def main():
# Setup the workspaces:
import docopt
args = docopt.docopt(__doc__)
work_blast, work_msa = MsaWorkspace.from_path(args['<msa_workspace>'])
work_dels = LoophashWorkspace(work_msa)
if args['--force']:
work_dels.rmdir()
work_dels.mkdir()
# Choose which deletions to make:
if work_dels.deletions_hdf5.exists():
dels = pd.read_hdf(work_dels.deletions_hdf5)
filters = GapFilters.from_toml(work_dels.filters_toml)
else:
msa = load_weighted_msa(work_msa)
scores = calc_deletion_scores(msa)
gaps, filters = load_spannable_gaps(work_dels, msa)
dels = choose_gaps_to_delete(scores, gaps, filters)
# Analyze the results:
print(filters)
print(dels.describe())
print()
work_dels.write_deletions(dels, filters)
work_dels.write_metadata()
def main():
# Setup the workspaces:
import docopt
args = docopt.docopt(__doc__)
work_blast, work_msa = MsaWorkspace.from_path(args['<msa_workspace>'])
work_dels = DeletionsWorkspace(work_msa, 'threshold')
if args['--force']:
work_dels.rmdir()
work_dels.mkdir()
# Choose which deletions to make:
if work_dels.deletions_hdf5.exists():
dels = pd.read_hdf(work_dels.deletions_hdf5)
else:
msa = load_weighted_msa(work_msa)
scores = calc_deletion_scores(msa)
dels = choose_deletions_via_thresholds(scores)
# Record the results:
print(f"Chose {len(dels)} deletions:\n")
print(dels.describe())
work_dels.write_deletions(dels)
work_dels.write_metadata()
def main():
# Parse the command-line arguments.
import docopt
args = docopt.docopt(__doc__)
work_homs, work_msa = MsaWorkspace.from_path(args['<msa_workspace>'])
msa = load_weighted_msa(work_msa)
scores = calc_deletion_scores(msa)
if os.fork():
sys.exit()
# Report statistics about the MSA.
print(f"{len(msa)} sequences aligned")
print(f"{sum(x.percent_id > 0.3 for x in msa)} exceed 30% identity")
y, xx = np.histogram(
[x.percent_id for x in msa],
bins=100,
range=(0, 1),
)
x = (xx[:-1] + xx[1:]) / 2
plt.subplot(2, 1, 1)
plt.title(work_msa.relpath)
plt.plot(x, y)
plt.axvline(0.3, color='red')
plt.ylabel('Count')
plt.xlabel('% Identity')
# Report statistics about the deletion scores.
threshold = np.mean(scores)
n = len(scores)
n_del = sum(scores > threshold)
print(
f"{n_del}/{n} residues ({100*n_del/n:.1f}%) have above-average deletion scores."
)
i = np.arange(n)
plt.subplot(2, 1, 2)
plt.plot(i, scores)
plt.tight_layout()
plt.ylabel('Score')
plt.xlabel('Residue index')
plt.xlim((0, len(i)))
plt.axhline(threshold, color='red')
plt.gcf().canvas.set_window_title(str(work_msa.relpath))
plt.show()
def __init__(self, dels_workspace, cursor=0, low=0, high=50):
work_dels = DeletionsWorkspace.from_path(dels_workspace)
msa = load_weighted_msa(work_dels.msa)
scores = calc_deletion_scores(msa)
self.dels = pd.read_hdf(work_dels.deletions_hdf5).sort_values(['del_start', 'del_end'])
self.cursor = cursor
self.low = float(low)
self.high = float(high)
self.sele = f'chain B and polymer.protein'
cmd.alter(
self.sele,
'b=scores[int(resi)-1]',
space={**locals(), **globals()},
)
self.redraw()
def paint_deletion_scores(msa_workspace, low=0, high=50):
"""
DESCRIPTION
Color each residue by its "deletion score", a measure of how commonly it is
deleted in homologous sequences.
USAGE
paint_deletion_scores dels_workspace
ARGUMENTS
dels_workspace = a path to a workspace for the final step of the pipeline,
which is to pick deletions.
low = the percentile of the data to make the most blue {default: 0}.
high = the percentile of the data to make the most red {default: 50}.
NOTES
This script assumes that the only structure loaded in pymol is the one
contained in the given workspace.
"""
work_blast, work_msa = MsaWorkspace.from_path(msa_workspace)
msa = load_weighted_msa(work_msa)
scores = calc_deletion_scores(msa)
cutoff_low = np.percentile(scores, float(low))
cutoff_high = np.percentile(scores, float(high))
sele = f'chain B and polymer.protein'
cmd.alter(sele, 'b=scores[int(resi)-1]', space={**locals(), **globals()})
cmd.spectrum('b', 'blue_white_red', sele, minimum=cutoff_low, maximum=cutoff_high)
print(f'low: {cutoff_low:.2f} ({float(low):.2f}%)')
print(f'high: {cutoff_high:.2f} ({float(high):.2f}%)')