def all_genes_in_submatrices(network, idx_ppi, idx_mut, idx_ppi_only,
idx_mut_only, mutation_profile):
"""Processing of sub-matrices for each case of genes
Extract the sub-matrices of references genes and Zero-padding of the
adjacency matrix.
┌ - - - - - - - ┐
| | | |
| AA |AB| AC |
| | | |
|- - - - - - - -|
| BA |BB| BC |
|- - - - - - - -|
| CA |CB| CC |
└ - - - - - - - ┘
AA, BB and CC are all adjacency matrces (0/1 matrices with 0 on diagonal) :
AA : common genes between PPI and patients' mutation profiles
BB : genes founded only in PPI
CC : genes founded only in patients' mutation profiles = zero matrix
Parameters
----------
network : sparse matrix, shape (len(gene_id_ppi),len(gene_id_ppi))
PPI data matrix, called also 'adjacency matrix'.
idx_ppi : list
List of common genes' indexes in PPI.
idx_ppi_only : list
List of genes' indexes only in PPI.
idx_mut_only : list
List of genes' indexes only in patients' mutation profiles.
Returns
-------
ppi_total : sparse matrix
Built from all sparse sub-matrices (AA, ... , CC).
mut_total : sparse matrix
Patients' mutation profiles of all genes (rows: patients,
columns: genes of AA, BB and CC).
ppi_filt : sparse matrix
Filtration from ppi_total : only genes in PPI are considered.
┌ - - - - -┐
| | |
| AA |AB|
| | |
|- - - - - |
| BA |BB|
└ - - - - -┘
mut_filt : sparse matrix
Filtration from mut_total : only genes in PPI are considered.
"""
print(' ==== all_genes_in_submatrices ')
AA = network[idx_ppi][:, idx_ppi]
if AA.shape[0] == 0:
warnings.warn("There are no common genes between PPI network and patients' mutation profile")
AB = network[idx_ppi][:, idx_ppi_only]
AC = sp.csc_matrix((len(idx_ppi), len(idx_mut_only))).astype(np.float32)
BA = network[idx_ppi_only][:, idx_ppi]
BB = network[idx_ppi_only][:, idx_ppi_only]
BC = sp.csc_matrix((len(idx_ppi_only), len(idx_mut_only))).astype(np.float32)
# TODO condition: if mutOnly = 0
CA = sp.csc_matrix((len(idx_mut_only), len(idx_ppi)), dtype=np.float32)
CB = sp.csc_matrix((len(idx_mut_only), len(idx_ppi_only)), dtype=np.float32)
CC = sp.csc_matrix((len(idx_mut_only), len(idx_mut_only)), dtype=np.float32)
print(' ==== ABC ')
ppi_total = sp.bmat([[AA, AB, AC], [BA, BB, BC], [CA, CB, CC]],
format='csc')
# NOTE ppi_total in COO matrix -> csc matrix
# ppi_total = ppi_total.tocsc()
print(' ==== mut_total ')
mut_total = sp.bmat([[mutation_profile[:, idx_mut],
sp.csc_matrix((mutation_profile.shape[0],
len(idx_ppi_only)), dtype=np.float32),
mutation_profile[:, idx_mut_only]]])
# filter only genes in PPI
print(' ==== filter only genes in PPI ')
degree = Ppi(ppi_total).deg
ppi_filt = ppi_total[degree > 0, :][:, degree > 0]
mut_filt = mut_total[:, degree > 0]
print(' ==== all_genes_in_submatrices finish ')
return ppi_total, mut_total, ppi_filt, mut_filt
def filter_ppi_patients(ppi_total, mut_total, ppi_filt, final_influence, ngh_max,
keep_singletons=False,
min_mutation=0, max_mutation=2000):
"""Keeping only the connections with the best influencers and Filtering some
patients based on mutation number
'the 11 most influential neighbors of each gene in the network as
determined by network influence distance were used'
'Only mutation data generated using the Illumina GAIIx platform were
retained for subsequent analy- sis, and patients with fewer than 10
mutations were discarded.'
Parameters
----------
ppi_total : sparse matrix
Built from all sparse sub-matrices (AA, ... , CC).
mut_total : sparse matrix
Patients' mutation profiles of all genes (rows: patients,
columns: genes of AA, BB and CC).
ppi_filt : sparse matrix
Filtration from ppi_total : only genes in PPI are considered.
final_influence :
Smoothed PPI influence matrices based on minimum or maximum weight.
ngh_max : int
Number of best influencers in PPI.
keep_singletons : boolean, default: False
If True, proteins not annotated in PPI (genes founded only in patients'
mutation profiles) will be also considered.
If False, only annotated proteins in PPI will be considered.
min_mutation, max_mutation : int
Numbers of lowest mutations and highest mutations per patient.
Returns
-------
ppi_final, mut_final : sparse matrix
PPI and mutation profiles after filtering.
"""
# n = final_influence.shape[0]
# final_influence = index_to_sym_matrix(n, final_influence)
ppi_ngh = best_neighboors(ppi_filt, final_influence, ngh_max)
deg0 = Ppi(ppi_total).deg == 0 # True if protein degree = 0
if keep_singletons:
ppi_final = sp.bmat([
[ppi_ngh, sp.csc_matrix((ppi_ngh.shape[0], sum(deg0)))],
[sp.csc_matrix((sum(deg0), ppi_ngh.shape[0])),
sp.csc_matrix((sum(deg0), sum(deg0)))]
]) # -> COO matrix
# mut_final=sp.bmat([[mut_total[:,deg0==False],mut_total[:,deg0==True]]])
mut_final = mut_total
else:
ppi_final = ppi_ngh
mut_final = mut_total[:, Ppi(ppi_total).deg > 0]
# filtered_patients = np.array([k < min_mutation or k > max_mutation for k in Patient(mut_final).mut_per_patient])
# mut_final = mut_final[filtered_patients == False, :]
# to avoid worse comparison '== False'
mut_final = mut_final[np.array([min_mutation < k < max_mutation for k in
Patient(mut_final).mut_per_patient])]
print(" Removing %i patients with less than %i or more than %i mutations" %
(mut_total.shape[0]-mut_final.shape[0], min_mutation, max_mutation))
return ppi_final, mut_final
def filter_ppi_patients(result_folder,
influence_weight,
simplification,
alpha,
tol,
ppi_total,
mut_total,
ppi_filt,
final_influence,
ngh_max,
keep_singletons=False,
min_mutation=0,
max_mutation=2000):
"""Keeping only the connections with the best influencers and Filtering some
patients based on mutation number
'the 11 most influential neighbors of each gene in the network as
determined by network influence distance were used'
'Only mutation data generated using the Illumina GAIIx platform were
retained for subsequent analy- sis, and patients with fewer than 10
mutations were discarded.'
Parameters
----------
ppi_total : sparse matrix
Built from all sparse sub-matrices (AA, ... , CC).
mut_total : sparse matrix
Patients' mutation profiles of all genes (rows: patients,
columns: genes of AA, BB and CC).
ppi_filt : sparse matrix
Filtration from ppi_total : only genes in PPI are considered.
final_influence :
Smoothed PPI influence matrices based on minimum or maximum weight.
ngh_max : int
Number of best influencers in PPI.
keep_singletons : boolean, default: False
If True, proteins not annotated in PPI (genes founded only in patients'
mutation profiles) will be also considered.
If False, only annotated proteins in PPI will be considered.
min_mutation, max_mutation : int
Numbers of lowest mutations and highest mutations per patient.
Returns
-------
ppi_final, mut_final : sparse matrix
PPI and mutation profiles after filtering.
"""
ppi_final_directory = result_folder + 'final_influence/'
ppi_final_file = (
ppi_final_directory +
'PPI_final_weight={}_simp={}_alpha={}_tol={}_singletons={}_ngh={}.mat'.
format(influence_weight, simplification, alpha, tol, keep_singletons,
ngh_max))
existance_same_param = os.path.exists(ppi_final_file)
if existance_same_param:
ppi_final_data = loadmat(ppi_final_file)
ppi_final = ppi_final_data['ppi_final']
print(' **** Same parameters file of PPI FINAL already exists')
if keep_singletons:
mut_final = mut_total
else:
mut_final = mut_total[:, Ppi(ppi_total).deg > 0]
else:
ppi_ngh = best_neighboors(ppi_filt, final_influence, ngh_max)
deg0 = Ppi(ppi_total).deg == 0 # True if protein degree = 0
if keep_singletons:
ppi_final = sp.bmat(
[[ppi_ngh,
sp.csc_matrix((ppi_ngh.shape[0], sum(deg0)))],
[
sp.csc_matrix((sum(deg0), ppi_ngh.shape[0])),
sp.csc_matrix((sum(deg0), sum(deg0)))
]]) # -> COO matrix
# mut_final=sp.bmat([[mut_total[:,deg0==False],mut_total[:,deg0==True]]])
mut_final = mut_total
else:
ppi_final = ppi_ngh
mut_final = mut_total[:, Ppi(ppi_total).deg > 0]
savemat(ppi_final_file, {'ppi_final': ppi_final}, do_compression=True)
# to avoid worse comparison '== False'
mut_final = mut_final[np.array([
min_mutation <= k <= max_mutation
for k in Patient(mut_final).mut_per_patient
])]
print(
" Removing %i patients with less than %i or more than %i mutations" %
(mut_total.shape[0] - mut_final.shape[0], min_mutation, max_mutation))
return ppi_final, mut_final