Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

enable np.array input #7

Closed
wants to merge 4 commits into from
Closed

enable np.array input #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7da8065
modify HaplotypeAlignment class to take np.array input
sanjaynagi Mar 11, 2023
4acd3dd
change input parameter to avoid confusion
sanjaynagi Mar 13, 2023
0567a79
add test
sanjaynagi Mar 13, 2023
3208ddb
run CI on push on all branches
sanjaynagi Mar 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 1 addition & 5 deletions .github/workflows/build.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,7 @@

name: build

on:
push:
branches: [ master ]
pull_request:
branches: [ master ]
on: [push]

jobs:
build:
Expand Down
31 changes: 20 additions & 11 deletions phasedibd/haplotype_alignment.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,19 +10,28 @@ cdef class HaplotypeAlignment:
Contains test data.
"""

def __init__(self):
def __init__(self, haplotype_array=None, chromosomes=None):

self.chromosomes = ['1']
self.current_chromosome = ''
self.haplotypes = [[0, 1, 0, 1, 0, 1],
[1, 1, 2, 0, 0, 1], # 2 represents missing/invalid allele
[1, 1, 1, 1, 1, 1],
[0, 1, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 1, 0],
[1, 1, 0, 0, 0, 1],
[0, 1, 0, 1, 1, 0]]
if haplotype_array is None:
# use test data
self.haplotypes = [[0, 1, 0, 1, 0, 1],
[1, 1, 2, 0, 0, 1], # 2 represents missing/invalid allele
[1, 1, 1, 1, 1, 1],
[0, 1, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 1, 0],
[1, 1, 0, 0, 0, 1],
[0, 1, 0, 1, 1, 0]]
else:
self.haplotypes = haplotype_array

if chromosomes is None:
self.chromosomes = ['1']
else:
self.chromosomes = chromosomes

self.current_chromosome = ''

self.num_all_haplotypes = len(self.haplotypes)
self.num_active_haplotypes = len(self.haplotypes)
self.num_sites = len(self.haplotypes[0])
Expand Down
29 changes: 29 additions & 0 deletions tests/unit_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,35 @@ def test_PBWT_default_haplotypes(self):
#print(ibd_segs)
#print(true_segs)
self.assertTrue(np.all(ibd_segs.eq(true_segs)))

def test_PBWT_default_haplotypes_np_array_input(self):
print("\nTesting non-templated PBWT matches over default haplotypes...")
haplotype_array = np.array([[0, 1, 0, 1, 0, 1],
[1, 1, 2, 0, 0, 1], # 2 represents missing/invalid allele
[1, 1, 1, 1, 1, 1],
[0, 1, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 1, 0],
[1, 1, 0, 0, 0, 1],
[0, 1, 0, 1, 1, 0]])

haplotypes = ibd.HaplotypeAlignment(haplotype_array=haplotype_array)
tpbwt = ibd.TPBWTAnalysis(template=[[1]])
ibd_segs = tpbwt.compute_ibd(haplotypes, L_m=3, L_f=0, missing_site_threshold=1, verbose=False)
true_segs = pd.DataFrame({'chromosome': ['1'] * 3,
'start': [0,0,1],
'end': [3,5,4],
'start_cm': [0,0,1],
'end_cm': [3,5,4],
'start_bp': [0,0,1],
'end_bp': [3,5,4],
'id1': [0,1,2],
'id2': [7,6,3],
'id1_haplotype': [0,0,0],
'id2_haplotype': [0,0,0]})
#print(ibd_segs)
#print(true_segs)
self.assertTrue(np.all(ibd_segs.eq(true_segs)))


def test_vcf_no_map(self):
Expand Down