fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-09-24 18:08:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add back in /expression and /diffexp endpoints

Browse Source
This commit is contained in:
Charlotte Weaver
2018-06-22 17:18:22 -07:00
parent ee8bb510ff
commit 15ce4cc338
2 changed files with 294 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/rest_api/rest.py
+220
View File
@@ -210,10 +210,230 @@ class CellsAPI(Resource):
return make_payload(payload)
class ExpressionAPI(Resource):
@swagger.doc({
'summary': 'Json with gene list and expression data by cell, limited to first 40 cells',
'tags': ['expression'],
'parameters': [
{
'name': 'include_unexpressed_genes',
'description': "Include genes that have 0 expression across all cells in set",
'in': 'path',
'type': 'bool',
}
],
'responses': {
'200': {
'description': 'Json for heatmap',
'examples': {
'application/json': {
"data": {
"cells": [
{
"cellname": "1/2-SBSRNA4",
"e": [0, 0, 214, 0, 0]
},
],
"genes": [
"1001000173.G8",
"1001000173.D4",
"1001000173.B4",
"1001000173.A2",
"1001000173.E2"
],
"nonzero_gene_count": 2857
},
"status": {
"error": False,
"errormessage": ""
}
}
}
}
}
})
def get(self):
from app import data
expression_data = data.expression()
return make_payload(expression_data)
@swagger.doc({
'summary': 'Json with gene list and expression data by cell',
'tags': ['expression'],
'parameters': [
{
'name': 'body',
'in': 'body',
"schema": {
"example": {
"celllist": ["1001000173.G8", "1001000173.D4"],
"genelist": ["1/2-SBSRNA4", "A1BG", "A1BG-AS1", "A1CF", "A2LD1", "A2M", "A2ML1", "A2MP1",
"A4GALT"],
"include_unexpressed_genes": True,
}
}
},
],
'responses': {
'200': {
'description': 'Json for expressiondata',
'examples': {
'application/json': {
"data": {
"cells": [
{
"cellname": "1001000173.D4",
"e": [0, 0]
},
{
"cellname": "1001000173.G8",
"e": [0, 0]
}
],
"genes": [
"ABCD4",
"ZWINT"
],
"nonzero_gene_count": 2857
},
"status": {
"error": False,
"errormessage": ""
}
}
}
},
'400': {
'description': 'Required parameter missing/incorrect',
}
}
})
def post(self):
from app import data
args = request.get_json()
cell_list = args.get('celllist', [])
gene_list = args.get('genelist', [])
if not (cell_list) and not (gene_list):
return make_payload([], "must include celllist and/or genelist parameter", 400)
expression_data = data.expression(cell_list, gene_list)
if cell_list and len(expression_data['cells']) < len(cell_list):
return make_payload([], "Some cell ids not available", 400)
if gene_list and len(expression_data['genes']) < len(gene_list):
return make_payload([], "Some genes not available", 400)
return make_payload(expression_data)
class DifferentialExpressionAPI(Resource):
@swagger.doc({
'summary': 'Get the top expressed genes for two cell sets. Calculated using t-test',
'tags': ['expression'],
'parameters': [
{
'name': 'body',
'in': 'body',
'schema': {
"example": {
"celllist1": ["1001000176.C12", "1001000176.C7", "1001000177.F11"],
"celllist2": ["1001000012.D2", "1001000017.F10", "1001000033.C3", "1001000229.D4"],
"num_genes": 5,
"pval": 0.000001,
},
}
}
],
"responses": {
'200': {
'description': 'top expressed genes for cellset1, cellset2',
'examples': {
'application/json': {
"data": {
"celllist1": {
"ave_diff": [
432.0132935431362,
12470.5623982637,
957.0246880086814
],
"mean_expression_cellset1": [
438.6185567010309,
13315.536082474227,
1076.5773195876288
],
"mean_expression_cellset2": [
6.605263157894737,
844.9736842105264,
119.55263157894737
],
"pval": [
3.8906598089944563e-35,
1.9086226376018916e-25,
7.847480544069826e-21
],
"topgenes": [
"TMSB10",
"FTL",
"TMSB4X"
]
},
"celllist2": {
"ave_diff": [
-6860.599158979924,
-519.1314432989691,
-10278.328269126423
],
"mean_expression_cellset1": [
2.8350515463917527,
0.6185567010309279,
23.09278350515464
],
"mean_expression_cellset2": [
6863.434210526316,
519.75,
10301.421052631578
],
"pval": [
4.662891833748732e-44,
3.6278087029927103e-37,
8.396825170618402e-35
],
"topgenes": [
"SPARCL1",
"C1orf61",
"CLU"
]
}
},
"status": {
"error": False,
"errormessage": ""
}
}
}
}
}
})
def post(self):
from app import data
args = request.get_json()
cell_list_1 = args.get('celllist1', [])
cell_list_2 = args.get('celllist2', [])
num_genes = args.get("num_genes", 7)
pval = args.get('pval', 0.5)
if not (cell_list_1 and cell_list_2):
return make_payload([],
"must include celllist1 and celllist2 parameters",
400)
data = data.diffexp(cell_list_1, cell_list_2, pval, num_genes)
return make_payload(data)
def get_api_resources():
bp = Blueprint('api', __name__, url_prefix='/api/v2.0')
api = Api(bp, add_api_spec_resource=False)
api.add_resource(InitializeAPI, "/initialize")
api.add_resource(CellsAPI, "/cells")
api.add_resource(ExpressionAPI, "/expression")
api.add_resource(DifferentialExpressionAPI, "/diffexp")
return api
backend/app/scanpy_engine/scanpy_engine.py
+74 -4
View File
@@ -1,5 +1,6 @@
import scanpy.api as sc
import numpy as np
from scipy import stats
import os
from ..util.schema_parse import parse_schema
@@ -112,11 +113,80 @@ class ScanpyEngine(CXGDriver):
return np.hstack((df.obs["cell_name"].values.reshape(len(df.obs.index), 1), normalized_graph)).tolist()
def diffexp(self, cells_iterator_1, cells_iterator_2):
pass
def diffexp(self, cell_list_1, cell_list_2, pval, num_genes):
cells_idx_1 = np.in1d(self.data.obs["cell_name"], cell_list_1)
cells_idx_2 = np.in1d(self.data.obs["cell_name"], cell_list_2)
expression_1 = self.data.X[cells_idx_1,:]
expression_2 = self.data.X[cells_idx_2,:]
diff_exp = stats.ttest_ind(expression_1, expression_2)
set1 = np.logical_and(diff_exp.pvalue < pval, diff_exp.statistic > 0)
set2 = np.logical_and(diff_exp.pvalue < pval, diff_exp.statistic < 0)
stat1 = diff_exp.statistic[set1]
stat2 = diff_exp.statistic[set2]
sort_set1 = np.argsort(stat1)[::-1]
sort_set2 = np.argsort(stat2)
pval1 = diff_exp.pvalue[set1][sort_set1]
pval2 = diff_exp.pvalue[set2][sort_set2]
mean_ex1_set1 = np.mean(expression_1[:, set1], axis=0)[sort_set1]
mean_ex2_set1 = np.mean(expression_2[:, set1], axis=0)[sort_set1]
mean_ex1_set2 = np.mean(expression_1[:, set2], axis=0)[sort_set2]
mean_ex2_set2 = np.mean(expression_2[:, set2], axis=0)[sort_set2]
mean_diff1 = mean_ex1_set1 - mean_ex2_set1
mean_diff2 = mean_ex1_set2 - mean_ex2_set2
genes_cellset_1 = self.data.var_names[set1][sort_set1]
genes_cellset_2 = self.data.var_names[set2][sort_set2]
return {
"celllist1": {
"topgenes": genes_cellset_1.tolist()[:num_genes],
"mean_expression_cellset1": mean_ex1_set1.tolist()[:num_genes],
"mean_expression_cellset2": mean_ex2_set1.tolist()[:num_genes],
"pval": pval1.tolist()[:num_genes],
"ave_diff": mean_diff1.tolist()[:num_genes]
},
"celllist2": {
"topgenes": genes_cellset_2.tolist()[:num_genes],
"mean_expression_cellset1": mean_ex1_set2.tolist()[:num_genes],
"mean_expression_cellset2": mean_ex2_set2.tolist()[:num_genes],
"pval": pval2.tolist()[:num_genes],
"ave_diff": mean_diff2.tolist()[:num_genes]
},
}
def expression(self, cells=None, genes=None):
"""
:param df:
:return:
"""
if cells:
cells_idx = np.in1d(self.data.obs["cell_name"], cells)
else:
cells_idx = np.ones((self.cell_count,), dtype=bool)
if genes:
genes_idx = np.in1d(self.data.var_names, genes)
else:
genes_idx = np.ones((self.gene_count,), dtype=bool)
index = np.ix_(cells_idx, genes_idx)
expression = self.data.X[index]
if not genes:
genes = self.data.var.index.tolist()
if not cells:
cells = self.data.obs["cell_name"].tolist()
cell_data = []
for idx, cell in enumerate(cells):
cell_data.append({
"cellname": cell,
"e": list(expression[idx]),
})
return {
"genes": genes,
"cells": cell_data,
"nonzero_gene_count": int(np.sum(expression.any(axis=0)))
}
def expression(self, ):
pass