def __init__(self, file_name, annotation_map=None, file_format='pty', profile2gene=None):
self.file_name = file_name
self.base_file_name = os.path.basename(file_name)
self.merged_files = set([self.file_name])
self.merged_base_files = set([self.base_file_name])
if file_format=='pty':
_genes = dt.get_pty_file(file_name, annotation_map=annotation_map, profile2gene=profile2gene)
else:
_genes = dt.get_pty_file_generic(file_name, profile2gene=profile2gene)
# print "File name:", file_name, "Genes size:",len(_genes)
self.genes = _genes
self.profiles = set(profile for g in _genes for profile in g.cogid.split(',') if profile != '')
self.gene_names = set(gene_name for g in _genes for gene_name in g.gene_name.split(',') if gene_name != '')
self.organism = _genes[0].organism
self.source = _genes[0].src
_forward = set()
_reverse = set()
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_forward.update((_cogid,))
if i == len(self.genes)-1:
continue
_next_gene = self.genes[i+1]
for _next_cogid in _next_gene.cogid.split(','):
_forward.update(("%s-%s" % (_cogid, _next_cogid),))
self.genes.sort(reverse=True)
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_reverse.update((_cogid,))
if i == len(self.genes)-1:
continue
_next_gene = self.genes[i+1]
for _next_cogid in _next_gene.cogid.split(','):
_reverse.update(("%s-%s" % (_cogid, _next_cogid),))
self.forward_set = _forward
self.reverse_set = _reverse
self.feature_weights = None
self.feature_labels = None
def __init__(self, file_name, annotation_map=None):
self.file_name = file_name
_genes = dt.get_pty_file_generic(file_name,
annotation_map=annotation_map)
self.genes = _genes
self.profiles = set(profile for g in _genes
for profile in g.cogid.split() if profile != '')
self.organism = _genes[0].organism
self.source = _genes[0].src
_forward = set()
_reverse = set()
for i in range(len(_genes)):
_gene = _genes[i]
for _cogid in _gene.cogid.split(','):
_forward.update((_cogid, ))
if i == len(_genes) - 1:
continue
_next_gene = _genes[i + 1]
for _next_cogid in _next_gene.cogid.split(','):
_forward.update(("%s-%s" % (_cogid, _next_cogid), ))
_genes.sort(reverse=True)
for i in range(len(_genes)):
_gene = _genes[i]
for _cogid in _gene.cogid.split(','):
_reverse.update((_cogid, ))
if i == len(_genes) - 1:
continue
_next_gene = _genes[i + 1]
for _next_cogid in _next_gene.cogid.split(','):
_reverse.update(("%s-%s" % (_cogid, _next_cogid), ))
self.forward_set = _forward
self.reverse_set = _reverse
self.feature_weights = None
self.feature_labels = None
if __name__ == '__main__':
# prok1402_path_file = '/mnt/storage/data/CDD/all_Prok1402.ccp.csv'
prok1402_path_file = os.path.join(os.path.expanduser('~'),
'data/CDD/all_Prok1402.ccp.csv')
print "Loading map_gid2cdd"
gi2annotation = t.map_gid2cdd()
print "Loading CRISPR loci"
# cas1402_loci_path = os.path.join(gv.project_data_path,'cas1402/files/')
cas1402_loci_path = os.path.join(gv.project_data_path, 'cas1402/files/')
cas1402_loci = [
dt.get_pty_file_generic(os.path.join(cas1402_loci_path, f),
annotation_map=gi2annotation)
for f in os.listdir(cas1402_loci_path)
]
cas1402_gis = set([gene.gid for locus in cas1402_loci for gene in locus])
cas1402_organisms = set([locus[0].organism for locus in cas1402_loci])
calculate_profile_based_crispricity(cas1402_loci, cas1402_gis,
cas1402_organisms, prok1402_path_file)
# all_orgs = set()
# for profile, org2gis in global_profile2orgs2gis.items():
# if 'Yersinia_pseudotuberculosis_PB1__uid59153' in org2gis:
# print "Yersinia_pseudotuberculosis_PB1__uid59153"
# for _org in org2gis.keys():
# all_orgs.update([_org])
plt.ylabel("Crispricity")
plt.legend(loc="upper left", fontsize=7)
plt.savefig(os.path.join(work_dir, 'crispricity_log.png'))
if __name__=='__main__':
# prok1402_path_file = '/mnt/storage/data/CDD/all_Prok1402.ccp.csv'
prok1402_path_file = os.path.join(os.path.expanduser('~'),'data/CDD/all_Prok1402.ccp.csv')
print "Loading map_gid2cdd"
gi2annotation = t.map_gid2cdd()
print "Loading CRISPR loci"
# cas1402_loci_path = os.path.join(gv.project_data_path,'cas1402/files/')
cas1402_loci_path = os.path.join(gv.project_data_path,'cas1402/files/')
cas1402_loci = [dt.get_pty_file_generic(os.path.join(cas1402_loci_path, f), annotation_map = gi2annotation) for f in os.listdir(cas1402_loci_path)]
cas1402_gis = set([gene.gid for locus in cas1402_loci for gene in locus])
cas1402_organisms = set([locus[0].organism for locus in cas1402_loci])
calculate_profile_based_crispricity(cas1402_loci, cas1402_gis, cas1402_organisms, prok1402_path_file)
# all_orgs = set()
# for profile, org2gis in global_profile2orgs2gis.items():
# if 'Yersinia_pseudotuberculosis_PB1__uid59153' in org2gis:
# print "Yersinia_pseudotuberculosis_PB1__uid59153"
# for _org in org2gis.keys():
# all_orgs.update([_org])
def kplet_list_to_file_summaries(kplets,
neighborhood_files_path,
filter_weak_hits=True):
file_summaries = list()
organisms = set()
_file2kplets = dict()
_kplet2count_af = dict() # kplet2count after filtration
_kplet2count_bf = dict() # kplet2count before filtration
_profile2count_bf = dict()
_profile2count_af = dict()
_cas_type2count = dict()
# filter_size = 5
for kplet in kplets:
for f in kplet.files:
t.update_dictionary(_file2kplets, f, [kplet])
initial_length = len(_file2kplets)
for f in _file2kplets.keys():
[
t.update_dictionary(_kplet2count_bf, kplet.id, 1)
for kplet in _file2kplets[f]
]
del f
# if filter_weak_hits:
# _file2kplets = {k: v for (k,v) in _file2kplets.items() if len(v) > filter_size}
if len(_file2kplets) < 2: return None
_file2genes = {
f: dt.get_pty_file_generic(os.path.join(neighborhood_files_path, f))
for f in _file2kplets.keys()
}
_files = set(_file2kplets.keys())
for _f in _files:
_genes = _file2genes[_f]
_src = _genes[0].src
_org = _genes[0].organism
organisms.update([_org])
_nfs = NeighborhoodFileSummary(_f, _file2kplets[_f], _genes, _org,
_src, _org2weight[_org])
for _gene in _genes:
if _gene.gid in _gi2castype:
_nfs.cas_type = ";".join(_gi2castype[_gene.gid])
for _cas_type in _gi2castype[_gene.gid]:
t.update_dictionary(_cas_type2count, _cas_type, 1)
break
[
t.update_dictionary(_kplet2count_af, kplet.id, 1)
for kplet in _file2kplets[_f]
]
for _gene in _genes:
for _c in _gene.cogid.split(','):
t.update_dictionary(_profile2count_af, _c, 1)
file_summaries.append(_nfs)
# file_summaries = [fs for fs in file_summaries if len(fs.kplets)>1]
# _files = [fs.file_name for fs in file_summaries]
# for _f in _files:
# [t.update_dictionary(_kplet2count_af, kplet.id, 1) for kplet in _file2kplets[_f]]
#
# _gene_list = _file2genes[_f]
# for _gene in _gene_list:
# for _c in _gene.cogid.split(','):
# t.update_dictionary(_profile2count_af, _c, 1)
file_summaries.sort(key=lambda x: x.org)
retval = GenericMergingKplets2FsOutput()
retval.file_summaries = file_summaries
retval.organisms = organisms
retval.profile2count_bf = _profile2count_bf
retval.profile2count_af = _profile2count_af
retval.kplet2count_af = _kplet2count_af
retval.kplet2count_bf = _kplet2count_bf
retval.weight = sum(fs.weight for fs in file_summaries)
retval.cas_type2count = _cas_type2count
return retval
def __init__(self,
file_name,
annotation_map=None,
file_format='pty',
profile2gene=None):
self.file_name = file_name
self.base_file_name = os.path.basename(file_name)
if file_format == 'pty':
_genes = dt.get_pty_file(file_name, annotation_map=annotation_map)
else:
_genes = dt.get_pty_file_generic(file_name,
profile2gene=profile2gene)
locus_file = open(file_name)
type_line = locus_file.readline()
if type_line.startswith('#type:'):
self.crispr_type = type_line.split(':')[1].strip()
else:
self.crispr_type = None
self.summary_line = locus_file.readline()
assert self.summary_line.startswith("===")
locus_file.close()
self.genes = _genes
self.profiles = set(profile for g in _genes
for profile in g.cogid.split() if profile != '')
self.gene_names = set(gene_name for g in _genes
for gene_name in g.gene_name.split(',')
if gene_name != '')
self.clusters = set(gene.cluster_id for gene in _genes)
self.organism = _genes[0].organism
self.source = _genes[0].src
_forward = set()
_reverse = set()
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_forward.update((_cogid, ))
if i == len(self.genes) - 1:
continue
_next_gene = self.genes[i + 1]
for _next_cogid in _next_gene.cogid.split(','):
_forward.update(("%s-%s" % (_cogid, _next_cogid), ))
self.genes.sort(reverse=True)
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_reverse.update((_cogid, ))
if i == len(self.genes) - 1:
continue
_next_gene = self.genes[i + 1]
for _next_cogid in _next_gene.cogid.split(','):
_reverse.update(("%s-%s" % (_cogid, _next_cogid), ))
self.forward_set = _forward
self.reverse_set = _reverse
self.feature_weights = None
self.feature_labels = None
def __init__(self,
file_name,
annotation_map=None,
file_format='pty',
profile2gene=None):
self.file_name = file_name
self.base_file_name = os.path.basename(file_name)
self.merged_files = set([self.file_name])
self.merged_base_files = set([self.base_file_name])
if file_format == 'pty':
_genes = dt.get_pty_file(file_name,
annotation_map=annotation_map,
profile2gene=profile2gene)
else:
_genes = dt.get_pty_file_generic(file_name,
profile2gene=profile2gene)
# print "File name:", file_name, "Genes size:",len(_genes)
self.genes = _genes
self.profiles = set(profile for g in _genes
for profile in g.cogid.split(',') if profile != '')
self.gene_names = set(gene_name for g in _genes
for gene_name in g.gene_name.split(',')
if gene_name != '')
self.organism = _genes[0].organism
self.source = _genes[0].src
_forward = set()
_reverse = set()
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_forward.update((_cogid, ))
if i == len(self.genes) - 1:
continue
_next_gene = self.genes[i + 1]
for _next_cogid in _next_gene.cogid.split(','):
_forward.update(("%s-%s" % (_cogid, _next_cogid), ))
self.genes.sort(reverse=True)
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_reverse.update((_cogid, ))
if i == len(self.genes) - 1:
continue
_next_gene = self.genes[i + 1]
for _next_cogid in _next_gene.cogid.split(','):
_reverse.update(("%s-%s" % (_cogid, _next_cogid), ))
self.forward_set = _forward
self.reverse_set = _reverse
self.feature_weights = None
self.feature_labels = None
sys.path.append('/Users/hudaiber/Projects/SystemFiles/')
elif sys.platform=='linux2':
sys.path.append('/home/hudaiber/Projects/SystemFiles/')
import global_variables as gv
# sys.path.append(gv.project_code_path)
import dm_tools as dt
cas_type_file = os.path.join(gv.project_data_path, 'cas1402/cas1402.type.tab')
_gi2castype = {l.strip().split('\t')[0]: l.strip().split('\t')[1].split(';') for l in open(cas_type_file).readlines()}
files_path = os.path.join(gv.project_data_path, 'cas1402/files')
file2type = {}
for f in os.listdir(files_path):
_genes = dt.get_pty_file_generic(os.path.join(files_path, f))
for _gene in _genes:
if _gene.gid in _gi2castype:
if f in file2type:
file2type[f] += _gi2castype[_gene.gid]
else:
file2type[f] = _gi2castype[_gene.gid]
print len(file2type)
print
outf = os.path.join(gv.project_data_path, 'cas1402/file2type.tab')
with open(outf,'w') as of:
for file, cas_type in file2type.items():
of.write("%s\t%s\n" % (file, ";".join(cas_type)))
def __init__(self, file_name, annotation_map=None, file_format='pty', profile2gene=None):
self.file_name = file_name
self.base_file_name = os.path.basename(file_name)
if file_format=='pty':
_genes = dt.get_pty_file(file_name, annotation_map=annotation_map)
else:
_genes = dt.get_pty_file_generic(file_name, profile2gene=profile2gene)
locus_file = open(file_name)
type_line = locus_file.readline()
if type_line.startswith('#type:'):
self.crispr_type = type_line.split(':')[1].strip()
else:
self.crispr_type = None
self.summary_line = locus_file.readline()
assert self.summary_line.startswith("===")
locus_file.close()
self.genes = _genes
self.profiles = set(profile for g in _genes for profile in g.cogid.split() if profile != '')
self.gene_names = set(gene_name for g in _genes for gene_name in g.gene_name.split(',') if gene_name != '')
self.clusters = set(gene.cluster_id for gene in _genes)
self.organism = _genes[0].organism
self.source = _genes[0].src
_forward = set()
_reverse = set()
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_forward.update((_cogid,))
if i == len(self.genes)-1:
continue
_next_gene = self.genes[i+1]
for _next_cogid in _next_gene.cogid.split(','):
_forward.update(("%s-%s" % (_cogid, _next_cogid),))
self.genes.sort(reverse=True)
for i in range(len(self.genes)):
_gene = self.genes[i]
for _cogid in _gene.cogid.split(','):
_reverse.update((_cogid,))
if i == len(self.genes)-1:
continue
_next_gene = self.genes[i+1]
for _next_cogid in _next_gene.cogid.split(','):
_reverse.update(("%s-%s" % (_cogid, _next_cogid),))
self.forward_set = _forward
self.reverse_set = _reverse
self.feature_weights = None
self.feature_labels = None