Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
C
CNAprioritization
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Operations
Operations
Incidents
Environments
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Beatrice Tan
CNAprioritization
Commits
690098a6
Commit
690098a6
authored
Feb 02, 2018
by
Tan
Browse files
Options
Browse Files
Download
Plain Diff
Updated config.
parents
33550014
2d3389cc
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
38 additions
and
15 deletions
+38
-15
config.yaml
config.yaml
+3
-0
scripts/ParseResults.py
scripts/ParseResults.py
+35
-15
No files found.
config.yaml
View file @
690098a6
...
...
@@ -2,6 +2,9 @@
workdir
:
/home/bftan/CNA_results
#directory to write output
gisticdir
:
/home/bftan/Tools/GISTIC2_test
#directory to install GISTIC2
#workdir: /home/bftan/CNA_results #directory to write output
#gisticdir: /home/bftan/Tools/GISTIC2 #directory to install GISTIC2
#workdir: /home/beatrice/CNA_analysis
#gisticdir: /home/beatrice/CNA_analysis/run_gistic2
...
...
scripts/ParseResults.py
View file @
690098a6
...
...
@@ -46,13 +46,30 @@ def parse_gistic_results(results_file, known_genes, census_genes):
start
,
end
=
bp
.
split
(
"-"
)
cnv_type
=
'amp'
if
stats
[
0
].
startswith
(
"Amplification"
)
else
'del'
qval
=
log10
(
float
(
stats
[
5
]))
*
-
1
#Convert q-value to log10(q-value)
list_genes
=
genes_locus
(
chrom
,
int
(
start
),
int
(
end
))
#list_genes = genes_locus(chrom, int(start), int(end))
result_dir
,
conf
=
results_file
.
split
(
"all_lesions"
)
gene_file
=
os
.
path
.
join
(
result_dir
,
cnv_type
+
"_genes"
+
conf
)
list_genes
=
gistic_genes
(
gene_file
,
CNV_id
)
known_overlap
=
set
(
list_genes
).
intersection
(
set
(
known_genes
))
census_overlap
=
set
(
list_genes
).
intersection
(
set
(
census_genes
))
cnv_data
=
[
chrom
,
start
,
end
,
cnv_type
,
qval
,
list
(
known_overlap
),
list
(
census_overlap
),
list_genes
]
regions
.
append
(
cnv_data
)
return
regions
def
gistic_genes
(
gene_file
,
CNV_id
):
"""Extract list of genes for a given recurrent CNV from GISTIC2 output."""
out_genes
=
[]
with
open
(
gene_file
,
'r'
)
as
genes
:
for
i
in
range
(
3
):
genes
.
readline
()
column_CNV
=
genes
.
readline
().
split
(
"
\t
"
).
index
(
CNV_id
)
for
line
in
genes
:
if
len
(
line
.
split
(
"
\t
"
))
>=
column_CNV
:
gene
=
line
.
split
(
"
\t
"
)[
column_CNV
]
if
gene
!=
''
:
out_genes
.
append
(
gene
)
return
out_genes
def
parse_rubic_results
(
results_gains
,
results_losses
,
known_genes
,
census_genes
):
"""Create a list of lists with the recurrent regions called by GISTIC2."""
regions
=
[]
...
...
@@ -63,21 +80,23 @@ def parse_rubic_results(results_gains, results_losses, known_genes, census_genes
chrom
,
start
,
end
,
qval_left
,
qval_right
,
genes
=
lesion
.
split
(
"
\t
"
)
CNV_id
=
"chr"
+
chrom
+
":"
+
start
+
"-"
+
end
cnv_type
=
'amp'
if
result_file
.
endswith
(
'gains.txt'
)
else
'del'
list_genes
=
genes_locus
(
chrom
,
int
(
start
),
int
(
end
))
#list_genes = genes_locus(chrom, int(start), int(end))
list_genes
=
genes
.
strip
().
split
(
","
)
print
(
list_genes
)
known_overlap
=
set
(
list_genes
).
intersection
(
set
(
known_genes
))
census_overlap
=
set
(
list_genes
).
intersection
(
set
(
census_genes
))
cnv_data
=
[
chrom
,
start
,
end
,
cnv_type
,
(
qval_left
,
qval_right
),
list
(
known_overlap
),
list
(
census_overlap
),
list_genes
]
regions
.
append
(
cnv_data
)
return
regions
def
genes_locus
(
chrom
,
start
,
end
):
"""Get list of gene IDs at certain location."""
IDs
=
[]
gene_info
=
ensembl
.
genes_at_locus
(
chrom
,
start
,
end
)
for
gene
in
gene_info
:
ID
=
gene
.
gene_id
IDs
.
append
(
ID
)
return
IDs
#
def genes_locus(chrom, start, end):
#
"""Get list of gene IDs at certain location."""
#
IDs = []
#
gene_info = ensembl.genes_at_locus(chrom, start, end)
#
for gene in gene_info:
#
ID = gene.gene_id
#
IDs.append(ID)
#
return IDs
def
gene_file_IDs
(
gene_file
,
top_nr
):
"""Parse a file with a list of genes (one gene per line or first column).
...
...
@@ -90,11 +109,12 @@ def gene_file_IDs(gene_file, top_nr):
continue
else
:
gene
=
line
.
split
(
"
\t
"
)[
0
]
try
:
gene_ID
=
ensembl
.
gene_ids_of_gene_name
(
gene
)
list_genes
=
list_genes
+
gene_ID
except
:
pass
list_genes
.
append
(
gene
)
#try:
# gene_ID = ensembl.gene_ids_of_gene_name(gene)
# list_genes = list_genes + gene_ID
#except:
# pass
if
top_nr
!=
np
.
inf
:
list_genes
=
list_genes
[
0
:
top_nr
]
return
list_genes
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment