EDA

from matplotlib import pyplot as plt from sklearn.decomposition import PCA import orchest import seaborn as sns import pandas as pd import numpy as np

data = orchest.get_inputs() bcell, covid, sars, bcell_sars = data["data"]

bcell_sars.head()

bcell_sars.target.value_counts()

idx_train = bcell_sars["target"].astype("bool").values fig, axes = plt.subplots(2, 2, figsize=(16, 8)) axes = [x for a in axes for x in a] for i, name in enumerate(["chou_fasman", "emini", "kolaskar_tongaonkar", "parker"]): value = bcell_sars[name] sns.distplot(value[~idx_train], ax=axes[i]) sns.distplot(value[idx_train], ax=axes[i]) axes[i].set_xlabel(name, fontsize=12) fig.legend(labels=["target 0", "target 1"], loc="right", fontsize=12)

clf = PCA(n_components=2) z = clf.fit_transform( bcell_sars[["chou_fasman", "emini", "kolaskar_tongaonkar", "parker"]] ) plt.figure(figsize=(8, 6)) plt.scatter(*z[idx_train].T, s=3) plt.scatter(*z[~idx_train].T, s=3) plt.legend(labels=["target_1", "target_0"], fontsize=12) plt.show()

idx_train = bcell_sars["target"].astype("bool").values fig, axes = plt.subplots(2, 2, figsize=(16, 8)) axes = [x for a in axes for x in a] for i, name in enumerate( ["isoelectric_point", "aromaticity", "hydrophobicity", "stability"] ): value = bcell_sars[name] sns.distplot(value[~idx_train], ax=axes[i]) sns.distplot(value[idx_train], ax=axes[i]) axes[i].set_xlabel(name, fontsize=12) fig.legend(labels=["target 0", "target 1"], loc="right", fontsize=12)

clf = PCA(n_components=2) z = clf.fit_transform( bcell_sars[["isoelectric_point", "aromaticity", "hydrophobicity", "stability"]] ) plt.figure(figsize=(8, 6)) plt.scatter(*z[idx_train].T, s=3) plt.scatter(*z[~idx_train].T, s=3) plt.legend(labels=["target_1", "target_0"], fontsize=12) plt.show()

# create length columns for df in [bcell, sars, covid, bcell_sars]: df["length"] = df["end_position"] - df["start_position"] + 1 fig, ax = plt.subplots(figsize=(12, 6)) sns.countplot(bcell_sars["length"], ax=ax, color="lightblue") sns.countplot(bcell_sars.query("target == 1")["length"], ax=ax, color="coral") plt.legend(labels=["target 0", "target 1"], fontsize=12) plt.show()

# Corelation Matrix corr_matrix = bcell_sars[ [ "parent_protein_id", "protein_seq", "start_position", "end_position", "peptide_seq", "chou_fasman", "emini", "kolaskar_tongaonkar", "parker", "isoelectric_point", "aromaticity", "hydrophobicity", "stability", "target", ] ].corr() mask = np.zeros_like(corr_matrix, dtype=np.bool) mask[np.triu_indices_from(mask)] = True #corr heatmap sns.set_style('whitegrid') f, ax = plt.subplots(figsize=(11, 15)) heatmap = sns.heatmap(corr_matrix, mask = mask, square = True, linewidths = .5, cmap = 'coolwarm', cbar_kws = {'shrink': .4, 'ticks' : [-1, -.5, 0, 0.5, 1]}, vmin = -1, vmax = 1, annot = False, annot_kws = {'size': 12}) #add the column names as labels ax.set_yticklabels(corr_matrix.columns, rotation = 0) ax.set_xticklabels(corr_matrix.columns) sns.set_style({'xtick.bottom': True}, {'ytick.left': True})