apply_w_hp,
)
if outprefix:
import pickle
with open(outprefix + '.boostrap.pickle', 'wb') as f:
pickle.dump(boots_x_w, f)
return boots_x_w