mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-30 03:08:12 +08:00
feat: diffexp returns two genesets (#2230)
* feat: return two lists for diffexp (#2221) * sp * split out derive sort order, tests passing * sp * return diff exp results in two lists * update * copy implementation over to desktop * add tests for two lists * small fixes to complete backend implementation * accept new diffexp response * map diff exp response to genesets * delete ) * name diffexp genesets with population names * take constants out of state and allow width prop to override * shorten mini-histo properly truncate and resize depending on expansion * prepend new genesets * rename data within diffexp action * backend * move diffexp ttest to common code module, update tests * update for unit tests * reference actual var Co-authored-by: Madison Dunitz <madison.dunitz@chanzuckerberg.com> Co-authored-by: Madison Dunitz <dunitzm@gmail.com>
This commit is contained in:
Severiano Badajoz
co-authored by
Madison Dunitz
Madison Dunitz
Madison Dunitz
Madison Dunitz
parent
7ed53c0f5b
commit
28b526b3fc
@@ -1,134 +0,0 @@
|
||||
import numpy as np
|
||||
from scipy import sparse, stats
|
||||
|
||||
|
||||
def diffexp_ttest(adaptor, maskA, maskB, top_n=8, diffexp_lfc_cutoff=0.01):
|
||||
"""
|
||||
Return differential expression statistics for top N variables.
|
||||
|
||||
Algorithm:
|
||||
- compute log fold change (log2(meanA/meanB))
|
||||
- compute Welch's t-test statistic and pvalue (w/ Bonferroni correction)
|
||||
- return top N abs(logfoldchange) where lfc > diffexp_lfc_cutoff
|
||||
|
||||
If there are not N which meet criteria, augment by removing the logfoldchange
|
||||
threshold requirement.
|
||||
|
||||
Notes on alogrithm:
|
||||
- Welch's ttest provides basic statistics test.
|
||||
https://en.wikipedia.org/wiki/Welch%27s_t-test
|
||||
- p-values adjusted with Bonferroni correction.
|
||||
https://en.wikipedia.org/wiki/Bonferroni_correction
|
||||
|
||||
:param adaptor: DataAdaptor instance
|
||||
:param maskA: observation selection mask for set 1
|
||||
:param maskB: observation selection mask for set 2
|
||||
:param top_n: number of variables to return stats for
|
||||
:param diffexp_lfc_cutoff: minimum
|
||||
:return: for top N genes, [ varindex, logfoldchange, pval, pval_adj ]
|
||||
"""
|
||||
|
||||
dataA = adaptor.get_X_array(maskA, None)
|
||||
dataB = adaptor.get_X_array(maskB, None)
|
||||
|
||||
# mean, variance, N - calculate for both selections
|
||||
meanA, vA, nA = mean_var_n(dataA)
|
||||
meanB, vB, nB = mean_var_n(dataB)
|
||||
res = diffexp_ttest_from_mean_var(meanA, vA, nA, meanB, vB, nB, top_n, diffexp_lfc_cutoff)
|
||||
|
||||
return res
|
||||
|
||||
|
||||
def diffexp_ttest_from_mean_var(meanA, varA, nA, meanB, varB, nB, top_n, diffexp_lfc_cutoff):
|
||||
n_var = meanA.shape[0]
|
||||
top_n = min(top_n, n_var)
|
||||
|
||||
# variance / N
|
||||
vnA = varA / min(nA, nB) # overestimate variance, would normally be nA
|
||||
vnB = varB / min(nA, nB) # overestimate variance, would normally be nB
|
||||
sum_vn = vnA + vnB
|
||||
|
||||
# degrees of freedom for Welch's t-test
|
||||
with np.errstate(divide="ignore", invalid="ignore"):
|
||||
dof = sum_vn ** 2 / (vnA ** 2 / (nA - 1) + vnB ** 2 / (nB - 1))
|
||||
dof[np.isnan(dof)] = 1
|
||||
|
||||
# Welch's t-test score calculation
|
||||
with np.errstate(divide="ignore", invalid="ignore"):
|
||||
tscores = (meanA - meanB) / np.sqrt(sum_vn)
|
||||
tscores[np.isnan(tscores)] = 0
|
||||
|
||||
# p-value
|
||||
pvals = stats.t.sf(np.abs(tscores), dof) * 2
|
||||
pvals_adj = pvals * n_var
|
||||
pvals_adj[pvals_adj > 1] = 1 # cap adjusted p-value at 1
|
||||
|
||||
# logfoldchanges: log2(meanA / meanB)
|
||||
logfoldchanges = np.log2(np.abs((meanA + 1e-9) / (meanB + 1e-9)))
|
||||
|
||||
# find all with lfc > cutoff
|
||||
lfc_above_cutoff_idx = np.nonzero(np.abs(logfoldchanges) > diffexp_lfc_cutoff)[0]
|
||||
stats_to_sort = np.abs(tscores)
|
||||
|
||||
# derive sort order
|
||||
if lfc_above_cutoff_idx.shape[0] > top_n:
|
||||
# partition top N
|
||||
rel_t_partition = np.argpartition(stats_to_sort[lfc_above_cutoff_idx], -top_n)[-top_n:]
|
||||
t_partition = lfc_above_cutoff_idx[rel_t_partition]
|
||||
# sort the top N partition
|
||||
rel_sort_order = np.argsort(stats_to_sort[t_partition])[::-1]
|
||||
sort_order = t_partition[rel_sort_order]
|
||||
else:
|
||||
# partition and sort top N, ignoring lfc cutoff
|
||||
partition = np.argpartition(stats_to_sort, -top_n)[-top_n:]
|
||||
rel_sort_order = np.argsort(stats_to_sort[partition])[::-1]
|
||||
indices = np.indices(stats_to_sort.shape)[0]
|
||||
sort_order = indices[partition][rel_sort_order]
|
||||
|
||||
# top n slice based upon sort order
|
||||
logfoldchanges_top_n = logfoldchanges[sort_order]
|
||||
pvals_top_n = pvals[sort_order]
|
||||
pvals_adj_top_n = pvals_adj[sort_order]
|
||||
|
||||
# varIndex, logfoldchange, pval, pval_adj
|
||||
result = [[sort_order[i], logfoldchanges_top_n[i], pvals_top_n[i], pvals_adj_top_n[i]] for i in range(top_n)]
|
||||
return result
|
||||
|
||||
|
||||
# Convenience function which handles sparse data
|
||||
def mean_var_n(X):
|
||||
"""
|
||||
Two-pass variance calculation. Numerically (more) stable
|
||||
than naive methods (and same method used by numpy.var())
|
||||
https://en.wikipedia.org/wiki/Algorithms_for_calculating_variance#Two-pass
|
||||
"""
|
||||
# fp_err_occurred is a flag indicating that a floating point error
|
||||
# occured somewhere in our compute. Used to trigger non-finite
|
||||
# number handling.
|
||||
fp_err_occurred = False
|
||||
|
||||
def fp_err_set(err, flag):
|
||||
nonlocal fp_err_occurred
|
||||
fp_err_occurred = True
|
||||
|
||||
with np.errstate(divide="call", invalid="call", call=fp_err_set):
|
||||
n = X.shape[0]
|
||||
if sparse.issparse(X):
|
||||
mean = X.mean(axis=0).A1
|
||||
dfm = X - mean
|
||||
sumsq = np.sum(np.multiply(dfm, dfm), axis=0).A1
|
||||
v = sumsq / (n - 1)
|
||||
else:
|
||||
mean = X.mean(axis=0)
|
||||
dfm = X - mean
|
||||
sumsq = np.sum(np.multiply(dfm, dfm), axis=0)
|
||||
v = sumsq / (n - 1)
|
||||
|
||||
if fp_err_occurred:
|
||||
mean[np.isfinite(mean) == False] = 0 # noqa: E712
|
||||
v[np.isfinite(v) == False] = 0 # noqa: E712
|
||||
else:
|
||||
mean[np.isnan(mean)] = 0
|
||||
v[np.isnan(v)] = 0
|
||||
|
||||
return mean, v, n
|
||||
@@ -8,7 +8,7 @@ from pandas.core.dtypes.dtypes import CategoricalDtype
|
||||
from scipy import sparse
|
||||
from server_timing import Timing as ServerTiming
|
||||
|
||||
import backend.server.compute.diffexp_generic as diffexp_generic
|
||||
import backend.common.compute.diffexp_generic as diffexp_generic
|
||||
from backend.common.colors import convert_anndata_category_colors_to_cxg_category_colors
|
||||
from backend.common.constants import Axis, MAX_LAYOUTS
|
||||
from backend.server.common.corpora import corpora_get_props_from_anndata
|
||||
|
||||
@@ -68,7 +68,7 @@ class DataAdaptor(metaclass=ABCMeta):
|
||||
|
||||
@abstractmethod
|
||||
def compute_embedding(self, method, filter):
|
||||
"""compute a new embedding on the specified obs subset, and return the embedding schema. """
|
||||
"""compute a new embedding on the specified obs subset, and return the embedding schema."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
@@ -324,7 +324,12 @@ class DataAdaptor(metaclass=ABCMeta):
|
||||
):
|
||||
raise ExceedsLimitError("Diffexp request exceeds max cell count limit")
|
||||
|
||||
result = self.compute_diffexp_ttest(obs_mask_A, obs_mask_B, top_n, self.dataset_config.diffexp__lfc_cutoff)
|
||||
result = self.compute_diffexp_ttest(
|
||||
maskA=obs_mask_A,
|
||||
maskB=obs_mask_B,
|
||||
top_n=top_n,
|
||||
lfc_cutoff=self.dataset_config.diffexp__lfc_cutoff,
|
||||
)
|
||||
|
||||
try:
|
||||
return jsonify_numpy(result)
|
||||
|
||||
Reference in New Issue
Block a user