def load_objects(self, is_bedgraph, verbose=False):
"""Load files and initialize object"""
for i, t in enumerate(self.types):
if verbose:
print("Loading file ",
self.files[self.names[i]],
file=sys.stderr)
if t not in ["regions", "genes"] and verbose:
print("Cannot load objects", file=sys.stderr)
if t == "regions":
regions = GenomicRegionSet(self.names[i])
if is_bedgraph:
regions.read_bedgraph(
os.path.abspath(self.files[self.names[i]]))
else:
regions.read_bed(
os.path.abspath(self.files[self.names[i]])
) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = regions
elif t == "genes":
genes = GeneSet(self.names[i])
genes.read(
os.path.abspath(self.files[self.names[i]])
) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = genes
def load_objects(self, is_bedgraph, verbose=False, test=False):
"""Load files and initialize object.
*Keyword arguments:*
- is_bedgraph -- Whether regions are in bedgraph format (default = False).
- verbose -- Verbose output (default = False).
- test -- Fetch only 10 regions form each BED files for test.
"""
for i, t in enumerate(self.types):
if verbose:
print("Loading file ",
self.files[self.names[i]],
file=sys.stderr)
if t not in ["regions", "genes"] and verbose:
print("Cannot load objects", file=sys.stderr)
if t == "regions":
regions = GenomicRegionSet(self.names[i])
if is_bedgraph:
regions.read_bedgraph(
os.path.abspath(self.files[self.names[i]]))
else:
regions.read_bed(os.path.abspath(
self.files[self.names[i]]))
if test: regions.sequences = regions.sequences[0:11]
self.objectsDict[self.names[i]] = regions
elif t == "genes":
genes = GeneSet(self.names[i])
genes.read(
os.path.abspath(self.files[self.names[i]])
) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = genes
def load_objects(self, is_bedgraph, verbose=False, test=False):
"""Load files and initialize object.
*Keyword arguments:*
- is_bedgraph -- Whether regions are in bedgraph format (default = False).
- verbose -- Verbose output (default = False).
- test -- Fetch only 10 regions form each BED files for test.
"""
for i, t in enumerate(self.types):
if verbose: print("Loading file ", self.files[self.names[i]], file = sys.stderr)
if t not in ["regions", "genes"] and verbose:
print("Cannot load objects", file=sys.stderr)
if t == "regions":
regions = GenomicRegionSet(self.names[i])
if is_bedgraph:
regions.read_bedgraph(os.path.abspath(self.files[self.names[i]]))
else:
if test:
g = GenomicRegionSet(self.names[i])
g.read_bed(os.path.abspath(self.files[self.names[i]]))
regions.sequences = g.sequences[0:11]
else:
regions.read_bed(os.path.abspath(self.files[self.names[i]])) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = regions
elif t == "genes":
genes = GeneSet(self.names[i])
genes.read(os.path.abspath(self.files[self.names[i]])) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = genes
args = parser.parse_args()
if os.path.isfile(args.i):
print()
for switch in [True, False]:
print("HAVANA filter:\t\t"+str(switch))
print("protein_coding filter:\t"+"True")
print("known_only filter:\t"+"True")
ann = AnnotationSet(args.organism, alias_source=args.organism,
filter_havana=switch,
protein_coding=True,
known_only=True)
genes = GeneSet("genes")
genes.read(args.i)
print("\tInput gene number: \t"+str(len(genes)))
print("\tFixing the names into Ensembl ID:")
de_ensembl, unmap_gs, ensembl2symbol = ann.fix_gene_names(gene_set=genes, output_dict=True, mute_warn=True)
print("\t\tMapped:\t\t"+str(len(de_ensembl)))
print("\t\tUnmapped:\t"+str(len(unmap_gs)))
genes.genes = de_ensembl
de_prom, unmapped_gene_list = ann.get_promoters(promoter_length=1000,
gene_set=genes,
unmaplist=True)
print("\tGetting promoters:")
print("\t\tMapped:\t\t"+str(len(de_prom)))
print("\t\tUnmapped:\t"+str(len(unmapped_gene_list)))
outputdir = args[3]
# experimental_matrix_file = "/home/manuel/workspace/cluster_p/THOR/exp/exp23_macs2_payton/1"
# gene_exp = "/home/manuel/workspace/cluster_p/allhoff/project_THOR/data/payton/gene_expression/CCmean.data"
# annotation_path = "/home/manuel/workspace/cluster_h/rgtdata/hg19/"
# outputdir = "/home/manuel/test/"
exps = ExperimentalMatrix()
exps.read(experimental_matrix_file)
regionsets = exps.get_regionsets()
genome_file = annotation_path + "/chrom.sizes"
gene_file = annotation_path + "/association_file.bed"
genes = GeneSet("Expression")
genes.read_expression(gene_exp)
for region in regionsets:
bedNew = GenomicRegionSet("")
[degenes, de_peak_genes, mappedGenes, totalPeaks, regionsToGenes] \
= bedNew.filter_by_gene_association_old(region.fileName, genes.genes, gene_file, genome_file)
[ct, labels] = averageExpression(region, genes, regionsToGenes)
aux = region.fileName.split("/")
fileName = aux[-1]
fileName = fileName.split(".")
output(genes.cond, labels, ct, outputdir + "/" + fileName[0] + ".txt")
annotation_path = args[2]
outputdir = args[3]
# experimental_matrix_file = "/home/manuel/workspace/cluster_p/THOR/exp/exp23_macs2_payton/1"
# gene_exp = "/home/manuel/workspace/cluster_p/allhoff/project_THOR/data/payton/gene_expression/CCmean.data"
# annotation_path = "/home/manuel/workspace/cluster_h/rgtdata/hg19/"
# outputdir = "/home/manuel/test/"
exps = ExperimentalMatrix()
exps.read(experimental_matrix_file)
regionsets = exps.get_regionsets()
genome_file = annotation_path + "/chrom.sizes"
gene_file = annotation_path + "/association_file.bed"
genes = GeneSet("Expression")
genes.read_expression(gene_exp)
for region in regionsets:
bedNew = GenomicRegionSet("")
[degenes, de_peak_genes, mappedGenes, totalPeaks, regionsToGenes] \
= bedNew.filter_by_gene_association_old(region.fileName, genes.genes, gene_file, genome_file, threshDist=options.dist)
[ct, labels] = averageExpression(region, genes, regionsToGenes)
fileName = path.splitext(path.basename(region.fileName))[0]
output(genes.cond, labels, ct, path.join(outputdir, fileName + ".txt"))
args = parser.parse_args()
if os.path.isfile(args.i):
print()
for switch in [True, False]:
print("HAVANA filter:\t\t"+str(switch))
print("protein_coding filter:\t"+"True")
print("known_only filter:\t"+"True")
ann = AnnotationSet(args.organism, alias_source=args.organism,
filter_havana=switch,
protein_coding=True,
known_only=True)
genes = GeneSet("genes")
genes.read(args.i)
print("\tInput gene number: \t"+str(len(genes)))
print("\tFixing the names into Ensembl ID:")
de_ensembl, unmap_gs, ensembl2symbol = ann.fix_gene_names(gene_set=genes, output_dict=True, mute_warn=True)
print("\t\tMapped:\t\t"+str(len(de_ensembl)))
print("\t\tUnmapped:\t"+str(len(unmap_gs)))
genes.genes = de_ensembl
de_prom, unmapped_gene_list = ann.get_promoters(promoter_length=1000,
gene_set=genes,
unmaplist=True)
print("\tGetting promoters:")
print("\t\tMapped:\t\t"+str(len(de_prom)))
print("\t\tUnmapped:\t"+str(len(unmapped_gene_list)))