In [19]:

# import important modules
import pandas as pd
matrix_gene = pd.read_csv("../Data/Comparisons/Matrisome_Hs_MasterList.csv") # MOCSvsMOSE
#matrix_gene

In [20]:

matrix_index = ["COL11A1","COMP","FN1","VCAN","CTSB","COL1A1","AGT","ANXA5","ANXA6",
            "LAMB1","FBLN2","LAMC1","LGALS3","CTSG",
            "HSPG2","ANXA1","LAMA4","COL6A6","VWF",
            "ABI3B","PTNXB","COL15A1"] # matrix index gene list

len(matrix_index)

Out[20]:

22

In [ ]:

In [21]:

# the rows that only contains the matrix index genes
matrix_gene_final=matrix_gene[matrix_gene['Gene.symbol'].isin
            (["COL11A1","COMP","FN1","VCAN","CTSB","COL1A1","AGT","ANXA5","ANXA6",
            "LAMB1","FBLN2","LAMC1","LGALS3","CTSG",
            "HSPG2","ANXA1","LAMA4","COL6A6","VWF",
            "ABI3B","PTNXB","COL15A1"])]
matrix_gene_final = matrix_gene_final.drop(matrix_gene_final.columns[[0]], axis=1)  # delete first column
matrix_gene_final.to_csv(r'../Python/ECM22genes.csv') # export as csv
matrix_gene_final
#len(matrix_gene_final)

# The genes that are not in the matrisome:
#ABI3B
#PTNXB

Out[21]:

	Category	Gene.symbol
15	ECM Glycoproteins	COMP
43	ECM Glycoproteins	FBLN2
54	ECM Glycoproteins	FN1
79	ECM Glycoproteins	LAMA4
81	ECM Glycoproteins	LAMB1
85	ECM Glycoproteins	LAMC1
186	ECM Glycoproteins	VWF
196	Collagens	COL11A1
201	Collagens	COL15A1
206	Collagens	COL1A1
232	Collagens	COL6A6
253	Proteoglycans	HSPG2
273	Proteoglycans	VCAN
274	ECM-affiliated Proteins	ANXA1
281	ECM-affiliated Proteins	ANXA5
282	ECM-affiliated Proteins	ANXA6
366	ECM-affiliated Proteins	LGALS3
492	ECM Regulators	AGT
520	ECM Regulators	CTSB
525	ECM Regulators	CTSG

-->