def _calc_eta_stats(truth_fn):
truth = resultserializer.Results(truth_fn)
eta = truth.get('eta')
K, S = eta[1:].shape
biggest_eta = np.max(eta, axis=1)[1:]
return (K, S, biggest_eta)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--tree-index', type=int, default=0)
parser.add_argument('results_fn')
parser.add_argument('html_out_fn')
args = parser.parse_args()
results = resultserializer.Results(args.results_fn)
sampnames = results.get('sampnames')
clusters = results.get('clusters')
phi = results.get('phi')[args.tree_index]
struct = results.get('struct')[args.tree_index]
K, S = phi.shape
assert len(sampnames) == S
eta = util.calc_eta(struct, phi)
pairs = {
'CNS': stephutil.find_samp_pairs(sampnames, ' BM', ' CNS'),
'Spleen': stephutil.find_samp_pairs(sampnames, ' BM', ' Spleen'),
}
html = '<script src="https://cdn.plot.ly/plotly-latest.min.js"></script>'
html += '<link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.4.1/css/bootstrap.min.css">'
for name, P in pairs.items():
di_results = _calc_di(eta, clusters, struct, sampnames, P)
html += f'<h1>{name}</h1>'
html += _process_di(di_results)
with open(args.html_out_fn, 'w') as outf:
print(html, file=outf)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--only-best', action='store_true')
parser.add_argument('pairtree_ssm_fn')
parser.add_argument('results_fn')
args = parser.parse_args()
results = resultserializer.Results(args.results_fn)
phi = results.get('phi')
clusters = [[]] + results.get('clusters')
llh = results.get('llh')
counts = results.get('count')
clusterings = [clusters for _ in range(len(llh))]
if args.only_best:
phi = [phi[0]]
clusterings = [clusterings[0]]
llh = [llh[0]]
counts = [1]
mphi = mutphi.calc_mutphi(phi, llh, clusterings, args.pairtree_ssm_fn,
counts)
print(score(mphi.stats))
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument('pairtree_results_fn')
parser.add_argument('params_fn')
parser.add_argument('neutree_fn')
args = parser.parse_args()
results = resultserializer.Results(args.pairtree_results_fn)
params = inputparser.load_params(args.params_fn)
ntree = convert(results, params['garbage'])
neutree.save(ntree, args.neutree_fn)
def write_truth(structs, phi, clusters, garbage, results_fn):
N = len(structs)
llhs = np.zeros(N)
probs = np.ones(N) / N
phis = np.array([phi for _ in range(N)])
counts = np.ones(N)
results = resultserializer.Results(results_fn)
results.add('struct', structs)
results.add('count', counts)
results.add('phi', phis)
results.add('llh', llhs)
results.add('prob', probs)
results.add('clusters', clusters)
results.add('garbage', garbage)
results.save()
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('pairtree_results_fn')
parser.add_argument('clustrel_mutrel_fn')
args = parser.parse_args()
results = resultserializer.Results(args.pairtree_results_fn)
clusters = [[]] + list(results.get('clusters'))
garbage = list(results.get('garbage'))
all_vids = set([V for C in results.get('clusters') for V in C] + garbage)
clustrel = perturb_clustrel(results.get_mutrel('clustrel_posterior'))
clustrel_mutrel = evalutil.make_mutrel_from_clustrel(clustrel, clusters)
clustrel_mutrel = evalutil.add_garbage(clustrel_mutrel, garbage)
assert set(clustrel_mutrel.vids) == all_vids
evalutil.save_sorted_mutrel(clustrel_mutrel, args.clustrel_mutrel_fn)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument('--tree-index', type=int, default=0)
parser.add_argument('results_fn')
parser.add_argument('baseline_mutdist_fn')
args = parser.parse_args()
results = resultserializer.Results(args.results_fn)
clusters = [[]] + results.get('clusters')
vids, membership = util.make_membership_mat(clusters)
mphi = np.dot(membership, results.get('phi')[args.tree_index])
baseline = mutstat.Mutstat(stats=mphi, vids=vids, assays=results.get('sampnames'))
mutstat.write(baseline, args.baseline_mutdist_fn)
def _calc_tree_stats(truth_fn):
truth = resultserializer.Results(truth_fn)
eta = truth.get('eta')
phi = truth.get('phi')
struct = truth.get('structure')
phi_std = np.std(phi, axis=1)
phi_mean = np.mean(phi, axis=1)
depth = _calc_depth(struct)
num_pops = _calc_num_pops(struct)
df = pd.DataFrame({
'phi_std': phi_std[1:],
'phi_mean': phi_mean[1:],
'largest_eta': np.max(eta, axis=1)[1:],
'depth': depth,
'num_pops': num_pops,
})
polyprimary = np.sum(struct == 0) > 1
return (df, polyprimary)
def main():
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--tree-index', type=int, default=0)
parser.add_argument('--truth', dest='truth_fn')
parser.add_argument('ssm_fn')
parser.add_argument('results_fn')
args = parser.parse_args()
variants = inputparser.load_ssms(args.ssm_fn)
if args.truth_fn:
truth = _parse_truth(args.truth_fn)
else:
truth = {}
results = resultserializer.Results(args.results_fn)
sampnames = results.get('sampnames')
clusters = results.get('clusters')
garbage = results.get('garbage')
variants = inputparser.remove_garbage(variants, garbage)
phi = results.get('phi')[args.tree_index]
struct = results.get('struct')[args.tree_index]
K, S = phi.shape
assert len(sampnames) == S
eta = util.calc_eta(struct, phi)
cns_pairs = stephutil.find_samp_pairs(sampnames, ' BM', ' CNS')
spleen_pairs = stephutil.find_samp_pairs(sampnames, ' BM', ' Spleen')
all_pairs = cns_pairs + spleen_pairs
concord = _calc_concord(variants, clusters, eta, sampnames, all_pairs,
truth)
results = {
'concord': concord,
}
print(json.dumps(results))
def main():
all_plot_choices = set((
'tree',
'pairwise_separate',
'pairwise_mle',
'vaf_matrix',
'phi',
'phi_hat',
'phi_interleaved',
'cluster_stats',
'eta',
'diversity_indices',
))
parser = argparse.ArgumentParser(
description='LOL HI THERE',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--seed', type=int)
parser.add_argument('--tree-index', type=int, default=0)
parser.add_argument('--plot',
dest='plot_choices',
type=lambda s: set(s.split(',')),
help='Things to plot; by default, plot everything')
parser.add_argument('--omit-plots',
dest='omit_plots',
type=lambda s: set(s.split(',')),
help='Things to omit from plotting; overrides --plot')
parser.add_argument('--runid')
parser.add_argument(
'--reorder-subclones',
action='store_true',
help=
'Reorder subclones according to depth-first search through tree structure'
)
parser.add_argument(
'--tree-json',
dest='tree_json_fn',
help=
'Additional external file in which to store JSON, which is already stored statically in the HTML file'
)
parser.add_argument('--phi-orientation',
choices=('samples_as_rows', 'populations_as_rows'),
default='populations_as_rows')
parser.add_argument(
'--remove-normal',
action='store_true',
help=
'Remove normal (non-cancerous) population 0 from tree, phi, and eta plots.'
)
parser.add_argument('ssm_fn')
parser.add_argument('params_fn')
parser.add_argument('results_fn')
parser.add_argument('discord_fn')
parser.add_argument('html_out_fn')
args = parser.parse_args()
np.seterr(divide='raise', invalid='raise', over='raise')
if args.seed is not None:
random.seed(args.seed)
np.random.seed(args.seed)
plot_choices = _choose_plots(args.plot_choices, args.omit_plots,
all_plot_choices)
results = resultserializer.Results(args.results_fn)
variants = inputparser.load_ssms(args.ssm_fn)
params = inputparser.load_params(args.params_fn)
discord = _parse_discord(args.discord_fn)
data = {
K: results.get(K)[args.tree_index]
for K in (
'struct',
'count',
'llh',
'prob',
'phi',
)
}
data['garbage'] = results.get('garbage')
data['clusters'] = results.get('clusters')
data['samples'] = params['samples']
data['clustrel_posterior'] = results.get_mutrel('clustrel_posterior')
if args.reorder_subclones:
data, params = _reorder_subclones(data, params)
if 'hidden_samples' in params:
hidden = set(params['hidden_samples'])
assert hidden.issubset(set(
data['samples'])) and len(hidden) < len(data['samples'])
visible_sampidxs = [
idx for idx, samp in enumerate(data['samples'])
if samp not in hidden
]
else:
visible_sampidxs = None
samp_colours = params.get('samp_colours', None)
pop_colours = params.get('pop_colours', None)
if samp_colours is not None:
assert set([S[0] for S in samp_colours]).issubset(data['samples'])
if pop_colours is not None:
assert len(pop_colours) == len(data['struct']) + 1
supervars = clustermaker.make_cluster_supervars(data['clusters'], variants)
supervars = [supervars[vid] for vid in common.sort_vids(supervars.keys())]
with open(args.html_out_fn, 'w') as outf:
write_header(args.runid, args.tree_index, outf)
if 'tree' in plot_choices:
tree_struct = util.make_tree_struct(
data['struct'],
data['count'],
data['llh'],
data['prob'],
data['phi'],
supervars,
data['clusters'],
data['samples'],
)
tree_struct['discord'] = discord
_write_tree_html(
tree_struct,
args.tree_index,
visible_sampidxs,
samp_colours,
pop_colours,
'eta' in plot_choices,
'diversity_indices' in plot_choices,
'phi' in plot_choices,
'phi_hat' in plot_choices,
'phi_interleaved' in plot_choices,
args.phi_orientation,
args.remove_normal,
outf,
)
if args.tree_json_fn is not None:
_write_tree_json(tree_struct, args.tree_json_fn)
if 'vaf_matrix' in plot_choices:
vaf_plotter.plot_vaf_matrix(
data['clusters'],
variants,
supervars,
data['garbage'],
data['phi'],
data['samples'],
should_correct_vaf=True,
outf=outf,
)
if 'pairwise_mle' in plot_choices:
relation_plotter.plot_ml_relations(data['clustrel_posterior'],
outf)
if 'pairwise_separate' in plot_choices:
relation_plotter.plot_separate_relations(
data['clustrel_posterior'], outf)
if 'cluster_stats' in plot_choices:
write_cluster_stats(data['clusters'], data['garbage'], supervars,
variants, outf)
write_footer(outf)