def pc_project(call_expr, loadings_expr, af_expr):
"""Projects genotypes onto pre-computed PCs. Requires loadings and
allele-frequency from a reference dataset (see example). Note that
`loadings_expr` must have no missing data and reflect the rows
from the original PCA run for this method to be accurate.
Example
-------
>>> # Compute loadings and allele frequency for reference dataset
>>> _, _, loadings_ht = hl.hwe_normalized_pca(mt.GT, k=10, compute_loadings=True) # doctest: +SKIP
>>> mt = mt.annotate_rows(af=hl.agg.mean(mt.GT.n_alt_alleles()) / 2) # doctest: +SKIP
>>> loadings_ht = loadings_ht.annotate(af=mt.rows()[loadings_ht.key].af) # doctest: +SKIP
>>> # Project new genotypes onto loadings
>>> ht = pc_project(mt_to_project.GT, loadings_ht.loadings, loadings_ht.af) # doctest: +SKIP
Parameters
----------
call_expr : :class:`.CallExpression`
Entry-indexed call expression for genotypes
to project onto loadings.
loadings_expr : :class:`.ArrayNumericExpression`
Location of expression for loadings
af_expr : :class:`.Float64Expression`
Location of expression for allele frequency
Returns
-------
:class:`.Table`
Table with scores calculated from loadings in column `scores`
"""
check_entry_indexed('pc_project', call_expr)
check_row_indexed('pc_project', loadings_expr)
check_row_indexed('pc_project', af_expr)
gt_source = call_expr._indices.source
loadings_source = loadings_expr._indices.source
af_source = af_expr._indices.source
loadings_expr = _get_expr_or_join(loadings_expr, loadings_source, gt_source, '_loadings')
af_expr = _get_expr_or_join(af_expr, af_source, gt_source, '_af')
mt = gt_source._annotate_all(row_exprs={'_loadings': loadings_expr, '_af': af_expr},
entry_exprs={'_call': call_expr})
if isinstance(loadings_source, hl.MatrixTable):
n_variants = loadings_source.count_rows()
else:
n_variants = loadings_source.count()
mt = mt.filter_rows(hl.is_defined(mt._loadings) & hl.is_defined(mt._af) & (mt._af > 0) & (mt._af < 1))
gt_norm = (mt._call.n_alt_alleles() - 2 * mt._af) / hl.sqrt(n_variants * 2 * mt._af * (1 - mt._af))
return mt.select_cols(scores=hl.agg.array_sum(mt._loadings * gt_norm)).cols()
def locus_windows(locus_expr, radius, coord_expr=None, _localize=True):
"""Returns start and stop indices for window around each locus.
Examples
--------
Windows with 2bp radius for one contig with positions 1, 2, 3, 4, 5:
>>> starts, stops = hl.linalg.utils.locus_windows(
... hl.balding_nichols_model(1, 5, 5).locus,
... radius=2)
>>> starts, stops
(array([0, 0, 0, 1, 2]), array([3, 4, 5, 5, 5]))
The following examples involve three contigs.
>>> loci = [{'locus': hl.Locus('1', 1), 'cm': 1.0},
... {'locus': hl.Locus('1', 2), 'cm': 3.0},
... {'locus': hl.Locus('1', 4), 'cm': 4.0},
... {'locus': hl.Locus('2', 1), 'cm': 2.0},
... {'locus': hl.Locus('2', 1), 'cm': 2.0},
... {'locus': hl.Locus('3', 3), 'cm': 5.0}]
>>> ht = hl.Table.parallelize(
... loci,
... hl.tstruct(locus=hl.tlocus('GRCh37'), cm=hl.tfloat64),
... key=['locus'])
Windows with 1bp radius:
>>> hl.linalg.utils.locus_windows(ht.locus, 1)
(array([0, 0, 2, 3, 3, 5]), array([2, 2, 3, 5, 5, 6]))
Windows with 1cm radius:
>>> hl.linalg.utils.locus_windows(ht.locus, 1.0, coord_expr=ht.cm)
(array([0, 1, 1, 3, 3, 5]), array([1, 3, 3, 5, 5, 6]))
Notes
-----
This function returns two 1-dimensional ndarrays of integers,
``starts`` and ``stops``, each of size equal to the number of rows.
By default, for all indices ``i``, ``[starts[i], stops[i])`` is the maximal
range of row indices ``j`` such that ``contig[i] == contig[j]`` and
``position[i] - radius <= position[j] <= position[i] + radius``.
If the :meth:`.global_position` on `locus_expr` is not in ascending order,
this method will fail. Ascending order should hold for a matrix table keyed
by locus or variant (and the associated row table), or for a table that has
been ordered by `locus_expr`.
Set `coord_expr` to use a value other than position to define the windows.
This row-indexed numeric expression must be non-missing, non-``nan``, on the
same source as `locus_expr`, and ascending with respect to locus
position for each contig; otherwise the function will fail.
The last example above uses centimorgan coordinates, so
``[starts[i], stops[i])`` is the maximal range of row indices ``j`` such
that ``contig[i] == contig[j]`` and
``cm[i] - radius <= cm[j] <= cm[i] + radius``.
Index ranges are start-inclusive and stop-exclusive. This function is
especially useful in conjunction with
:meth:`.BlockMatrix.sparsify_row_intervals`.
Parameters
----------
locus_expr : :class:`.LocusExpression`
Row-indexed locus expression on a table or matrix table.
radius: :obj:`int`
Radius of window for row values.
coord_expr: :class:`.Float64Expression`, optional
Row-indexed numeric expression for the row value.
Must be on the same table or matrix table as `locus_expr`.
By default, the row value is given by the locus position.
Returns
-------
(:class:`ndarray` of :obj:`int64`, :class:`ndarray` of :obj:`int64`)
Tuple of start indices array and stop indices array.
"""
if radius < 0:
raise ValueError(f"locus_windows: 'radius' must be non-negative, found {radius}")
check_row_indexed('locus_windows', locus_expr)
if coord_expr is not None:
check_row_indexed('locus_windows', coord_expr)
src = locus_expr._indices.source
if locus_expr not in src._fields_inverse:
locus = Env.get_uid()
annotate_fields = {locus: locus_expr}
if coord_expr is not None:
if coord_expr not in src._fields_inverse:
coords = Env.get_uid()
annotate_fields[coords] = coord_expr
else:
coords = src._fields_inverse[coord_expr]
if isinstance(src, hl.MatrixTable):
new_src = src.annotate_rows(**annotate_fields)
else:
new_src = src.annotate(**annotate_fields)
locus_expr = new_src[locus]
if coord_expr is not None:
coord_expr = new_src[coords]
if coord_expr is None:
coord_expr = locus_expr.position
rg = locus_expr.dtype.reference_genome
contig_group_expr = hl.agg.group_by(hl.locus(locus_expr.contig, 1, reference_genome=rg), hl.agg.collect(coord_expr))
# check loci are in sorted order
last_pos = hl.fold(lambda a, elt: (hl.case()
.when(a <= elt, elt)
.or_error("locus_windows: 'locus_expr' global position must be in ascending order.")),
-1,
hl.agg.collect(hl.case()
.when(hl.is_defined(locus_expr), locus_expr.global_position())
.or_error("locus_windows: missing value for 'locus_expr'.")))
checked_contig_groups = (hl.case()
.when(last_pos >= 0, contig_group_expr)
.or_error("locus_windows: 'locus_expr' has length 0"))
contig_groups = locus_expr._aggregation_method()(checked_contig_groups, _localize=False)
coords = hl.sorted(hl.array(contig_groups)).map(lambda t: t[1])
starts_and_stops = hl._locus_windows_per_contig(coords, radius)
if not _localize:
return starts_and_stops
starts, stops = hl.eval(starts_and_stops)
return np.array(starts), np.array(stops)
def locus_windows(locus_expr, radius, coord_expr=None, _localize=True):
"""Returns start and stop indices for window around each locus.
Examples
--------
Windows with 2bp radius for one contig with positions 1, 2, 3, 4, 5:
>>> starts, stops = hl.linalg.utils.locus_windows(
... hl.balding_nichols_model(1, 5, 5).locus,
... radius=2)
>>> starts, stops
(array([0, 0, 0, 1, 2]), array([3, 4, 5, 5, 5]))
The following examples involve three contigs.
>>> loci = [{'locus': hl.Locus('1', 1), 'cm': 1.0},
... {'locus': hl.Locus('1', 2), 'cm': 3.0},
... {'locus': hl.Locus('1', 4), 'cm': 4.0},
... {'locus': hl.Locus('2', 1), 'cm': 2.0},
... {'locus': hl.Locus('2', 1), 'cm': 2.0},
... {'locus': hl.Locus('3', 3), 'cm': 5.0}]
>>> ht = hl.Table.parallelize(
... loci,
... hl.tstruct(locus=hl.tlocus('GRCh37'), cm=hl.tfloat64),
... key=['locus'])
Windows with 1bp radius:
>>> hl.linalg.utils.locus_windows(ht.locus, 1)
(array([0, 0, 2, 3, 3, 5]), array([2, 2, 3, 5, 5, 6]))
Windows with 1cm radius:
>>> hl.linalg.utils.locus_windows(ht.locus, 1.0, coord_expr=ht.cm)
(array([0, 1, 1, 3, 3, 5]), array([1, 3, 3, 5, 5, 6]))
Notes
-----
This function returns two 1-dimensional ndarrays of integers,
``starts`` and ``stops``, each of size equal to the number of rows.
By default, for all indices ``i``, ``[starts[i], stops[i])`` is the maximal
range of row indices ``j`` such that ``contig[i] == contig[j]`` and
``position[i] - radius <= position[j] <= position[i] + radius``.
If the :meth:`.global_position` on `locus_expr` is not in ascending order,
this method will fail. Ascending order should hold for a matrix table keyed
by locus or variant (and the associated row table), or for a table that has
been ordered by `locus_expr`.
Set `coord_expr` to use a value other than position to define the windows.
This row-indexed numeric expression must be non-missing, non-``nan``, on the
same source as `locus_expr`, and ascending with respect to locus
position for each contig; otherwise the function will fail.
The last example above uses centimorgan coordinates, so
``[starts[i], stops[i])`` is the maximal range of row indices ``j`` such
that ``contig[i] == contig[j]`` and
``cm[i] - radius <= cm[j] <= cm[i] + radius``.
Index ranges are start-inclusive and stop-exclusive. This function is
especially useful in conjunction with
:meth:`.BlockMatrix.sparsify_row_intervals`.
Parameters
----------
locus_expr : :class:`.LocusExpression`
Row-indexed locus expression on a table or matrix table.
radius: :obj:`int`
Radius of window for row values.
coord_expr: :class:`.Float64Expression`, optional
Row-indexed numeric expression for the row value.
Must be on the same table or matrix table as `locus_expr`.
By default, the row value is given by the locus position.
Returns
-------
(:class:`ndarray` of :obj:`int64`, :class:`ndarray` of :obj:`int64`)
Tuple of start indices array and stop indices array.
"""
if radius < 0:
raise ValueError(f"locus_windows: 'radius' must be non-negative, found {radius}")
check_row_indexed('locus_windows', locus_expr)
if coord_expr is not None:
check_row_indexed('locus_windows', coord_expr)
src = locus_expr._indices.source
if locus_expr not in src._fields_inverse:
locus = Env.get_uid()
annotate_fields = {locus: locus_expr}
if coord_expr is not None:
if coord_expr not in src._fields_inverse:
coords = Env.get_uid()
annotate_fields[coords] = coord_expr
else:
coords = src._fields_inverse[coord_expr]
if isinstance(src, hl.MatrixTable):
new_src = src.annotate_rows(**annotate_fields)
else:
new_src = src.annotate(**annotate_fields)
locus_expr = new_src[locus]
if coord_expr is not None:
coord_expr = new_src[coords]
if coord_expr is None:
coord_expr = locus_expr.position
rg = locus_expr.dtype.reference_genome
contig_group_expr = hl.agg.group_by(hl.locus(locus_expr.contig, 1, reference_genome=rg), hl.agg.collect(coord_expr))
# check loci are in sorted order
last_pos = hl.fold(lambda a, elt: (hl.case()
.when(a <= elt, elt)
.or_error("locus_windows: 'locus_expr' global position must be in ascending order.")),
-1,
hl.agg.collect(hl.case()
.when(hl.is_defined(locus_expr), locus_expr.global_position())
.or_error("locus_windows: missing value for 'locus_expr'.")))
checked_contig_groups = (hl.case()
.when(last_pos >= 0, contig_group_expr)
.or_error("locus_windows: 'locus_expr' has length 0"))
contig_groups = locus_expr._aggregation_method()(checked_contig_groups, _localize=False)
coords = hl.sorted(hl.array(contig_groups)).map(lambda t: t[1])
starts_and_stops = hl._locus_windows_per_contig(coords, radius)
if not _localize:
return starts_and_stops
starts, stops = hl.eval(starts_and_stops)
return np.array(starts), np.array(stops)
def locus_windows(locus_expr, radius, coord_expr=None):
"""Returns start and stop indices for window around each locus.
Examples
--------
Windows with 2bp radius for one contig with positions 1, 2, 3, 4, 5:
>>> starts, stops = hl.linalg.utils.locus_windows(
... hl.balding_nichols_model(1, 5, 5).locus,
... radius=2)
>>> starts, stops
(array([0, 0, 0, 1, 2]), array([3, 4, 5, 5, 5]))
The following examples involve three contigs.
>>> loci = [{'locus': hl.Locus('1', 1), 'cm': 1.0},
... {'locus': hl.Locus('1', 2), 'cm': 3.0},
... {'locus': hl.Locus('1', 4), 'cm': 4.0},
... {'locus': hl.Locus('2', 1), 'cm': 2.0},
... {'locus': hl.Locus('2', 1), 'cm': 2.0},
... {'locus': hl.Locus('3', 3), 'cm': 5.0}]
>>> ht = hl.Table.parallelize(
... loci,
... hl.tstruct(locus=hl.tlocus('GRCh37'), cm=hl.tfloat64),
... key=['locus'])
Windows with 1bp radius:
>>> hl.linalg.utils.locus_windows(ht.locus, 1)
(array([0, 0, 2, 3, 3, 5]), array([2, 2, 3, 5, 5, 6]))
Windows with 1cm radius:
>>> hl.linalg.utils.locus_windows(ht.locus, 1.0, coord_expr=ht.cm)
(array([0, 1, 1, 3, 3, 5]), array([1, 3, 3, 5, 5, 6]))
Notes
-----
This function returns two 1-dimensional ndarrays of integers,
``starts`` and ``stops``, each of size equal to the number of rows.
By default, for all indices ``i``, ``[starts[i], stops[i])`` is the maximal
range of row indices ``j`` such that ``contig[i] == contig[j]`` and
``position[i] - radius <= position[j] <= position[i] + radius``.
If the :meth:`.global_position` on `locus_expr` is not in ascending order,
this method will fail. Ascending order should hold for a matrix table keyed
by locus or variant (and the associated row table), or for a table that has
been ordered by `locus_expr`.
Set `coord_expr` to use a value other than position to define the windows.
This row-indexed numeric expression must be non-missing, non-``nan``, on the
same source as `locus_expr`, and ascending with respect to locus
position for each contig; otherwise the function will fail.
The last example above uses centimorgan coordinates, so
``[starts[i], stops[i])`` is the maximal range of row indices ``j`` such
that ``contig[i] == contig[j]`` and
``cm[i] - radius <= cm[j] <= cm[i] + radius``.
Index ranges are start-inclusive and stop-exclusive. This function is
especially useful in conjunction with
:meth:`.BlockMatrix.sparsify_row_intervals`.
Parameters
----------
locus_expr : :class:`.LocusExpression`
Row-indexed locus expression on a table or matrix table.
radius: :obj:`int`
Radius of window for row values.
coord_expr: :class:`.Float64Expression`, optional
Row-indexed numeric expression for the row value.
Must be on the same table or matrix table as `locus_expr`.
By default, the row value is given by the locus position.
Returns
-------
(:class:`ndarray` of :obj:`int64`, :class:`ndarray` of :obj:`int64`)
Tuple of start indices array and stop indices array.
"""
if radius < 0:
raise ValueError(
f"locus_windows: 'radius' must be non-negative, found {radius}")
check_row_indexed('locus_windows', locus_expr)
if coord_expr is None:
global_pos_list = locus_expr.global_position().collect()
n_loci = len(global_pos_list)
global_pos = np.zeros(n_loci, dtype=np.int64)
for i, p in enumerate(global_pos_list):
if p is None:
raise ValueError(
f"locus_windows: missing value for 'locus_expr' global position at row {i}"
)
global_pos[i] = p
coord = global_pos
del global_pos_list
else:
check_row_indexed('locus_windows', coord_expr)
global_pos_and_coord =\
hl.tuple([locus_expr.global_position(), coord_expr]).collect() # raises exception if sources differ
n_loci = len(global_pos_and_coord)
global_pos = np.zeros(n_loci, dtype=np.int64)
coord = np.zeros(n_loci, dtype=np.float64)
for i, x in enumerate(global_pos_and_coord):
if x[0] is None:
raise ValueError(
f"locus_windows: missing value for 'locus_expr' global position at row {i}"
)
global_pos[i] = x[0]
if x[1] is None:
raise ValueError(
f"locus_windows: missing value for 'coord_expr' at row {i}"
)
coord[i] = x[1]
del global_pos_and_coord
if n_loci == 0:
return np.zeros(shape=0, dtype=np.int64), np.zeros(shape=0,
dtype=np.int64)
contig_name = locus_expr.dtype.reference_genome.contigs
contig_len = locus_expr.dtype.reference_genome.lengths
contig_cum_len = np.cumsum([contig_len[name] for name in contig_name])
assert (global_pos[-1] < contig_cum_len[-1])
contig_start_idx = _compute_contig_start_idx(global_pos, contig_cum_len)
n_contigs = len(contig_start_idx)
contig_start_idx.append(n_loci)
contig_bounds = [
array_windows(coord[contig_start_idx[c]:contig_start_idx[c + 1]],
radius) for c in range(n_contigs)
]
starts = np.concatenate(
[contig_start_idx[c] + contig_bounds[c][0] for c in range(n_contigs)])
stops = np.concatenate(
[contig_start_idx[c] + contig_bounds[c][1] for c in range(n_contigs)])
return starts, stops