Skip to content

Fix genetic_relatedness to allow single sample set with self-comparisons #3235

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

Merged
merged 1 commit into from
Sep 16, 2025
Merged

Fix genetic_relatedness to allow single sample set with self-comparisons #3235

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 1 addition & 19 deletions c/tests/test_stats.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -881,9 +881,6 @@ verify_two_way_stat_func_errors(
ret = method(ts, 0, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
options | TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
ret = method(ts, 1, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
options | TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);

ret = method(ts, 2, sample_set_sizes, samples, 0, set_indexes, 0, NULL,
options | TSK_STAT_SITE, &result);
Expand Down Expand Up @@ -938,12 +935,6 @@ verify_three_way_stat_func_errors(tsk_treeseq_t *ts, general_sample_stat_method
ret = method(ts, 0, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
ret = method(ts, 1, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
ret = method(ts, 2, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);

ret = method(ts, 3, sample_set_sizes, samples, 0, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
Expand Down Expand Up @@ -972,15 +963,6 @@ verify_four_way_stat_func_errors(tsk_treeseq_t *ts, general_sample_stat_method *
ret = method(ts, 0, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
ret = method(ts, 1, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
ret = method(ts, 2, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
ret = method(ts, 3, sample_set_sizes, samples, 1, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_SAMPLE_SETS);

ret = method(ts, 4, sample_set_sizes, samples, 0, set_indexes, 0, NULL,
TSK_STAT_SITE, &result);
Expand Down Expand Up @@ -3684,7 +3666,7 @@ test_two_locus_stat_input_errors(void)
NULL, 0, result);
CU_ASSERT_EQUAL_FATAL(ret, TSK_ERR_INSUFFICIENT_INDEX_TUPLES);

num_sample_sets = 1;
num_sample_sets = 0;
num_index_tuples = 1;
ret = tsk_treeseq_D2_ij(&ts, num_sample_sets, sample_set_sizes, sample_sets,
num_index_tuples, index_tuples, num_sites, row_sites, NULL, num_sites, col_sites,
Expand Down
2 changes: 1 addition & 1 deletion c/tskit/trees.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4515,7 +4515,7 @@ check_sample_stat_inputs(tsk_size_t num_sample_sets, tsk_size_t tuple_size,
{
int ret = 0;

if (num_sample_sets < tuple_size) {
if (num_sample_sets < 1) {
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe add a comment here to explain the check?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It seems pretty self-explanatory to me? Like, how can you compute a statistic with only one sample set? (The comment would be something like // check there is at least one sample set, but we like to avoid this sort of comment that just says the same thing as the code?)

ret = tsk_trace_error(TSK_ERR_INSUFFICIENT_SAMPLE_SETS);
goto out;
}
Expand Down
6 changes: 6 additions & 0 deletions python/CHANGELOG.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,12 @@
when using ``TableCollection.assert_equals`` and ``Table.assert_equals``.
(:user:`benjeffery`, :pr:`3246`, :issue:`3244`)

- k-way statistics no longer require k sample sets, allowing in particular
"self" comparisons for `TreeSequence.genetic_relatedness`. This changes the
error code returned in some situations.
(:user:`andrewkern`, :user:`petrelharp`, :pr:`3235`, :issue:`3055`)


**Breaking changes**

- ``ltrim``, ``rtrim``, ``trim`` and ``shift`` raise an error if used on a tree sequence
Expand Down
8 changes: 2 additions & 6 deletions python/tests/test_lowlevel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1871,17 +1871,13 @@ def test_ld_matrix_multipop(self, stat_method_name):
stat_method(
bad_ss_sizes, bad_ss, indexes, None, None, row_pos, col_pos, "branch"
)
with pytest.raises(
_tskit.LibraryError, match="TSK_ERR_INSUFFICIENT_SAMPLE_SETS"
):
with pytest.raises(_tskit.LibraryError, match="TSK_ERR_BAD_SAMPLE_SET_INDEX"):
bad_ss = np.array([], dtype=np.int32)
bad_ss_sizes = np.array([0], dtype=np.uint32)
stat_method(
bad_ss_sizes, bad_ss, indexes, row_sites, col_sites, None, None, "site"
)
with pytest.raises(
_tskit.LibraryError, match="TSK_ERR_INSUFFICIENT_SAMPLE_SETS"
):
with pytest.raises(_tskit.LibraryError, match="TSK_ERR_BAD_SAMPLE_SET_INDEX"):
bad_ss = np.array([], dtype=np.int32)
bad_ss_sizes = np.array([0], dtype=np.uint32)
stat_method(
Expand Down
40 changes: 40 additions & 0 deletions python/tests/test_tree_stats.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2307,6 +2307,46 @@ def test_shapes(self, proportion):
else:
assert x.shape == (2,)

def test_single_sample_set_self_comparison(self, ts_12_highrecomb_fixture):
if self.mode is None:
return
# Test for issue #3055 - self-comparisons with single sample set
ts = ts_12_highrecomb_fixture
# Single sample set with self-comparison
result = ts.genetic_relatedness([[0]], indexes=[(0, 0)], mode=self.mode)
result_shape = (ts.num_nodes, 1) if self.mode == "node" else (1,)
assert result.shape == result_shape
# Should work for multiple samples in single set too
result = ts.genetic_relatedness([[0, 1, 2]], indexes=[(0, 0)], mode=self.mode)
assert result.shape == result_shape
# Test with multiple self-comparisons
result = ts.genetic_relatedness(
[[0, 1], [2, 3]], indexes=[(0, 0), (1, 1)], mode=self.mode
)
result_shape = (ts.num_nodes, 2) if self.mode == "node" else (2,)
assert result.shape == result_shape

def test_single_sample_set_invalid_indexes(self, ts_12_highrecomb_fixture):
if self.mode is None:
return
# Test that invalid indexes raise ValueError with single sample set
ts = ts_12_highrecomb_fixture
# Index out of bounds (only have 1 sample set, but trying to access index 1)
with pytest.raises(
exceptions.LibraryError, match="TSK_ERR_BAD_SAMPLE_SET_INDEX"
):
ts.genetic_relatedness([[0]], indexes=[(0, 1)], mode=self.mode)
# Negative index
with pytest.raises(
exceptions.LibraryError, match="TSK_ERR_BAD_SAMPLE_SET_INDEX"
):
ts.genetic_relatedness([[0]], indexes=[(-1, 0)], mode=self.mode)
# Both indexes out of bounds
with pytest.raises(
exceptions.LibraryError, match="TSK_ERR_BAD_SAMPLE_SET_INDEX"
):
ts.genetic_relatedness([[0, 1]], indexes=[(2, 2)], mode=self.mode)


class TestBranchGeneticRelatedness(TestGeneticRelatedness, TopologyExamplesMixin):
mode = "branch"
Expand Down
Loading