Table 4 Sample code for the comparison between 4 different decoy populations

Load

import pandas as pd

import rstoolbox as rs

import matplotlib.pyplot as plt

Read

df = []

# With Rosetta installed, scoring can be run for a single structure

baseline =  rs.io.get_sequence_and_structure (‘4yod.pdb’)

experiments = [‘no_target’, ‘static’, ‘pack’, ‘packmin’]

scores = [‘score’, ‘LocalRMSDH’, ‘post_ddg’, ‘bb_clash’]

scorename = [‘score’, ‘RMSD’, ‘ddG’, ‘bb_clash’]

for experiment in experiments:

  # Load Rosetta silent file from decoy generation

  ds = rs.io.parse_rosetta_file(experiment + ‘.design’)

  # Load decoy evaluation from a pre-processed CSV file.

  # Casting pd. DataFrame into DesignFrame is as easy as shown here.

  ev = rs.components. DesignFrame(pd.read_csv(experiment + ‘.evals’))

  # Different outputs for the same decoys can be combined through

  # their ‘description’ field (decoy identifier)

  df.append(ds.merge (ev, on = ‘description’))

  # Tables can be joined together into a single working object

  df = pd.concat(df)

  # As we are comparing over BINDI’s sequence, that is our reference.

  df.add_reference_sequence(‘B’, baseline.iloc[0].get_sequence(‘B’)[:-1])

Plot

fig = plt.figure (figsize = (170 / 25.4, 170 / 25.4))

grid = (12, 4)

# Show the distribution for key score terms

axs =  rs.plot.multiple_distributions (df, fig, grid, values = scores, rowspan = 3,

labels = scorename, x = ‘binder_state’, order = experiments, showfliers = False)

# Sequence score for a selected decoys with standard-matrix weights

ax = plt.subplot2grid(grid, (3, 0), fig = fig, colspan = 4, rowspan = 4)

qr = df[df[‘binder_state’] == ‘no_target’].sort_values(‘score’).iloc[0]

rs.plot.per_residue_matrix_score_plot ( qr , ‘B’, ax, ‘BLOSUM62’, add_alignment = False, color = 0)

qr = df[df[‘binder_state’] == ‘no_pack’].sort_values(‘score’).iloc[0]

rs.plot.per_residue_matrix_score_plot (qr, ‘B’, ax, ‘BLOSUM62’, add_alignment = False, color = 2,

selections = [(‘43–64’, ‘red’)])

# Small functions help edit the plot display

rs.utils.add_top_title (ax, ‘no_target (blue) - pack (green)’)

# Evaluate the variability of residue types in the binding region

ax = plt.subplot2grid(grid, (7, 0), fig = fig, colspan = 2, rowspan = 4)

qr = df[df[‘binder_state’] == ‘no_target’]

rs.plot.sequence_frequency_plot (qr, ‘B’, ax, key_residues = ‘43–64’, cbar = False, clean_unused = 0.1, xrotation = 90)

rs.utils.add_top_title (ax, ‘no_target’)

ax = plt.subplot2grid(grid, (7, 2), fig = fig, colspan = 2, rowspan = 4)

ax_cbar = plt.subplot2grid(grid, (11, 0), fig = fig, colspan = 4)

rs.plot.sequence_frequency_plot (df[df[‘binder_state’] == ‘pack’], ‘B’, ax, key_residues = ‘43–64’,                                                                                                 cbar_ax = ax_cbar, clean_unused = 0.1, xrotation = 90)

rs.utils.add_top_title (ax, ‘pack’)

plt.tight_layout()

plt.savefig(‘BMC_Fig5.png’, dpi = 300)