mirror of
https://github.com/haniffalab/scRNA-seq_analysis.git
synced 2024-10-23 08:29:24 -07:00
93 lines
3.1 KiB
Python
Executable file
93 lines
3.1 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Wed Aug 1 15:18:12 2018
|
|
|
|
@author: doru
|
|
"""
|
|
|
|
import sys
|
|
args = sys.argv
|
|
CWD = args[1]
|
|
#split_cat = args[2]
|
|
from os import chdir
|
|
chdir(CWD)
|
|
|
|
import matplotlib; matplotlib.use('Agg');
|
|
import scanpy.api as sc;
|
|
import pandas as pd
|
|
from scipy.sparse import csr_matrix
|
|
import numpy as np
|
|
|
|
sc.settings.verbosity = 3
|
|
|
|
scObj = sc.read("./material/raw_data.mtx", cache = False).T
|
|
|
|
# load gene names
|
|
scObj.var_names = pd.read_csv("./material/genenames.csv").iloc[:, 1]
|
|
|
|
# load cell names
|
|
scObj.obs_names = pd.read_csv("./material/cellnames.csv").iloc[:, 1]
|
|
|
|
# filter out genes present in less than 3 cells
|
|
sc.pp.filter_genes(scObj, min_cells=3)
|
|
|
|
# log-normalize the data
|
|
scObj.raw = sc.pp.log1p(scObj, copy=True)
|
|
sc.pp.normalize_per_cell(scObj, counts_per_cell_after=1e4)
|
|
|
|
# variable genes
|
|
filter_result = sc.pp.filter_genes_dispersion(
|
|
scObj.X, min_mean=0.0125, max_mean=3, min_disp=0.5)
|
|
# subset data on variable genes
|
|
scObj = scObj[:, filter_result.gene_subset]
|
|
# not sure?
|
|
sc.pp.log1p(scObj)
|
|
|
|
# scale the data
|
|
sc.pp.scale(scObj, max_value=10)
|
|
|
|
# run pca
|
|
sc.tl.pca(scObj)
|
|
|
|
# compunte neighborhood graph
|
|
sc.pp.neighbors(scObj, n_neighbors = 15, n_pcs = 20, knn = True, random_state = 10, method = "gauss")
|
|
|
|
# add cell labels
|
|
cell_labels = pd.read_csv("./material/cell_labels.csv", index_col = 0)
|
|
|
|
scObj.obs["cell_labels"] = cell_labels
|
|
|
|
# run aga
|
|
sc.tl.paga(scObj, groups = "cell_labels")
|
|
|
|
# save the scipy paga graph to disk for comparison to the plot generated by ggplot - for trouble shooting
|
|
|
|
sc.pl.paga(scObj, save = "_ugly_scanpy_plot.pdf", show = True, edge_width_scale = .4, solid_edges = "connectivities", layout="fa")
|
|
|
|
#sc.pl.paga(scObj, save = "ugly_scanpy_plot.pdf", show = False, edge_width_scale = .4, solid_edges = "connectivities",
|
|
# layout = "fa")
|
|
|
|
#sc.pl.paga(scObj, save = "_ugly_scanpy_plot.pdf", show = True, edge_width_scale = .4, solid_edges = "connectivities", layout = "fa")
|
|
|
|
#sc.pl.paga(scObj, save = "{split_cat}_ugly_scanpy_plot.pdf".format(split_cat=split_cat), show = True, edge_width_scale = .4, solid_edges = "connectivities", layout = "fa")
|
|
|
|
#sc.pl.paga(scObj, save = "{split_cat}_ugly_scanpy_plot.pdf".format(split_cat=split_cat),
|
|
# show = True, edge_width_scale = .4, solid_edges = "connectivities",
|
|
# layout = "fa") # layout = "fa"
|
|
|
|
# prepare the output and save it to disk
|
|
cell_cats = list(scObj.obs["cell_labels"].cat.categories)
|
|
population_size = cell_labels["Labels"].value_counts()
|
|
population_size = population_size[cell_cats].values
|
|
|
|
connectivities = np.array(csr_matrix.todense(scObj.uns["paga"]["connectivities"]), dtype = "float64")
|
|
connectivities[connectivities < .05] = 0.0
|
|
|
|
#connectivities[connectivities < .1] = 0.0
|
|
connectivities = pd.DataFrame(connectivities, columns = cell_cats, index = cell_cats)
|
|
connectivities.to_csv("./AGA_folder/connectivities.csv", index = True, header = True)
|
|
|
|
coordinates = pd.DataFrame(scObj.uns["paga"]["pos"], columns = ["X", "Y"], index = cell_cats)
|
|
coordinates["Size"] = pd.Series(population_size, coordinates.index)
|
|
coordinates.to_csv("AGA_folder/coordinates.csv", index = True, header = True)
|