Extract pathways from a Five3 Genomics Pathway database file as a basis for including gene-gene interactions in a model.
In [2]:
import os
import pandas as pd
In [3]:
# Load the entire pathway database into a dataframe for parsing and extraction
interactions = pd.read_csv("data/pid_120912_pathway.tab", sep="\t", names=["parent", "child", "interaction"])
interactions.head()
Out[3]:
In [4]:
# interactions.query("interaction=='-a>' | interaction=='-a|'").head()
interactions.query("parent=='abstract'").head()
Out[4]:
In [6]:
interactions[interactions['child'].str.contains("apoptosis")][0:20]
Out[6]: