def export_pathways():
change_dist = load_pickle(SingleRegion.change_dist_filename)
matlab_g2i = {g:(i+1) for i,g in enumerate(change_dist.genes)} # NOTE that matlab is one based
pathways = pathway_lists.read_all_pathways()
pathway_names = pathways.keys() # make sure the order stays fixed
pathway_genes_names = np.array([list_of_strings_to_matlab_cell_array(pathways[p]) for p in pathway_names], dtype=object)
pathway_genes_idx = np.array([np.array([matlab_g2i[g] for g in pathways[p]]) for p in pathway_names], dtype=object)
matlab_p2i = {p:(i+1) for i,p in enumerate(pathway_names)} # NOTE matlab indexing is one based
list_names = pathway_lists.all_pathway_lists()
list_pathway_names = np.empty(len(list_names), dtype=object)
list_pathway_idx = np.empty(len(list_names), dtype=object)
for i,listname in enumerate(list_names):
pathways_in_list = pathway_lists.list_to_pathway_names(listname)
list_pathway_names[i] = list_of_strings_to_matlab_cell_array(pathways_in_list)
list_pathway_idx[i] = [matlab_p2i[p] for p in pathways_in_list]
README = """\
pathway_names:
Cell array of all pathway names. The name in cell number k is the name of the
pathway at position k in "pathway_genes_names" and "pathway_genes_idx".
pathway_genes_names:
Cell array (size <n-pathways>). Each cell contains a cell array of strings which
are the gene symbols of the genes in that pathway.
pathway_genes_idx:
Same as pathway_genes_names, but each cell in the outer cell array is now an
array of gene indices corresponding to the gene positions in cube.mat and change-distributions.mat.
Hopefully this should be easier to use in matlab.
list_names:
Names of pathway lists prepared by Noa
list_pathway_names:
Call array. One item per list. Each item is a cell array of strings which are
the names of the pathways belonging to that list.
list_pathway_idx:
Same as list_pathway_names, but instead of listing the pathways by name, they
are given as indices into the previous pathway_xxx structures.
"""
mdict = dict(
README_PATHWAYS = README,
pathway_names = list_of_strings_to_matlab_cell_array(pathway_names),
pathway_genes_names = pathway_genes_names,
pathway_genes_idx = pathway_genes_idx,
list_names = list_of_strings_to_matlab_cell_array(list_names),
list_pathway_names = list_pathway_names,
list_pathway_idx = list_pathway_idx,
)
save_matfile(mdict, join(results_dir(), 'export', 'pathways.mat'))
def __init__(self, listname='all'):
self.listname = listname
self.pathways = pathway_lists.read_all_pathways(listname)
self.change_dist = load_pickle(SingleRegion.change_dist_filename, 'change distribution for all genes and regions')
self.genes = self.change_dist.genes
self.regions = self.change_dist.regions
self.g2i = {g:i for i,g in enumerate(self.genes)}
self.r2i = {r:i for i,r in enumerate(self.regions)}
self.age_scaler = self.change_dist.age_scaler
self.mu = self.change_dist.mu
self.std = self.change_dist.std
self.bin_edges = self.change_dist.bin_edges
self.bin_centers = self.change_dist.bin_centers
self.weights = self.change_dist.weights
def __init__(self, listname='all'):
self.listname = listname
self.pathways = pathway_lists.read_all_pathways(listname)
self.change_dist = load_pickle(
SingleRegion.change_dist_filename,
'change distribution for all genes and regions')
self.genes = self.change_dist.genes
self.regions = self.change_dist.regions
self.g2i = {g: i for i, g in enumerate(self.genes)}
self.r2i = {r: i for i, r in enumerate(self.regions)}
self.age_scaler = self.change_dist.age_scaler
self.mu = self.change_dist.mu
self.std = self.change_dist.std
self.bin_edges = self.change_dist.bin_edges
self.bin_centers = self.change_dist.bin_centers
self.weights = self.change_dist.weights
def export_pathways():
change_dist = load_pickle(SingleRegion.change_dist_filename)
matlab_g2i = {g: (i + 1)
for i, g in enumerate(change_dist.genes)
} # NOTE that matlab is one based
pathways = pathway_lists.read_all_pathways()
pathway_names = pathways.keys() # make sure the order stays fixed
pathway_genes_names = np.array([
list_of_strings_to_matlab_cell_array(pathways[p])
for p in pathway_names
],
dtype=object)
pathway_genes_idx = np.array([
np.array([matlab_g2i[g] for g in pathways[p]]) for p in pathway_names
],
dtype=object)
matlab_p2i = {p: (i + 1)
for i, p in enumerate(pathway_names)
} # NOTE matlab indexing is one based
list_names = pathway_lists.all_pathway_lists()
list_pathway_names = np.empty(len(list_names), dtype=object)
list_pathway_idx = np.empty(len(list_names), dtype=object)
for i, listname in enumerate(list_names):
pathways_in_list = pathway_lists.list_to_pathway_names(listname)
list_pathway_names[i] = list_of_strings_to_matlab_cell_array(
pathways_in_list)
list_pathway_idx[i] = [matlab_p2i[p] for p in pathways_in_list]
README = """\
pathway_names:
Cell array of all pathway names. The name in cell number k is the name of the
pathway at position k in "pathway_genes_names" and "pathway_genes_idx".
pathway_genes_names:
Cell array (size <n-pathways>). Each cell contains a cell array of strings which
are the gene symbols of the genes in that pathway.
pathway_genes_idx:
Same as pathway_genes_names, but each cell in the outer cell array is now an
array of gene indices corresponding to the gene positions in cube.mat and change-distributions.mat.
Hopefully this should be easier to use in matlab.
list_names:
Names of pathway lists prepared by Noa
list_pathway_names:
Call array. One item per list. Each item is a cell array of strings which are
the names of the pathways belonging to that list.
list_pathway_idx:
Same as list_pathway_names, but instead of listing the pathways by name, they
are given as indices into the previous pathway_xxx structures.
"""
mdict = dict(
README_PATHWAYS=README,
pathway_names=list_of_strings_to_matlab_cell_array(pathway_names),
pathway_genes_names=pathway_genes_names,
pathway_genes_idx=pathway_genes_idx,
list_names=list_of_strings_to_matlab_cell_array(list_names),
list_pathway_names=list_pathway_names,
list_pathway_idx=list_pathway_idx,
)
save_matfile(mdict, join(results_dir(), 'export', 'pathways.mat'))
