def compute_tsne(self):
Database = self.Database2
smiles = list(Database["SMILES"])
smi = [Chem.MolFromSmiles(x) for x in smiles]
fps = [AllChem.GetMorganFingerprintAsBitVect(x, 3) for x in smi]
tanimoto_sim_mat_lower_triangle = GetTanimotoSimMat(fps)
n_mol = len(fps)
similarity_matrix = np.ones([n_mol, n_mol])
i_lower = np.tril_indices(n=n_mol, m=n_mol, k=-1)
i_upper = np.triu_indices(n=n_mol, m=n_mol, k=1)
similarity_matrix[i_lower] = tanimoto_sim_mat_lower_triangle
similarity_matrix[i_upper] = similarity_matrix.T[i_upper]
distance_matrix = np.subtract(1, similarity_matrix)
TSNE_sim = TSNE(
n_components=2,
init='pca',
random_state=1992,
angle=0.3,
perplexity=self.perplexity).fit_transform(distance_matrix)
tsne_result = pd.DataFrame(data=TSNE_sim, columns=["PC1", "PC2"])
tsne_result["LIBRARY"] = list(Database.LIBRARY)
tsne_result["TIPO"] = list(Database.LIBRARY)
tsne_result["SMILES"] = list(Database.SMILES)
tsne_result["NAME"] = list(Database.NAME)
self.tsne_result = tsne_result.set_index('TIPO')
def compute_pca(self):
Database = self.Database2
smiles = list(Database.SMILES)
smi = [Chem.MolFromSmiles(x) for x in smiles]
fps = [AllChem.GetMorganFingerprintAsBitVect(x, 2) for x in smi]
tanimoto_sim_mat_lower_triangle = GetTanimotoSimMat(fps)
n_mol = len(fps)
similarity_matrix = np.ones([n_mol, n_mol])
i_lower = np.tril_indices(n=n_mol, m=n_mol, k=-1)
i_upper = np.triu_indices(n=n_mol, m=n_mol, k=1)
similarity_matrix[i_lower] = tanimoto_sim_mat_lower_triangle
similarity_matrix[i_upper] = similarity_matrix.T[i_upper]
sklearn_pca = sklearn.decomposition.PCA(n_components=2,
svd_solver="full",
whiten=True)
sklearn_pca.fit(similarity_matrix)
variance = list(sklearn_pca.explained_variance_ratio_)
a = round(variance[0] * 100, 2)
b = round(variance[1] * 100, 2)
pca_result = pd.DataFrame(sklearn_pca.transform(similarity_matrix),
columns=['PC1', 'PC2'])
pca_result["LIBRARY"] = Database.LIBRARY
pca_result["TIPO"] = Database.LIBRARY
pca_result["SMILES"] = Database.SMILES
pca_result["NAME"] = Database.NAME
self.pca_result = pca_result.set_index('TIPO')
variance = list(sklearn_pca.explained_variance_ratio_)
self.a = round(variance[0] * 100, 2)
self.b = round(variance[1] * 100, 2)
return pca_result
def compute_maccskeys_fp(Data):
smiles = list(Data["canonical_smiles"]) # set smile colum
smi = [Chem.MolFromSmiles(x) for x in smiles]
fps = [MACCSkeys.GenMACCSKeys(x) for x in smi]
tanimoto_sim_mat_lower_triangle = GetTanimotoSimMat(fps)
n_mol = len(fps)
similarity_matrix = np.ones([n_mol, n_mol])
i_lower = np.tril_indices(n=n_mol, m=n_mol, k=-1)
i_upper = np.triu_indices(n=n_mol, m=n_mol, k=1)
similarity_matrix[i_lower] = tanimoto_sim_mat_lower_triangle
similarity_matrix[i_upper] = similarity_matrix.T[i_upper]
distance_matrix = np.subtract(1, similarity_matrix)
distance_matrix = np.round(distance_matrix, 2)
print(distance_matrix)
ids = list(Data["chembl_id"]) # set id columns
return distance_matrix, ids