Specificity

import pandas as pd
from katlas.core import *

pssms= pd.read_parquet('out/CDDM_pssms.parquet')

spec = pssms.apply(get_specificity_flat , axis=1)

df=Data.get_ks_dataset()

CPU times: user 759 ms, sys: 409 ms, total: 1.17 s
Wall time: 4min 45s

df['kinase_id'] = df['kinase_uniprot'] + '_' + df['kinase_genes'].str.split().str[0]

info = df[['kinase_id','kinase_group']].drop_duplicates()

info['specificity'] = info.kinase_id.map(spec)

info.isna().sum()

kinase_id         0
kinase_group     30
specificity     120
dtype: int64

There are 30 kinase without assigning a kinase group

info = info.dropna()

info = info.sort_values('specificity',ascending=False)

from katlas.plot import *

set_sns()

plot_rank(info,x='kinase_id',y='specificity',hue='kinase_group',palette=group_color)

plot_bar(info,value='specificity',group='kinase_group',palette=group_color)