nzimmermann
/
projet_court_nz
1
0
Fork 0
Code Releases Activity

added Conformations.dist_from_dissimilarity function

master
nicolas-zimmermann 2019-09-18 14:41:55 +02:00
parent 0017ab32fd
commit d77136b7f4
1 changed files with 25 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
src/projet8.py
View File

@ -5,7 +5,11 @@ import numpy as np
import pbxplore as pbx import pbxplore as pbx
import sys import sys
from scipy.spatial.distance import squareform, pdist, jaccard from scipy.spatial.distance import squareform, pdist, jaccard
from pyclustering.cluster.kmedoids import kmedoids # for kmedoids method from pyclustering.cluster.kmedoids import kmedoids
from pyclustering.cluster import cluster_visualizer
from pyclustering.utils import read_sample
from pyclustering.samples.definitions import FCPS_SAMPLES
class Conformations: class Conformations:
""" """
@ -20,8 +24,6 @@ class Conformations:
df : pd.DataFrame object df : pd.DataFrame object
Each row of the dataframe is a conformation and each column a position Each row of the dataframe is a conformation and each column a position
of the sequence. of the sequence.
dfnum : to compute dissimilarity with the function pdist, elements of
the DataFrame must be float
""" """
self.df = pd.DataFrame() self.df = pd.DataFrame()
for chain_name, chain in pbx.chains_from_files([filename]): for chain_name, chain in pbx.chains_from_files([filename]):
@ -51,7 +53,7 @@ class Conformations:
If no substitution matrix is specified, use the matrix from the If no substitution matrix is specified, use the matrix from the
PBxplore package. PBxplore package.
""" """
dissimilarity = np.ndarray((self.df.shape[0],self.df.shape[0])) dissimilarity = np.zeros((self.df.shape[0],self.df.shape[0]))
if matrix == None: if matrix == None:
matrix = pd.read_table("data/PBs_substitution_matrix.dat", matrix = pd.read_table("data/PBs_substitution_matrix.dat",
index_col=False, sep ='\t') index_col=False, sep ='\t')
@ -61,14 +63,30 @@ class Conformations:
ncol = self.df.shape[1] ncol = self.df.shape[1]
nrow = self.df.shape[0] nrow = self.df.shape[0]
it1 = self.df.iterrows() it1 = self.df.iterrows()
for i in range(1,nrow): for i in range(1,nrow): # compute each pairwise distance once only
for j in range(i): for j in range(i):
for k in range(ncol): for k in range(ncol):
dissimilarity[i][j] += matrix[confs.df.loc[i,k]][confs.df.loc[j,k]] dissimilarity[i][j] += matrix[confs.df.loc[i,k]][confs.df.loc[j,k]]
dissimilarity = dissimilarity + dissimilarity.T dissimilarity = dissimilarity + dissimilarity.T # fills the whole matrix
return dissimilarity return dissimilarity
def dist_from_dissimilarity(diss_matrix):
"""
Using the substitution matrix from the PBxplore package, the obtained
dissimilarity matrix has both positive and negative values. Low value
represent strong differences as identical PB substitution are high
positive value.
This function returns a distance matrix from the dissimilarity matrix.
Arguments :
- diss_matrix : ndarray obtained from Configurations.dissimilarity
"""
diss_matrix = -diss_matrix
diss_matrix = (diss_matrix - np.min(diss_matrix))/np.ptp(diss_matrix)
dist = diss_matrix * abs((np.identity(confs.df.shape[0])-1))
return dist
if __name__ == "__main__": if __name__ == "__main__":
if len(sys.argv) != 2: if len(sys.argv) != 2: