yml_path = Path('manual_alignments.yml')
with yml_path.open() as file:
manual_alignments = yaml.load(file)
for hit in hits:
real_seq = sgrna_sensor.from_name(hit).rna
aligned_seq = ''.join(
x for x in manual_alignments[hit]
if x in 'ACGU'
)
if real_seq != aligned_seq:
raise ValueError(f"""\
The manual alignment for {hit} has the wrong sequence!
> {real_seq}
> {aligned_seq}""")
return manual_alignments
if __name__ == '__main__':
args = docopt.docopt(__doc__)
fold_changes = calc_fold_changes(args['--force'])
fold_change_strs = {
k: fr"{v[0]:.1f}\textsuperscript{{{'−+'[v[1]]}}}"
for k,v in fold_changes.items()
}
manual_alignments = load_manual_alignments()
ligands = {k: sgrna_sensor.from_name(k).ligand or 'theo' for k in hits}
sgrna_sensor.render_latex_table('library_hits.tex', locals())
#!/usr/bin/env python3
"""\
Make a table of the randomly generated spacer sequences.
Usage:
tabulate_doench_spacers.py
"""
from os.path import join, dirname
from sgrna_sensor import render_latex_table
from pprint import pprint
fields = []
context = {'fields': fields}
doench_tsv = join(dirname(__file__), 'doench_spacers.tsv')
with open(doench_tsv) as file:
for line in file:
d_id, seq, score = line.split()
id = int(d_id.strip('d'))
row = 1 + (id - 1) // 8
col = 1 + (id - 1) % 8
seq = seq[0:4].lower() + seq[4:24].upper() + seq[24:30].lower()
score = float(score)
if id <= 24:
fields.append((id, row, col, seq, score))
render_latex_table('doench_spacers.tex', context)
return 'Upper Stem'
if name[1] == 'x':
return 'Nexus'
if name[1] == 'h':
return 'Hairpin'
raise ValueError(f"can't determine domain for {name}")
if __name__ == '__main__':
args = docopt.docopt(__doc__)
df = tabulate_sequences()
# Initialize the manual alignment file.
if args['reset_alignment']:
if alignment_path.exists() and not args['--force']:
print(f"{alignment_path} already exists, pass -f to overwrite.")
raise SystemExit
print(df)
sequences = {
row['name']: row['sequence']
for i, row in df.iterrows()
}
with alignment_path.open('w') as file:
yaml.dump(sequences, file)
# Make the table.
else:
sgrna_sensor.render_latex_table('library_sequences.tex', locals())
return names[x]
args = docopt.docopt(__doc__)
# Parse the densiometry data.
df = densiometry.load_cleavage_data_from_xlsx_dir(DATA_DIR)
df = densiometry.calc_mean_change(df)
# Add NaNs for the experiments that didn't work.
df = df.append({'spacer': 'd9', 'design': 'on'}, ignore_index=True)
# Add a column for the names I want to display.
df = df[df.design.isin(DESIGN_ORDER)]
df['construct'] = df.design.apply(get_construct)
# Put the rows in the order I want to display them in.
spacer_order = densiometry.sort_spacers_by_activity(df, ['mhf 30', 'rxb 11,1'])
df['spacer'] = pd.Categorical(df.spacer, spacer_order)
df['design'] = pd.Categorical(df.design, DESIGN_ORDER)
df = df.sort_values(['spacer', 'design']).reset_index()
n = len(df) // 2
context = { #
'df': df,
'spacers': parse_spacers(spacer_order),
'isnull': pd.isnull,
}
render_latex_table('raw_data.tex', context)
('folA spacer', spacer('fol1')),
('Theophylline (theo) aptamer', aptamer('theo')),
('3-Methylxanthine (3mx) aptamer', aptamer('3mx')),
('Thiamine pyrophosphate (tpp) aptamer', aptamer('tpp')),
('Positive control', from_name('on')),
(r'Negative control (G63C, G64C)', from_name('off')),
(r'\ligrnaF{}', from_name('mhf/30')),
(r'\ligrnaF[2]{}', from_name('mhf/37')),
(r'\ligrnaF[3]{}', from_name('w30/65')),
(r'\ligrnaF[4]{}', from_name('w30/64/1')),
(r'\ligrnaB{}', from_name('rxb/11/1')),
(r'\ligrnaB[2]{}', from_name('w11/2')),
(r'\ligrnaB[3]{}', from_name('m11/ga')),
]
with open('manual_alignments.yml') as file:
manual_alignments = yaml.load(file)
# Make sure there aren't any typos.
for name, sgrna in components:
if name in manual_alignments:
aligned_seq = ''.join(x for x in manual_alignments[name] if x in 'ATCG')
assert sgrna.dna.upper() == aligned_seq.upper(), f"""\
Name: {name}
Expected: {sgrna.dna.upper()}
Actual: {aligned_seq.upper()}
"""
render_latex_table('components.tex', locals())