cplaisier’s gists

cplaisier / BT145_C_script.py

Created May 14, 2020 23:51

	cd /Users/baileyquinn/Desktop/BT145/

	docker run -it -v "/Users/baileyquinn/Desktop/BT145:/files" cplaisier/scrna_seq_velocity

	cd /files

	pip3 install clusim
	pip3 install statsmodels

	python3

cplaisier / getPostProcessedForClusters_VCNA_2_18_2020.py

Created May 11, 2020 20:09

	#import statsmodels.formula.api as sm
	#import numpy as np
	from sklearn.linear_model import LinearRegression
	from scipy import stats
	import pandas as pd
	from matplotlib.backends.backend_pdf import PdfPages
	import matplotlib.pyplot as plt
	import seaborn as sns
	import json

cplaisier / clustersOfBiclusters.R

Created May 8, 2020 17:42

Example code to conduct AM and MDM analyses:

	# Set working directory
	#setwd('C:/Users/cplaisie/Dropbox/Urdahl/Ag85B_ESAT6_ts/network')
	#setwd('/home/cplaisier/Dropbox (ASU)/Urdahl/macs/cMonkey')
	setwd('C:/Users/plais/Dropbox (ASU)/Urdahl/macs/cMonkey')
	#setwd('C:/Users/Christopher/Dropbox/Urdahl/Ag85B_ESAT6_ts/network')

	# Get eigengenes
	d1 = read.csv('eigengenes/biclusterEigengenes_tfbs_db.csv',header=T, row.names=1)
	rownames(d1) = paste('TFBS_DB_',rownames(d1),sep='')
	d2 = read.csv('eigengenes/biclusterEigengenes_pita.csv',header=T, row.names=1)

cplaisier / scanpy_clp_3_3_2020.py

Created March 3, 2020 19:37

Scanpy code for BT145.

	# docker run -it -v "/home/cplaisier/Dropbox (ASU):/files" cplaisier/scrna_seq_velocity
	# docker run -it -v "/home/swilferd:/files/scRNA_seq_Mehta" cplaisier/scrna_seq_velocity
	# docker run -it -v "/home/swilferd:/files" cplaisier/scrna_seq_velocity
	# pip3 intall mygene

	#python3 entry:
	import numpy as np
	import pandas as pd
	import scanpy as sc
	import mygene as mg

cplaisier / ccAF.R

Last active February 12, 2020 15:35

R script to apply cell cycle ccAF classifier to single cell dataset.

	library(Seurat)
	library(ranger)

	# Modified function from Seurat V2
	ClassifyCells = function (classifier, training.genes = NULL, training.classes = NULL,
	new.data = NULL, ...)
	{
	features <- classifier$forest$independent.variable.names
	genes.to.add <- setdiff(x = features, y = rownames(x = new.data))
	data.to.add <- matrix(data = 0, nrow = length(x = genes.to.add),

cplaisier / 6.1_Intro_to_Data_and_GEOquery.R

Created October 15, 2019 14:52

Example code form Systems Biology of Disease course

	####################################################
	## Systems Biology of Disease: Intro to LUSC Data ##
	## ______ ______ __ __ ##
	## /\ __ \ /\ ___\ /\ \/\ \ ##
	## \ \ __ \ \ \___ \ \ \ \_\ \ ##
	## \ \_\ \_\ \/\_____\ \ \_____\ ##
	## \/_/\/_/ \/_____/ \/_____/ ##
	## @Developed by: Plaisier Lab ##
	## (https://plaisierlab.engineering.asu.edu/) ##
	## Arizona State University ##

cplaisier / stemCell.py

Created October 10, 2019 00:08

Stem Cell Changes

	from __future__ import division

	##########################################################
	## Consistilator: plotNetworkMotifs_SCD.py ##
	## ______ ______ __ __ ##
	## /\ __ \ /\ ___\ /\ \/\ \ ##
	## \ \ __ \ \ \___ \ \ \ \_\ \ ##
	## \ \_\ \_\ \/\_____\ \ \_____\ ##
	## \/_/\/_/ \/_____/ \/_____/ ##
	## @Developed by: Plaisier Lab ##

cplaisier / Correlation Matrix Practice.py

Last active January 14, 2019 15:14 — forked from mkcook/Correlation Matrix Practice

	import pandas as pd # May not need this or may have already done this but so you know where pd comes from

	#### Two possible solutions

	##############################################################################
	### 1. Calculate all possible values which is what you are doing currently ###
	##############################################################################
	corrDF_R = pd.DataFrame(index=df.index, columns=df.index)
	corrDF_p = pd.DataFrame(index=df.index, columns=df.index)
	for i in corrDF_p.index:

cplaisier / gist:6d644e2064b6e04bb80a14f2258fc489

Last active November 14, 2018 16:07 — forked from mkcook/gist:6326fe1ea37cb7ab13e6e66a5c80fff3

Practice Computational Task

	# Import libraries up front
	import json

	# From Table S13 in Plaisier et al., Cell Systems 2016
	# These are Entrez IDs (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3013746/)
	input = ['430', '1052', '1053', '1385', '84699', '9586', '1871', '1874', '144455', '79733', '1960', '1997', '2002', '2004', '80712', '2114', '2115', '2120', '51513', '2551', '2623', '2624', '2625', '9421', '3232', '10320', '3659', '3662', '3670', '91464', '3726', '10661', '11278', '128209', '10365', '9314', '1316', '51176', '9935', '23269', '4602', '4774', '4790', '7025', '9480', '5468', '5914', '5916', '3516', '5971', '864', '6257', '4093', '6659', '6660', '6662', '25803', '347853', '30009', '9496', '6929', '6925', '8463', '7022', '29842', '10155', '6935', '132625', '23051', '85416', '7707', '7764', '23528', '201516']

	# Loading JSON file
	# https://www.safaribooksonline.com/library/view/python-cookbook-3rd/9781449357337/ch06s02.html
	# Example:

cplaisier / tcgaReplicationDataCollection.py

Created October 22, 2018 20:08

Python script to download gene expression datasets from GEO.

	import GEOparse
	import pandas as pd
	import matplotlib.pyplot as plt
	import numpy
	from matplotlib.backends.backend_pdf import PdfPages

	gseNums = ['GSEXXXXX1','GSEXXXXX2']

	with PdfPages('GSE_boxplots.pdf') as pdf:
	for gse1 in gseNums:

Christopher L Plaisier, PhD cplaisier