# coding: utf-8
from Bio import SeqIO
peptides = SeqIO('Data/anti_microbial_peptide.fasta', 'fasta')
peptides = SeqIO.parse('Data/anti_microbial_peptide.fasta', 'fasta')
peptides
peptides = []
for seq in SeqIO.p('Data/anti_microbial_peptide.fasta', 'fasta'):
peptides.append(seq)
for seq in SeqIO.parse('Data/anti_microbial_peptide.fasta', 'fasta'):
peptides.append(seq)
peptides
import pandas as pd
from protein_sequence_features import protein_features
from protein_sequence_features import protein_features
features = map(protein_features, peptides)
features[0]
peptides_dataset = pd.DataFrame(features, index=map(lambda x: x.id, peptides))
peptides_dataset
peptides_dataset.to_csv('Data/anti_microbial_peptide_features.csv')
from sklearn.manifold import TSNE
tsne = TSNE()
tsne.fit(peptides_dataset.values)
X = tsne.fit_transform(peptides_dataset.values)
import matplotlib.pyplot as plt
import seaborn as sns
plt.scatter(X)
plt.scatter(X[:, 0], X[:, 1])
plt.imshow()
plt.show()
